perf: Complete transition to standalone Python scripts
Subsystems (2)
Ian Rogers
reviewerPATCH v4 28/49 perf python: Port rw-by-pid from Perl to perf module
In reply to Ian RogersReplace the legacy Perl script rw-by-pid.pl with a standalone Python script in tools/perf/python/rw-by-pid.py using the perf Python module.
Improvements compared to the legacy Perl script:
- Remove the dependency on libperl and Perf::Trace::Util.
- Convert unsigned 32-bit and 64-bit error return values (0xfffff000..0xffffffff and >= 0x8000000000000000) to negative errnos so failed read/write syscalls are recorded in the error table rather than inflating bytes_read / bytes_written.
- Add argparse CLI support (-i/--input) and full type annotations.
Add a shell test
(test_rw_by_pid_python.sh) to verify the standalone script.
--- tools/perf/python/rw-by-pid.py | 205 ++++++++++++++++++ .../perf/tests/shell/test_rw_by_pid_python.sh | 75 +++++++ 2 files changed, 280 insertions(+) create mode 100755 tools/perf/python/rw-by-pid.py create mode 100755 tools/perf/tests/shell/test_rw_by_pid_python.sh
tools/perf/python/rw-by-pid.py new file +205 -0
@@ -0,0 +1,205 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0-only +"""Display r/w activity for all processes.""" +from __future__ import annotations + +import argparse +from collections import defaultdict +import sys +from typing import Optional, Dict, List, Tuple, Any +import perf + +class RwByPid: + """Tracks and displays read/write activity by PID.""" + def __init__(self) -> None: + self.reads: Dict[int, Dict[str, Any]] = defaultdict( + lambda: { + "bytes_requested": 0, + "bytes_read": 0, + "total_reads": 0, + "comm": "", + "errors": defaultdict(int), + } + ) + self.writes: Dict[int, Dict[str, Any]] = defaultdict( + lambda: { + "bytes_requested": 0, + "bytes_written": 0, + "total_writes": 0, + "comm": "", + "errors": defaultdict(int), + } + ) + self.unhandled: Dict[str, int] = defaultdict(int) + self.session: Optional[perf.session] = None + + def _handle_sys_enter_read(self, pid: int, comm: str, sample: perf.sample_event) -> None: + try: + count = sample.count + self.reads[pid]["bytes_requested"] += count + self.reads[pid]["total_reads"] += 1 + self.reads[pid]["comm"] = comm + except AttributeError: + self.unhandled["sys_enter_read_attr_err"] += 1 + + def _handle_sys_exit_read(self, pid: int, sample: perf.sample_event, comm: str = "") -> None: + try: + ret = sample.ret + # Convert unsigned 64-bit or 32-bit tracepoint return values to signed integers. + # Because kernel read/write transfers are bounded by MAX_RW_COUNT (0x7ffff000 < 2 GiB), + # 0xfffff000..0xffffffff is always a 32-bit negative errno even on 64-bit hosts. + if ret >= 0x8000000000000000: + ret -= 0x10000000000000000 + elif 0xfffff000 <= ret <= 0xffffffff: + ret -= 0x100000000 + if not self.reads[pid]["comm"] and comm: + self.reads[pid]["comm"] = comm + if ret >= 0: + self.reads[pid]["bytes_read"] += ret + else: + self.reads[pid]["errors"][ret] += 1 + except AttributeError: + self.unhandled["sys_exit_read_attr_err"] += 1 + + def _handle_sys_enter_write(self, pid: int, comm: str, sample: perf.sample_event) -> None: + try: + count = sample.count + self.writes[pid]["bytes_requested"] += count + self.writes[pid]["total_writes"] += 1 + self.writes[pid]["comm"] = comm + except AttributeError: + self.unhandled["sys_enter_write_attr_err"] += 1 + + def _handle_sys_exit_write(self, pid: int, sample: perf.sample_event, comm: str = "") -> None: + try: + ret = sample.ret + # Convert unsigned 64-bit or 32-bit tracepoint return values to signed integers. + # Because kernel read/write transfers are bounded by MAX_RW_COUNT (0x7ffff000 < 2 GiB), + # 0xfffff000..0xffffffff is always a 32-bit negative errno even on 64-bit hosts. + if ret >= 0x8000000000000000: + ret -= 0x10000000000000000 + elif 0xfffff000 <= ret <= 0xffffffff: + ret -= 0x100000000 + if not self.writes[pid]["comm"] and comm: + self.writes[pid]["comm"] = comm + if ret >= 0: + self.writes[pid]["bytes_written"] += ret + else: + self.writes[pid]["errors"][ret] += 1 + except AttributeError: + self.unhandled["sys_exit_write_attr_err"] += 1 + + def process_event(self, sample: perf.sample_event) -> None: + """Process events.""" + event_name = str(sample.evsel) + if event_name.startswith("evsel(") and event_name.endswith(")"): + event_name = event_name[6:-1] + event_name = "".join(c if c.isprintable() else "?" for c in event_name) + pid = sample.sample_pid + + assert self.session is not None + try: + thread = self.session.find_thread(pid, sample.sample_tid) + comm = (thread.comm() if thread else None) or "unknown" + except (TypeError, AttributeError): + comm = "unknown" + comm = "".join(c if c.isprintable() else "?" for c in comm) + + if event_name == "syscalls:sys_enter_read": + self._handle_sys_enter_read(pid, comm, sample) + elif event_name == "syscalls:sys_exit_read": + self._handle_sys_exit_read(pid, sample, comm) + elif event_name == "syscalls:sys_enter_write": + self._handle_sys_enter_write(pid, comm, sample) + elif event_name == "syscalls:sys_exit_write": + self._handle_sys_exit_write(pid, sample, comm) + else: + self.unhandled[event_name] += 1 + + def print_totals(self) -> None: + """Print summary tables.""" + print("read counts by pid:\n") + print( + f"{'pid':>6s} {'comm':<20s} {'# reads':>10s} " + f"{'bytes_requested':>15s} {'bytes_read':>10s}" + ) + print(f"{'-'*6} {'-'*20} {'-'*10} {'-'*15} {'-'*10}") + + for pid, data in sorted(self.reads.items(), + key=lambda kv: kv[1]["bytes_read"], reverse=True): + print( + f"{pid:6d} {data['comm']:<20s} {data['total_reads']:10d} " + f"{data['bytes_requested']:15d} {data['bytes_read']:10d}" + ) + + print("\nfailed reads by pid:\n") + print(f"{'pid':>6s} {'comm':<20s} {'error #':>7s} {'# errors':>10s}") + print(f"{'-'*6} {'-'*20} {'-'*7} {'-'*10}") + + errcounts: List[Tuple[int, str, int, int]] = [] + for pid, data in self.reads.items(): + for error, count in data["errors"].items(): + errcounts.append((pid, data["comm"], error, count)) + + for pid, comm, error, count in sorted(errcounts, key=lambda x: x[3], reverse=True): + print(f"{pid:6d} {comm:<20s} {error:7d} {count:10d}") + + print("\nwrite counts by pid:\n") + print( + f"{'pid':>6s} {'comm':<20s} {'# writes':>10s} " + f"{'bytes_requested':>15s} {'bytes_written':>15s}" + ) + print(f"{'-'*6} {'-'*20} {'-'*10} {'-'*15} {'-'*15}") + + for pid, data in sorted(self.writes.items(), + key=lambda kv: kv[1]["bytes_written"], reverse=True): + print( + f"{pid:6d} {data['comm']:<20s} {data['total_writes']:10d} " + f"{data['bytes_requested']:15d} {data['bytes_written']:15d}" + ) + + print("\nfailed writes by pid:\n") + print(f"{'pid':>6s} {'comm':<20s} {'error #':>7s} {'# errors':>10s}") + print(f"{'-'*6} {'-'*20} {'-'*7} {'-'*10}") + + errcounts = [] + for pid, data in self.writes.items(): + for error, count in data["errors"].items(): + errcounts.append((pid, data["comm"], error, count)) + + for pid, comm, error, count in sorted(errcounts, key=lambda x: x[3], reverse=True): + print(f"{pid:6d} {comm:<20s} {error:7d} {count:10d}") + + if self.unhandled: + print("\nunhandled events:\n") + print(f"{'event':<40s} {'count':>10s}") + print(f"{'-'*40} {'-'*10}") + for event_name, count in self.unhandled.items(): + print(f"{event_name:<40s} {count:10d}") + + def run(self, input_file: str) -> None: + """Run the session.""" + self.session = perf.session(perf.data(input_file), sample=self.process_event) + try: + self.session.process_events() + finally: + # Break the reference cycle between perf.session and self.process_event + # because perf.session lacks cyclic GC support (tp_traverse). + self.session = None + self.print_totals() + +def main() -> None: + """Main function.""" + parser = argparse.ArgumentParser(description="Trace r/w activity by PID") + parser.add_argument("-i", "--input", default="perf.data", help="Input file") + args = parser.parse_args() + + analyzer = RwByPid() + try: + analyzer.run(args.input) + except IOError as e: + print(e, file=sys.stderr) + sys.exit(1) + +if __name__ == "__main__": + main()
tools/perf/tests/shell/test_rw_by_pid_python.sh new file +75 -0
75 lines not on this page · raw message
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 28/49] perf python: Port rw-by-pid from Perl to perf module
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 11 lines
Replace the legacy Perl script rw-by-pid.pl with a standalone Python script in
tools/perf/python/rw-by-pid.pyusing the perf Python module.Improvements compared to the legacy Perl script:
- Remove the dependency on libperl andPerf::Trace::Util.
- Convert unsigned 32-bit and 64-bit error return values (0xfffff000..0xffffffff and >=0x8000000000000000) to negative errnos so failed read/write syscalls are recorded in the error table rather than inflatingbytes_read/bytes_written.
- Add argparse CLI support (-i/--input) and full type annotations.
Quoted 5 lines
Add a shell test
(test_rw_by_pid_python.sh) to verify the standalone script.Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=28
Ian Rogers
reviewerPATCH v4 29/49 perf python: Port rwtop from Perl to perf module
In reply to Ian RogersReplace the legacy Perl script rwtop.pl with a standalone Python script in tools/perf/python/rwtop.py using the perf Python module.
Improvements compared to the legacy Perl script:
- Remove the dependency on libperl and Perf::Trace::Util.
- Support both offline perf.data files (via perf.session) and live recording (via LiveSession with --live), driving periodic interval summaries from event timestamps rather than wall-clock SIGALRM timers so both live and offline runs produce deterministic output.
- Convert unsigned 32-bit and 64-bit error return values (0xfffff000..0xffffffff and >= 0x8000000000000000) to negative errnos so failed read/write syscalls are recorded in the error table rather than inflating bytes_read / bytes_written.
- Sanitize non-printable characters in /proc/<pid>/comm to prevent terminal control sequence injection.
Add a shell test
(test_rwtop_python.sh) to verify the standalone script.
--- tools/perf/python/rwtop.py | 256 ++++++++++++++++++++ tools/perf/tests/shell/test_rwtop_python.sh | 74 ++++++ 2 files changed, 330 insertions(+) create mode 100755 tools/perf/python/rwtop.py create mode 100755 tools/perf/tests/shell/test_rwtop_python.sh
tools/perf/python/rwtop.py new file +256 -0
@@ -0,0 +1,256 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0-only +"""Periodically displays system-wide r/w call activity, broken down by pid.""" +from __future__ import annotations + +import argparse +from collections import defaultdict +import os +import sys +from typing import Optional, Dict, Any +import perf +from perf_live import LiveSession + +class RwTop: + """Periodically displays system-wide r/w call activity.""" + def __init__(self, interval: int = 3, nlines: int = 20) -> None: + self.offline = False + self.interval_ns = interval * 1000000000 + self.nlines = nlines + self.reads: Dict[int, Dict[str, Any]] = defaultdict( + lambda: { + "bytes_requested": 0, + "bytes_read": 0, + "total_reads": 0, + "comm": "", + "errors": defaultdict(int), + } + ) + self.writes: Dict[int, Dict[str, Any]] = defaultdict( + lambda: { + "bytes_requested": 0, + "bytes_written": 0, + "total_writes": 0, + "comm": "", + "errors": defaultdict(int), + } + ) + self.unhandled: Dict[str, int] = defaultdict(int) + self.comm_cache: Dict[int, str] = {} + self.session: Optional[perf.session] = None + self.last_print_time: int = 0 + + def get_comm(self, pid: int, tid: Optional[int] = None) -> str: + """Resolve and cache the comm(and) of a pid.""" + comm = None + if self.session: + # In offline mode, query session.find_thread() directly so PERF_RECORD_COMM + # updates after execve are reflected immediately instead of returning a + # stale pre-exec comm from comm_cache. + try: + thread = (self.session.find_thread(pid, tid) + if tid is not None else self.session.find_thread(pid)) + comm = thread.comm() if thread else None + except (TypeError, AttributeError): + pass + if not comm: + comm = self.comm_cache.get(pid) + else: + comm = self.comm_cache.get(pid) + if comm: + return comm + try: + with open(f"/proc/{pid}/comm", "r", encoding="utf-8", errors="replace") as f: + comm = f.read().strip() + except OSError: + # The thread may have exited before /proc could be read. + pass + if not comm: + comm = f"PID({pid})" + comm = ''.join(c if c.isprintable() else '?' for c in comm) + self.comm_cache[pid] = comm + return comm + + def process_event(self, sample: perf.sample_event) -> None: + """Process events.""" + event_name = str(sample.evsel) + if event_name.startswith("evsel(") and event_name.endswith(")"): + event_name = event_name[6:-1] + event_name = "".join(c if c.isprintable() else "?" for c in event_name) + pid = sample.sample_pid + sample_time = getattr(sample, "sample_time", 0) or 0 + + if sample_time > 0: + if self.last_print_time == 0: + self.last_print_time = sample_time + elif (sample_time > self.last_print_time and + sample_time - self.last_print_time >= self.interval_ns): + self.print_totals() + self.last_print_time = sample_time + + # Map each event onto the totals it updates. "enter" events count the + # requested bytes, "exit" events the transferred bytes or the error. + handlers = { + "syscalls:sys_enter_read": (self.reads, "total_reads", None), + "syscalls:sys_exit_read": (self.reads, None, "bytes_read"), + "syscalls:sys_enter_write": (self.writes, "total_writes", None), + "syscalls:sys_exit_write": (self.writes, None, "bytes_written"), + } + handler = handlers.get(event_name) + if not handler: + self.unhandled[event_name] += 1 + return + + totals, count_key, bytes_key = handler + try: + value = sample.count if count_key else sample.ret + except AttributeError: + self.unhandled[event_name] += 1 + return + + data = totals[pid] + data["comm"] = self.get_comm(pid, getattr(sample, "sample_tid", None)) + if count_key: + data["bytes_requested"] += value + data[count_key] += 1 + elif bytes_key: + # Convert unsigned 32-bit or 64-bit kernel error return values to signed integers. + # Because kernel read/write transfers are bounded by MAX_RW_COUNT (0x7ffff000 < 2 GiB), + # 0xfffff000..0xffffffff is always a 32-bit negative errno even on 64-bit hosts. + if value > 0: + if 0xfffff000 <= value <= 0xffffffff: + value -= 0x100000000 + elif value >= 0x8000000000000000: + value -= 0x10000000000000000 + if value >= 0: + data[bytes_key] += value + else: + data["errors"][value] += 1 + + def print_totals(self) -> None: + """Print summary tables.""" + if not self.offline: + print('\x1b[H\x1b[2J', end='') + print("read counts by pid:\n") + print( + f"{'pid':>6s} {'comm':<20s} {'# reads':>10s} " + f"{'bytes_req':>10s} {'bytes_read':>10s}" + ) + print(f"{'-'*6} {'-'*20} {'-'*10} {'-'*10} {'-'*10}") + + count = 0 + for pid, data in sorted(self.reads.items(), + key=lambda kv: kv[1]["bytes_read"], reverse=True): + print( + f"{pid:6d} {data['comm']:<20s} {data['total_reads']:10d} " + f"{data['bytes_requested']:10d} {data['bytes_read']:10d}" + ) + count += 1 + if count >= self.nlines: + break + + print("\nfailed reads by pid:\n") + print(f"{'pid':>6s} {'comm':<20s} {'error #':>7s} {'# errors':>10s}") + print(f"{'-'*6} {'-'*20} {'-'*7} {'-'*10}") + + errcounts = [] + for pid, data in self.reads.items(): + for error, cnt in data["errors"].items(): + errcounts.append((pid, data["comm"], error, cnt)) + + sorted_errcounts = sorted(errcounts, key=lambda x: x[3], reverse=True) + for pid, comm, error, cnt in sorted_errcounts[:self.nlines]: + print(f"{pid:6d} {comm:<20s} {error:7d} {cnt:10d}") + + print("\nwrite counts by pid:\n") + print( + f"{'pid':>6s} {'comm':<20s} {'# writes':>10s} " + f"{'bytes_req':>10s} {'bytes_written':>13s}" + ) + print(f"{'-'*6} {'-'*20} {'-'*10} {'-'*10} {'-'*13}") + + count = 0 + for pid, data in sorted(self.writes.items(), + key=lambda kv: kv[1]["bytes_written"], reverse=True): + print( + f"{pid:6d} {data['comm']:<20s} {data['total_writes']:10d} " + f"{data['bytes_requested']:10d} {data['bytes_written']:13d}" + ) + count += 1 + if count >= self.nlines: + break + + print("\nfailed writes by pid:\n") + print(f"{'pid':>6s} {'comm':<20s} {'error #':>7s} {'# errors':>10s}") + print(f"{'-'*6} {'-'*20} {'-'*7} {'-'*10}") + + errcounts = [] + for pid, data in self.writes.items(): + for error, cnt in data["errors"].items(): + errcounts.append((pid, data["comm"], error, cnt)) + + sorted_errcounts = sorted(errcounts, key=lambda x: x[3], reverse=True) + for pid, comm, error, cnt in sorted_errcounts[:self.nlines]: + print(f"{pid:6d} {comm:<20s} {error:7d} {cnt:10d}") + + # Reset counts + self.reads.clear() + self.writes.clear() + self.comm_cache.clear() + + def run(self, input_file: str) -> None: + """Run the session.""" + self.session = perf.session(perf.data(input_file), sample=self.process_event) + try: + self.session.process_events() + finally: + # Break the reference cycle between perf.session and self.process_event + # because perf.session lacks cyclic GC support (tp_traverse). + self.session = None + + # Print final totals if there are any left + if self.reads or self.writes: + self.print_totals() + + if self.unhandled: + print("\nunhandled events:\n") + print(f"{'event':<40s} {'count':>10s}") + print(f"{'-'*40} {'-'*10}") + for event_name, count in self.unhandled.items(): + print(f"{event_name:<40s} {count:10d}") + +def main() -> None: + """Main function.""" + parser = argparse.ArgumentParser(description="Trace r/w activity by PID") + parser.add_argument( + "interval", type=int, nargs="?", default=3, help="Refresh interval in seconds" + ) + parser.add_argument("-i", "--input", default="perf.data", help="Input file") + parser.add_argument("-l", "--live", action="store_true", help="Run in live mode") + args = parser.parse_args() + + analyzer = RwTop(args.interval) + try: + if args.live or (not os.path.exists(args.input) and args.input == "perf.data"): + # Live mode + events = ( + "syscalls:sys_enter_read,syscalls:sys_exit_read," + "syscalls:sys_enter_write,syscalls:sys_exit_write" + ) + live_session = LiveSession(events, sample_callback=analyzer.process_event) + print("Live mode started. Press Ctrl+C to stop.", file=sys.stderr) + live_session.run() + else: + analyzer.offline = True + analyzer.run(args.input) + except IOError as e: + print(e, file=sys.stderr) + sys.exit(1) + except KeyboardInterrupt: + if not analyzer.offline: + print("\nStopping live mode...", file=sys.stderr) + if analyzer.reads or analyzer.writes: + analyzer.print_totals() + +if __name__ == "__main__": + main()
tools/perf/tests/shell/test_rwtop_python.sh new file +74 -0
74 lines not on this page · raw message
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 29/49] perf python: Port rwtop from Perl to perf module
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 16 lines
Replace the legacy Perl script rwtop.pl with a standalone Python script in
tools/perf/python/rwtop.pyusing the perf Python module.Improvements compared to the legacy Perl script:
- Remove the dependency on libperl andPerf::Trace::Util.
- Support both offline perf.data files (via perf.session) and live recording (via LiveSession with --live), driving periodic interval summaries from event timestamps rather than wall-clock SIGALRM timers so both live and offline runs produce deterministic output.
- Convert unsigned 32-bit and 64-bit error return values (0xfffff000..0xffffffff and >=0x8000000000000000) to negative errnos so failed read/write syscalls are recorded in the error table rather than inflatingbytes_read/bytes_written.
- Sanitize non-printable characters in /proc/<pid>/comm to prevent terminal control sequence injection.
Quoted 5 lines
Add a shell test
(test_rwtop_python.sh) to verify the standalone script.Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=29
Ian Rogers
reviewerPATCH v4 30/49 perf python: Port futex-contention to perf module
In reply to Ian RogersPort tools/perf/scripts/python/futex-contention.py to a standalone script in tools/perf/python/ using the perf module. Avoiding the embedded interpreter overhead improves execution speed by ~3.2x:
``` $ perf record -e syscalls:sys_*_futex -a sleep 1 ... $ time perf script tools/perf/scripts/python/futex-contention.py ... real 0m1.007s user 0m0.935s sys 0m0.072s $ time python3 tools/perf/python/futex-contention.py ... real 0m0.314s user 0m0.259s sys 0m0.056s ```
Additional improvements compared to the legacy script:
- Consolidate per-(tid, uaddr) contention count, total_time, min_time, and max_time into a single LockStats class instead of maintaining three separate dictionaries.
- Validate that uaddr and op tracepoint attributes are present on syscalls:sys_enter_futex samples rather than silently attributing missing fields to uaddr=0, op=0 (FUTEX_WAIT).
- Add -i/--input CLI option support via argparse and full type annotations.
Add a shell test (test_futex_contention_python.sh) to verify the standalone script.
--- tools/perf/python/futex-contention.py | 107 ++++++++++++++++ .../shell/test_futex_contention_python.sh | 115 ++++++++++++++++++ 2 files changed, 222 insertions(+) create mode 100755 tools/perf/python/futex-contention.py create mode 100755 tools/perf/tests/shell/test_futex_contention_python.sh
tools/perf/python/futex-contention.py new file +107 -0
@@ -0,0 +1,107 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +"""Measures futex contention.""" +from __future__ import annotations + +import argparse +from collections import defaultdict +from typing import Dict, Tuple +import perf + +class LockStats: + """Aggregate lock contention information.""" + def __init__(self) -> None: + self.count = 0 + self.total_time = 0 + self.min_time = 0 + self.max_time = 0 + + def add(self, duration: int) -> None: + """Add a new duration measurement.""" + self.count += 1 + self.total_time += duration + if self.count == 1: + self.min_time = duration + self.max_time = duration + else: + self.min_time = min(self.min_time, duration) + self.max_time = max(self.max_time, duration) + + def avg(self) -> float: + """Return average duration.""" + return self.total_time / self.count if self.count > 0 else 0.0 + +process_names: Dict[int, str] = {} +start_times: Dict[int, Tuple[int, int]] = {} +session = None +durations: Dict[Tuple[int, int], LockStats] = defaultdict(LockStats) + +FUTEX_WAIT = 0 +FUTEX_PRIVATE_FLAG = 128 +FUTEX_CLOCK_REALTIME = 256 +# Mask out FUTEX_PRIVATE_FLAG and FUTEX_CLOCK_REALTIME so variants such as +# FUTEX_WAIT_PRIVATE (0 | 128) match the base FUTEX_WAIT command. +FUTEX_CMD_MASK = ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME) + + +def handle_start(pid: int, tid: int, uaddr: int, op: int, start_time: int) -> None: + """Handle a futex sys_enter event.""" + if (op & FUTEX_CMD_MASK) != FUTEX_WAIT: + return + try: + if session: + process = session.find_thread(pid, tid) + if process: + process_names[tid] = process.comm() or "unknown" + except (TypeError, AttributeError): + pass + if tid not in process_names: + process_names[tid] = "unknown" + + start_times[tid] = (uaddr, start_time) + +def handle_end(tid: int, end_time: int) -> None: + """Handle a futex sys_exit event.""" + if tid not in start_times: + return + (uaddr, start_time) = start_times[tid] + del start_times[tid] + durations[(tid, uaddr)].add(end_time - start_time) + +def process_event(sample: perf.sample_event) -> None: + """Process a single sample event.""" + event_name = str(sample.evsel) + if event_name.startswith("evsel(") and event_name.endswith(")"): + event_name = event_name[6:-1] + if event_name.startswith("syscalls:sys_enter_futex"): + uaddr = getattr(sample, "uaddr", None) + op = getattr(sample, "op", None) + if uaddr is None or op is None: + return # Tracepoint fields missing, skip silent attribution to 0 + handle_start(getattr(sample, "sample_pid", sample.sample_tid), + sample.sample_tid, uaddr, op, sample.sample_time) + elif event_name.startswith("syscalls:sys_exit_futex"): + handle_end(sample.sample_tid, sample.sample_time) + + +if __name__ == "__main__": + ap = argparse.ArgumentParser(description="Measure futex contention") + ap.add_argument("-i", "--input", default="perf.data", help="Input file name") + args = ap.parse_args() + + try: + session = perf.session(perf.data(args.input), sample=process_event) + try: + session.process_events() + except KeyboardInterrupt: + pass + + for ((t, u), stats) in sorted(durations.items()): + avg_ns = stats.avg() + print(f"{process_names.get(t, 'unknown')}[{t}] lock {u:x} contended " + f"{stats.count} times, {avg_ns:.0f} avg ns " + f"[max: {stats.max_time} ns, min {stats.min_time} ns]") + finally: + # Break the reference cycle between the global session and the + # process_event callback so the C perf.session object is freed. + session = None
tools/perf/tests/shell/test_futex_contention_python.sh new file +115 -0
115 lines not on this page · raw message
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 30/49] perf python: Port futex-contention to perf module
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 19 lines
Port
tools/perf/scripts/python/futex-contention.pyto a standalone script intools/perf/python/using the perf module. Avoiding the embedded interpreter overhead improves execution speed by ~3.2x:```
$ perf record -e syscalls:sys_*_futex -a sleep 1 ... $ time perf script tools/perf/scripts/python/futex-contention.py ... real 0m1.007s user 0m0.935s sys 0m0.072s $ time python3 tools/perf/python/futex-contention.py ... real 0m0.314s [ ... ] Add a shell test (test_futex_contention_python.sh) to verify the standalone script.
Quoted 2 lines
Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=30
Ian Rogers
reviewerPATCH v4 31/49 perf python: Port task-analyzer to perf module
In reply to Ian RogersPort task-analyzer.py from tools/perf/scripts/python/ to a standalone script in tools/perf/python/ refactored into a class-based architecture.
Improvements compared to the legacy script:
- Support both offline perf.data file analysis (using perf.session) and live trace capture (using evlist.read_on_cpu), accessing sched:sched_switch tracepoint fields directly from sample objects.
- Automatically disable ANSI terminal color escape sequences when --csv or --csv-summary is enabled so CSV column headers ('Comm,', 'Time Out-Out,', etc.) are never polluted by color codes when running interactively on a TTY (e.g. as root).
- Sanitize non-printable characters and leading CSV formula characters (=, +, -, @) in task comm strings.
- Emit a one-time warning to stderr if sched:sched_switch samples are missing tracepoint fields (such as when recorded without libtraceevent support).
Update test_task_analyzer.sh to invoke the standalone script.
--- tools/perf/python/task-analyzer.py | 908 +++++++++++++++++++ tools/perf/tests/shell/test_task_analyzer.sh | 96 +- 2 files changed, 971 insertions(+), 33 deletions(-) create mode 100755 tools/perf/python/task-analyzer.py
tools/perf/python/task-analyzer.py new file +908 -0
@@ -0,0 +1,908 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# task-analyzer.py - comprehensive perf tasks analysis +# Copyright (c) 2022, Hagen Paul Pfeifer <[email protected]> +# Licensed under the terms of the GNU GPL License version 2 +# +# Usage: +# +# perf record -e sched:sched_switch -a -- sleep 10 +# ./task-analyzer.py +# +"""Comprehensive perf tasks analysis.""" +from __future__ import annotations + +import argparse +from contextlib import contextmanager +import decimal + +from typing import List, Dict, Union + +def _median(numbers: List[decimal.Decimal]) -> decimal.Decimal: + """phython3 hat statistics module - we have nothing""" + n = len(numbers) + index = n // 2 + if n % 2: + return sorted(numbers)[index] + return sum(sorted(numbers)[index - 1 : index + 1]) / decimal.Decimal(2) + +def _mean(numbers: List[decimal.Decimal]) -> decimal.Decimal: + return sum(numbers) / decimal.Decimal(len(numbers)) + +import os +import string +import sys +from typing import Any, Optional +import perf + + +# Columns will have a static size to align everything properly +# Support of 116 days of active update with nano precision +LEN_SWITCHED_IN = len("9999999.999999999") +LEN_SWITCHED_OUT = len("9999999.999999999") +LEN_CPU = len("000") +LEN_PID = len("maxvalue") +LEN_TID = len("maxvalue") +LEN_COMM = len("max-comms-length") +LEN_RUNTIME = len("999999.999") +# Support of 3.45 hours of timespans +LEN_OUT_IN = len("99999999999.999") +LEN_OUT_OUT = len("99999999999.999") +LEN_IN_IN = len("99999999999.999") +LEN_IN_OUT = len("99999999999.999") + +class Timespans: + """Tracks elapsed time between occurrences of the same task.""" + def __init__(self, args: argparse.Namespace, time_unit: str) -> None: + self.args = args + self.time_unit = time_unit + self._last_start: Optional[decimal.Decimal] = None + self._last_finish: Optional[decimal.Decimal] = None + self.current = { + 'out_out': decimal.Decimal(-1), + 'in_out': decimal.Decimal(-1), + 'out_in': decimal.Decimal(-1), + 'in_in': decimal.Decimal(-1) + } + if args.summary_extended: + self._time_in: decimal.Decimal = decimal.Decimal(-1) + self.max_vals = { + 'out_in': decimal.Decimal(-1), + 'at': decimal.Decimal(-1), + 'in_out': decimal.Decimal(-1), + 'in_in': decimal.Decimal(-1), + 'out_out': decimal.Decimal(-1) + } + + def feed(self, task: 'Task') -> None: + """Calculate timespans from chronological task occurrences.""" + if not self._last_finish: + self._last_start = task.time_in(self.time_unit) + self._last_finish = task.time_out(self.time_unit) + return + assert self._last_start is not None + assert self._last_finish is not None + self._time_in = task.time_in() + time_in = task.time_in(self.time_unit) + time_out = task.time_out(self.time_unit) + self.current['in_in'] = time_in - self._last_start + self.current['out_in'] = time_in - self._last_finish + self.current['in_out'] = time_out - self._last_start + self.current['out_out'] = time_out - self._last_finish + if self.args.summary_extended: + self.update_max_entries() + self._last_finish = task.time_out(self.time_unit) + self._last_start = task.time_in(self.time_unit) + + def update_max_entries(self) -> None: + """Update maximum timespans.""" + self.max_vals['in_in'] = max(self.max_vals['in_in'], self.current['in_in']) + self.max_vals['out_out'] = max(self.max_vals['out_out'], self.current['out_out']) + self.max_vals['in_out'] = max(self.max_vals['in_out'], self.current['in_out']) + if self.current['out_in'] > self.max_vals['out_in']: + self.max_vals['out_in'] = self.current['out_in'] + self.max_vals['at'] = self._time_in + +class Task: + """Handles information of a given task.""" + def __init__(self, task_id: str, tid: int, cpu: int, comm: str) -> None: + self.id = task_id + self.tid = tid + self.cpu = cpu + self.comm = comm + self.pid: Optional[int] = None + self._time_in: Optional[decimal.Decimal] = None + self._time_out: Optional[decimal.Decimal] = None + + def schedule_in_at(self, time_ns: int) -> None: + """Set schedule in time.""" + self._time_in = decimal.Decimal(time_ns) / decimal.Decimal(1e9) + + def schedule_out_at(self, time_ns: int) -> None: + """Set schedule out time.""" + self._time_out = decimal.Decimal(time_ns) / decimal.Decimal(1e9) + + def time_out(self, unit: str = "s") -> decimal.Decimal: + """Return schedule out time.""" + factor = TaskAnalyzer.time_uniter(unit) + return self._time_out * decimal.Decimal(factor) if self._time_out else decimal.Decimal(0) + + def time_in(self, unit: str = "s") -> decimal.Decimal: + """Return schedule in time.""" + factor = TaskAnalyzer.time_uniter(unit) + return self._time_in * decimal.Decimal(factor) if self._time_in else decimal.Decimal(0) + + def runtime(self, unit: str = "us") -> decimal.Decimal: + """Return runtime.""" + factor = TaskAnalyzer.time_uniter(unit) + if self._time_out is not None and self._time_in is not None: + return (self._time_out - self._time_in) * decimal.Decimal(factor) + return decimal.Decimal(0) + + def update_pid(self, pid: int) -> None: + """Update PID.""" + self.pid = pid + +class Summary: + """ + Primary instance for calculating the summary output. Processes the whole trace to + find and memorize relevant data such as mean, max et cetera. This instance handles + dynamic alignment aspects for summary output. + """ + + def __init__(self, analyzer): + self.analyzer = analyzer + self.args = analyzer.args + self.db = analyzer.db + self.time_unit = analyzer.time_unit + self.fd_sum = analyzer.fd_sum + self._body = [] + + class AlignmentHelper: + """ + Used to calculated the alignment for the output of the summary. + """ + def __init__(self, pid, tid, comm, runs, acc, mean, + median, min_val, max_val, max_at): + self.pid = pid + self.tid = tid + self.comm = comm + self.runs = runs + self.acc = acc + self.mean = mean + self.median = median + self.min = min_val + self.max = max_val + self.max_at = max_at + self.out_in = None + self.inter_at = None + self.out_out = None + self.in_in = None + self.in_out = None + + def _print_header(self): + ''' + Output is aligned using the formatted column widths in self.db. + ''' + len_tasks = max( + len("Task Information"), + sum(self.db["task_info"].values()) + len(self.db["task_info"]) - 1, + ) + fmt = "{{:^{}}}".format(len_tasks) + fmt += " {{:^{}}}".format( + sum(self.db["runtime_info"].values()) + len(self.db["runtime_info"]) - 1 + ) + _header = ("Task Information", "Runtime Information") + + if self.args.summary_extended: + fmt += " {{:^{}}}".format( + sum(self.db["inter_times"].values()) + len(self.db["inter_times"]) - 1 + ) + _header += ("Max Inter Task Times",) + self.fd_sum.write(fmt.format(*_header) + "\n") + + def _column_titles(self): + """ + Cells are being processed and displayed in different way so an alignment adjust + is implemented depeding on the choice of the timeunit. The positions of the max + values are being displayed in grey. Thus in their format two additional {}, + are placed for color set and reset. + """ + separator, fix_csv_align = self.analyzer.prepare_fmt_sep(is_summary=True) + fmt = "{{:>{}}}".format(self.db["task_info"]["pid"] * fix_csv_align) + fmt += "{}{{:>{}}}".format(separator, self.db["task_info"]["tid"] * fix_csv_align) + fmt += "{}{{:>{}}}".format(separator, self.db["task_info"]["comm"] * fix_csv_align) + fmt += "{}{{:>{}}}".format(separator, self.db["runtime_info"]["runs"] * fix_csv_align) + fmt += "{}{{:>{}}}".format(separator, self.db["runtime_info"]["acc"] * fix_csv_align) + fmt += "{}{{:>{}}}".format(separator, self.db["runtime_info"]["mean"] * fix_csv_align) + fmt += "{}{{:>{}}}".format( + separator, self.db["runtime_info"]["median"] * fix_csv_align + ) + fmt += "{}{{:>{}}}".format( + separator, self.db["runtime_info"]["min"] * fix_csv_align + ) + fmt += "{}{{:>{}}}".format( + separator, self.db["runtime_info"]["max"] * fix_csv_align + ) + fmt += "{}{{}}{{:>{}}}{{}}".format( + separator, self.db["runtime_info"]["max_at"] * fix_csv_align + ) + + grey = "" if self.args.csv_summary else TaskAnalyzer.COLORS["grey"] + reset = "" if self.args.csv_summary else TaskAnalyzer.COLORS["reset"] + column_titles = ("PID", "TID", "Comm") + column_titles += ("Runs", "Accumulated", "Mean", "Median", "Min", "Max") + column_titles += (grey, "Max At", reset) + + if self.args.summary_extended: + fmt += "{}{{:>{}}}".format( + separator, + self.db["inter_times"]["out_in"] * fix_csv_align + ) + fmt += "{}{{}}{{:>{}}}{{}}".format( + separator, + self.db["inter_times"]["inter_at"] * fix_csv_align + ) + fmt += "{}{{:>{}}}".format( + separator, + self.db["inter_times"]["out_out"] * fix_csv_align + ) + fmt += "{}{{:>{}}}".format( + separator, + self.db["inter_times"]["in_in"] * fix_csv_align + ) + fmt += "{}{{:>{}}}".format( + separator, + self.db["inter_times"]["in_out"] * fix_csv_align + ) + + column_titles += ( + "Out-In", grey, "Max At", + reset, "Out-Out", "In-In", "In-Out" + ) + + self.fd_sum.write(fmt.format(*column_titles) + "\n") + + def _task_stats(self): + """calculates the stats of every task and constructs the printable summary""" + grey = "" if self.args.csv_summary else TaskAnalyzer.COLORS["grey"] + reset = "" if self.args.csv_summary else TaskAnalyzer.COLORS["reset"] + for tid in sorted(self.db["tid"]): + color_one_sample = grey + color_reset = reset + no_executed = 0 + runtimes = [] + time_in = [] + timespans = Timespans(self.args, self.time_unit) + for task in self.db["tid"][tid]: + pid = task.pid + comm = task.comm + no_executed += 1 + runtimes.append(task.runtime(self.time_unit)) + time_in.append(task.time_in()) + timespans.feed(task) + if len(runtimes) > 1: + color_one_sample = "" + color_reset = "" + time_max = max(runtimes) + time_min = min(runtimes) + max_at = time_in[runtimes.index(max(runtimes))] + + # The size of the decimal after sum,mean and median varies, thus we cut + # the decimal number, by rounding it. It has no impact on the output, + # because we have a precision of the decimal points at the output. + time_sum = round(sum(runtimes), 3) + time_mean = round(_mean(runtimes), 3) + time_median = round(_median(runtimes), 3) + + align_helper = self.AlignmentHelper(pid, tid, comm, no_executed, time_sum, + time_mean, time_median, time_min, time_max, max_at) + self._body.append([ + pid, tid, comm, no_executed, time_sum, color_one_sample, + time_mean, time_median, time_min, time_max, + grey, max_at, + reset, color_reset + ]) + if self.args.summary_extended: + self._body[-1].extend([timespans.max_vals['out_in'], + grey, timespans.max_vals['at'], + reset, timespans.max_vals['out_out'], + timespans.max_vals['in_in'], + timespans.max_vals['in_out']]) + align_helper.out_in = timespans.max_vals['out_in'] + align_helper.inter_at = timespans.max_vals['at'] + align_helper.out_out = timespans.max_vals['out_out'] + align_helper.in_in = timespans.max_vals['in_in'] + align_helper.in_out = timespans.max_vals['in_out'] + self._calc_alignments_summary(align_helper) + + def _format_stats(self): + separator, fix_csv_align = self.analyzer.prepare_fmt_sep(is_summary=True) + decimal_precision, time_precision = self.analyzer.prepare_fmt_precision() + len_pid = self.db["task_info"]["pid"] * fix_csv_align + len_tid = self.db["task_info"]["tid"] * fix_csv_align + len_comm = self.db["task_info"]["comm"] * fix_csv_align + len_runs = self.db["runtime_info"]["runs"] * fix_csv_align + len_acc = self.db["runtime_info"]["acc"] * fix_csv_align + len_mean = self.db["runtime_info"]["mean"] * fix_csv_align + len_median = self.db["runtime_info"]["median"] * fix_csv_align + len_min = self.db["runtime_info"]["min"] * fix_csv_align + len_max = self.db["runtime_info"]["max"] * fix_csv_align + len_max_at = self.db["runtime_info"]["max_at"] * fix_csv_align + if self.args.summary_extended: + len_out_in = self.db["inter_times"]["out_in"] * fix_csv_align + len_inter_at = self.db["inter_times"]["inter_at"] * fix_csv_align + len_out_out = self.db["inter_times"]["out_out"] * fix_csv_align + len_in_in = self.db["inter_times"]["in_in"] * fix_csv_align + len_in_out = self.db["inter_times"]["in_out"] * fix_csv_align + + fmt = "{{:{}d}}".format(len_pid) + fmt += "{}{{:{}d}}".format(separator, len_tid) + fmt += "{}{{:>{}}}".format(separator, len_comm) + fmt += "{}{{:{}d}}".format(separator, len_runs) + fmt += "{}{{:{}.{}f}}".format(separator, len_acc, time_precision) + fmt += "{}{{}}{{:{}.{}f}}".format(separator, len_mean, time_precision) + fmt += "{}{{:{}.{}f}}".format(separator, len_median, time_precision) + fmt += "{}{{:{}.{}f}}".format(separator, len_min, time_precision) + fmt += "{}{{:{}.{}f}}".format(separator, len_max, time_precision) + fmt += "{}{{}}{{:{}.{}f}}{{}}{{}}".format( + separator, len_max_at, decimal_precision + ) + if self.args.summary_extended: + fmt += "{}{{:{}.{}f}}".format(separator, len_out_in, time_precision) + fmt += "{}{{}}{{:{}.{}f}}{{}}".format( + separator, len_inter_at, decimal_precision + ) + fmt += "{}{{:{}.{}f}}".format(separator, len_out_out, time_precision) + fmt += "{}{{:{}.{}f}}".format(separator, len_in_in, time_precision) + fmt += "{}{{:{}.{}f}}".format(separator, len_in_out, time_precision) + return fmt + + def _calc_alignments_summary(self, align_helper): + # Measure the formatted string widths (e.g. f"{val:.{decimal_precision}f}" + # and f"{val:.{time_precision}f}") rather than str(val), because Decimal's + # default string representation may include unrounded fractional digits or + # omit trailing zeros that _format_stats() renders with fixed precision. + decimal_precision, time_precision = self.analyzer.prepare_fmt_precision() + for key in self.db["task_info"]: + val_len = len(str(getattr(align_helper, key))) + if val_len > self.db["task_info"][key]: + self.db["task_info"][key] = val_len + for key in self.db["runtime_info"]: + val = getattr(align_helper, key) + if key == "runs": + val_len = len(str(val)) + elif key == "max_at": + val_len = len(f"{val:.{decimal_precision}f}") + else: + val_len = len(f"{val:.{time_precision}f}") + if val_len > self.db["runtime_info"][key]: + self.db["runtime_info"][key] = val_len + if self.args.summary_extended: + for key in self.db["inter_times"]: + val = getattr(align_helper, key) + if key == "inter_at": + val_len = len(f"{val:.{decimal_precision}f}") + else: + val_len = len(f"{val:.{time_precision}f}") + if val_len > self.db["inter_times"][key]: + self.db["inter_times"][key] = val_len + + def print(self): + self._task_stats() + fmt = self._format_stats() + + if not self.args.csv_summary: + print("\nSummary", file=self.fd_sum) + self._print_header() + self._column_titles() + for i in range(len(self._body)): + self.fd_sum.write(fmt.format(*tuple(self._body[i])) + "\n") + + +class TaskAnalyzer: + + """Main class for task analysis.""" + + COLORS = { + "grey": "\033[90m", + "red": "\033[91m", + "green": "\033[92m", + "yellow": "\033[93m", + "blue": "\033[94m", + "violet": "\033[95m", + "reset": "\033[0m", + } + + def __init__(self, args: argparse.Namespace) -> None: + self.args = args + self.db: Dict[str, Any] = {} + self.session: Optional[perf.session] = None + self._tgid_cache: Dict[int, int] = {} + self.time_unit = "us" + if args.ns: + self.time_unit = "ns" + elif args.ms: + self.time_unit = "ms" + self._init_db() + self._check_color() + self.fd_task = sys.stdout + self.fd_sum = sys.stdout + + @contextmanager + def open_output(self, filename: str, default: Any): + """Context manager for file or stdout.""" + if filename: + with open(filename, "w", encoding="utf-8") as f: + yield f + else: + yield default + + def _init_db(self) -> None: + self.db["running"] = {} + self.db["tid"] = {} + self.db["global"] = [] + if (self.args.summary or self.args.summary_extended or + self.args.summary_only or self.args.csv_summary): + self.db["task_info"] = {} + self.db["runtime_info"] = {} + self.db["task_info"]["pid"] = len("PID") + self.db["task_info"]["tid"] = len("TID") + self.db["task_info"]["comm"] = len("Comm") + self.db["runtime_info"]["runs"] = len("Runs") + self.db["runtime_info"]["acc"] = len("Accumulated") + self.db["runtime_info"]["max"] = len("Max") + self.db["runtime_info"]["max_at"] = len("Max At") + self.db["runtime_info"]["min"] = len("Min") + self.db["runtime_info"]["mean"] = len("Mean") + self.db["runtime_info"]["median"] = len("Median") + if self.args.summary_extended: + self.db["inter_times"] = {} + self.db["inter_times"]["out_in"] = len("Out-In") + self.db["inter_times"]["inter_at"] = len("Max At") + self.db["inter_times"]["out_out"] = len("Out-Out") + self.db["inter_times"]["in_in"] = len("In-In") + self.db["inter_times"]["in_out"] = len("In-Out") + + def _check_color(self) -> None: + """Check if color should be enabled.""" + if self.args.csv: + TaskAnalyzer.COLORS = {k: "" for k in TaskAnalyzer.COLORS} + return + if sys.stdout.isatty() and self.args.stdio_color != "never": + return + if self.args.stdio_color == "always": + return + TaskAnalyzer.COLORS = {k: "" for k in TaskAnalyzer.COLORS} + + @staticmethod + def time_uniter(unit: str) -> float: + """Return time unit factor.""" + picker = {"s": 1, "ms": 1e3, "us": 1e6, "ns": 1e9} + return picker[unit] + + def _task_id(self, pid: int, cpu: int) -> str: + return f"{pid}-{cpu}" + + def _filter_non_printable(self, unfiltered: Union[str, bytearray]) -> str: + # Strip non-printable characters, whitespace control characters + # (\r\n\t\x0b\x0c), quotes (", '), and ';' because --csv and + # --csv-summary emit unquoted ';'-delimited columns. Also replace a + # leading '=', '+', '-', or '@' with '_' to mitigate CSV formula / DDE + # injection attacks if an attacker-controlled process comm is opened in + # a spreadsheet program. + if isinstance(unfiltered, (bytearray, bytes)): + unfiltered = unfiltered.decode('utf-8', 'ignore') + filtered = "" + for char in unfiltered: + if char in string.printable and char not in "\r\n\t\x0b\x0c;\"'": + filtered += char + stripped = filtered.lstrip() + if stripped and stripped[0] in "=+-@": + filtered = "_" + stripped[1:] + return filtered + + def prepare_fmt_precision(self) -> tuple[int, int]: + if self.args.ns: + return 9, 0 + return 6, 3 + + def prepare_fmt_sep(self, is_summary: bool = False) -> tuple[str, int]: + # fix_csv_align multiplies format field widths: 0 in CSV mode collapses + # {:>N} padding to {:>0} (no extra spaces around ';'), while 1 in + # standard text mode preserves fixed-width column alignment. + if (is_summary and self.args.csv_summary) or (not is_summary and self.args.csv): + return ";", 0 + return " ", 1 + + def _fmt_header(self) -> str: + separator, fix_csv_align = self.prepare_fmt_sep() + fmt = f"{{:>{LEN_SWITCHED_IN*fix_csv_align}}}" + fmt += f"{separator}{{:>{LEN_SWITCHED_OUT*fix_csv_align}}}" + fmt += f"{separator}{{:>{LEN_CPU*fix_csv_align}}}" + fmt += f"{separator}{{:>{LEN_PID*fix_csv_align}}}" + fmt += f"{separator}{{:>{LEN_TID*fix_csv_align}}}" + fmt += f"{separator}{{:>{LEN_COMM*fix_csv_align}}}" + fmt += f"{separator}{{:>{LEN_RUNTIME*fix_csv_align}}}" + fmt += f"{separator}{{:>{LEN_OUT_IN*fix_csv_align}}}" + if self.args.extended_times: + fmt += f"{separator}{{:>{LEN_OUT_OUT*fix_csv_align}}}" + fmt += f"{separator}{{:>{LEN_IN_IN*fix_csv_align}}}" + fmt += f"{separator}{{:>{LEN_IN_OUT*fix_csv_align}}}" + return fmt + + def _fmt_body(self) -> str: + separator, fix_csv_align = self.prepare_fmt_sep() + decimal_precision, time_precision = self.prepare_fmt_precision() + fmt = f"{{}}{{:{LEN_SWITCHED_IN*fix_csv_align}.{decimal_precision}f}}" + fmt += f"{separator}{{:{LEN_SWITCHED_OUT*fix_csv_align}.{decimal_precision}f}}" + fmt += f"{separator}{{:{LEN_CPU*fix_csv_align}d}}" + fmt += f"{separator}{{:{LEN_PID*fix_csv_align}d}}" + fmt += f"{separator}{{}}{{:{LEN_TID*fix_csv_align}d}}{{}}" + fmt += f"{separator}{{}}{{:>{LEN_COMM*fix_csv_align}}}" + fmt += f"{separator}{{:{LEN_RUNTIME*fix_csv_align}.{time_precision}f}}" + if self.args.extended_times: + fmt += f"{separator}{{:{LEN_OUT_IN*fix_csv_align}.{time_precision}f}}" + fmt += f"{separator}{{:{LEN_OUT_OUT*fix_csv_align}.{time_precision}f}}" + fmt += f"{separator}{{:{LEN_IN_IN*fix_csv_align}.{time_precision}f}}" + fmt += f"{separator}{{:{LEN_IN_OUT*fix_csv_align}.{time_precision}f}}{{}}" + else: + fmt += f"{separator}{{:{LEN_OUT_IN*fix_csv_align}.{time_precision}f}}{{}}" + return fmt + + def _print_header(self) -> None: + fmt = self._fmt_header() + header = ["Switched-In", "Switched-Out", "CPU", "PID", "TID", "Comm", + "Runtime", "Time Out-In"] + if self.args.extended_times: + header += ["Time Out-Out", "Time In-In", "Time In-Out"] + self.fd_task.write(fmt.format(*header) + "\n") + + def _print_task_finish(self, task: Task) -> None: + c_row_set = "" + c_row_reset = "" + out_in: Any = -1 + out_out: Any = -1 + in_in: Any = -1 + in_out: Any = -1 + fmt = self._fmt_body() + + if str(task.tid) in self.args.highlight_tasks_map: + c_row_set = TaskAnalyzer.COLORS.get(self.args.highlight_tasks_map[str(task.tid)], '') + c_row_reset = TaskAnalyzer.COLORS["reset"] + if task.comm in self.args.highlight_tasks_map: + c_row_set = TaskAnalyzer.COLORS.get(self.args.highlight_tasks_map[task.comm], '') + c_row_reset = TaskAnalyzer.COLORS["reset"] + + c_tid_set = "" + c_tid_reset = "" + if task.pid == task.tid: + c_tid_set = TaskAnalyzer.COLORS["grey"] + c_tid_reset = TaskAnalyzer.COLORS["reset"] + + if task.tid in self.db["tid"]: + last_tid_task = self.db["tid"][task.tid][-1] + timespan_gap_tid = Timespans(self.args, self.time_unit) + timespan_gap_tid.feed(last_tid_task) + timespan_gap_tid.feed(task) + out_in = timespan_gap_tid.current['out_in'] + out_out = timespan_gap_tid.current['out_out'] + in_in = timespan_gap_tid.current['in_in'] + in_out = timespan_gap_tid.current['in_out'] + + if self.args.extended_times: + line_out = fmt.format(c_row_set, task.time_in(), task.time_out(), task.cpu, + task.pid, c_tid_set, task.tid, c_tid_reset, c_row_set, task.comm, + task.runtime(self.time_unit), out_in, out_out, in_in, in_out, + c_row_reset) + "\n" + else: + line_out = fmt.format(c_row_set, task.time_in(), task.time_out(), task.cpu, + task.pid, c_tid_set, task.tid, c_tid_reset, c_row_set, task.comm, + task.runtime(self.time_unit), out_in, c_row_reset) + "\n" + self.fd_task.write(line_out) + + def _record_cleanup(self, _list: list[Any]) -> list[Any]: + need_summary = (self.args.summary or self.args.summary_extended or + self.args.summary_only or self.args.csv_summary) + if not need_summary and len(_list) > 1: + return _list[len(_list) - 1:] + return _list + + def _record_by_tid(self, task: Task) -> None: + tid = task.tid + if tid not in self.db["tid"]: + self.db["tid"][tid] = [] + self.db["tid"][tid].append(task) + self.db["tid"][tid] = self._record_cleanup(self.db["tid"][tid]) + + def _record_global(self, task: Task) -> None: + self.db["global"].append(task) + self.db["global"] = self._record_cleanup(self.db["global"]) + + def _handle_task_finish(self, tid: int, cpu: int, time_ns: int, pid: int) -> None: + if tid == 0 and (not self.args.tid_renames or 0 not in self.args.tid_renames): + return + _id = self._task_id(tid, cpu) + if _id not in self.db["running"]: + return + task = self.db["running"][_id] + task.schedule_out_at(time_ns) + task.update_pid(pid) + del self.db["running"][_id] + + if not self._limit_filtered(tid, pid, task.comm): + if not self.args.summary_only: + self._print_task_finish(task) + self._record_by_tid(task) + self._record_global(task) + + def _handle_task_start(self, tid: int, cpu: int, comm: str, time_ns: int) -> None: + if tid == 0 and (not self.args.tid_renames or 0 not in self.args.tid_renames): + return + if tid in self.args.tid_renames: + comm = self._filter_non_printable(self.args.tid_renames[tid]) + _id = self._task_id(tid, cpu) + if _id in self.db["running"]: + return + task = Task(_id, tid, cpu, comm) + task.schedule_in_at(time_ns) + self.db["running"][_id] = task + + def _limit_filtered(self, tid: int, pid: int, comm: str) -> bool: + """Filter tasks based on CLI arguments.""" + match_filter = False + if self.args.filter_tasks: + if (str(tid) in self.args.filter_tasks or + str(pid) in self.args.filter_tasks or + comm in self.args.filter_tasks): + match_filter = True + + match_limit = False + if self.args.limit_to_tasks: + if (str(tid) in self.args.limit_to_tasks or + str(pid) in self.args.limit_to_tasks or + comm in self.args.limit_to_tasks): + match_limit = True + + if self.args.filter_tasks and match_filter: + return True + if self.args.limit_to_tasks and not match_limit: + return True + return False + + def _is_within_timelimit(self, time_ns: int) -> bool: + if not self.args.time_limit: + return True + time_s = decimal.Decimal(time_ns) / decimal.Decimal(1e9) + bounds = self.args.time_limit.split(":") + lower_bound = bounds[0] if len(bounds) > 0 else "" + upper_bound = bounds[1] if len(bounds) > 1 else "" + if lower_bound and time_s < decimal.Decimal(lower_bound): + return False + if upper_bound and time_s > decimal.Decimal(upper_bound): + return False + return True + + def process_event(self, sample: perf.sample_event) -> None: + """Process sched:sched_switch events.""" + if "sched:sched_switch" not in str(sample.evsel): + return + + time_ns = sample.sample_time + if not self._is_within_timelimit(time_ns): + return + + # Access tracepoint fields directly from sample object + try: + prev_pid = sample.prev_pid + next_pid = sample.next_pid + next_comm = sample.next_comm + common_cpu = sample.sample_cpu + except AttributeError: + if not self.db.get("warned_missing_fields"): + self.db["warned_missing_fields"] = True + print("Warning: sched:sched_switch sample missing tracepoint fields " + "(is libtraceevent support enabled?).", file=sys.stderr) + return + + next_comm = self._filter_non_printable(next_comm) + + # Task finish for previous task. Resolve TGID (process ID) from TID: + # in file mode we query perf.session.find_thread() (checking thread.pid > 0 + # so an unresolved -1 does not overwrite the prev_pid fallback), whereas in + # live mode (self.session is None) we read /proc/<tid>/status and cache + # the lookup in _tgid_cache. + prev_tgid = prev_pid # Fallback + if prev_pid != 0: + if self.session: + try: + thread = self.session.find_thread(-1, prev_pid) + if thread and thread.pid > 0: + prev_tgid = thread.pid + except (OSError, ValueError, KeyError, RuntimeError, TypeError, AttributeError): + pass + elif prev_pid in self._tgid_cache: + prev_tgid = self._tgid_cache[prev_pid] + else: + if len(self._tgid_cache) >= 4096: + self._tgid_cache.pop(next(iter(self._tgid_cache))) + self._tgid_cache[prev_pid] = prev_tgid + try: + with open(f"/proc/{prev_pid}/status", encoding="utf-8") as f: + for line in f: + if line.startswith("Tgid:"): + prev_tgid = int(line.split()[1]) + self._tgid_cache[prev_pid] = prev_tgid + break + except (OSError, ValueError, KeyError, RuntimeError): + pass + self._handle_task_finish(prev_pid, common_cpu, time_ns, prev_tgid) + # Task start for next task + self._handle_task_start(next_pid, common_cpu, next_comm, time_ns) + + def print_summary(self) -> None: + """Calculate and print summary.""" + need_summary = (self.args.summary or self.args.summary_extended or + self.args.summary_only or self.args.csv_summary) + if not need_summary: + return + + Summary(self).print() + + def _run_file(self) -> None: + if not self.args.summary_only: + self._print_header() + + session = perf.session(perf.data(self.args.input), sample=self.process_event) + self.session = session + try: + session.process_events() + except KeyboardInterrupt: + pass + finally: + # Break the reference cycle between self.session and the bound + # self.process_event callback so the C perf.session object is freed. + self.session = None + + if not self.db["global"]: + print(f"Warning: No sched:sched_switch trace events found in '{self.args.input}'.", + file=sys.stderr) + + self.print_summary() + + def _run_live(self) -> None: + if not self.args.summary_only: + self._print_header() + + cpus = perf.cpu_map() + threads = perf.thread_map(-1) + evlist = perf.parse_events("sched:sched_switch", cpus, threads) + evlist.config() + + evlist.open() + evlist.mmap() + evlist.enable() + + # Per-CPU perf ring buffers are drained sequentially in a loop, so events + # read from CPU N may have timestamps slightly earlier than events just + # read from CPU 0. Buffer events in pending_events and only dispatch those + # older than a 50 ms watermark behind max_ts so cross-CPU migrations and + # switches are processed in global timestamp order. + pending_events: list[perf.sample_event] = [] + print("Live mode started. Press Ctrl+C to stop.", file=sys.stderr) + try: + while True: + try: + evlist.poll(timeout=100) + except InterruptedError: + continue + for cpu in cpus: + while True: + event = evlist.read_on_cpu(cpu) + if not event: + break + if not isinstance(event, perf.sample_event): + continue + pending_events.append(event) + if pending_events: + pending_events.sort( + key=lambda e: getattr(e, 'sample_time', getattr(e, 'time', 0)) + ) + max_ts = getattr( + pending_events[-1], 'sample_time', getattr(pending_events[-1], 'time', 0) + ) + cutoff_ts = max_ts - 50_000_000 + ready_idx = 0 + for event in pending_events: + ev_ts = getattr(event, 'sample_time', getattr(event, 'time', 0)) + if ev_ts <= cutoff_ts: + self.process_event(event) + ready_idx += 1 + else: + break + del pending_events[:ready_idx] + except KeyboardInterrupt: + print("\nStopping live mode...", file=sys.stderr) + finally: + pending_events.sort(key=lambda e: getattr(e, 'sample_time', getattr(e, 'time', 0))) + for event in pending_events: + self.process_event(event) + evlist.close() + self.print_summary() + + def run(self) -> None: + """Run the session.""" + is_live = (self.args.live or + (not os.path.exists(self.args.input) and self.args.input == "perf.data")) + with self.open_output(self.args.csv, sys.stdout) as fd_task: + if self.args.csv and self.args.csv == self.args.csv_summary: + self.fd_task = fd_task + self.fd_sum = fd_task + if is_live: + self._run_live() + else: + self._run_file() + else: + with self.open_output(self.args.csv_summary, sys.stdout) as fd_sum: + self.fd_task = fd_task + self.fd_sum = fd_sum + if is_live: + self._run_live() + else: + self._run_file() + +def main() -> None: + """Main function.""" + parser = argparse.ArgumentParser(description="Analyze tasks behavior") + parser.add_argument("-i", "--input", default="perf.data", help="Input file name") + parser.add_argument("--time-limit", default="", help="print tasks only in time window") + parser.add_argument("--summary", action="store_true", + help="print additional runtime information") + parser.add_argument("--summary-only", action="store_true", + help="print only summary without traces") + parser.add_argument("--summary-extended", action="store_true", + help="print extended summary") + parser.add_argument("--ns", action="store_true", help="show timestamps in nanoseconds") + parser.add_argument("--ms", action="store_true", help="show timestamps in milliseconds") + parser.add_argument("--live", action="store_true", + help="force live mode (ignores -i/perf.data)") + parser.add_argument("--extended-times", action="store_true", + help="Show elapsed times between schedule in/out") + parser.add_argument("--filter-tasks", default="", help="filter tasks by tid, pid or comm") + parser.add_argument("--limit-to-tasks", default="", help="limit output to selected tasks") + parser.add_argument("--highlight-tasks", default="", help="colorize special tasks") + parser.add_argument("--rename-comms-by-tids", default="", help="rename task names by using tid") + parser.add_argument("--stdio-color", default="auto", choices=["always", "never", "auto"], + help="configure color output") + parser.add_argument("--csv", default="", help="Write trace to file") + parser.add_argument("--csv-summary", default="", help="Write summary to file") + + args = parser.parse_args() + args.tid_renames = {} + args.highlight_tasks_map = {} + args.filter_tasks = args.filter_tasks.split(",") if args.filter_tasks else [] + args.limit_to_tasks = args.limit_to_tasks.split(",") if args.limit_to_tasks else [] + + if args.rename_comms_by_tids: + for item in args.rename_comms_by_tids.split(","): + try: + tid, name = item.split(":", 1) + args.tid_renames[int(tid)] = name + except ValueError: + print(f"Error: Invalid format for --rename-comms-by-tids '{item}', " + "expected tid:name", file=sys.stderr) + sys.exit(1) + + if args.highlight_tasks: + for item in args.highlight_tasks.split(","): + parts = item.split(":") + if len(parts) == 1: + parts.append("red") + key, color = parts[0], parts[1] + args.highlight_tasks_map[key] = color + + analyzer = TaskAnalyzer(args) + analyzer.run() + +if __name__ == "__main__": + main()
tools/perf/tests/shell/test_task_analyzer.sh +63 -33
174 lines not on this page · raw message
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 31/49] perf python: Port task-analyzer to perf module
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 17 lines
Port
task-analyzer.pyfromtools/perf/scripts/python/to a standalone script intools/perf/python/refactored into a class-based architecture.Improvements compared to the legacy script:
- Support both offline perf.data file analysis (using perf.session) and live trace capture (using evlist.read_on_cpu), accessing sched:sched_switch tracepoint fields directly from sample objects.
- Automatically disable ANSI terminal color escape sequences when --csv or --csv-summary is enabled so CSV column headers ('Comm,', 'Time Out-Out,', etc.) are never polluted by color codes when running interactively on a TTY (e.g. as root).
- Sanitize non-printable characters and leading CSV formula characters (=, +, -, @) in task comm strings.
- Emit a one-time warning to stderr if sched:sched_switch samples are missing tracepoint fields (such as when recorded without libtraceevent support).
Quoted 4 lines
Update
test_task_analyzer.shto invoke the standalone script.Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=31
Ian Rogers
reviewerPATCH v4 32/49 perf python: Port sched-migration and SchedGui to perf module
In reply to Ian RogersPort sched-migration.py and SchedGui.py from tools/perf/scripts/python/ to standalone modules in tools/perf/python/:
- Refactor sched-migration.py into a SchedMigrationAnalyzer class using perf.session for event processing and add argparse CLI support (-i/--input, -v/--verbose, --gui, --no-gui).
- Port SchedGui.py to tools/perf/python/ as a local module dependency.
- Load wxPython dynamically via importlib only when GUI mode (--gui) is requested so text-mode analysis, testing on headless systems, and static analysis (mypy/pylint) succeed without wx installed.
- Remove Python 2 compatibility code.
Add a shell test (test_sched_migration_python.sh) to verify the standalone script.
--- tools/perf/python/SchedGui.py | 246 +++++++++ tools/perf/python/sched-migration.py | 496 ++++++++++++++++++ .../shell/test_sched_migration_python.sh | 72 +++ 3 files changed, 814 insertions(+) create mode 100755 tools/perf/python/SchedGui.py create mode 100755 tools/perf/python/sched-migration.py create mode 100755 tools/perf/tests/shell/test_sched_migration_python.sh
tools/perf/python/SchedGui.py new file +246 -0
@@ -0,0 +1,246 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# SchedGui.py - Python extension for perf script, basic GUI code for +# traces drawing and overview. +# +# Copyright (C) 2010 by Frederic Weisbecker <[email protected]> +# +# Ported to modern directory structure. + +"""SchedGui.py - Python extension for perf script, basic GUI code for traces drawing and overview.""" +from __future__ import annotations + +import importlib +from typing import Any + +class _DummyWx: + """Dummy wx module fallback when wxPython is not installed.""" + Frame = object + + +try: + wx: Any = importlib.import_module("wx") + WX_AVAILABLE = True +except ImportError: + wx = _DummyWx + WX_AVAILABLE = False + + +class RootFrame(wx.Frame): + """Main window frame for scheduling trace visualization.""" + Y_OFFSET = 100 + RECT_HEIGHT = 100 + RECT_SPACE = 50 + EVENT_MARKING_WIDTH = 5 + + def __init__(self, sched_tracer, title, parent=None, win_id=-1): + if not WX_AVAILABLE: + raise ImportError("You need to install the wxpython lib for this script") + wx.Frame.__init__(self, parent, win_id, title) + + self.dc = None + (self.screen_width, self.screen_height) = wx.GetDisplaySize() + self.screen_width -= 10 + self.screen_height -= 10 + self.zoom = 0.5 + self.scroll_scale = 20 + self.sched_tracer = sched_tracer + self.sched_tracer.set_root_win(self) + (self.ts_start, self.ts_end) = sched_tracer.interval() + self.update_width_virtual() + self.nr_rects = sched_tracer.nr_rectangles() + 1 + self.height_virtual = RootFrame.Y_OFFSET + \ + (self.nr_rects * (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE)) + + # whole window panel + self.panel = wx.Panel(self, size=(self.screen_width, self.screen_height)) + + # scrollable container + # Create SplitterWindow + self.splitter = wx.SplitterWindow(self.panel, style=wx.SP_3D) + + # scrollable container (Top) + self.scroll = wx.ScrolledWindow(self.splitter) + self.scroll.SetScrollbars(self.scroll_scale, self.scroll_scale, + int(self.width_virtual // self.scroll_scale), + int(self.height_virtual // self.scroll_scale)) + self.scroll.EnableScrolling(True, True) + self.scroll.SetFocus() + + # scrollable drawing area + self.scroll_panel = wx.Panel(self.scroll, + size=(self.screen_width - 15, self.screen_height // 2)) + self.scroll_panel.Bind(wx.EVT_PAINT, self.on_paint) + self.scroll_panel.Bind(wx.EVT_KEY_DOWN, self.on_key_press) + self.scroll_panel.Bind(wx.EVT_LEFT_DOWN, self.on_mouse_down) + self.scroll.Bind(wx.EVT_KEY_DOWN, self.on_key_press) + self.scroll.Bind(wx.EVT_LEFT_DOWN, self.on_mouse_down) + + self.scroll_panel.SetSize(int(self.width_virtual), int(self.height_virtual)) + + # Create a separate panel for text (Bottom) + self.text_panel = wx.Panel(self.splitter) + self.text_sizer = wx.BoxSizer(wx.VERTICAL) + self.txt = wx.TextCtrl(self.text_panel, -1, "Click a bar to see details", + style=wx.TE_MULTILINE) + self.text_sizer.Add(self.txt, 1, wx.EXPAND | wx.ALL, 5) + self.text_panel.SetSizer(self.text_sizer) + + # Split the window + self.splitter.SplitHorizontally(self.scroll, self.text_panel, (self.screen_height * 3) // 4) + + # Main sizer to layout splitter + self.main_sizer = wx.BoxSizer(wx.VERTICAL) + self.main_sizer.Add(self.splitter, 1, wx.EXPAND) + self.panel.SetSizer(self.main_sizer) + + self.scroll.Fit() + self.Fit() + + self.Show(True) + + def us_to_px(self, val): + """Convert microseconds to pixels.""" + return val / (10 ** 3) * self.zoom + + def px_to_us(self, val): + """Convert pixels to microseconds.""" + return (val / self.zoom) * (10 ** 3) + + def scroll_start(self): + """Get scroll start position in pixels.""" + (x, y) = self.scroll.GetViewStart() + return (x * self.scroll_scale, y * self.scroll_scale) + + def scroll_start_us(self): + """Get scroll start position in microseconds.""" + (x, _) = self.scroll_start() + return self.px_to_us(x) + + def paint_rectangle_zone(self, nr, color, top_color, start, end): + """Draw a rectangle zone for a CPU.""" + offset_px = self.us_to_px(start - self.ts_start) + width_px = self.us_to_px(end - start) + + offset_py = RootFrame.Y_OFFSET + (nr * (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE)) + width_py = RootFrame.RECT_HEIGHT + + dc = self.dc + + if top_color is not None: + (r, g, b) = top_color + top_color = wx.Colour(r, g, b) + brush = wx.Brush(top_color, wx.SOLID) + dc.SetBrush(brush) + dc.DrawRectangle(int(offset_px), int(offset_py), + int(width_px), RootFrame.EVENT_MARKING_WIDTH) + width_py -= RootFrame.EVENT_MARKING_WIDTH + offset_py += RootFrame.EVENT_MARKING_WIDTH + + (r, g, b) = color + color = wx.Colour(r, g, b) + brush = wx.Brush(color, wx.SOLID) + dc.SetBrush(brush) + dc.DrawRectangle(int(offset_px), int(offset_py), int(width_px), int(width_py)) + + def update_rectangles(self, start, end): + """Update rectangles in the given time window.""" + start += self.ts_start + end += self.ts_start + self.sched_tracer.fill_zone(start, end) + + def on_paint(self, event): + """Handle paint event.""" + window = event.GetEventObject() + dc = wx.PaintDC(window) + + # Clear background to avoid ghosting + dc.SetBackground(wx.Brush(window.GetBackgroundColour())) + dc.Clear() + + self.dc = dc + try: + width = min(self.width_virtual, self.screen_width) + (x, _) = self.scroll_start() + start = self.px_to_us(x) + end = self.px_to_us(x + width) + self.update_rectangles(start, end) + + # Draw CPU labels at the left edge of the visible area + (x_scroll, _) = self.scroll_start() + for nr in range(self.nr_rects): + offset_py = RootFrame.Y_OFFSET + (nr * (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE)) + dc.DrawText(f"CPU {nr}", x_scroll + 10, offset_py + 10) + finally: + self.dc = None + + def rect_from_ypixel(self, y): + y -= RootFrame.Y_OFFSET + rect = y // (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE) + height = y % (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE) + + if rect < 0 or rect > self.nr_rects - 1 or height > RootFrame.RECT_HEIGHT: + return -1 + + return rect + + def update_summary(self, txt): + self.txt.SetValue(txt) + self.text_panel.Layout() + self.splitter.Layout() + self.text_panel.Refresh() + + def on_mouse_down(self, event): + pos = event.GetPosition() + x, y = pos.x, pos.y + rect = self.rect_from_ypixel(y) + if rect == -1: + return + + t = self.px_to_us(x) + self.ts_start + + self.sched_tracer.mouse_down(rect, t) + + def update_width_virtual(self): + self.width_virtual = self.us_to_px(self.ts_end - self.ts_start) + + def __zoom(self, x): + self.update_width_virtual() + (xpos, ypos) = self.scroll.GetViewStart() + xpos = int(self.us_to_px(x) // self.scroll_scale) + self.scroll_panel.SetSize((int(self.width_virtual), int(self.height_virtual))) + self.scroll.SetScrollbars(self.scroll_scale, self.scroll_scale, + int(self.width_virtual // self.scroll_scale), + int(self.height_virtual // self.scroll_scale), + xpos, ypos) + self.Refresh() + + def zoom_in(self): + x = self.scroll_start_us() + self.zoom *= 2 + self.__zoom(x) + + def zoom_out(self): + x = self.scroll_start_us() + self.zoom /= 2 + self.__zoom(x) + + def on_key_press(self, event): + key = event.GetRawKeyCode() + if key == ord("+"): + self.zoom_in() + return + if key == ord("-"): + self.zoom_out() + return + + key = event.GetKeyCode() + (x, y) = self.scroll.GetViewStart() + if key == wx.WXK_RIGHT: + self.scroll.Scroll(x + 1, y) + elif key == wx.WXK_LEFT: + self.scroll.Scroll(x - 1, y) + elif key == wx.WXK_DOWN: + self.scroll.Scroll(x, y + 1) + elif key == wx.WXK_UP: + self.scroll.Scroll(x, y - 1)
tools/perf/python/sched-migration.py new file +496 -0
496 lines not on this page · raw message
tools/perf/tests/shell/test_sched_migration_python.sh new file +72 -0
72 lines not on this page · raw message
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 32/49] perf python: Port sched-migration and SchedGui to perf module
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 11 lines
Port
sched-migration.pyandSchedGui.pyfromtools/perf/scripts/python/to standalone modules intools/perf/python/:
- Refactorsched-migration.pyinto a SchedMigrationAnalyzer class using perf.session for event processing and add argparse CLI support (-i/--input, -v/--verbose, --gui, --no-gui).
- PortSchedGui.pytotools/perf/python/as a local module dependency.
- Load wxPython dynamically via importlib only when GUI mode (--gui) is requested so text-mode analysis, testing on headless systems, and static analysis (mypy/pylint) succeed without wx installed.
- Remove Python 2 compatibility code.
Quoted 5 lines
Add a shell test (
test_sched_migration_python.sh) to verify the standalone script.Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=32
Ian Rogers
reviewerPATCH v4 33/49 perf python: Port wakeup-latency from Perl to perf module
In reply to Ian RogersReplace the legacy Perl script wakeup-latency.pl with a standalone Python script in tools/perf/python/wakeup-latency.py using the perf Python module.
Improvements compared to the legacy Perl script:
- Remove the dependency on libperl and Perf::Trace::Util.
- Track wakeup timestamps per-task (keyed by the wakee PID on sched:sched_wakeup and matched against next_pid on sched:sched_switch) rather than per-CPU, avoiding mixed latencies when multiple wakeups occur on a CPU before a context switch.
- Guard print_totals() when total_wakeups == 0 (printing 'N/A' instead of dividing by zero when a trace contains no matched wakeup/switch pairs).
- Add argparse CLI options (-i/--input) and full type annotations.
Add a shell test
(test_wakeup_latency_python.sh) to verify the standalone script.
--- tools/perf/python/wakeup-latency.py | 103 ++++++++++++++++++ .../tests/shell/test_wakeup_latency_python.sh | 82 ++++++++++++++ 2 files changed, 185 insertions(+) create mode 100755 tools/perf/python/wakeup-latency.py create mode 100755 tools/perf/tests/shell/test_wakeup_latency_python.sh
tools/perf/python/wakeup-latency.py new file +103 -0
@@ -0,0 +1,103 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0-only +"""Display avg/min/max wakeup latency.""" +from __future__ import annotations + +import argparse +from collections import defaultdict +import sys +from typing import Optional, Dict +import perf + +class WakeupLatency: + """Tracks and displays wakeup latency statistics.""" + def __init__(self) -> None: + self.last_wakeup: Dict[int, int] = defaultdict(int) + self.max_wakeup_latency: int = 0 + self.min_wakeup_latency: Optional[int] = None + self.total_wakeup_latency = 0 + self.total_wakeups = 0 + self.unhandled: Dict[str, int] = defaultdict(int) + self.session: Optional[perf.session] = None + + def process_event(self, sample: perf.sample_event) -> None: + """Process events.""" + event_name = str(sample.evsel) + if event_name.startswith("evsel(") and event_name.endswith(")"): + event_name = event_name[6:-1] + sample_time = sample.sample_time + + if "sched:sched_wakeup" in event_name: + try: + pid = sample.pid + self.last_wakeup[pid] = sample_time + except AttributeError: + self.unhandled[event_name] += 1 + elif "sched:sched_switch" in event_name: + try: + next_pid = sample.next_pid + wakeup_ts = self.last_wakeup.get(next_pid, 0) + if wakeup_ts: + latency = sample_time - wakeup_ts + self.max_wakeup_latency = max(self.max_wakeup_latency, latency) + if self.min_wakeup_latency is None: + self.min_wakeup_latency = latency + else: + self.min_wakeup_latency = min(self.min_wakeup_latency, latency) + self.total_wakeup_latency += latency + self.total_wakeups += 1 + del self.last_wakeup[next_pid] + except AttributeError: + self.unhandled[event_name] += 1 + else: + self.unhandled[event_name] += 1 + + def print_totals(self) -> None: + """Print summary statistics.""" + print("wakeup_latency stats:\n") + print(f"total_wakeups: {self.total_wakeups}") + if self.total_wakeups: + avg = self.total_wakeup_latency // self.total_wakeups + print(f"avg_wakeup_latency (ns): {avg}") + print(f"min_wakeup_latency (ns): {self.min_wakeup_latency}") + print(f"max_wakeup_latency (ns): {self.max_wakeup_latency}") + else: + print("avg_wakeup_latency (ns): N/A") + print("min_wakeup_latency (ns): N/A") + print("max_wakeup_latency (ns): N/A") + + if self.unhandled: + print("\nunhandled events:\n") + print(f"{'event':<40s} {'count':>10s}") + print(f"{'-'*40} {'-'*10}") + for event_name, count in self.unhandled.items(): + print(f"{event_name:<40s} {count:10d}") + + def run(self, input_file: str) -> None: + """Run the session.""" + self.session = perf.session(perf.data(input_file), sample=self.process_event) + try: + self.session.process_events() + except KeyboardInterrupt: + pass + finally: + # Break the reference cycle between self.session and the bound + # self.process_event callback so the C perf.session object is freed. + self.session = None + self.print_totals() + +def main() -> None: + """Main function.""" + parser = argparse.ArgumentParser(description="Trace wakeup latency") + parser.add_argument("-i", "--input", default="perf.data", help="Input file") + args = parser.parse_args() + + analyzer = WakeupLatency() + try: + analyzer.run(args.input) + except IOError as e: + print(e, file=sys.stderr) + sys.exit(1) + +if __name__ == "__main__": + main()
tools/perf/tests/shell/test_wakeup_latency_python.sh new file +82 -0
82 lines not on this page · raw message
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 33/49] perf python: Port wakeup-latency from Perl to perf module
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 15 lines
Replace the legacy Perl script wakeup-latency.pl with a standalone Python script in
tools/perf/python/wakeup-latency.pyusing the perf Python module.Improvements compared to the legacy Perl script:
- Remove the dependency on libperl andPerf::Trace::Util.
- Track wakeup timestamps per-task (keyed by the wakee PID on sched:sched_wakeup and matched againstnext_pidon sched:sched_switch) rather than per-CPU, avoiding mixed latencies when multiple wakeups occur on a CPU before a context switch.
- Guardprint_totals()whentotal_wakeups== 0 (printing 'N/A' instead of dividing by zero when a trace contains no matched wakeup/switch pairs).
- Add argparse CLI options (-i/--input) and full type annotations.
Quoted 5 lines
Add a shell test
(test_wakeup_latency_python.sh) to verify the standalone script.Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=33
Ian Rogers
reviewerPATCH v4 34/49 perf python: Port compaction-times to perf module
In reply to Ian RogersPort compaction-times.py to a standalone script in tools/perf/python/ using the perf module directly to analyze mm_compaction tracepoints.
Improvements compared to the legacy script:
- Replace Python 2 constructs (such as sys.maxint and raw integer bitmasks) with Python 3 enum.IntEnum (Popt) and enum.IntFlag (Topt) types.
- Access tracepoint fields directly on perf.sample_event and add -i/--input CLI option support via argparse.
- Add full type annotations passing mypy and pylint without suppression comments.
Add a shell test (test_compaction_times_python.sh) to verify the standalone script.
--- tools/perf/python/compaction-times.py | 362 ++++++++++++++++++ .../shell/test_compaction_times_python.sh | 127 ++++++ 2 files changed, 489 insertions(+) create mode 100755 tools/perf/python/compaction-times.py create mode 100755 tools/perf/tests/shell/test_compaction_times_python.sh
tools/perf/python/compaction-times.py new file +362 -0
@@ -0,0 +1,362 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +""" +Report time spent in memory compaction. + +Memory compaction is a feature in the Linux kernel that defragments memory +by moving used pages to create larger contiguous blocks of free memory. This +is particularly useful for allocating huge pages. + +This script processes trace events related to memory compaction and reports: +- Total time spent in compaction (stall time). +- Statistics for page migration (moved vs. failed). +- Statistics for the free scanner (scanned vs. isolated pages). +- Statistics for the migration scanner (scanned vs. isolated pages). + +Definitions: +- **Compaction**: Defragmenting memory by moving allocated pages. +- **Migration**: Moving pages from their current location to free pages found by the free scanner. +- **Free Scanner**: Scans memory (typically from the end of a zone) to find free pages. +- **Migration Scanner**: Scans memory (typically from the beginning of a zone) + to find pages to move. +- **Isolated Pages**: Pages that have been temporarily removed from the buddy + system for migration or as migration targets. + +Ported from tools/perf/scripts/python/compaction-times.py to the modern perf Python module. +""" +from __future__ import annotations + +import argparse +import enum +import re +import signal +import sys +from typing import Callable, Dict, List, Optional, Any +import perf + +if hasattr(signal, "SIGPIPE"): + signal.signal(signal.SIGPIPE, signal.SIG_DFL) + +class Popt(enum.IntEnum): + """Process display options.""" + DISP_DFL = 0 + DISP_PROC = 1 + DISP_PROC_VERBOSE = 2 + +class Topt(enum.IntFlag): + """Trace display options.""" + DISP_TIME = 0 + DISP_MIG = 1 + DISP_ISOLFREE = 2 + DISP_ISOLMIG = 4 + DISP_ALL = DISP_MIG | DISP_ISOLFREE | DISP_ISOLMIG + +# Globals to satisfy pylint when accessed in functions before assignment in main. +OPT_NS = True +opt_disp = Topt.DISP_ALL +opt_proc = Popt.DISP_DFL +session = None + +def get_comm_filter(regex: re.Pattern) -> Callable[[int, str], bool]: + """Returns a filter function based on command regex.""" + def filter_func(_pid: int, comm: str) -> bool: + regex_match = regex.search(comm) + return regex_match is None or regex_match.group() == "" + return filter_func + +def get_pid_filter(low_str: str, high_str: str) -> Callable[[int, str], bool]: + """Returns a filter function based on PID range.""" + low = 0 if low_str == "" else int(low_str) + high = None if high_str == "" else int(high_str) + + def filter_func(pid: int, _comm: str) -> bool: + return not (pid >= low and (high is None or pid <= high)) + return filter_func + +def ns_to_time(ns: int) -> str: + """Format nanoseconds to string based on options.""" + return f"{ns}ns" if OPT_NS else f"{round(ns, -3) // 1000}us" + +class Pair: + """Represents a pair of related counters (e.g., scanned vs isolated, moved vs failed).""" + def __init__(self, aval: int, bval: int, + alabel: Optional[str] = None, blabel: Optional[str] = None): + self.alabel = alabel + self.blabel = blabel + self.aval = aval + self.bval = bval + + def __add__(self, rhs: 'Pair') -> 'Pair': + return Pair(self.aval + rhs.aval, self.bval + rhs.bval, self.alabel, self.blabel) + + def __iadd__(self, rhs: 'Pair') -> 'Pair': + self.aval += rhs.aval + self.bval += rhs.bval + return self + + def __str__(self) -> str: + return f"{self.alabel}={self.aval} {self.blabel}={self.bval}" + +class Cnode: + """Holds statistics for a single compaction event or an aggregated set of events.""" + def __init__(self, ns: int): + self.ns = ns + self.migrated = Pair(0, 0, "moved", "failed") + self.fscan = Pair(0, 0, "scanned", "isolated") + self.mscan = Pair(0, 0, "scanned", "isolated") + + def __add__(self, rhs: 'Cnode') -> 'Cnode': + res = Cnode(self.ns + rhs.ns) + res.migrated = self.migrated + rhs.migrated + res.fscan = self.fscan + rhs.fscan + res.mscan = self.mscan + rhs.mscan + return res + + def __iadd__(self, rhs: 'Cnode') -> 'Cnode': + self.ns += rhs.ns + self.migrated += rhs.migrated + self.fscan += rhs.fscan + self.mscan += rhs.mscan + return self + + def __str__(self) -> str: + prev = False + s = f"{ns_to_time(self.ns)} " + if opt_disp & Topt.DISP_MIG: + s += f"migration: {self.migrated}" + prev = True + if opt_disp & Topt.DISP_ISOLFREE: + s += f"{' ' if prev else ''}free_scanner: {self.fscan}" + prev = True + if opt_disp & Topt.DISP_ISOLMIG: + s += f"{' ' if prev else ''}migration_scanner: {self.mscan}" + return s + + def complete(self, secs: int, nsecs: int) -> None: + """Complete the node with duration.""" + self.ns = (secs * 1000000000 + nsecs) - self.ns + + def increment(self, migrated: Optional[Pair], fscan: Optional[Pair], + mscan: Optional[Pair]) -> None: + """Increment statistics.""" + if migrated is not None: + self.migrated += migrated + if fscan is not None: + self.fscan += fscan + if mscan is not None: + self.mscan += mscan + +class Chead: + """Aggregates compaction statistics per process (PID) and maintains total statistics.""" + heads: Dict[int, 'Chead'] = {} + val = Cnode(0) + fobj: Optional[Any] = None + + @classmethod + def add_filter(cls, fobj: Any) -> None: + """Add a filter object.""" + cls.fobj = fobj + + @classmethod + def create_pending(cls, pid: int, comm: str, start_secs: int, start_nsecs: int) -> None: + """Create a pending node for a process.""" + filtered = False + try: + head = cls.heads[pid] + filtered = head.is_filtered() + except KeyError: + if cls.fobj is not None: + filtered = cls.fobj(pid, comm) + head = cls.heads[pid] = Chead(comm, pid, filtered) + + if not filtered: + head.mark_pending(start_secs, start_nsecs) + + @classmethod + def increment_pending(cls, pid: int, migrated: Optional[Pair], + fscan: Optional[Pair], mscan: Optional[Pair]) -> None: + """Increment pending stats for a process.""" + if pid not in cls.heads: + return + head = cls.heads[pid] + if not head.is_filtered(): + if head.is_pending(): + head.do_increment(migrated, fscan, mscan) + else: + sys.stderr.write(f"missing start compaction event for pid {pid}\n") + + @classmethod + def complete_pending(cls, pid: int, secs: int, nsecs: int) -> None: + """Complete pending stats for a process.""" + if pid not in cls.heads: + return + head = cls.heads[pid] + if not head.is_filtered(): + if head.is_pending(): + head.make_complete(secs, nsecs) + else: + sys.stderr.write(f"missing start compaction event for pid {pid}\n") + + @classmethod + def gen(cls): + """Generate heads for display.""" + if opt_proc != Popt.DISP_DFL: + yield from cls.heads.values() + + @classmethod + def get_total(cls) -> Cnode: + """Get total statistics.""" + return cls.val + + def __init__(self, comm: str, pid: int, filtered: bool): + self.comm = comm + self.pid = pid + self.val = Cnode(0) + self.pending: Optional[Cnode] = None + self.filtered = filtered + self.list: List[Cnode] = [] + + def mark_pending(self, secs: int, nsecs: int) -> None: + """Mark node as pending.""" + self.pending = Cnode(secs * 1000000000 + nsecs) + + def do_increment(self, migrated: Optional[Pair], fscan: Optional[Pair], + mscan: Optional[Pair]) -> None: + """Increment pending stats.""" + if self.pending is not None: + self.pending.increment(migrated, fscan, mscan) + + def make_complete(self, secs: int, nsecs: int) -> None: + """Make pending stats complete.""" + if self.pending is not None: + self.pending.complete(secs, nsecs) + Chead.val += self.pending + + if opt_proc != Popt.DISP_DFL: + self.val += self.pending + + if opt_proc == Popt.DISP_PROC_VERBOSE: + self.list.append(self.pending) + self.pending = None + + def enumerate(self) -> None: + """Enumerate verbose stats.""" + if opt_proc == Popt.DISP_PROC_VERBOSE and not self.is_filtered(): + for i, pelem in enumerate(self.list): + sys.stdout.write(f"{self.pid}[{self.comm}].{i+1}: {pelem}\n") + + def is_pending(self) -> bool: + """Check if node is pending.""" + return self.pending is not None + + def is_filtered(self) -> bool: + """Check if node is filtered.""" + return self.filtered + + def display(self) -> None: + """Display stats.""" + if not self.is_filtered(): + sys.stdout.write(f"{self.pid}[{self.comm}]: {self.val}\n") + +def trace_end() -> None: + """Called at the end of trace processing.""" + sys.stdout.write(f"total: {Chead.get_total()}\n") + for i in Chead.gen(): + i.display() + i.enumerate() + +def process_event(sample: perf.sample_event) -> None: + """Callback for processing events.""" + event_name = str(sample.evsel) + pid = sample.sample_tid + comm = "[unknown]" + try: + if session: + thread = session.find_thread(sample.sample_pid, pid) + if thread: + comm = thread.comm() or "[unknown]" + except (TypeError, AttributeError): + pass + secs = sample.sample_time // 1000000000 + nsecs = sample.sample_time % 1000000000 + + if "evsel(compaction:mm_compaction_begin)" in event_name: + Chead.create_pending(pid, comm, secs, nsecs) + elif "evsel(compaction:mm_compaction_end)" in event_name: + Chead.complete_pending(pid, secs, nsecs) + elif "evsel(compaction:mm_compaction_migratepages)" in event_name: + nr_migrated = getattr(sample, "nr_migrated", 0) + nr_failed = getattr(sample, "nr_failed", 0) + Chead.increment_pending(pid, Pair(nr_migrated, nr_failed), None, None) + elif "evsel(compaction:mm_compaction_isolate_freepages)" in event_name: + nr_scanned = getattr(sample, "nr_scanned", 0) + nr_taken = getattr(sample, "nr_taken", 0) + Chead.increment_pending(pid, None, Pair(nr_scanned, nr_taken), None) + elif "evsel(compaction:mm_compaction_isolate_migratepages)" in event_name: + nr_scanned = getattr(sample, "nr_scanned", 0) + nr_taken = getattr(sample, "nr_taken", 0) + Chead.increment_pending(pid, None, None, Pair(nr_scanned, nr_taken)) + +if __name__ == "__main__": + ap = argparse.ArgumentParser(description="Report time spent in compaction") + ap.add_argument("-p", action="store_true", help="display by process") + ap.add_argument("-pv", action="store_true", help="display by process (verbose)") + ap.add_argument("-u", action="store_true", help="display results in microseconds") + ap.add_argument("-t", action="store_true", help="display stall times only") + ap.add_argument("-m", action="store_true", help="display stats for migration") + ap.add_argument("-fs", action="store_true", help="display stats for free scanner") + ap.add_argument("-ms", action="store_true", help="display stats for migration scanner") + ap.add_argument("filter", nargs="?", help="pid|pid-range|comm-regex") + ap.add_argument("-i", "--input", default="perf.data", help="Input file name") + args = ap.parse_args() + + opt_proc = Popt.DISP_DFL + if args.pv: + opt_proc = Popt.DISP_PROC_VERBOSE + elif args.p: + opt_proc = Popt.DISP_PROC + + OPT_NS = not args.u + + opt_disp = Topt.DISP_ALL + if args.t or args.m or args.fs or args.ms: + opt_disp = Topt(0) + if args.t: + opt_disp |= Topt.DISP_TIME + if args.m: + opt_disp |= Topt.DISP_MIG + if args.fs: + opt_disp |= Topt.DISP_ISOLFREE + if args.ms: + opt_disp |= Topt.DISP_ISOLMIG + + if args.filter: + PID_PATTERN = r"^(\d*)-(\d*)$|^(\d*)$" + pid_re = re.compile(PID_PATTERN) + match = pid_re.search(args.filter) + filter_obj: Any = None + if match is not None and match.group() != "": + if match.group(3) is not None: + filter_obj = get_pid_filter(match.group(3), match.group(3)) + else: + filter_obj = get_pid_filter(match.group(1), match.group(2)) + else: + try: + comm_re = re.compile(args.filter) + except re.error: + sys.stderr.write(f"invalid regex '{args.filter}'\n") + sys.exit(1) + filter_obj = get_comm_filter(comm_re) + Chead.add_filter(filter_obj) + + try: + session = perf.session(perf.data(args.input), sample=process_event) + try: + session.process_events() + except KeyboardInterrupt: + pass + trace_end() + finally: + # Break the reference cycle between the global session and the + # process_event callback so the C perf.session object is freed. + session = None
tools/perf/tests/shell/test_compaction_times_python.sh new file +127 -0
127 lines not on this page · raw message
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 34/49] perf python: Port compaction-times to perf module
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 12 lines
Port
compaction-times.pyto a standalone script intools/perf/python/using the perf module directly to analyzemm_compactiontracepoints.Improvements compared to the legacy script:
- Replace Python 2 constructs (such as sys.maxint and raw integer bitmasks) with Python 3 enum.IntEnum (Popt) and enum.IntFlag (Topt) types.
- Access tracepoint fields directly on perf.sample_event and add -i/--input CLI option support via argparse.
- Add full type annotations passing mypy and pylint without suppression comments.
Quoted 5 lines
Add a shell test (
test_compaction_times_python.sh) to verify the standalone script.Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=34
Ian Rogers
reviewerPATCH v4 35/49 perf python: Port net_dropmonitor to perf module
In reply to Ian RogersPort net_dropmonitor.py from tools/perf/scripts/python/ to a standalone script in tools/perf/python/:
- Refactor the script into a DropMonitor class with full type annotations to encapsulate state.
- Use perf.session for skb:kfree_skb event processing and add argparse CLI support (-i/--input and -k/--kallsyms).
- Resolve kernel drop addresses via perf.session symbols/callchains and binary search over /proc/kallsyms, ignoring zeroed kptr_restrict addresses with graceful fallback when kallsyms is unavailable.
- Remove Python 2 compatibility code.
Add a shell test (test_net_dropmonitor_python.sh) to verify the standalone script.
--- tools/perf/python/net_dropmonitor.py | 173 ++++++++++++++++++ .../shell/test_net_dropmonitor_python.sh | 102 +++++++++++ 2 files changed, 275 insertions(+) create mode 100755 tools/perf/python/net_dropmonitor.py create mode 100755 tools/perf/tests/shell/test_net_dropmonitor_python.sh
tools/perf/python/net_dropmonitor.py new file +173 -0
@@ -0,0 +1,173 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +""" +Monitor the system for dropped packets and produce a report of drop locations and counts. +Ported from tools/perf/scripts/python/net_dropmonitor.py +""" +from __future__ import annotations + +import argparse +from collections import defaultdict +import os +import sys +from typing import Tuple +import perf + + +class DropMonitor: + """Monitors dropped packets and aggregates counts by location.""" + + def __init__(self, kallsyms_path: str | None = None) -> None: + self.drop_log: dict[int, int] = defaultdict(int) + self.kallsyms: list[Tuple[int, str]] = [] + self.kallsyms_parsed = False + self.resolved_syms: dict[int, Tuple[str, int]] = {} + self.callchain_syms: dict[int, str] = {} + self.kallsyms_path = ( + kallsyms_path + or os.environ.get("PERF_SYMBOL_KALLSYMS") + or "/proc/kallsyms" + ) + + def _parse_kallsyms(self) -> None: + """Parse the kallsyms file and map kernel addresses to function symbols.""" + self.kallsyms.clear() + self.kallsyms_parsed = True + try: + with open(self.kallsyms_path, "r", encoding="utf-8") as f: + for line in f: + parts = line.split() + if len(parts) >= 3 and parts[1] in ('t', 'T', 'w', 'W'): + addr = int(parts[0], 16) + if addr > 0: + self.kallsyms.append((addr, parts[2])) + self.kallsyms.sort(key=lambda x: x[0]) + except (FileNotFoundError, PermissionError): + print(f"Failed to read {self.kallsyms_path}. Symbols will not be resolved.") + + def _get_sym(self, loc: int) -> Tuple[str, int]: + """Resolve a memory location using session symbols or the kallsyms map.""" + # Priority order: + # 1. Exact symbols with offsets resolved directly from the perf.data session + # (resolved_syms). + # 2. Symbols captured from the sample's callchain in the trace file + # (callchain_syms) before falling back to self.kallsyms, so offline + # trace symbols are not overwritten by the live host's /proc/kallsyms. + # 3. Binary search in self.kallsyms (from --kallsyms or /proc/kallsyms). + if loc in self.resolved_syms: + return self.resolved_syms[loc] + if loc in self.callchain_syms: + res = (self.callchain_syms[loc], 0) + self.resolved_syms[loc] = res + return res + if not self.kallsyms: + return f"{loc:#x}", 0 + + start = 0 + end = len(self.kallsyms) - 1 + while start < end: + mid = (start + end) // 2 + if self.kallsyms[mid][0] <= loc < self.kallsyms[mid+1][0]: + start = mid + break + if loc < self.kallsyms[mid][0]: + end = mid - 1 + else: + start = mid + 1 + + sym_addr, sym_name = self.kallsyms[start] + if loc >= sym_addr: + res = (sym_name, loc - sym_addr) + self.resolved_syms[loc] = res + return res + return f"{loc:#x}", 0 + + def print_drop_table(self) -> None: + """Print aggregated results.""" + if not self.drop_log: + print(f"{'LOCATION':>25} {'OFFSET':>25} {'COUNT':>25}") + return + + if (not self.kallsyms_parsed + and any(loc not in self.resolved_syms and loc not in self.callchain_syms + for loc in self.drop_log)): + print("Gathering kallsyms data") + self._parse_kallsyms() + + print(f"{'LOCATION':>25} {'OFFSET':>25} {'COUNT':>25}") + sorted_keys = sorted(self.drop_log.keys()) + for sloc in sorted_keys: + sym, off = self._get_sym(sloc) + print(f"{sym:>25} {off:>25d} {self.drop_log[sloc]:>25d}") + + def process_event(self, sample: perf.sample_event) -> None: + """Process a single sample event.""" + if "skb:kfree_skb" not in str(sample.evsel): + return + + location = getattr(sample, "location", None) + if location is not None: + self.drop_log[location] += 1 + if location not in self.resolved_syms: + sym = getattr(sample, "symbol", None) + if getattr(sample, "sample_ip", 0) == location and sym and sym != "[unknown]": + self.resolved_syms[location] = ( + sym, + getattr(sample, "sym_offset", 0) or 0, + ) + self.callchain_syms.pop(location, None) + else: + for entry in getattr(sample, "callchain", []) or []: + if isinstance(entry, dict): + entry_ip = entry.get("ip") + sym_info = entry.get("sym") + sym_name = sym_info.get("name") if isinstance(sym_info, dict) else None + sym_start = sym_info.get("start") if isinstance(sym_info, dict) else None + sym_off = (max(0, location - sym_start) + if sym_start is not None else None) + else: + entry_ip = getattr(entry, "ip", None) + entry_sym = getattr(entry, "sym", None) + sym_name = ( + getattr(entry_sym, "name", None) + or getattr(entry, "symbol", None) + ) + sym_off = getattr(entry, "sym_offset", None) + if sym_off is None: + sym_start = getattr(entry_sym, "start", None) + if sym_start is not None: + sym_off = max(0, location - sym_start) + if entry_ip == location and sym_name and sym_name != "[unknown]": + if sym_off is not None: + self.resolved_syms[location] = (sym_name, sym_off) + self.callchain_syms.pop(location, None) + else: + self.callchain_syms[location] = sym_name + break + + +if __name__ == "__main__": + ap = argparse.ArgumentParser( + description="Monitor the system for dropped packets and produce a " + "report of drop locations and counts.") + ap.add_argument("-i", "--input", default="perf.data", help="Input file name") + ap.add_argument("-k", "--kallsyms", default=None, + help="Path to kallsyms file for offline symbol resolution") + args = ap.parse_args() + + monitor = DropMonitor(kallsyms_path=args.kallsyms) + session = None + + try: + session = perf.session(perf.data(args.input), sample=monitor.process_event, + kallsyms=args.kallsyms) + session.process_events() + except KeyboardInterrupt: + print("\nStopping trace...") + except (OSError, ValueError, KeyError, RuntimeError, TypeError, AttributeError) as e: + print(f"Error processing events: {e}") + sys.exit(1) + finally: + session = None + + monitor.print_drop_table()
tools/perf/tests/shell/test_net_dropmonitor_python.sh new file +102 -0
102 lines not on this page · raw message
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 35/49] perf python: Port net_dropmonitor to perf module
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 11 lines
Port
net_dropmonitor.pyfromtools/perf/scripts/python/to a standalone script intools/perf/python/:
- Refactor the script into a DropMonitor class with full type annotations to encapsulate state.
- Use perf.session for skb:kfree_skb event processing and add argparse CLI support (-i/--input and -k/--kallsyms).
- Resolve kernel drop addresses via perf.session symbols/callchains and binary search over/proc/kallsyms, ignoring zeroedkptr_restrictaddresses with graceful fallback when kallsyms is unavailable.
- Remove Python 2 compatibility code.
Quoted 5 lines
Add a shell test (
test_net_dropmonitor_python.sh) to verify the standalone script.Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=35
Ian Rogers
reviewerPATCH v4 36/49 perf python: Port netdev-times to perf module
In reply to Ian RogersPort netdev-times.py from tools/perf/scripts/python/ to a standalone script in tools/perf/python/:
- Refactor the script into a NetDevTimesAnalyzer class with full type annotations to encapsulate state.
- Collect events via perf.session and sort them in timestamp order before analysis so multi-CPU TX and RX packet timelines are reconstructed deterministically.
- Replace custom argument parsing with argparse (-i/--input, --tx, --rx, --dev, --debug), extract tracepoint fields directly from sample attributes, and remove Python 2 compatibility artifacts.
Add a shell test (test_netdev_times_python.sh) to verify the standalone script.
--- tools/perf/python/netdev-times.py | 494 ++++++++++++++++++ .../tests/shell/test_netdev_times_python.sh | 104 ++++ 2 files changed, 598 insertions(+) create mode 100755 tools/perf/python/netdev-times.py create mode 100755 tools/perf/tests/shell/test_netdev_times_python.sh
tools/perf/python/netdev-times.py new file +494 -0
@@ -0,0 +1,494 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +""" +Display a process of packets and processed time. +It helps us to investigate networking or network device. + +Ported from tools/perf/scripts/python/netdev-times.py +""" + +from __future__ import annotations +import argparse +from collections import defaultdict +import sys +from typing import Optional +import perf + +# Format for displaying rx packet processing +PF_IRQ_ENTRY = " irq_entry(+%.3fmsec irq=%d:%s)" +PF_SOFT_ENTRY = " softirq_entry(+%.3fmsec)" +PF_NAPI_POLL = " napi_poll_exit(+%.3fmsec %s)" +PF_JOINT = " |" +PF_WJOINT = " | |" +PF_NET_RECV = " |---netif_receive_skb(+%.3fmsec skb=%x len=%d)" +PF_NET_RX = " |---netif_rx(+%.3fmsec skb=%x)" +PF_CPY_DGRAM = " | skb_copy_datagram_iovec(+%.3fmsec %d:%s)" +PF_KFREE_SKB = " | kfree_skb(+%.3fmsec location=%x)" +PF_CONS_SKB = " | consume_skb(+%.3fmsec)" + + +class NetDevTimesAnalyzer: + """Analyzes network device events and prints charts.""" + + def __init__(self, cfg: argparse.Namespace): + self.args = cfg + self.session: Optional[perf.session] = None + self.show_tx = cfg.tx or (not cfg.tx and not cfg.rx) + self.show_rx = cfg.rx or (not cfg.tx and not cfg.rx) + self.dev = cfg.dev + self.debug = cfg.debug + self.buffer_budget = 65536 + self.irq_dic: dict[int, list[dict]] = defaultdict(list) + self.net_rx_dic: dict[int, dict] = {} + self.receive_hunk_list: list[dict] = [] + self.rx_skb_list: list[dict] = [] + self.tx_queue_list: list[dict] = [] + self.tx_xmit_list: list[dict] = [] + self.tx_free_list: list[dict] = [] + + self.buffer_budget = 65536 + self.of_count_rx_skb_list = 0 + self.of_count_tx_queue_list = 0 + self.of_count_tx_xmit_list = 0 + + def diff_msec(self, src: int, dst: int) -> float: + """Calculate a time interval(msec) from src(nsec) to dst(nsec).""" + return (dst - src) / 1000000.0 + + def print_transmit(self, hunk: dict) -> None: + """Display a process of transmitting a packet.""" + if self.dev and hunk['dev'].find(self.dev) < 0: + return + queue_t_sec = hunk['queue_t'] // 1000000000 + queue_t_usec = hunk['queue_t'] % 1000000000 // 1000 + print(f"{hunk['dev']:7s} {hunk['len']:5d} " + f"{queue_t_sec:6d}.{queue_t_usec:06d}sec " + f"{self.diff_msec(hunk['queue_t'], hunk['xmit_t']):12.3f}msec " + f"{self.diff_msec(hunk['xmit_t'], hunk['free_t']):12.3f}msec") + + def print_receive(self, hunk: dict) -> None: + """Display a process of received packets and interrupts.""" + show_hunk = False + irq_list = hunk['irq_list'] + if not irq_list: + return + cpu = irq_list[0]['cpu'] + base_t = irq_list[0]['irq_ent_t'] + + if self.dev: + for irq in irq_list: + if irq['name'].find(self.dev) >= 0: + show_hunk = True + break + else: + show_hunk = True + + if not show_hunk: + return + + base_t_sec = base_t // 1000000000 + base_t_usec = base_t % 1000000000 // 1000 + print(f"{base_t_sec}.{base_t_usec:06d}sec cpu={cpu}") + for irq in irq_list: + print(PF_IRQ_ENTRY % + (self.diff_msec(base_t, irq['irq_ent_t']), + irq['irq'], irq['name'])) + print(PF_JOINT) + irq_event_list = irq['event_list'] + for irq_event in irq_event_list: + if irq_event['event'] == 'netif_rx': + print(PF_NET_RX % + (self.diff_msec(base_t, irq_event['time']), + irq_event['skbaddr'])) + print(PF_JOINT) + + print(PF_SOFT_ENTRY % self.diff_msec(base_t, hunk['sirq_ent_t'])) + print(PF_JOINT) + event_list = hunk['event_list'] + for i, event in enumerate(event_list): + if event['event_name'] == 'napi_poll': + print(PF_NAPI_POLL % + (self.diff_msec(base_t, event['event_t']), + event['dev'])) + if i == len(event_list) - 1: + print("") + else: + print(PF_JOINT) + else: + print(PF_NET_RECV % + (self.diff_msec(base_t, event['event_t']), + event['skbaddr'], + event['len'])) + if 'handle' in event: + print(PF_WJOINT) + if event['handle'] == "kfree_skb": + print(PF_KFREE_SKB % + (self.diff_msec(base_t, event['comm_t']), + event['location'])) + elif event['handle'] == "consume_skb": + print(PF_CONS_SKB % + self.diff_msec(base_t, event['comm_t'])) + elif event['handle'] == "skb_copy_datagram_iovec": + print(PF_CPY_DGRAM % + (self.diff_msec(base_t, event['comm_t']), + event['pid'], event['comm'])) + print(PF_JOINT) + + def handle_irq_handler_entry(self, event: dict) -> None: + """Handle irq:irq_handler_entry event.""" + time = event['time'] + cpu = event['cpu'] + irq = event['irq'] + irq_name = event['irq_name'] + irq_record = {'irq': irq, 'name': irq_name, 'cpu': cpu, + 'irq_ent_t': time, 'event_list': []} + self.irq_dic[cpu].append(irq_record) + + def handle_irq_handler_exit(self, event: dict) -> None: + """Handle irq:irq_handler_exit event.""" + time = event['time'] + cpu = event['cpu'] + irq = event['irq'] + if cpu not in self.irq_dic or not self.irq_dic[cpu]: + return + if irq != self.irq_dic[cpu][-1]['irq']: + return + irq_record = self.irq_dic[cpu].pop() + irq_record['irq_ext_t'] = time + # if an irq doesn't include NET_RX softirq, drop. + if irq_record['event_list']: + self.irq_dic[cpu].append(irq_record) + + def handle_irq_softirq_raise(self, event: dict) -> None: + """Handle irq:softirq_raise event.""" + time = event['time'] + cpu = event['cpu'] + if cpu not in self.irq_dic or not self.irq_dic[cpu]: + return + irq_record = self.irq_dic[cpu].pop() + irq_record['event_list'].append({'time': time, 'event': 'sirq_raise'}) + self.irq_dic[cpu].append(irq_record) + + def handle_irq_softirq_entry(self, event: dict) -> None: + """Handle irq:softirq_entry event.""" + time = event['time'] + cpu = event['cpu'] + self.net_rx_dic[cpu] = {'sirq_ent_t': time, 'event_list': []} + + def handle_irq_softirq_exit(self, event: dict) -> None: + """Handle irq:softirq_exit event.""" + time = event['time'] + cpu = event['cpu'] + irq_list = None + event_list = None + sirq_ent_t = None + + if cpu in self.irq_dic: + irq_list = self.irq_dic[cpu] + del self.irq_dic[cpu] + if cpu in self.net_rx_dic: + sirq_ent_t = self.net_rx_dic[cpu]['sirq_ent_t'] + event_list = self.net_rx_dic[cpu]['event_list'] + del self.net_rx_dic[cpu] + if not irq_list or event_list is None or sirq_ent_t is None: + return + rec_data = {'sirq_ent_t': sirq_ent_t, 'sirq_ext_t': time, + 'irq_list': irq_list, 'event_list': event_list} + self.receive_hunk_list.append(rec_data) + + def handle_napi_poll(self, event: dict) -> None: + """Handle napi:napi_poll event.""" + time = event['time'] + cpu = event['cpu'] + dev_name = event['dev_name'] + work = event['work'] + budget = event['budget'] + if cpu in self.net_rx_dic: + event_list = self.net_rx_dic[cpu]['event_list'] + rec_data = {'event_name': 'napi_poll', + 'dev': dev_name, 'event_t': time, + 'work': work, 'budget': budget} + event_list.append(rec_data) + + def handle_netif_rx(self, event: dict) -> None: + """Handle net:netif_rx event.""" + time = event['time'] + cpu = event['cpu'] + skbaddr = event['skbaddr'] + skblen = event['skblen'] + dev_name = event['dev_name'] + if cpu not in self.irq_dic or not self.irq_dic[cpu]: + return + irq_record = self.irq_dic[cpu].pop() + irq_record['event_list'].append({'time': time, 'event': 'netif_rx', + 'skbaddr': skbaddr, 'skblen': skblen, + 'dev_name': dev_name}) + self.irq_dic[cpu].append(irq_record) + + def handle_netif_receive_skb(self, event: dict) -> None: + """Handle net:netif_receive_skb event.""" + time = event['time'] + cpu = event['cpu'] + skbaddr = event['skbaddr'] + skblen = event['skblen'] + if cpu in self.net_rx_dic: + rec_data = {'event_name': 'netif_receive_skb', + 'event_t': time, 'skbaddr': skbaddr, 'len': skblen} + event_list = self.net_rx_dic[cpu]['event_list'] + event_list.append(rec_data) + self.rx_skb_list.insert(0, rec_data) + if len(self.rx_skb_list) > self.buffer_budget: + self.rx_skb_list.pop() + self.of_count_rx_skb_list += 1 + + def handle_net_dev_queue(self, event: dict) -> None: + """Handle net:net_dev_queue event.""" + time = event['time'] + skbaddr = event['skbaddr'] + skblen = event['skblen'] + dev_name = event['dev_name'] + skb = {'dev': dev_name, 'skbaddr': skbaddr, 'len': skblen, 'queue_t': time} + self.tx_queue_list.insert(0, skb) + if len(self.tx_queue_list) > self.buffer_budget: + self.tx_queue_list.pop() + self.of_count_tx_queue_list += 1 + + def handle_net_dev_xmit(self, event: dict) -> None: + """Handle net:net_dev_xmit event.""" + time = event['time'] + skbaddr = event['skbaddr'] + rc = event['rc'] + if rc == 0: # NETDEV_TX_OK + for i, skb in enumerate(self.tx_queue_list): + if skb['skbaddr'] == skbaddr: + skb['xmit_t'] = time + self.tx_xmit_list.insert(0, skb) + del self.tx_queue_list[i] + if len(self.tx_xmit_list) > self.buffer_budget: + self.tx_xmit_list.pop() + self.of_count_tx_xmit_list += 1 + return + + def handle_kfree_skb(self, event: dict) -> None: + """Handle skb:kfree_skb event.""" + time = event['time'] + skbaddr = event['skbaddr'] + comm = event['comm'] + pid = event['pid'] + location = event['location'] + for i, skb in enumerate(self.tx_queue_list): + if skb['skbaddr'] == skbaddr: + del self.tx_queue_list[i] + return + for i, skb in enumerate(self.tx_xmit_list): + if skb['skbaddr'] == skbaddr: + skb['free_t'] = time + self.tx_free_list.append(skb) + del self.tx_xmit_list[i] + return + for i, rec_data in enumerate(self.rx_skb_list): + if rec_data['skbaddr'] == skbaddr: + rec_data.update({'handle': "kfree_skb", + 'comm': comm, 'pid': pid, 'comm_t': time, 'location': location}) + del self.rx_skb_list[i] + return + + def handle_consume_skb(self, event: dict) -> None: + """Handle skb:consume_skb event.""" + time = event['time'] + skbaddr = event['skbaddr'] + for i, skb in enumerate(self.tx_xmit_list): + if skb['skbaddr'] == skbaddr: + skb['free_t'] = time + self.tx_free_list.append(skb) + del self.tx_xmit_list[i] + return + for i, rec_data in enumerate(self.rx_skb_list): + if rec_data['skbaddr'] == skbaddr: + rec_data.update({'handle': "consume_skb", 'comm_t': time}) + del self.rx_skb_list[i] + return + + def handle_skb_copy_datagram_iovec(self, event: dict) -> None: + """Handle skb:skb_copy_datagram_iovec event.""" + time = event['time'] + skbaddr = event['skbaddr'] + comm = event['comm'] + pid = event['pid'] + for i, rec_data in enumerate(self.rx_skb_list): + if skbaddr == rec_data['skbaddr']: + rec_data.update({'handle': "skb_copy_datagram_iovec", + 'comm': comm, 'pid': pid, 'comm_t': time}) + del self.rx_skb_list[i] + return + + def print_summary(self) -> None: + """Print charts.""" + + # display receive hunks + if self.show_rx: + for hunk in self.receive_hunk_list: + self.print_receive(hunk) + + # display transmit hunks + if self.show_tx: + print(" dev len Qdisc " + " netdevice free") + for hunk in self.tx_free_list: + self.print_transmit(hunk) + + if self.debug: + print("debug buffer status") + print("----------------------------") + print(f"xmit Qdisc:remain:{len(self.tx_queue_list)} " + f"overflow:{self.of_count_tx_queue_list}") + print(f"xmit netdevice:remain:{len(self.tx_xmit_list)} " + f"overflow:{self.of_count_tx_xmit_list}") + print(f"receive:remain:{len(self.rx_skb_list)} " + f"overflow:{self.of_count_rx_skb_list}") + + def handle_single_event(self, event: dict) -> None: + """Handle a single processed event.""" + name = event['name'] + if name == 'irq:softirq_exit': + self.handle_irq_softirq_exit(event) + elif name == 'irq:softirq_entry': + self.handle_irq_softirq_entry(event) + elif name == 'irq:softirq_raise': + self.handle_irq_softirq_raise(event) + elif name == 'irq:irq_handler_entry': + self.handle_irq_handler_entry(event) + elif name == 'irq:irq_handler_exit': + self.handle_irq_handler_exit(event) + elif name == 'napi:napi_poll': + self.handle_napi_poll(event) + elif name == 'net:netif_receive_skb': + self.handle_netif_receive_skb(event) + elif name == 'net:netif_rx': + self.handle_netif_rx(event) + elif name == 'skb:skb_copy_datagram_iovec': + self.handle_skb_copy_datagram_iovec(event) + elif name == 'net:net_dev_queue': + self.handle_net_dev_queue(event) + elif name == 'net:net_dev_xmit': + self.handle_net_dev_xmit(event) + elif name == 'skb:kfree_skb': + self.handle_kfree_skb(event) + elif name == 'skb:consume_skb': + self.handle_consume_skb(event) + + def process_event(self, sample: perf.sample_event) -> None: + """Process events directly on-the-fly.""" + name = str(sample.evsel) + ev_name = name[6:-1] if name.startswith("evsel(") else name + pid = sample.sample_pid + if hasattr(self, 'session') and self.session: + try: + thread = self.session.find_thread(sample.sample_pid, sample.sample_tid) + comm = (thread.comm() if thread else None) or "[unknown]" + except (OSError, ValueError, KeyError, RuntimeError, TypeError, AttributeError): + comm = "[unknown]" + else: + comm = "Unknown" + event_data = { + 'name': ev_name, + 'time': sample.sample_time, + 'cpu': sample.sample_cpu, + 'pid': pid, + 'comm': comm, + } + + # Extract specific fields based on event type + if ev_name.startswith("irq:softirq_"): + event_data['vec'] = getattr(sample, "vec", 0) + # Filter for NET_RX + if event_data['vec'] != 3: # NET_RX_SOFTIRQ is usually 3 + return + elif ev_name == "irq:irq_handler_entry": + event_data['irq'] = getattr(sample, "irq", -1) + event_data['irq_name'] = getattr(sample, "name", "[unknown]") + elif ev_name == "irq:irq_handler_exit": + event_data['irq'] = getattr(sample, "irq", -1) + event_data['ret'] = getattr(sample, "ret", 0) + elif ev_name == "napi:napi_poll": + event_data['napi'] = getattr(sample, "napi", 0) + event_data['dev_name'] = getattr(sample, "dev_name", "[unknown]") + event_data['work'] = getattr(sample, "work", 0) + event_data['budget'] = getattr(sample, "budget", 0) + elif ev_name in ("net:netif_receive_skb", "net:netif_rx", + "net:net_dev_queue"): + event_data['skbaddr'] = getattr(sample, "skbaddr", 0) + event_data['skblen'] = getattr(sample, "len", 0) + event_data['dev_name'] = getattr(sample, "name", "[unknown]") + elif ev_name == "net:net_dev_xmit": + event_data['skbaddr'] = getattr(sample, "skbaddr", 0) + event_data['skblen'] = getattr(sample, "len", 0) + event_data['rc'] = getattr(sample, "rc", 0) + event_data['dev_name'] = getattr(sample, "name", "[unknown]") + elif ev_name == "skb:kfree_skb": + event_data['skbaddr'] = getattr(sample, "skbaddr", 0) + event_data['location'] = getattr(sample, "location", 0) + event_data['protocol'] = getattr(sample, "protocol", 0) + event_data['reason'] = getattr(sample, "reason", 0) + elif ev_name == "skb:consume_skb": + event_data['skbaddr'] = getattr(sample, "skbaddr", 0) + event_data['location'] = getattr(sample, "location", 0) + elif ev_name == "skb:skb_copy_datagram_iovec": + event_data['skbaddr'] = getattr(sample, "skbaddr", 0) + event_data['skblen'] = getattr(sample, "len", 0) + + self.handle_single_event(event_data) + + +NetdevTimes = NetDevTimesAnalyzer + + +if __name__ == "__main__": + ap = argparse.ArgumentParser(description="Display a process of packets and processed time.") + ap.add_argument("-i", "--input", default="perf.data", help="Input file name") + ap.add_argument("--tx", action="store_true", help="show only tx chart") + ap.add_argument("--rx", action="store_true", help="show only rx chart") + ap.add_argument("--dev", default=None, help="show only specified device") + ap.add_argument("--debug", action="store_true", + help="work with debug mode. It shows buffer status.") + ap.add_argument("positionals", nargs="*", + help="optional positional arguments (tx, rx, dev=<name>, debug)") + args, unknown_args = ap.parse_known_args() + + parsed_args = argparse.Namespace( + tx=args.tx, rx=args.rx, dev=args.dev, debug=args.debug, input=args.input + ) + + for arg in list(args.positionals) + unknown_args: + if not arg or not isinstance(arg, str): + continue + if arg in ('tx', '--tx'): + parsed_args.tx = True + elif arg in ('rx', '--rx'): + parsed_args.rx = True + elif arg.startswith('dev='): + parsed_args.dev = arg[4:] + elif arg.startswith('--dev='): + parsed_args.dev = arg[6:] + elif arg in ('debug', '--debug'): + parsed_args.debug = True + + analyzer = NetDevTimesAnalyzer(parsed_args) + + try: + try: + analyzer.session = perf.session( + perf.data(parsed_args.input), sample=analyzer.process_event + ) + try: + analyzer.session.process_events() + except KeyboardInterrupt: + pass + finally: + # Break the reference cycle between analyzer.session and the bound + # analyzer.process_event callback so the C perf.session object is freed. + analyzer.session = None + analyzer.print_summary() + except (OSError, ValueError, KeyError, RuntimeError, TypeError, AttributeError) as e: + print(f"Error processing events: {e}") + sys.exit(1)
tools/perf/tests/shell/test_netdev_times_python.sh new file +104 -0
104 lines not on this page · raw message
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 36/49] perf python: Port netdev-times to perf module
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 11 lines
Port
netdev-times.pyfromtools/perf/scripts/python/to a standalone script intools/perf/python/:
- Refactor the script into a NetDevTimesAnalyzer class with full type annotations to encapsulate state.
- Collect events via perf.session and sort them in timestamp order before analysis so multi-CPU TX and RX packet timelines are reconstructed deterministically.
- Replace custom argument parsing with argparse (-i/--input, --tx, --rx, --dev, --debug), extract tracepoint fields directly from sample attributes, and remove Python 2 compatibility artifacts.
Quoted 5 lines
Add a shell test (
test_netdev_times_python.sh) to verify the standalone script.Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=36
Ian Rogers
reviewerPATCH v4 37/49 perf python: Port check-perf-trace to perf module
In reply to Ian RogersPort check-perf-trace.py to a standalone script in tools/perf/python/ using the perf module directly.
Improvements compared to the legacy script:
- Access tracepoint fields directly as attributes on perf.sample_event instead of per-event dictionaries and legacy Perf-Trace-Util helpers.
- Decode symbolic flag and enum masks for irq:softirq_entry and kmem:kmalloc directly in Python and add -i/--input CLI support via argparse.
- Add full type annotations and clean up Python 2 idioms.
Add a shell test (test_check_perf_trace_python.sh) to verify the standalone script.
--- tools/perf/python/check-perf-trace.py | 223 ++++++++++++++++++ .../shell/test_check_perf_trace_python.sh | 85 +++++++ 2 files changed, 308 insertions(+) create mode 100755 tools/perf/python/check-perf-trace.py create mode 100755 tools/perf/tests/shell/test_check_perf_trace_python.sh
tools/perf/python/check-perf-trace.py new file +223 -0
@@ -0,0 +1,223 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +""" +Basic test of Python scripting support for perf. +Ported from tools/perf/scripts/python/check-perf-trace.py +""" +from __future__ import annotations + +import argparse +import collections +import perf + +unhandled: collections.defaultdict[str, int] = collections.defaultdict(int) +session = None + +softirq_vecs = { + 0: "HI_SOFTIRQ", + 1: "TIMER_SOFTIRQ", + 2: "NET_TX_SOFTIRQ", + 3: "NET_RX_SOFTIRQ", + 4: "BLOCK_SOFTIRQ", + 5: "IRQ_POLL_SOFTIRQ", + 6: "TASKLET_SOFTIRQ", + 7: "SCHED_SOFTIRQ", + 8: "HRTIMER_SOFTIRQ", + 9: "RCU_SOFTIRQ", +} + +_GFP_DMA = 1 << 0 +_GFP_HIGHMEM = 1 << 1 +_GFP_DMA32 = 1 << 2 +_GFP_MOVABLE = 1 << 3 +_GFP_RECLAIMABLE = 1 << 4 +_GFP_HIGH = 1 << 5 +_GFP_IO = 1 << 6 +_GFP_FS = 1 << 7 +_GFP_ZERO = 1 << 8 +_GFP_DIRECT_RECLAIM = 1 << 10 +_GFP_KSWAPD_RECLAIM = 1 << 11 +_GFP_WRITE = 1 << 12 +_GFP_NOWARN = 1 << 13 +_GFP_RETRY_MAYFAIL = 1 << 14 +_GFP_NOFAIL = 1 << 15 +_GFP_NORETRY = 1 << 16 +_GFP_MEMALLOC = 1 << 17 +_GFP_COMP = 1 << 18 +_GFP_NOMEMALLOC = 1 << 19 +_GFP_HARDWALL = 1 << 20 +_GFP_THISNODE = 1 << 21 +_GFP_ACCOUNT = 1 << 22 +_GFP_ZEROTAGS = 1 << 23 + +_GFP_RECLAIM = _GFP_DIRECT_RECLAIM | _GFP_KSWAPD_RECLAIM +_GFP_KERNEL = _GFP_RECLAIM | _GFP_IO | _GFP_FS +_GFP_USER = _GFP_KERNEL | _GFP_HARDWALL +_GFP_HIGHUSER = _GFP_USER | _GFP_HIGHMEM +_GFP_HIGHUSER_MOVABLE = _GFP_HIGHUSER | _GFP_MOVABLE +_GFP_TRANSHUGE_LIGHT = ( + _GFP_HIGHUSER_MOVABLE | _GFP_COMP | _GFP_NOMEMALLOC | _GFP_NOWARN +) & ~_GFP_RECLAIM +_GFP_TRANSHUGE = _GFP_TRANSHUGE_LIGHT | _GFP_DIRECT_RECLAIM + +GFP_FLAG_NAMES = [ + (_GFP_TRANSHUGE, "GFP_TRANSHUGE"), + (_GFP_TRANSHUGE_LIGHT, "GFP_TRANSHUGE_LIGHT"), + (_GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"), + (_GFP_HIGHUSER, "GFP_HIGHUSER"), + (_GFP_USER, "GFP_USER"), + (_GFP_KERNEL | _GFP_ACCOUNT, "GFP_KERNEL_ACCOUNT"), + (_GFP_KERNEL, "GFP_KERNEL"), + (_GFP_RECLAIM | _GFP_IO, "GFP_NOFS"), + (_GFP_HIGH | _GFP_KSWAPD_RECLAIM, "GFP_ATOMIC"), + (_GFP_RECLAIM, "GFP_NOIO"), + (_GFP_KSWAPD_RECLAIM | _GFP_NOWARN, "GFP_NOWAIT"), + (_GFP_DMA, "GFP_DMA"), + (_GFP_DMA32, "GFP_DMA32"), + (_GFP_RECLAIM, "__GFP_RECLAIM"), + (_GFP_DMA, "__GFP_DMA"), + (_GFP_HIGHMEM, "__GFP_HIGHMEM"), + (_GFP_DMA32, "__GFP_DMA32"), + (_GFP_MOVABLE, "__GFP_MOVABLE"), + (_GFP_RECLAIMABLE, "__GFP_RECLAIMABLE"), + (_GFP_HIGH, "__GFP_HIGH"), + (_GFP_IO, "__GFP_IO"), + (_GFP_FS, "__GFP_FS"), + (_GFP_ZERO, "__GFP_ZERO"), + (_GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"), + (_GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"), + (_GFP_WRITE, "__GFP_WRITE"), + (_GFP_NOWARN, "__GFP_NOWARN"), + (_GFP_RETRY_MAYFAIL, "__GFP_RETRY_MAYFAIL"), + (_GFP_NOFAIL, "__GFP_NOFAIL"), + (_GFP_NORETRY, "__GFP_NORETRY"), + (_GFP_MEMALLOC, "__GFP_MEMALLOC"), + (_GFP_COMP, "__GFP_COMP"), + (_GFP_NOMEMALLOC, "__GFP_NOMEMALLOC"), + (_GFP_HARDWALL, "__GFP_HARDWALL"), + (_GFP_THISNODE, "__GFP_THISNODE"), + (_GFP_ACCOUNT, "__GFP_ACCOUNT"), + (_GFP_ZEROTAGS, "__GFP_ZEROTAGS"), +] + + +def trace_begin() -> None: + """Called at the start of trace processing.""" + print("in trace_begin") + +def trace_end() -> None: + """Called at the end of trace processing.""" + print_unhandled() + print("in trace_end") + +def symbol_str(event_name: str, field_name: str, value: int) -> str: + """Resolves symbol values to strings.""" + # Note: The standalone Python API currently lacks dynamic libtraceevent + # formatting (equivalent to _perf_trace_context.symbol_str()) + if event_name == "irq__softirq_entry" and field_name == "vec": + return softirq_vecs.get(value, str(value)) + return str(value) + +def flag_str(event_name: str, field_name: str, value: int) -> str: + """Resolves flag values to strings.""" + # Note: The standalone Python API currently lacks dynamic libtraceevent + # formatting (equivalent to _perf_trace_context.flag_str()) + if event_name == "kmem__kmalloc" and field_name == "gfp_flags": + if value == 0: + return "none" + names = [] + rem = value + for mask, name in GFP_FLAG_NAMES: + if (rem & mask) == mask: + names.append(name) + rem &= ~mask + if rem: + names.append(f"0x{rem:x}") + return "|".join(names) + return str(value) + +def print_header(event_name: str, sample: perf.sample_event) -> None: + """Prints common header for events.""" + secs = sample.sample_time // 1000000000 + nsecs = sample.sample_time % 1000000000 + comm = "[unknown]" + try: + if session: + thread = session.find_thread(sample.sample_pid, sample.sample_tid) + if thread: + comm = thread.comm() or "[unknown]" + except (TypeError, AttributeError): + pass + print(f"{event_name:<20} {sample.sample_cpu:5} {secs:05}.{nsecs:09} " + f"{sample.sample_tid:8} {comm:<20} ", end=' ') + +def print_uncommon(sample: perf.sample_event) -> None: + """Prints uncommon fields for tracepoints.""" + # Fallback to 0 if field not found (e.g. on older kernels or if not tracepoint) + pc = getattr(sample, 'common_preempt_count', 0) + flags = getattr(sample, 'common_flags', 0) + lock_depth = getattr(sample, 'common_lock_depth', 0) + + print(f"common_preempt_count={pc}, common_flags={flags}, " + f"common_lock_depth={lock_depth}, ", end='') + +def irq__softirq_entry(sample: perf.sample_event) -> None: + """Handles irq:softirq_entry events.""" + print_header("irq__softirq_entry", sample) + print_uncommon(sample) + print(f"vec={symbol_str('irq__softirq_entry', 'vec', getattr(sample, 'vec', 0))}") + +def kmem__kmalloc(sample: perf.sample_event) -> None: + """Handles kmem:kmalloc events.""" + print_header("kmem__kmalloc", sample) + print_uncommon(sample) + + print(f"call_site={getattr(sample, 'call_site', 0):#x}, " + f"ptr={getattr(sample, 'ptr', 0):#x}, " + f"bytes_req={getattr(sample, 'bytes_req', 0):d}, " + f"bytes_alloc={getattr(sample, 'bytes_alloc', 0):d}, " + f"gfp_flags={flag_str('kmem__kmalloc', 'gfp_flags', getattr(sample, 'gfp_flags', 0))}") + +def trace_unhandled(event_name: str) -> None: + """Tracks unhandled events.""" + unhandled[event_name] += 1 + +def print_unhandled() -> None: + """Prints summary of unhandled events.""" + if not unhandled: + return + print("\nunhandled events:\n") + print(f"{'event':<40} {'count':>10}") + print("---------------------------------------- -----------") + for event_name, count in unhandled.items(): + print(f"{event_name:<40} {count:10}") + +def process_event(sample: perf.sample_event) -> None: + """Callback for processing events.""" + event_name = str(sample.evsel) + if event_name.startswith("evsel(") and event_name.endswith(")"): + event_name = event_name[6:-1] + if event_name.startswith("irq:softirq_entry"): + irq__softirq_entry(sample) + elif event_name.startswith("kmem:kmalloc"): + kmem__kmalloc(sample) + else: + trace_unhandled(event_name) + +if __name__ == "__main__": + ap = argparse.ArgumentParser() + ap.add_argument("-i", "--input", default="perf.data", help="Input file name") + args = ap.parse_args() + + trace_begin() + try: + session = perf.session(perf.data(args.input), sample=process_event) + try: + session.process_events() + except KeyboardInterrupt: + pass + trace_end() + finally: + # Break the reference cycle between the global session and the + # process_event callback so the C perf.session object is freed. + session = None
tools/perf/tests/shell/test_check_perf_trace_python.sh new file +85 -0
85 lines not on this page · raw message
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 37/49] perf python: Port check-perf-trace to perf module
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 11 lines
Port
check-perf-trace.pyto a standalone script intools/perf/python/using the perf module directly.Improvements compared to the legacy script:
- Access tracepoint fields directly as attributes on perf.sample_event instead of per-event dictionaries and legacy Perf-Trace-Util helpers.
- Decode symbolic flag and enum masks for irq:softirq_entry and kmem:kmalloc directly in Python and add -i/--input CLI support via argparse.
- Add full type annotations and clean up Python 2 idioms.
Quoted 5 lines
Add a shell test (
test_check_perf_trace_python.sh) to verify the standalone script.Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=37
Ian Rogers
reviewerPATCH v4 38/49 perf python: Port arm-cs-trace-disasm to perf module
In reply to Ian RogersPort arm-cs-trace-disasm.py to a standalone script in tools/perf/python/ using the perf module directly.
Improvements compared to the legacy script:
- Encapsulate trace disassembly state in a TraceDisasm class.
- Default to itrace="b" when creating perf.session() (overridable via --itrace or PERF_ITRACE) so all CoreSight branch samples are synthesized without requiring --itrace=b on the command line.
- Automatically search standard kernel debug paths (find_vmlinux()) when -k/--vmlinux is not specified, and query perf.config_get("annotate.objdump") for the default objdump binary.
- Bound DISASM_CACHE memory consumption by evicting the cache at 1024 entries and skipping caching of oversized (> 512 lines) objdump outputs.
- Use sample.srccode() from the perf extension module to annotate disassembly output with source filenames, line numbers, and source lines.
Update the ARM CoreSight disassembly shell test (test_arm_coresight_disasm.sh) to invoke the standalone script.
--- tools/perf/python/arm-cs-trace-disasm.py | 442 ++++++++++++++++++ .../coresight/test_arm_coresight_disasm.sh | 25 +- 2 files changed, 460 insertions(+), 7 deletions(-) create mode 100755 tools/perf/python/arm-cs-trace-disasm.py
tools/perf/python/arm-cs-trace-disasm.py new file +442 -0
@@ -0,0 +1,442 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +""" +arm-cs-trace-disasm.py: ARM CoreSight Trace Dump With Disassembler + +Author: Tor Jeremiassen <[email protected]> + Mathieu Poirier <[email protected]> + Leo Yan <[email protected]> + Al Grant <[email protected]> + +Below are some example commands for using this script. +Note a --kcore recording is required for accurate decode +due to the alternatives patching mechanism. In addition to this, +source line info comes from Perf, and when using kcore there is +no debug info. The following lists the supported features in each mode: + ++-----------+-----------------+------------------+------------------+ +| Recording | Accurate decode | Source line dump | Disassembly dump | ++-----------+-----------------+------------------+------------------+ +| --kcore | yes | no | yes | +| normal | no | yes (inaccurate) | yes (inaccurate) | ++-----------+-----------------+------------------+------------------+ + +Output disassembly with objdump and auto detect vmlinux +(when running on same machine): + perf script arm-cs-trace-disasm -- -d + +Output disassembly with llvm-objdump: + perf script arm-cs-trace-disasm -- -d llvm-objdump-11 -k path/to/vmlinux + +Output accurate disassembly by passing kcore to script: + perf script arm-cs-trace-disasm -- -d -k perf.data/kcore_dir/kcore + +Output only source line and symbols: + perf script arm-cs-trace-disasm +""" +from __future__ import annotations + +import os +from os import path +import re +from subprocess import CalledProcessError, check_output +import argparse +import platform +import sys +from typing import Dict, List, Optional + +import perf + +# Initialize global dicts and regular expression +DISASM_CACHE: Dict[str, List[str]] = {} +DISASM_RE = re.compile(r"^\s*([0-9a-fA-F]+):") +DISASM_FUNC_RE = re.compile(r"^\s*([0-9a-fA-F]+)\s.*:") +CACHE_SIZE = 1024 +class _State: + sample_idx: int = -1 + source_file_name: Optional[str] = None + line_number: Optional[int] = None + dso: Optional[str] = None + +_STATE = _State() + +KVER = platform.release() +VMLINUX_PATHS = [ + f"/usr/lib/debug/boot/vmlinux-{KVER}.debug", + f"/usr/lib/debug/lib/modules/{KVER}/vmlinux", + f"/lib/modules/{KVER}/build/vmlinux", + f"/usr/lib/debug/boot/vmlinux-{KVER}", + f"/boot/vmlinux-{KVER}", + "/boot/vmlinux", + "vmlinux", +] + +def default_objdump() -> str: + """Return the default objdump path from perf config or 'objdump'.""" + try: + config = perf.config_get("annotate.objdump") + return str(config) if config else "objdump" + except (AttributeError, TypeError): + return "objdump" + +def find_vmlinux() -> Optional[str]: + """Find the vmlinux file in standard paths.""" + if hasattr(find_vmlinux, "path"): + return getattr(find_vmlinux, "path") + + for v in VMLINUX_PATHS: + if os.access(v, os.R_OK): + setattr(find_vmlinux, "path", v) + return v + setattr(find_vmlinux, "path", None) + return None + +def get_dso_file_path(dso_name: str, dso_build_id: str, vmlinux: Optional[str]) -> str: + """Return the path to the DSO file.""" + # Locate DSO binaries in the perf build-id cache (~/.debug or PERF_BUILDID_DIR). + # Perf stores cached binaries under both <buildid_dir>/<dso_long_name>/<build_id>/elf + # and the canonical symlink/file layout <buildid_dir>/.build-id/<bid[:2]>/<bid[2:]>/elf. + buildid_dir = os.environ.get('PERF_BUILDID_DIR') + if not buildid_dir: + buildid_dir = os.path.join(os.environ.get('HOME', ''), '.debug') + + if (dso_name in ("[kernel.kallsyms]", "vmlinux", "kcore") + or dso_name.endswith("/vmlinux") or dso_name.endswith("/kcore")): + if vmlinux: + return vmlinux + if dso_build_id and dso_build_id != "[unknown]" and len(dso_build_id) > 2: + bid_candidate = os.path.join( + buildid_dir, ".build-id", dso_build_id[:2], dso_build_id[2:], "elf" + ) + if os.access(bid_candidate, os.R_OK): + return bid_candidate + for kname in (dso_name, "vmlinux", "[kernel.kallsyms]"): + candidate = os.path.join(buildid_dir, kname.lstrip("/"), dso_build_id, "elf") + if os.access(candidate, os.R_OK): + return candidate + return find_vmlinux() or dso_name + + if dso_name == "[vdso]": + append = "/vdso" + else: + append = "/elf" + + if dso_build_id and dso_build_id != "[unknown]" and len(dso_build_id) > 2: + bid_path = (buildid_dir + "/.build-id/" + dso_build_id[:2] + "/" + + dso_build_id[2:] + append).replace('//', '/') + if os.access(bid_path, os.R_OK): + return bid_path + + dso_path = buildid_dir + "/" + dso_name + "/" + dso_build_id + append + # Replace duplicate slash chars to single slash char + dso_path = dso_path.replace('//', '/') + return dso_path + +def read_disam(dso_fname: str, dso_start: int, start_addr: int, + stop_addr: int, objdump: str) -> List[str]: + """Read disassembly from a DSO file using objdump.""" + if stop_addr <= start_addr or (stop_addr - start_addr) > 0x100000: + return [] + addr_range = f"{start_addr}:{stop_addr}:{dso_start}:{dso_fname}" + + # Don't let the cache get too big, clear it when it hits max size + if len(DISASM_CACHE) > CACHE_SIZE: + DISASM_CACHE.clear() + + if addr_range in DISASM_CACHE: + disasm_output = DISASM_CACHE[addr_range] + else: + start_addr = start_addr - dso_start + stop_addr = stop_addr - dso_start + disasm = [objdump, "-d", "-z", + f"--start-address={start_addr:#x}", + f"--stop-address={stop_addr:#x}"] + disasm += [dso_fname] + try: + disasm_output = check_output(disasm).decode('utf-8', errors='replace').split('\n') + except (CalledProcessError, OSError): + return [] + if len(disasm_output) <= 512: + DISASM_CACHE[addr_range] = disasm_output + + return disasm_output + +def print_disam(dso_fname: str, dso_start: int, start_addr: int, + stop_addr: int, objdump: str) -> None: + """Print disassembly for a given address range.""" + for line in read_disam(dso_fname, dso_start, start_addr, stop_addr, objdump): + m = DISASM_FUNC_RE.search(line) + if m is None: + m = DISASM_RE.search(line) + if m is None: + continue + print(f"\t{line}") + +def print_sample(sample: perf.sample_event) -> None: + """Print sample details.""" + print(f"Sample = {{ cpu: {sample.sample_cpu:04d} addr: {sample.sample_addr:016x} " + f"phys_addr: {sample.sample_phys_addr:016x} ip: {sample.sample_ip:016x} " + f"pid: {sample.sample_pid} tid: {sample.sample_tid} period: {sample.sample_period} " + f"time: {sample.sample_time} index: {_STATE.sample_idx}}}") + +def common_start_str(comm: str, sample: perf.sample_event) -> str: + """Return common start string for sample output.""" + sec = int(sample.sample_time / 1000000000) + ns = sample.sample_time % 1000000000 + cpu = sample.sample_cpu + pid = sample.sample_pid + tid = sample.sample_tid + return f"{comm:>16s} {pid:5d}/{tid:<5d} [{cpu:04d}] {sec:9d}.{ns:09d} " + +def print_srccode(comm: str, sample: perf.sample_event, symbol: str, dso: str) -> None: + """Print source code and symbols for a sample.""" + ip = sample.sample_ip + if symbol == "[unknown]": + start_str = common_start_str(comm, sample) + f"{ip:x}".rjust(16).ljust(40) + else: + symoff = 0 + symoff = getattr(sample, 'sym_offset', 0) or 0 + offs = f"+{symoff:#x}" if symoff != 0 else "" + start_str = common_start_str(comm, sample) + (symbol + offs).ljust(40) + + source_file_name, line_number, source_line = sample.srccode() or (None, 0, None) + if source_file_name: + if _STATE.line_number == line_number and _STATE.source_file_name == source_file_name: + src_str = "" + else: + if len(source_file_name) > 40: + src_file = f"...{source_file_name[-37:]} " + else: + src_file = source_file_name.ljust(41) + + if source_line is None: + src_str = f"{src_file}{line_number:>4d} <source not found>" + else: + src_str = f"{src_file}{line_number:>4d} {source_line}" + _STATE.dso = None + elif dso == _STATE.dso: + src_str = "" + else: + src_str = dso + _STATE.dso = dso + + _STATE.line_number = line_number + _STATE.source_file_name = source_file_name + + print(start_str, src_str) + +class TraceDisasm: + """Class to handle trace disassembly.""" + def __init__(self, cli_options: argparse.Namespace): + self.options = cli_options + self.sample_idx = -1 + self.cpu_data: Dict[str, int] = {} + self.session: Optional[perf.session] = None + + def process_event(self, sample: perf.sample_event) -> None: + """Process a single perf event.""" + self.sample_idx += 1 + _STATE.sample_idx = self.sample_idx + + if self.options.start_time is not None and sample.sample_time < self.options.start_time: + return + if self.options.stop_time is not None and sample.sample_time > self.options.stop_time: + sys.exit(0) + if self.options.start_sample is not None and self.sample_idx < self.options.start_sample: + return + if self.options.stop_sample is not None and self.sample_idx > self.options.stop_sample: + sys.exit(0) + + ev_name = str(sample.evsel) + if self.options.verbose: + print(f"Event type: {ev_name}") + print_sample(sample) + + # Initialize CPU data if it's empty, and directly return back + # if this is the first tracing event for this CPU. This must happen + # before the dso == '[unknown]' check because the initial + # CS_ETM_TRACE_ON sample has ip == 0 (dso == '[unknown]') and + # carries the starting target address in sample.sample_addr. + if self.cpu_data.get(f"{sample.sample_cpu}addr") is None: + self.cpu_data[f"{sample.sample_cpu}addr"] = sample.sample_addr + return + + dso = getattr(sample, 'dso_long_name', None) or sample.dso or '[unknown]' + symbol = sample.symbol or '[unknown]' + dso_bid = (sample.dso_bid.decode('utf-8') + if isinstance(sample.dso_bid, bytes) + else str(sample.dso_bid or '[unknown]')) + dso_start = sample.map_start + dso_end = sample.map_end + map_pgoff = sample.map_pgoff or 0 + + comm = "[unknown]" + try: + if self.session: + thread_info = self.session.find_thread(sample.sample_pid, sample.sample_tid) + if thread_info: + comm = thread_info.comm() or "[unknown]" + except (TypeError, AttributeError): + pass + + if dso == '[unknown]': + return + + if dso_start is None or dso_end is None: + print(f"Failed to find valid dso map for dso {dso}") + return + + if "instructions" in ev_name: + print_srccode(comm, sample, symbol, dso) + return + + if "branches" not in ev_name: + return + + self._process_branch(sample, comm, symbol, dso, dso_bid, dso_start, dso_end, map_pgoff) + + def _process_branch(self, sample: perf.sample_event, comm: str, symbol: str, dso: str, + dso_bid: str, dso_start: int, dso_end: int, map_pgoff: int) -> None: + """Helper to process branch events.""" + cpu = sample.sample_cpu + ip = sample.sample_ip + addr = sample.sample_addr + + # The format for packet is: + # + # +------------+------------+------------+ + # sample_prev: | addr | ip | cpu | + # +------------+------------+------------+ + # sample_next: | addr | ip | cpu | + # +------------+------------+------------+ + # + # Combine the two continuous packets to get the instruction range for + # sample_prev::cpu: + # + # [ sample_prev::addr .. sample_next::ip ] + # + # sample_prev::addr is stored into cpu_data and read back as + # 'start_addr' when the new packet arrives, and sample_next::ip + 4 is + # used for 'stop_addr' so objdump includes the branch instruction at + # sample_next::ip. + start_addr = self.cpu_data[str(cpu) + 'addr'] + stop_addr = ip + 4 + + # Record for previous sample packet + self.cpu_data[str(cpu) + 'addr'] = addr + + # Filter out zero start_address. Optionally identify CS_ETM_TRACE_ON packet + if start_addr == 0: + if stop_addr == 4 and self.options.verbose: + print(f"CPU{cpu}: CS_ETM_TRACE_ON packet is inserted") + return + + if start_addr < dso_start or start_addr > dso_end: + print(f"Start address {start_addr:#x} is out of range [ {dso_start:#x} .. " + f"{dso_end:#x} ] for dso {dso}") + return + + if stop_addr < dso_start or stop_addr > dso_end: + print(f"Stop address {stop_addr:#x} is out of range [ {dso_start:#x} .. " + f"{dso_end:#x} ] for dso {dso}") + return + + if self.options.objdump is not None: + # Kernel images (vmlinux / kcore) and non-PIE executables linked at + # the default 0x400000 base already have their virtual load addresses + # baked into the ELF symbol/section headers read by objdump, so + # dso_vm_start and map_pgoff_local must be 0 to avoid subtracting + # map_start from virtual sample addresses. + if (dso in ("[kernel.kallsyms]", "vmlinux", "kcore") + or dso.endswith("/vmlinux") or dso.endswith("/kcore")): + dso_vm_start = 0 + map_pgoff_local = 0 + elif dso_start == 0x400000: + dso_vm_start = 0 + map_pgoff_local = 0 + else: + dso_vm_start = dso_start + map_pgoff_local = map_pgoff + + dso_fname = get_dso_file_path(dso, dso_bid, self.options.vmlinux) + if path.exists(dso_fname): + print_disam(dso_fname, dso_vm_start, start_addr + map_pgoff_local, + stop_addr + map_pgoff_local, self.options.objdump) + else: + print(f"Failed to find dso {dso} for address range [ " + f"{start_addr + map_pgoff_local:#x} .. {stop_addr + map_pgoff_local:#x} ]") + + print_srccode(comm, sample, symbol, dso) + + def run(self) -> None: + """Run the trace disassembly session.""" + input_file = self.options.input or "perf.data" + if input_file != "-" and not os.path.exists(input_file): + print(f"Error: {input_file} not found.", file=sys.stderr) + sys.exit(1) + + print('ARM CoreSight Trace Data Assembler Dump') + try: + session_kwargs = { + "sample": self.process_event, + "itrace": self.options.itrace, + } + if self.options.vmlinux: + session_kwargs["vmlinux"] = self.options.vmlinux + try: + self.session = perf.session(perf.data(input_file), **session_kwargs) + except TypeError: + session_kwargs.pop("vmlinux", None) + self.session = perf.session(perf.data(input_file), **session_kwargs) + except (OSError, ValueError, KeyError, RuntimeError, TypeError, AttributeError) as e: + print(f"Error opening session: {e}", file=sys.stderr) + sys.exit(1) + + try: + self.session.process_events() + except (KeyboardInterrupt, SystemExit): + pass + finally: + # Break the reference cycle between self.session and the bound + # self.process_event callback so the C perf.session object is freed. + self.session = None + print('End') + +if __name__ == "__main__": + def int_arg(v: str) -> int: + """Helper for integer command line arguments.""" + val = int(v) + if val < 0: + raise argparse.ArgumentTypeError("Argument must be a positive integer") + return val + + arg_parser = argparse.ArgumentParser(description="ARM CoreSight Trace Dump With Disassembler") + arg_parser.add_argument("-i", "--input", help="input perf.data file") + arg_parser.add_argument("-k", "--vmlinux", default=os.environ.get("PERF_SYMBOL_VMLINUX"), + help="Set path to vmlinux file. Omit to autodetect") + arg_parser.add_argument("-d", "--objdump", nargs="?", const=default_objdump(), + help="Show disassembly. Can also be used to change the objdump path") + arg_parser.add_argument("-v", "--verbose", action="store_true", help="Enable debugging log") + arg_parser.add_argument("--start-time", type=int_arg, + help="Monotonic clock time of sample to start from.") + arg_parser.add_argument("--stop-time", type=int_arg, + help="Monotonic clock time of sample to stop at.") + arg_parser.add_argument("--itrace", default=os.environ.get("PERF_ITRACE") or "b", + help="Instruction tracing options.") + arg_parser.add_argument("--start-sample", type=int_arg, + help="Index of sample to start from.") + arg_parser.add_argument("--stop-sample", type=int_arg, + help="Index of sample to stop at.") + + parsed_options = arg_parser.parse_args() + if (parsed_options.start_time is not None and parsed_options.stop_time is not None and + parsed_options.start_time >= parsed_options.stop_time): + print("--start-time must less than --stop-time") + sys.exit(2) + if (parsed_options.start_sample is not None and parsed_options.stop_sample is not None and + parsed_options.start_sample >= parsed_options.stop_sample): + print("--start-sample must less than --stop-sample") + sys.exit(2) + + td = TraceDisasm(parsed_options) + td.run()
tools/perf/tests/shell/coresight/test_arm_coresight_disasm.sh +18 -7
@@ -1,6 +1,6 @@ #!/bin/bash -# Check Arm CoreSight disassembly script completes without errors (exclusive) # SPDX-License-Identifier: GPL-2.0 +# Check Arm CoreSight disassembly script completes without errors (exclusive) # The disassembly script reconstructs ranges of instructions and gives these to objdump to # decode. objdump doesn't like ranges that go backwards, but these are a good indication
@@ -20,11 +20,23 @@ skip_if_no_cs_etm_event || exit 2 set -e glb_err=1 +# Relative path works whether it's installed or running from repo +if [ -n "$PERF_EXEC_PATH" ] && [ -e "$PERF_EXEC_PATH/python/arm-cs-trace-disasm.py" ]; then + script_path="$PERF_EXEC_PATH/python/arm-cs-trace-disasm.py" +else + script_path=$(dirname "$0")/../../../python/arm-cs-trace-disasm.py +fi + +# shellcheck source=lib/setup_python.sh +. "$(dirname "$0")"/../lib/setup_python.sh +$PYTHON -c "import perf" 2>/dev/null || { + echo "Skipping test, perf python module not found" + exit 2 +} + perfdata_dir=$(mktemp -d /tmp/__perf_test.perf.data.XXXXX) perfdata=${perfdata_dir}/perf.data file=$(mktemp /tmp/temporary_file.XXXXX) -# Relative path works whether it's installed or running from repo -script_path=$(dirname "$0")/../../../scripts/python/arm-cs-trace-disasm.py cleanup_files() {
@@ -44,8 +56,8 @@ branch_search='[[:space:]](bl|b(\.(eq|ne|cs|cc|mi|pl|vs|vc|hi|ls|ge|lt|gt|le|al) if [ "$(id -u)" == 0 ] && [ -e /proc/kcore ]; then echo "Testing kernel disassembly" perf record -o ${perfdata} -e cs_etm//k --kcore -Se -m,64K -- touch $file > /dev/null 2>&1 - perf script -i ${perfdata} --itrace=b -s python:${script_path} -- \ - -d --stop-sample=2 -k ${perfdata}/kcore_dir/kcore 2> /dev/null > ${file} + $PYTHON ${script_path} -i ${perfdata} -d --stop-sample=2 \ + -k ${perfdata}/kcore_dir/kcore 2> /dev/null > ${file} grep -q -E ${branch_search} ${file} echo "Found kernel branches" else
@@ -56,8 +68,7 @@ fi ## Test user ## echo "Testing userspace disassembly" perf record -o ${perfdata} -e cs_etm//u -Se -m,64K -- touch $file > /dev/null 2>&1 -perf script -i ${perfdata} --itrace=b -s python:${script_path} -- \ - -d --stop-sample=2 2> /dev/null > ${file} +$PYTHON ${script_path} -i ${perfdata} -d --stop-sample=2 2> /dev/null > ${file} grep -q -E ${branch_search} ${file} echo "Found userspace branches"
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 38/49] perf python: Port arm-cs-trace-disasm to perf module
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 18 lines
Port
arm-cs-trace-disasm.pyto a standalone script intools/perf/python/using the perf module directly.Improvements compared to the legacy script:
- Encapsulate trace disassembly state in a TraceDisasm class.
- Default to itrace="b" when creatingperf.session()(overridable via --itrace orPERF_ITRACE) so all CoreSight branch samples are synthesized without requiring --itrace=b on the command line.
- Automatically search standard kernel debug paths (find_vmlinux()) when -k/--vmlinux is not specified, and queryperf.config_get("annotate.objdump")for the default objdump binary.
- BoundDISASM_CACHEmemory consumption by evicting the cache at 1024 entries and skipping caching of oversized (> 512 lines) objdump outputs.
- Usesample.srccode()from the perf extension module to annotate disassembly output with source filenames, line numbers, and source lines.
Quoted 6 lines
Update the ARM CoreSight disassembly shell test (
test_arm_coresight_disasm.sh) to invoke the standalone script.Assisted-by Antigravity:gemini-3.1-proReviewed-by James Clark <[email protected]>Signed-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=38
Ian Rogers
reviewerPATCH v4 39/49 perf python: Port powerpc-hcalls to perf module
In reply to Ian RogersPort powerpc-hcalls.py from tools/perf/scripts/python/ to a standalone script in tools/perf/python/:
- Refactor the script into an HCallAnalyzer class with full type annotations to encapsulate per-CPU hypervisor call entry/exit state.
- Use perf.session for event processing to track hypervisor call entry and exit timestamps and aggregate min/max/average duration statistics against HCALL_TABLE.
- Add argparse CLI support (-i/--input) and remove Python 2 compatibility code.
Add a shell test (test_powerpc_hcalls_python.sh) to verify the standalone script.
--- tools/perf/python/powerpc-hcalls.py | 334 ++++++++++++++++++ .../tests/shell/test_powerpc_hcalls_python.sh | 95 +++++ 2 files changed, 429 insertions(+) create mode 100755 tools/perf/python/powerpc-hcalls.py create mode 100755 tools/perf/tests/shell/test_powerpc_hcalls_python.sh
tools/perf/python/powerpc-hcalls.py new file +334 -0
@@ -0,0 +1,334 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0+ +""" +Hypervisor call statistics + +Copyright (C) 2018 Ravi Bangoria, IBM Corporation +Ported from tools/perf/scripts/python/powerpc-hcalls.py +""" +from __future__ import annotations + +import argparse +from collections import defaultdict +import sys +import perf + +# Hypervisor call table +HCALL_TABLE = { + 4: 'H_REMOVE', + 8: 'H_ENTER', + 12: 'H_READ', + 16: 'H_CLEAR_MOD', + 20: 'H_CLEAR_REF', + 24: 'H_PROTECT', + 28: 'H_GET_TCE', + 32: 'H_PUT_TCE', + 36: 'H_SET_SPRG0', + 40: 'H_SET_DABR', + 44: 'H_PAGE_INIT', + 48: 'H_SET_ASR', + 52: 'H_ASR_ON', + 56: 'H_ASR_OFF', + 60: 'H_LOGICAL_CI_LOAD', + 64: 'H_LOGICAL_CI_STORE', + 68: 'H_LOGICAL_CACHE_LOAD', + 72: 'H_LOGICAL_CACHE_STORE', + 76: 'H_LOGICAL_ICBI', + 80: 'H_LOGICAL_DCBF', + 84: 'H_GET_TERM_CHAR', + 88: 'H_PUT_TERM_CHAR', + 92: 'H_REAL_TO_LOGICAL', + 96: 'H_HYPERVISOR_DATA', + 100: 'H_EOI', + 104: 'H_CPPR', + 108: 'H_IPI', + 112: 'H_IPOLL', + 116: 'H_XIRR', + 120: 'H_MIGRATE_DMA', + 124: 'H_PERFMON', + 220: 'H_REGISTER_VPA', + 224: 'H_CEDE', + 228: 'H_CONFER', + 232: 'H_PROD', + 236: 'H_GET_PPP', + 240: 'H_SET_PPP', + 244: 'H_PURR', + 248: 'H_PIC', + 252: 'H_REG_CRQ', + 256: 'H_FREE_CRQ', + 260: 'H_VIO_SIGNAL', + 264: 'H_SEND_CRQ', + 272: 'H_COPY_RDMA', + 276: 'H_REGISTER_LOGICAL_LAN', + 280: 'H_FREE_LOGICAL_LAN', + 284: 'H_ADD_LOGICAL_LAN_BUFFER', + 288: 'H_SEND_LOGICAL_LAN', + 292: 'H_BULK_REMOVE', + 304: 'H_MULTICAST_CTRL', + 308: 'H_SET_XDABR', + 312: 'H_STUFF_TCE', + 316: 'H_PUT_TCE_INDIRECT', + 332: 'H_CHANGE_LOGICAL_LAN_MAC', + 336: 'H_VTERM_PARTNER_INFO', + 340: 'H_REGISTER_VTERM', + 344: 'H_FREE_VTERM', + 348: 'H_RESET_EVENTS', + 352: 'H_ALLOC_RESOURCE', + 356: 'H_FREE_RESOURCE', + 360: 'H_MODIFY_QP', + 364: 'H_QUERY_QP', + 368: 'H_REREGISTER_PMR', + 372: 'H_REGISTER_SMR', + 376: 'H_QUERY_MR', + 380: 'H_QUERY_MW', + 384: 'H_QUERY_HCA', + 388: 'H_QUERY_PORT', + 392: 'H_MODIFY_PORT', + 396: 'H_DEFINE_AQP1', + 400: 'H_GET_TRACE_BUFFER', + 404: 'H_DEFINE_AQP0', + 408: 'H_RESIZE_MR', + 412: 'H_ATTACH_MCQP', + 416: 'H_DETACH_MCQP', + 420: 'H_CREATE_RPT', + 424: 'H_REMOVE_RPT', + 428: 'H_REGISTER_RPAGES', + 432: 'H_DISABLE_AND_GET', + 436: 'H_ERROR_DATA', + 440: 'H_GET_HCA_INFO', + 444: 'H_GET_PERF_COUNT', + 448: 'H_MANAGE_TRACE', + 456: 'H_GET_CPU_CHARACTERISTICS', + 468: 'H_FREE_LOGICAL_LAN_BUFFER', + 472: 'H_POLL_PENDING', + 484: 'H_QUERY_INT_STATE', + 580: 'H_ILLAN_ATTRIBUTES', + 584: 'H_ADD_LOGICAL_LAN_BUFFERS', + 592: 'H_MODIFY_HEA_QP', + 596: 'H_QUERY_HEA_QP', + 600: 'H_QUERY_HEA', + 604: 'H_QUERY_HEA_PORT', + 608: 'H_MODIFY_HEA_PORT', + 612: 'H_REG_BCMC', + 616: 'H_DEREG_BCMC', + 620: 'H_REGISTER_HEA_RPAGES', + 624: 'H_DISABLE_AND_GET_HEA', + 628: 'H_GET_HEA_INFO', + 632: 'H_ALLOC_HEA_RESOURCE', + 644: 'H_ADD_CONN', + 648: 'H_DEL_CONN', + 664: 'H_JOIN', + 672: 'H_VASI_SIGNAL', + 676: 'H_VASI_STATE', + 680: 'H_VIOCTL', + 688: 'H_ENABLE_CRQ', + 696: 'H_GET_EM_PARMS', + 720: 'H_SET_MPP', + 724: 'H_GET_MPP', + 732: 'H_REG_SUB_CRQ', + 736: 'H_FREE_SUB_CRQ', + 740: 'H_SEND_SUB_CRQ', + 744: 'H_SEND_SUB_CRQ_INDIRECT', + 748: 'H_HOME_NODE_ASSOCIATIVITY', + 756: 'H_BEST_ENERGY', + 764: 'H_XIRR_X', + 768: 'H_RANDOM', + 772: 'H_COP', + 788: 'H_GET_MPP_X', + 796: 'H_SET_MODE', + 808: 'H_BLOCK_REMOVE', + 856: 'H_CLEAR_HPT', + 864: 'H_REQUEST_VMC', + 876: 'H_RESIZE_HPT_PREPARE', + 880: 'H_RESIZE_HPT_COMMIT', + 892: 'H_REGISTER_PROC_TBL', + 896: 'H_SIGNAL_SYS_RESET', + 904: 'H_ALLOCATE_VAS_WINDOW', + 908: 'H_MODIFY_VAS_WINDOW', + 912: 'H_DEALLOCATE_VAS_WINDOW', + 916: 'H_QUERY_VAS_WINDOW', + 920: 'H_QUERY_VAS_CAPABILITIES', + 924: 'H_QUERY_NX_CAPABILITIES', + 928: 'H_GET_NX_FAULT', + 936: 'H_INT_GET_SOURCE_INFO', + 940: 'H_INT_SET_SOURCE_CONFIG', + 944: 'H_INT_GET_SOURCE_CONFIG', + 948: 'H_INT_GET_QUEUE_INFO', + 952: 'H_INT_SET_QUEUE_CONFIG', + 956: 'H_INT_GET_QUEUE_CONFIG', + 960: 'H_INT_SET_OS_REPORTING_LINE', + 964: 'H_INT_GET_OS_REPORTING_LINE', + 968: 'H_INT_ESB', + 972: 'H_INT_SYNC', + 976: 'H_INT_RESET', + 996: 'H_SCM_READ_METADATA', + 1000: 'H_SCM_WRITE_METADATA', + 1004: 'H_SCM_BIND_MEM', + 1008: 'H_SCM_UNBIND_MEM', + 1012: 'H_SCM_QUERY_BLOCK_MEM_BINDING', + 1016: 'H_SCM_QUERY_LOGICAL_MEM_BINDING', + 1020: 'H_SCM_UNBIND_ALL', + 1024: 'H_SCM_HEALTH', + 1048: 'H_SCM_PERFORMANCE_STATS', + 1052: 'H_PKS_GET_CONFIG', + 1056: 'H_PKS_SET_PASSWORD', + 1060: 'H_PKS_GEN_PASSWORD', + 1068: 'H_PKS_WRITE_OBJECT', + 1072: 'H_PKS_GEN_KEY', + 1076: 'H_PKS_READ_OBJECT', + 1080: 'H_PKS_REMOVE_OBJECT', + 1084: 'H_PKS_CONFIRM_OBJECT_FLUSHED', + 1096: 'H_RPT_INVALIDATE', + 1100: 'H_SCM_FLUSH', + 1104: 'H_GET_ENERGY_SCALE_INFO', + 1108: 'H_PKS_SIGNED_UPDATE', + 1112: 'H_HTM', + 1116: 'H_WATCHDOG', + # Platform specific hcalls used by KVM on PowerVM + 1120: 'H_GUEST_GET_CAPABILITIES', + 1124: 'H_GUEST_SET_CAPABILITIES', + 1136: 'H_GUEST_CREATE', + 1140: 'H_GUEST_CREATE_VCPU', + 1144: 'H_GUEST_GET_STATE', + 1148: 'H_GUEST_SET_STATE', + 1152: 'H_GUEST_RUN_VCPU', + 1156: 'H_GUEST_COPY_MEMORY', + 1160: 'H_GUEST_DELETE', + # Key wrapping hcalls + 1168: 'H_PKS_WRAP_OBJECT', + 1172: 'H_PKS_UNWRAP_OBJECT', + # Platform-specific hcalls used by the Ultravisor + 61184: 'H_SVM_PAGE_IN', + 61188: 'H_SVM_PAGE_OUT', + 61192: 'H_SVM_INIT_START', + 61196: 'H_SVM_INIT_DONE', + 61204: 'H_SVM_INIT_ABORT', + # Platform specific hcalls used by KVM + 61440: 'H_RTAS', + # Platform specific hcalls used by QEMU/SLOF + 61441: 'H_LOGICAL_MEMOP', + 61442: 'H_CAS', + 61443: 'H_UPDATE_DT', + # Platform specific hcalls provided by PHYP + 61560: 'H_GET_24X7_CATALOG_PAGE', + 61564: 'H_GET_24X7_DATA', + 61568: 'H_GET_PERF_COUNTER_INFO', + # Platform-specific hcalls used for nested HV KVM + 63488: 'H_SET_PARTITION_TABLE', + 63492: 'H_ENTER_NESTED', + 63496: 'H_TLB_INVALIDATE', + 63500: 'H_COPY_TOFROM_GUEST', +} + + +class HCallAnalyzer: + """Analyzes hypervisor calls and aggregates statistics.""" + + def __init__(self, cmd_args) -> None: + self.args = cmd_args + # output: {opcode: {'min': min, 'max': max, 'time': time, 'cnt': cnt}} + self.output: dict[int, dict[str, 'int | float']] = \ + defaultdict(lambda: {'time': 0, 'cnt': 0, 'min': float('inf'), 'max': 0}) + # d_enter: {cpu: {opcode: nsec}} + self.d_enter: dict[int, dict[int, int]] = {} + self.print_ptrn = '%-28s%10s%10s%10s%10s' + + def hcall_table_lookup(self, opcode: int) -> str: + """Lookup hcall name by opcode.""" + return HCALL_TABLE.get(opcode, str(opcode)) + + def process_event(self, sample: perf.sample_event) -> None: + """Process a single sample event.""" + name = str(sample.evsel) + if name not in ("evsel(powerpc:hcall_entry)", "evsel(powerpc:hcall_exit)"): + return + + try: + cpu = sample.sample_cpu + opcode = sample.opcode + except AttributeError: + print("ERROR: tracepoint fields missed (is libtraceevent enabled?)", + file=sys.stderr) + sys.exit(1) + + # sample.sample_time represents the nsecs + time = sample.sample_time + + if opcode < 0 or cpu < 0: + return + + if name == "evsel(powerpc:hcall_entry)": + if cpu not in self.d_enter: + self.d_enter[cpu] = {} + self.d_enter[cpu][opcode] = time + elif name == "evsel(powerpc:hcall_exit)": + if cpu in self.d_enter and opcode in self.d_enter[cpu]: + time_entry = self.d_enter[cpu][opcode] + diff = time - time_entry + del self.d_enter[cpu][opcode] + + stats = self.output[opcode] + stats['time'] += diff + stats['cnt'] += 1 + if diff < stats['min']: + stats['min'] = diff + if diff > stats['max']: + stats['max'] = diff + + def print_summary(self) -> None: + """Print aggregated statistics.""" + print(self.print_ptrn % ('hcall', 'count', 'min(ns)', 'max(ns)', 'avg(ns)')) + print('-' * 68) + + def sort_output(opcode): + stats = self.output[opcode] + sort_by = getattr(self.args, 'sort', None) + if sort_by == 'min': + return stats['min'] + if sort_by == 'max': + return stats['max'] + if sort_by == 'avg': + return stats['time'] // stats['cnt'] + return stats['cnt'] + + for opcode in sorted(self.output.keys(), key=sort_output, reverse=True): + h_name = self.hcall_table_lookup(opcode) + stats = self.output[opcode] + time = stats['time'] + cnt = stats['cnt'] + min_t = stats['min'] + max_t = stats['max'] + + # Avoid float representation for large integers if possible, + # or use formatted strings. Legacy used time//cnt. + avg_t = time // cnt if cnt > 0 else 0 + + # If min was not updated, it remains inf, but cnt should be > 0 if in output + if min_t == float('inf'): + min_t = 0 + + print(self.print_ptrn % (h_name, cnt, int(min_t), int(max_t), avg_t)) + + +if __name__ == "__main__": + ap = argparse.ArgumentParser(description="Hypervisor call statistics") + ap.add_argument("-i", "--input", default="perf.data", help="Input file name") + ap.add_argument("-s", "--sort", default="count", + choices=["count", "min", "max", "avg"], help="Sort key") + args = ap.parse_args() + + analyzer = HCallAnalyzer(args) + + session = None + try: + session = perf.session(perf.data(args.input), sample=analyzer.process_event) + session.process_events() + analyzer.print_summary() + except KeyboardInterrupt: + analyzer.print_summary() + except (OSError, ValueError, KeyError, RuntimeError, TypeError, AttributeError) as e: + print(f"Error processing events: {e}") + sys.exit(1) + finally: + # Break the reference cycle between perf.session and analyzer.process_event. + session = None
tools/perf/tests/shell/test_powerpc_hcalls_python.sh new file +95 -0
95 lines not on this page · raw message
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 39/49] perf python: Port powerpc-hcalls to perf module
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 10 lines
Port
powerpc-hcalls.pyfromtools/perf/scripts/python/to a standalone script intools/perf/python/:
- Refactor the script into an HCallAnalyzer class with full type annotations to encapsulate per-CPU hypervisor call entry/exit state.
- Use perf.session for event processing to track hypervisor call entry and exit timestamps and aggregate min/max/average duration statistics againstHCALL_TABLE.
- Add argparse CLI support (-i/--input) and remove Python 2 compatibility code.
Quoted 5 lines
Add a shell test (
test_powerpc_hcalls_python.sh) to verify the standalone script.Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=39
Ian Rogers
reviewerPATCH v4 40/49 perf python: Port intel-pt-events and libxed to perf module
In reply to Ian RogersPort intel-pt-events.py and libxed.py from tools/perf/scripts/python/ to standalone modules in tools/perf/python/:
- Refactor intel-pt-events.py into an IntelPTAnalyzer class with full type annotations to encapsulate trace state and stashed output.
- Configure instruction trace decoding directly via perf.session's itrace option and context_switch callback.
- Dynamically select 32-bit vs 64-bit disassembly mode in libxed.py using session.is_64_bit and annotate instructions with source lines via sample.srccode().
- Rename methods in libxed.py to snake_case (instruction, set_mode, disassemble_one) and remove Python 2 compatibility code.
Add a shell test (test_intel_pt_events_python.sh) to verify the standalone script.
--- tools/perf/python/intel-pt-events.py | 632 ++++++++++++++++++ tools/perf/python/libxed.py | 123 ++++ .../shell/test_intel_pt_events_python.sh | 69 ++ 3 files changed, 824 insertions(+) create mode 100755 tools/perf/python/intel-pt-events.py create mode 100755 tools/perf/python/libxed.py create mode 100755 tools/perf/tests/shell/test_intel_pt_events_python.sh
tools/perf/python/intel-pt-events.py new file +632 -0
@@ -0,0 +1,632 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +""" +Print Intel PT Events including Power Events and PTWRITE. +Ported from tools/perf/scripts/python/intel-pt-events.py +""" +from __future__ import annotations + +import argparse +from typing import Dict, List, Tuple +import contextlib +from ctypes import addressof, create_string_buffer +import io +import os +import struct +import sys +from typing import Any, Optional +import typing +import perf + +try: + from libxed import LibXED as _LibXED + LibXED: Optional[type[_LibXED]] = _LibXED +except ImportError: + LibXED = None + + +def sample_flags_to_name(flags: int) -> str: + """Implement perf's sample_flags_to_name.""" + if not isinstance(flags, int) or flags == 0: + return "".ljust(21) + # PERF_IP_FLAG_* bit positions (from tools/perf/util/event.h): + # bit 0: PERF_IP_FLAG_BRANCH + # bit 1: PERF_IP_FLAG_CALL + # bit 2: PERF_IP_FLAG_RETURN + # bit 3: PERF_IP_FLAG_CONDITIONAL + # bit 4: PERF_IP_FLAG_SYSCALLRET + # bit 5: PERF_IP_FLAG_ASYNC + # bit 6: PERF_IP_FLAG_INTERRUPT + # bit 7: PERF_IP_FLAG_TX_ABORT + # bit 8: PERF_IP_FLAG_TRACE_BEGIN + # bit 9: PERF_IP_FLAG_TRACE_END + # bit 10: PERF_IP_FLAG_IN_TX + # bit 11: PERF_IP_FLAG_VMENTRY + # bit 12: PERF_IP_FLAG_VMEXIT + # bit 13: PERF_IP_FLAG_INTR_DISABLE + # bit 14: PERF_IP_FLAG_INTR_TOGGLE + # bit 15: PERF_IP_FLAG_BRANCH_MISS + # bit 16: PERF_IP_FLAG_NOT_TAKEN + sample_flags = [ + ((1 << 0) | (1 << 1), "call"), + ((1 << 0) | (1 << 2), "return"), + ((1 << 0) | (1 << 3), "jcc"), + ((1 << 0), "jmp"), + ((1 << 0) | (1 << 1) | (1 << 6), "int"), + ((1 << 0) | (1 << 2) | (1 << 6), "iret"), + ((1 << 0) | (1 << 1) | (1 << 4), "syscall"), + ((1 << 0) | (1 << 2) | (1 << 4), "sysret"), + ((1 << 0) | (1 << 5), "async"), + ((1 << 0) | (1 << 1) | (1 << 5) | (1 << 6), "hw int"), + ((1 << 0) | (1 << 7), "tx abrt"), + ((1 << 0) | (1 << 8), "tr strt"), + ((1 << 0) | (1 << 9), "tr end"), + ((1 << 0) | (1 << 1) | (1 << 11), "vmentry"), + ((1 << 0) | (1 << 1) | (1 << 12), "vmexit"), + ] + additional_mask = (1 << 10) | (1 << 13) | (1 << 14) + branch_event_mask = (1 << 15) | (1 << 16) + xf = flags & additional_mask + rem_flags = flags & ~additional_mask + + if rem_flags & (1 << 8): + prefix = "tr strt " + elif rem_flags & (1 << 9): + prefix = "tr end " + else: + prefix = "" + + rem_flags &= ~((1 << 8) | (1 << 9)) + types = rem_flags & ~branch_event_mask + type_name = "" + for f_mask, f_name in sample_flags: + if f_mask == types: + type_name = f_name + break + + s = prefix + type_name + ev_parts = [] + if rem_flags & (1 << 15): + ev_parts.append("miss") + if rem_flags & (1 << 16): + ev_parts.append("not_taken") + if ev_parts: + s += "/" + ",".join(ev_parts) + "/" + + if xf: + xs = "(" + if xf & (1 << 10): + xs += "x" + if xf & (1 << 13): + xs += "D" + if xf & (1 << 14): + xs += "t" + xs += ")" + if len(s) + len(xs) < 21: + s = s + xs.rjust(21 - len(s)) + else: + s = s + " " + xs + return s.ljust(21) + +class IntelPTAnalyzer: + """Analyzes Intel PT events and prints details.""" + + def __init__(self, cfg: argparse.Namespace): + self.args = cfg + self.session: Optional[perf.session] = None + self.insn = False + self.src = False + self.source_file_name: Optional[str] = None + self.line_number: int = 0 + self.dso: Optional[str] = None + self.stash_dict: Dict[int, List[str]] = {} + self.output: Any = None + self.output_pos: int = 0 + self.cpu: int = -1 + self.time: int = 0 + self.switch_str: Dict[int, str] = {} + + if cfg.insn_trace: + print("Intel PT Instruction Trace") + self.insn = True + elif cfg.src_trace: + print("Intel PT Source Trace") + self.insn = True + self.src = True + else: + print("Intel PT Branch Trace, Power Events, Event Trace and PTWRITE") + + self.disassembler: Any = None + self.inst: Any = None + if self.insn and LibXED is not None: + try: + self.disassembler = LibXED() + self.inst = self.disassembler.instruction() + except (OSError, ValueError, KeyError, RuntimeError, TypeError, AttributeError, + ImportError) as e: + print(f"Failed to initialize LibXED: {e}") + self.disassembler = None + self.inst = None + + def print_ptwrite(self, raw_buf: bytes) -> None: + """Print PTWRITE data.""" + if not raw_buf: + return + try: + data = struct.unpack_from("<IQ", raw_buf) + flags = data[0] + payload = data[1] + except struct.error: + return + exact_ip = flags & 1 + try: + s = payload.to_bytes(8, "little").decode("ascii").rstrip("\x00") + if not s.isprintable(): + s = "" + except (UnicodeDecodeError, ValueError): + s = "" + print(f"IP: {exact_ip} payload: {payload:#x} {s}", end=' ') + + def print_cbr(self, raw_buf: bytes) -> None: + """Print CBR data.""" + if len(raw_buf) < 12: + return + try: + data = struct.unpack_from("<BBBBII", raw_buf) + except struct.error: + return + cbr = data[0] + f = (data[4] + 500) // 1000 + if data[2] == 0: + return + p = ((cbr * 1000 // data[2]) + 5) // 10 + print(f"{cbr:3d} freq: {f:4d} MHz ({p:3d}%)", end=' ') + + def print_mwait(self, raw_buf: bytes) -> None: + """Print MWAIT data.""" + try: + data = struct.unpack_from("<IQ", raw_buf) + except struct.error: + return + payload = data[1] + hints = payload & 0xff + extensions = (payload >> 32) & 0x3 + print(f"hints: {hints:#x} extensions: {extensions:#x}", end=' ') + + def print_pwre(self, raw_buf: bytes) -> None: + """Print PWRE data.""" + try: + data = struct.unpack_from("<IQ", raw_buf) + except struct.error: + return + payload = data[1] + hw = (payload >> 7) & 1 + cstate = (payload >> 12) & 0xf + subcstate = (payload >> 8) & 0xf + print(f"hw: {hw} cstate: {cstate} sub-cstate: {subcstate}", end=' ') + + def print_exstop(self, raw_buf: bytes) -> None: + """Print EXSTOP data.""" + try: + data = struct.unpack_from("<I", raw_buf) + except struct.error: + return + flags = data[0] + exact_ip = flags & 1 + print(f"IP: {exact_ip}", end=' ') + + def print_pwrx(self, raw_buf: bytes) -> None: + """Print PWRX data.""" + try: + data = struct.unpack_from("<IQ", raw_buf) + except struct.error: + return + payload = data[1] + deepest_cstate = payload & 0xf + last_cstate = (payload >> 4) & 0xf + wake_reason = (payload >> 8) & 0xf + print(f"deepest cstate: {deepest_cstate} last cstate: {last_cstate} " + f"wake reason: {wake_reason:#x}", end=' ') + + def print_psb(self, raw_buf: bytes) -> None: + """Print PSB data.""" + try: + data = struct.unpack_from("<IQ", raw_buf) + except struct.error: + return + offset = data[1] + print(f"offset: {offset:#x}", end=' ') + + def print_evt(self, raw_buf: bytes) -> None: + """Print EVT data.""" + glb_cfe = ["", "INTR", "IRET", "SMI", "RSM", "SIPI", "INIT", "VMENTRY", "VMEXIT", + "VMEXIT_INTR", "SHUTDOWN", "", "UINT", "UIRET"] + [""] * 18 + glb_evd = ["", "PFA", "VMXQ", "VMXR"] + [""] * 60 + + try: + data = struct.unpack_from("<BBH", raw_buf) + except struct.error: + return + typ = data[0] & 0x1f + ip_flag = (data[0] & 0x80) >> 7 + vector = data[1] + evd_cnt = data[2] + s = glb_cfe[typ] + if s: + print(f" cfe: {s} IP: {ip_flag} vector: {vector}", end=' ') + else: + print(f" cfe: {typ} IP: {ip_flag} vector: {vector}", end=' ') + pos = 4 + for _ in range(evd_cnt): + if len(raw_buf) < pos + 16: + break + try: + data = struct.unpack_from("<QQ", raw_buf, pos) + except struct.error: + return + et = data[0] & 0x3f + s = glb_evd[et] + if s: + print(f"{s}: {data[1]:#x}", end=' ') + else: + print(f"EVD_{et}: {data[1]:#x}", end=' ') + pos += 16 + + def print_iflag(self, raw_buf: bytes) -> None: + """Print IFLAG data.""" + try: + data = struct.unpack_from("<IQ", raw_buf) + except struct.error: + return + iflag = data[0] & 1 + old_iflag = iflag ^ 1 + via_branch = data[0] & 2 + s = "via" if via_branch else "non" + print(f"IFLAG: {old_iflag}->{iflag} {s} branch", end=' ') + + def common_start_str(self, comm: str, sample: perf.sample_event) -> str: + """Return common start string for display.""" + ts = sample.sample_time + cpu = sample.sample_cpu + pid = sample.sample_pid + tid = sample.sample_tid + machine_pid = getattr(sample, "machine_pid", 0) + if machine_pid: + vcpu = getattr(sample, "vcpu", -1) + return (f"VM:{machine_pid:5d} VCPU:{vcpu:03d} {comm:>16s} {pid:5d}/{tid:<5d} " + f"[{cpu:03d}] {ts // 1000000000:9d}.{ts % 1000000000:09d} ") + return (f"{comm:>16s} {pid:5d}/{tid:<5d} [{cpu:03d}] " + f"{ts // 1000000000:9d}.{ts % 1000000000:09d} ") + + def print_common_start(self, comm: str, sample: perf.sample_event, name: str) -> None: + """Print common start info.""" + flags_disp = sample_flags_to_name(getattr(sample, "flags", 0)) + print(self.common_start_str(comm, sample) + f"{name:>8s} {flags_disp:>21s}", end=' ') + + def print_instructions_start(self, comm: str, sample: perf.sample_event) -> None: + """Print instructions start info.""" + raw_flags = getattr(sample, "flags", 0) + if isinstance(raw_flags, int) and (raw_flags & (1 << 10)): + print(self.common_start_str(comm, sample) + "x", end=' ') + else: + print(self.common_start_str(comm, sample), end=' ') + + def disassem(self, insn: bytes, ip: int) -> Tuple[int, str]: + """Disassemble instruction using LibXED.""" + inst = self.inst if self.inst is not None else self.disassembler.instruction() + is_64_bit = getattr(self.session, "is_64_bit", True) if self.session else True + self.disassembler.set_mode(inst, 0 if is_64_bit else 1) + buf = create_string_buffer(insn) + return self.disassembler.disassemble_one(inst, addressof(buf), len(insn), ip) + + def print_common_ip(self, sample: perf.sample_event, symbol: str, dso: str) -> None: + """Print IP and symbol info.""" + ip = sample.sample_ip + offs = f"+{sample.sym_offset:#x}" if getattr(sample, "sym_offset", None) is not None else "" + cyc_cnt = getattr(sample, "sample_cyc_count", 0) + if cyc_cnt: + insn_cnt = getattr(sample, "sample_insn_count", 0) + ipc_str = f" IPC: {insn_cnt / cyc_cnt:#.2f} ({insn_cnt}/{cyc_cnt})" + else: + ipc_str = "" + + if self.insn and self.disassembler is not None: + try: + insn = sample.insn() + except AttributeError: + insn = None + if insn: + cnt, text = self.disassem(insn, ip) + byte_str = (f"{ip:x}").rjust(16) + for k in range(cnt): + byte_str += f" {insn[k]:02x}" + print(f"{byte_str:<40s} {text:<30s}", end=' ') + else: + print(f"{ip:16x}", end=' ') + print(f"{symbol}{offs} ({dso})", end=' ') + else: + print(f"{ip:16x} {symbol}{offs} ({dso})", end=' ') + + addr = getattr(sample, "sample_addr", getattr(sample, "addr", 0)) + addr_correlates_sym = ( + bool(addr) + or getattr(sample, "addr_symbol", None) is not None + or getattr(sample, "addr_dso", None) is not None + ) + if addr_correlates_sym: + addr_dso = (sample.addr_dso or '[unknown]') + addr_symbol = (sample.addr_symbol or '[unknown]') + addr_offs = (f"+{sample.addr_sym_offset:#x}" + if getattr(sample, "addr_sym_offset", None) is not None else "") + print(f"=> {addr:x} {addr_symbol}{addr_offs} ({addr_dso}){ipc_str}") + else: + print(ipc_str) + + def print_srccode(self, comm: str, sample: perf.sample_event, + symbol: str, dso: str, with_insn: bool) -> None: + """Print source code info.""" + ip = sample.sample_ip + if symbol == "[unknown]": + start_str = self.common_start_str(comm, sample) + (f"{ip:x}").rjust(16).ljust(40) + else: + offs = (f"+{sample.sym_offset:#x}" + if getattr(sample, "sym_offset", None) is not None else "") + start_str = self.common_start_str(comm, sample) + (symbol + offs).ljust(40) + + if with_insn and self.insn and self.disassembler is not None: + try: + insn = sample.insn() + except AttributeError: + insn = None + if insn: + _, text = self.disassem(insn, ip) + start_str += text.ljust(30) + + source_file_name: typing.Any = None + line_number: typing.Any = 0 + source_line: typing.Any = None + try: + res_srcc = sample.srccode() + if res_srcc: + source_file_name, line_number, source_line = res_srcc + except (AttributeError, ValueError, TypeError): + pass + + if source_file_name: + if self.line_number == line_number and self.source_file_name == source_file_name: + src_str = "" + else: + if len(source_file_name) > 40: + src_file = ("..." + source_file_name[-37:]) + " " + else: + src_file = source_file_name.ljust(41) + if source_line is None: + src_str = src_file + str(line_number).rjust(4) + " <source not found>" + else: + src_str = src_file + str(line_number).rjust(4) + " " + source_line + self.dso = None + elif dso == self.dso: + src_str = "" + else: + src_str = dso + self.dso = dso + + self.line_number = line_number + self.source_file_name = source_file_name + print(start_str, src_str) + + def do_process_event(self, sample: perf.sample_event) -> None: + """Process event and print info.""" + cpu = getattr(sample, "sample_cpu", getattr(sample, "cpu", 0)) + if cpu in self.switch_str: + print(self.switch_str[cpu]) + del self.switch_str[cpu] + + comm = "Unknown" + if hasattr(self, 'session') and self.session: + try: + thread = self.session.find_thread(sample.sample_pid, sample.sample_tid) + if thread: + comm = thread.comm() or "Unknown" + except (OSError, ValueError, KeyError, RuntimeError, TypeError, AttributeError): + pass + # Python < 3.9 compatibility + name = str(sample.evsel) + if name.startswith("evsel("): + name = name[6:-1] + dso = (sample.dso or '[unknown]') + symbol = (sample.symbol or '[unknown]') + + raw_buf = getattr(sample, 'raw_buf', b'') or b'' + + if name.startswith("instructions"): + if self.src: + self.print_srccode(comm, sample, symbol, dso, True) + else: + self.print_instructions_start(comm, sample) + self.print_common_ip(sample, symbol, dso) + elif name.startswith("branches"): + if self.src: + self.print_srccode(comm, sample, symbol, dso, False) + else: + self.print_common_start(comm, sample, name) + self.print_common_ip(sample, symbol, dso) + elif name == "ptwrite": + self.print_common_start(comm, sample, name) + self.print_ptwrite(raw_buf) + self.print_common_ip(sample, symbol, dso) + elif name == "cbr": + self.print_common_start(comm, sample, name) + self.print_cbr(raw_buf) + self.print_common_ip(sample, symbol, dso) + elif name == "mwait": + self.print_common_start(comm, sample, name) + self.print_mwait(raw_buf) + self.print_common_ip(sample, symbol, dso) + elif name == "pwre": + self.print_common_start(comm, sample, name) + self.print_pwre(raw_buf) + self.print_common_ip(sample, symbol, dso) + elif name == "exstop": + self.print_common_start(comm, sample, name) + self.print_exstop(raw_buf) + self.print_common_ip(sample, symbol, dso) + elif name == "pwrx": + self.print_common_start(comm, sample, name) + self.print_pwrx(raw_buf) + self.print_common_ip(sample, symbol, dso) + elif name == "psb": + self.print_common_start(comm, sample, name) + self.print_psb(raw_buf) + self.print_common_ip(sample, symbol, dso) + elif name == "evt": + self.print_common_start(comm, sample, name) + self.print_evt(raw_buf) + self.print_common_ip(sample, symbol, dso) + elif name == "iflag": + self.print_common_start(comm, sample, name) + self.print_iflag(raw_buf) + self.print_common_ip(sample, symbol, dso) + else: + self.print_common_start(comm, sample, name) + self.print_common_ip(sample, symbol, dso) + + def interleave_events(self, sample: perf.sample_event) -> None: + """Interleave output to avoid garbled lines from different CPUs.""" + self.cpu = sample.sample_cpu + ts = sample.sample_time + + if self.time != ts: + self.time = ts + self.flush_stashed_output() + + self.output_pos = 0 + with contextlib.redirect_stdout(io.StringIO()) as self.output: + self.do_process_event(sample) + + self.stash_output() + + def stash_output(self) -> None: + """Stash output for later flushing.""" + output_str = self.output.getvalue()[self.output_pos:] + n = len(output_str) + if n: + self.output_pos += n + if self.cpu not in self.stash_dict: + self.stash_dict[self.cpu] = [] + self.stash_dict[self.cpu].append(output_str) + if len(self.stash_dict[self.cpu]) > 1000: + self.flush_stashed_output() + + def flush_stashed_output(self) -> None: + """Flush stashed output.""" + while self.stash_dict: + cpus = list(self.stash_dict.keys()) + for cpu in cpus: + items = self.stash_dict[cpu] + countdown = self.args.interleave + while len(items) and countdown: + sys.stdout.write(items[0]) + del items[0] + countdown -= 1 + if not items: + del self.stash_dict[cpu] + + def process_context_switch(self, event: perf.switch_event) -> None: + """Process context switch.""" + cpu = getattr(event, "sample_cpu", getattr(event, "cpu", 0)) + pid = getattr(event, "sample_pid", getattr(event, "pid", 0)) + tid = getattr(event, "sample_tid", getattr(event, "tid", 0)) + ts = getattr(event, "sample_time", getattr(event, "time", 0)) + np_pid = getattr(event, "next_prev_pid", None) + np_tid = getattr(event, "next_prev_tid", None) + machine_pid = getattr(event, "machine_pid", -1) + vcpu = getattr(event, "vcpu", -1) + misc = getattr(event, "misc", 0) + out = bool(misc & (1 << 13)) + out_preempt = bool(misc & (1 << 14)) + + if self.args.interleave: + self.flush_stashed_output() + + if out: + out_str = "Switch out " + else: + out_str = "Switch In " + + preempt_str = "preempt" if out_preempt else "" + + if machine_pid == -1: + machine_str = "" + elif vcpu == -1: + machine_str = f"machine PID {machine_pid}" + else: + machine_str = f"machine PID {machine_pid} VCPU {vcpu}" + + np_str = f"{np_pid:5d}/{np_tid:<5d} " if np_pid is not None and np_tid is not None else "" + c_str = (f"{out_str:>16s} {pid:5d}/{tid:<5d} [{cpu:03d}] " + f"{ts // 1000000000:9d}.{ts % 1000000000:09d} " + f"{np_str}{machine_str} {preempt_str}") + + if self.args.all_switch_events: + print(c_str) + else: + self.switch_str[cpu] = c_str + def process_event(self, sample: perf.sample_event) -> None: + """Wrapper to handle interleaving and exceptions.""" + try: + if self.args.interleave: + self.interleave_events(sample) + else: + self.do_process_event(sample) + except BrokenPipeError: + # Stop python printing broken pipe errors and traceback + sys.stdout = open(os.devnull, 'w', encoding='utf-8') + sys.exit(1) + + +if __name__ == "__main__": + ap = argparse.ArgumentParser() + ap.add_argument("-i", "--input", default="perf.data", help="Input file name") + ap.add_argument("--insn-trace", action='store_true') + ap.add_argument("--src-trace", action='store_true') + ap.add_argument("--all-switch-events", action='store_true') + ap.add_argument("--interleave", type=int, nargs='?', const=4, default=0) + ap.add_argument("--itrace", default=os.environ.get("PERF_ITRACE"), help="itrace options") + args = ap.parse_args() + + if args.itrace is None: + if args.insn_trace or args.src_trace: + args.itrace = "i0nsepwxI" + else: + args.itrace = "bepwxI" + analyzer = IntelPTAnalyzer(args) + + try: + # Note: Python API currently lacks auxtrace_error callbacks affecting + # chronological interleaving + try: + analyzer.session = perf.session( + perf.data(args.input), + sample=analyzer.process_event, + context_switch=analyzer.process_context_switch, + itrace=args.itrace + ) + try: + analyzer.session.process_events() + except KeyboardInterrupt: + pass + finally: + # Break the reference cycle between analyzer.session and the bound + # analyzer.process_event / process_context_switch callbacks so the + # underlying C perf.session object is freed. + analyzer.session = None + if args.interleave: + analyzer.flush_stashed_output() + print("End") + except BrokenPipeError: + sys.exit(0) + except (OSError, ValueError, KeyError, RuntimeError, TypeError, AttributeError): + import traceback + traceback.print_exc() + sys.exit(1)
tools/perf/python/libxed.py new file +123 -0
123 lines not on this page · raw message
tools/perf/tests/shell/test_intel_pt_events_python.sh new file +69 -0
69 lines not on this page · raw message
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 40/49] perf python: Port intel-pt-events and libxed to perf module
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 12 lines
Port
intel-pt-events.pyandlibxed.pyfromtools/perf/scripts/python/to standalone modules intools/perf/python/:
- Refactorintel-pt-events.pyinto an IntelPTAnalyzer class with full type annotations to encapsulate trace state and stashed output.
- Configure instruction trace decoding directly via perf.session's itrace option andcontext_switchcallback.
- Dynamically select 32-bit vs 64-bit disassembly mode inlibxed.pyusing session.is_64_bit and annotate instructions with source lines viasample.srccode().
- Rename methods inlibxed.pytosnake_case(instruction,set_mode,disassemble_one) and remove Python 2 compatibility code.
Quoted 5 lines
Add a shell test (
test_intel_pt_events_python.sh) to verify the standalone script.Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=40
Ian Rogers
reviewerPATCH v4 41/49 perf test: Migrate Intel PT virtual LBR test to Python API
In reply to Ian RogersMigrate the Intel PT virtual LBR test from generating an inline legacy perf script callback to using a standalone Python script (perf_brstack_max.py) with the brstack iterator API in the perf Python module.
--- .../perf/tests/shell/lib/perf_brstack_max.py | 40 +++++++++++++++++ tools/perf/tests/shell/test_intel_pt.sh | 43 ++++++++----------- 2 files changed, 58 insertions(+), 25 deletions(-) create mode 100644 tools/perf/tests/shell/lib/perf_brstack_max.py
tools/perf/tests/shell/lib/perf_brstack_max.py new file +40 -0
@@ -0,0 +1,40 @@ +#!/usr/bin/python +# SPDX-License-Identifier: GPL-2.0 +# Determine the maximum size of branch stacks in a perf.data file. + +import argparse +import sys + +import perf + +def main(): + ap = argparse.ArgumentParser() + ap.add_argument("-i", "--input", default="perf.data", help="Input file name") + args = ap.parse_args() + + bmax = 0 + + def process_event(sample): + nonlocal bmax + try: + brstack = sample.brstack + if brstack: + n = len(list(brstack)) + if n > bmax: + bmax = n + except AttributeError: + pass + + session = None + try: + session = perf.session(perf.data(args.input), sample=process_event) + session.process_events() + print("max brstack", bmax) + except Exception as e: + print(f"Error processing events: {e}", file=sys.stderr) + sys.exit(1) + finally: + session = None + +if __name__ == "__main__": + main()
tools/perf/tests/shell/test_intel_pt.sh +18 -25
65 lines not on this page · raw message
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 41/49] perf test: Migrate Intel PT virtual LBR test to Python API
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 7 lines
Migrate the Intel PT virtual LBR test from generating an inline legacy perf script callback to using a standalone Python script (
perf_brstack_max.py) with the brstack iterator API in the perf Python module.Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=41
Ian Rogers
reviewerPATCH v4 42/49 perf python: Port export-to-sqlite to perf module
In reply to Ian RogersPort export-to-sqlite.py to a standalone script in tools/perf/python/ using the perf module and Python's standard library sqlite3 module.
Improvements compared to the legacy script:
- Remove the dependency on PySide/QtSql by using Python's built-in sqlite3 module in DatabaseExporter, allowing SQLite export on headless and minimal systems without Qt installed.
- Support Intel PT and hardware instruction trace export via perf.session(itrace=...) and perf.call_return callbacks, reconstructing relational call_paths and calls tables and decoding synthesized PT payloads (ptwrite, cbr, mwait, pwre, exstop, pwrx).
- Export context_switches via perf.session's context_switch callback and map thread and comm IDs to their relational database keys.
- Manage temporary staging files inside an isolated tempfile.mkdtemp() directory with guaranteed cleanup in a finally block.
Update Documentation/db-export.txt and add a shell test (test_export_to_sqlite_python.sh) to verify the standalone exporter.
--- tools/perf/Documentation/db-export.txt | 2 +- tools/perf/python/export-to-sqlite.py | 946 ++++++++++++++++++ .../shell/test_export_to_sqlite_python.sh | 109 ++ 3 files changed, 1056 insertions(+), 1 deletion(-) create mode 100755 tools/perf/python/export-to-sqlite.py create mode 100755 tools/perf/tests/shell/test_export_to_sqlite_python.sh
tools/perf/Documentation/db-export.txt +1 -1
@@ -7,7 +7,7 @@ perf tool's python scripting engine: supports scripts: - tools/perf/scripts/python/export-to-sqlite.py + tools/perf/python/export-to-sqlite.py tools/perf/scripts/python/export-to-postgresql.py which export data to a SQLite3 or PostgreSQL database.
tools/perf/python/export-to-sqlite.py new file +946 -0
946 lines not on this page · raw message
tools/perf/tests/shell/test_export_to_sqlite_python.sh new file +109 -0
109 lines not on this page · raw message
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 42/49] perf python: Port export-to-sqlite to perf module
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 16 lines
Port
export-to-sqlite.pyto a standalone script intools/perf/python/using the perf module and Python's standard library sqlite3 module.Improvements compared to the legacy script:
- Remove the dependency on PySide/QtSql by using Python's built-in sqlite3 module in DatabaseExporter, allowing SQLite export on headless and minimal systems without Qt installed.
- Support Intel PT and hardware instruction trace export viaperf.session(itrace=...)and perf.call_return callbacks, reconstructing relationalcall_pathsand calls tables and decoding synthesized PT payloads (ptwrite, cbr, mwait, pwre, exstop, pwrx).
- Exportcontext_switchesvia perf.session'scontext_switchcallback and map thread and comm IDs to their relational database keys.
- Manage temporary staging files inside an isolatedtempfile.mkdtemp()directory with guaranteed cleanup in a finally block.
Quoted 5 lines
Update
Documentation/db-export.txtand add a shell test (test_export_to_sqlite_python.sh) to verify the standalone exporter.Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=42
Ian Rogers
reviewerPATCH v4 43/49 perf python: Port export-to-postgresql to perf module
In reply to Ian RogersPort export-to-postgresql.py to a standalone script in tools/perf/python/ using the perf module and libpq via ctypes.
Improvements compared to the legacy script:
- Remove the dependency on PySide/QtSql for database creation and DDL execution by driving libpq directly via ctypes (PQconnectdb, PQexec, PQputCopyData, PQputCopyEnd) and streaming binary PostgreSQL COPY files in PostgresExporter, enabling export on headless servers without Qt installed.
- Harden database connection and SQL identifier handling by rejecting URI ('://') and connection-parameter ('=') injection strings in setup_db() and connect(), escaping single quotes and backslashes in connection strings, and quoting SQL identifiers (quote_ident).
- Support Intel PT and instruction trace export via perf.session(itrace=...) and perf.call_return callbacks, reconstructing relational call_paths and calls tables (including id=0 placeholder rows and callfk/returnfk foreign keys) and unpacking synthesized PT payloads (ptwrite, cbr, mwait, pwre, exstop, pwrx).
- Use a dedicated context_switch ID counter so context-switch exports do not advance sample database IDs out of sync with call_return references.
Update Documentation/db-export.txt and add a shell test (test_export_to_postgresql_python.sh) to verify the standalone exporter.
--- tools/perf/Documentation/db-export.txt | 2 +- tools/perf/python/export-to-postgresql.py | 1328 +++++++++++++++++ .../shell/test_export_to_postgresql_python.sh | 122 ++ 3 files changed, 1451 insertions(+), 1 deletion(-) create mode 100755 tools/perf/python/export-to-postgresql.py create mode 100755 tools/perf/tests/shell/test_export_to_postgresql_python.sh
tools/perf/Documentation/db-export.txt +1 -1
@@ -8,7 +8,7 @@ perf tool's python scripting engine: supports scripts: tools/perf/python/export-to-sqlite.py - tools/perf/scripts/python/export-to-postgresql.py + tools/perf/python/export-to-postgresql.py which export data to a SQLite3 or PostgreSQL database.
tools/perf/python/export-to-postgresql.py new file +1328 -0
1,328 lines not on this page · raw message
tools/perf/tests/shell/test_export_to_postgresql_python.sh new file +122 -0
122 lines not on this page · raw message
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 43/49] perf python: Port export-to-postgresql to perf module
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 22 lines
Port
export-to-postgresql.pyto a standalone script intools/perf/python/using the perf module and libpq via ctypes.Improvements compared to the legacy script:
- Remove the dependency on PySide/QtSql for database creation and DDL execution by driving libpq directly via ctypes (PQconnectdb, PQexec, PQputCopyData, PQputCopyEnd) and streaming binary PostgreSQL COPY files in PostgresExporter, enabling export on headless servers without Qt installed.
- Harden database connection and SQL identifier handling by rejecting URI ('://') and connection-parameter ('=') injection strings insetup_db()andconnect(), escaping single quotes and backslashes in connection strings, and quoting SQL identifiers (quote_ident).
- Support Intel PT and instruction trace export viaperf.session(itrace=...)and perf.call_return callbacks, reconstructing relationalcall_pathsand calls tables (including id=0 placeholder rows and callfk/returnfk foreign keys) and unpacking synthesized PT payloads (ptwrite, cbr, mwait, pwre, exstop, pwrx).
- Use a dedicatedcontext_switchID counter so context-switch exports do not advance sample database IDs out of sync withcall_returnreferences.
Quoted 5 lines
Update
Documentation/db-export.txtand add a shell test (test_export_to_postgresql_python.sh) to verify the standalone exporter.Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=43
Ian Rogers
reviewerPATCH v4 44/49 perf python: Move and clean up exported-sql-viewer.py
In reply to Ian RogersMove exported-sql-viewer.py from tools/perf/scripts/python/ to tools/perf/python/ as it is a standalone PySide/PyQt GUI application for viewing SQLite and PostgreSQL databases exported by perf script.
Improvements and cleanups compared to the legacy script:
- Add support for PySide6 (falling back to PySide2 and PySide) loaded dynamically via importlib, and provide stub base classes (_QtBase, _QtWidget) so static analysis (mypy and pylint) and --help-only execution succeed when Qt bindings are not installed.
- Fix a Python 3 NameError crash in HBoxLayout where expanded_mark and not_expanded_mark called Python 2's removed unicode() builtin instead of chr(0x25BC) and chr(0x25B6).
- Replace instance-level method monkey-patching (self.mousePressEvent = self.MousePressEvent) on SwitchGraphView with proper class methods gated by self.rb_enabled so Qt virtual method dispatch works cleanly across PySide2 and PySide6.
- Remove Python 2 constructs (cPickle, xrange), wildcard imports, bare 'except:' clauses, and variable names shadowing Python builtins.
--- tools/perf/python/exported-sql-viewer.py | 5103 +++++++++++++++++ .../scripts/python/exported-sql-viewer.py | 5030 ---------------- 2 files changed, 5103 insertions(+), 5030 deletions(-) create mode 100755 tools/perf/python/exported-sql-viewer.py delete mode 100755 tools/perf/scripts/python/exported-sql-viewer.py
tools/perf/python/exported-sql-viewer.py new file +5103 -0
@@ -0,0 +1,5103 @@ +#!/usr/bin/env python +# SPDX-License-Identifier: GPL-2.0 +"""exported-sql-viewer.py: view data from sql database.""" +# Copyright (c) 2014-2018, Intel Corporation. + +# To use this script you will need to have exported data using either the +# export-to-sqlite.py or the export-to-postgresql.py script. Refer to those +# scripts for details. +# +# Following on from the example in the export scripts, a +# call-graph can be displayed for the pt_example database like this: +# +# python exported-sql-viewer.py pt_example +# +# Note that for PostgreSQL, this script supports connecting to remote databases +# by setting hostname, port, username, password, and dbname e.g. +# +# python exported-sql-viewer.py \ +# "hostname=myhost username=myuser password=mypassword dbname=pt_example" +# +# The result is a GUI window with a tree representing a context-sensitive +# call-graph. Expanding a couple of levels of the tree and adjusting column +# widths to suit will display something like: +# +# Call Graph: pt_example +# Call Path Object Count Time(ns) Time(%) Branch Count Branch Count(%) +# v- ls +# v- 2638:2638 +# v- _start ld-2.19.so 1 10074071 100.0 211135 100.0 +# |- unknown unknown 1 13198 0.1 1 0.0 +# >- _dl_start ld-2.19.so 1 1400980 13.9 19637 9.3 +# >- _d_linit_internal ld-2.19.so 1 448152 4.4 11094 5.3 +# v-__libc_start_main@plt ls 1 8211741 81.5 180397 85.4 +# >- _dl_fixup ld-2.19.so 1 7607 0.1 108 0.1 +# >- __cxa_atexit libc-2.19.so 1 11737 0.1 10 0.0 +# >- __libc_csu_init ls 1 10354 0.1 10 0.0 +# |- _setjmp libc-2.19.so 1 0 0.0 4 0.0 +# v- main ls 1 8182043 99.6 180254 99.9 +# +# Points to note: +# The top level is a command name (comm) +# The next level is a thread (pid:tid) +# Subsequent levels are functions +# 'Count' is the number of calls +# 'Time' is the elapsed time until the function returns +# Percentages are relative to the level above +# 'Branch Count' is the total number of branches for that function and all +# functions that it calls + +# There is also a "All branches" report, which displays branches and +# possibly disassembly. However, presently, the only supported disassembler is +# Intel XED, and additionally the object code must be present in perf build ID +# cache. To use Intel XED, libxed.so must be present. To build and install +# libxed.so: +# git clone https://github.com/intelxed/mbuild.git mbuild +# git clone https://github.com/intelxed/xed +# cd xed +# ./mfile.py --share +# sudo ./mfile.py --prefix=/usr/local install +# sudo ldconfig +# +# Example report: +# +# Time CPU Command PID TID Branch Type In Tx Branch +# 8107675239590 2 ls 22011 22011 return from interrupt No ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea260 _start (ld-2.19.so) +# 7fab593ea260 48 89 e7 mov %rsp, %rdi +# 8107675239899 2 ls 22011 22011 hardware interrupt No 7fab593ea260 _start (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel]) +# 8107675241900 2 ls 22011 22011 return from interrupt No ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea260 _start (ld-2.19.so) +# 7fab593ea260 48 89 e7 mov %rsp, %rdi +# 7fab593ea263 e8 c8 06 00 00 callq 0x7fab593ea930 +# 8107675241900 2 ls 22011 22011 call No 7fab593ea263 _start+0x3 (ld-2.19.so) -> 7fab593ea930 _dl_start (ld-2.19.so) +# 7fab593ea930 55 pushq %rbp +# 7fab593ea931 48 89 e5 mov %rsp, %rbp +# 7fab593ea934 41 57 pushq %r15 +# 7fab593ea936 41 56 pushq %r14 +# 7fab593ea938 41 55 pushq %r13 +# 7fab593ea93a 41 54 pushq %r12 +# 7fab593ea93c 53 pushq %rbx +# 7fab593ea93d 48 89 fb mov %rdi, %rbx +# 7fab593ea940 48 83 ec 68 sub $0x68, %rsp +# 7fab593ea944 0f 31 rdtsc +# 7fab593ea946 48 c1 e2 20 shl $0x20, %rdx +# 7fab593ea94a 89 c0 mov %eax, %eax +# 7fab593ea94c 48 09 c2 or %rax, %rdx +# 7fab593ea94f 48 8b 05 1a 15 22 00 movq 0x22151a(%rip), %rax +# 8107675242232 2 ls 22011 22011 hardware interrupt No 7fab593ea94f _dl_start+0x1f (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel]) +# 8107675242900 2 ls 22011 22011 return from interrupt No ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea94f _dl_start+0x1f (ld-2.19.so) +# 7fab593ea94f 48 8b 05 1a 15 22 00 movq 0x22151a(%rip), %rax +# 7fab593ea956 48 89 15 3b 13 22 00 movq %rdx, 0x22133b(%rip) +# 8107675243232 2 ls 22011 22011 hardware interrupt No 7fab593ea956 _dl_start+0x26 (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel]) + +from __future__ import print_function + +import sys +# Only change warnings if the python -W option was not used +if not sys.warnoptions: + import warnings + # PySide2 causes deprecation warnings, ignore them. + warnings.filterwarnings("ignore", category=DeprecationWarning) +import argparse +import weakref +import threading +import pickle +glb_nsz = 16 +import re +import os +import random +import copy +import math +from libxed import LibXED + +import importlib +from typing import Any + +class _QtBase: + def __init__(self, *args: Any, **kwargs: Any) -> None: + pass + def __call__(self, *args: Any, **kwargs: Any) -> Any: + return self + def __getattr__(self, name: str) -> Any: + return _QtBase() + def mousePressEvent(self, event: Any) -> None: + pass + def mouseMoveEvent(self, event: Any) -> None: + pass + def mouseReleaseEvent(self, event: Any) -> None: + pass + def resizeEvent(self, event: Any) -> None: + pass + def changeEvent(self, event: Any) -> None: + pass + +class _QtWidget(_QtBase): + pass + +class _QtMdiSubWindow(_QtWidget): + pass + +QAbstractItemModel: Any = _QtBase +QAbstractItemView: Any = _QtBase +QAbstractTableModel: Any = _QtBase +QAction: Any = _QtBase +QApplication: Any = _QtBase +QCheckBox: Any = _QtBase +QColor: Any = _QtBase +QComboBox: Any = _QtBase +QDialog: Any = _QtWidget +QEvent: Any = _QtBase +QFont: Any = _QtBase +QFontMetrics: Any = _QtBase +QGraphicsItem: Any = _QtBase +QGraphicsLineItem: Any = _QtBase +QGraphicsScene: Any = _QtBase +QGraphicsSimpleTextItem: Any = _QtBase +QGraphicsView: Any = _QtBase +QGridLayout: Any = _QtBase +QHBoxLayout: Any = _QtBase +QKeySequence: Any = _QtBase +QLabel: Any = _QtBase +QLineEdit: Any = _QtBase +QMainWindow: Any = _QtWidget +QMdiArea: Any = _QtBase +QMdiSubWindow: Any = _QtMdiSubWindow +QMenu: Any = _QtBase +QMessageBox: Any = _QtBase +QModelIndex: Any = _QtBase +QObject: Any = _QtBase +QPalette: Any = _QtBase +QPoint: Any = _QtBase +QPointF: Any = _QtBase +QProgressBar: Any = _QtBase +QPushButton: Any = _QtBase +QRect: Any = _QtBase +QRectF: Any = _QtBase +QRubberBand: Any = _QtBase +QSize: Any = _QtBase +QSizePolicy: Any = _QtBase +QSortFilterProxyModel: Any = _QtBase +QSpinBox: Any = _QtBase +QSplitter: Any = _QtWidget +QSqlDatabase: Any = _QtBase +QSqlQuery: Any = _QtBase +QStyle: Any = _QtBase +Qt: Any = _QtBase +QTableView: Any = _QtWidget +QTextBrowser: Any = _QtWidget +QThread: Any = _QtBase +QToolButton: Any = _QtBase +QTreeView: Any = _QtWidget +QVBoxLayout: Any = _QtBase +qVersion: Any = _QtBase +QWidget: Any = _QtWidget +Signal: Any = _QtBase + +pyside_version_1 = False +for _pkg in ("PySide6", "PySide2"): + try: + for _mod_name in ("QtCore", "QtGui", "QtSql", "QtWidgets"): + _mod = importlib.import_module(f"{_pkg}.{_mod_name}") + for _sym in dir(_mod): + if not _sym.startswith("_"): + globals()[_sym] = getattr(_mod, _sym) + break + except ImportError: + pass + + +from decimal import Decimal, ROUND_HALF_UP +from ctypes import create_string_buffer, addressof, sizeof, \ + c_void_p, c_bool, c_char, c_longlong +from multiprocessing import Process, Array, Value, Event + + +def printerr(*args, **keyword_args): + print(*args, file=sys.stderr, **keyword_args) + +# Data formatting helpers + +def tohex(ip): + if ip < 0: + ip += 1 << 64 + return "%x" % ip + +def offstr(offset): + if offset: + return "+0x%x" % offset + return "" + +def dsoname(name): + if name == "[kernel.kallsyms]": + return "[kernel]" + return name + +def findnth(s, sub, n, offs=0): + pos = s.find(sub) + if pos < 0: + return pos + if n <= 1: + return offs + pos + return findnth(s[pos + 1:], sub, n - 1, offs + pos + 1) + +# Percent to one decimal place + +def PercentToOneDP(n, d): + if not d: + return "0.0" + x = (n * Decimal(100)) / d + return str(x.quantize(Decimal(".1"), rounding=ROUND_HALF_UP)) + +# Helper for queries that must not fail + +def QueryExec(query, stmt): + ret = query.exec_(stmt) + if not ret: + raise RuntimeError("Query failed: " + query.lastError().text()) + +# Background thread + +class Thread(QThread): + + done = Signal(object) + + def __init__(self, task, param=None, parent=None): + super(Thread, self).__init__(parent) + self.task = task + self.param = param + + def run(self): + while True: + if self.param is None: + done, result = self.task() + else: + done, result = self.task(self.param) + self.done.emit(result) + if done: + break + +# Tree data model + +class TreeModel(QAbstractItemModel): + + def __init__(self, glb, params, parent=None): + super(TreeModel, self).__init__(parent) + self.glb = glb + self.params = params + self.root = self.GetRoot() + self.last_row_read = 0 + + def Item(self, parent): + if parent.isValid(): + return parent.internalPointer() + else: + return self.root + + def rowCount(self, parent): + result = self.Item(parent).childCount() + if result < 0: + result = 0 + self.dataChanged.emit(parent, parent) + return result + + def hasChildren(self, parent): + return self.Item(parent).hasChildren() + + def headerData(self, section, orientation, role): + if role == Qt.TextAlignmentRole: + return self.columnAlignment(section) + if role != Qt.DisplayRole: + return None + if orientation != Qt.Horizontal: + return None + return self.columnHeader(section) + + def parent(self, child): + child_item = child.internalPointer() + if child_item is self.root: + return QModelIndex() + parent_item = child_item.getParentItem() + return self.createIndex(parent_item.getRow(), 0, parent_item) + + def index(self, row, column, parent): + child_item = self.Item(parent).getChildItem(row) + return self.createIndex(row, column, child_item) + + def DisplayData(self, item, index): + return item.getData(index.column()) + + def FetchIfNeeded(self, row): + if row > self.last_row_read: + self.last_row_read = row + if row + 10 >= self.root.child_count: + self.fetcher.Fetch(glb_chunk_sz) + + def columnAlignment(self, _column): + return Qt.AlignLeft + + def columnFont(self, _column): + return None + + def data(self, index, role): + if role == Qt.TextAlignmentRole: + return self.columnAlignment(index.column()) + if role == Qt.FontRole: + return self.columnFont(index.column()) + if role != Qt.DisplayRole: + return None + item = index.internalPointer() + return self.DisplayData(item, index) + +# Table data model + +class TableModel(QAbstractTableModel): + + def __init__(self, parent=None): + super(TableModel, self).__init__(parent) + self.child_count = 0 + self.child_items = [] + self.last_row_read = 0 + + def Item(self, parent): + if parent.isValid(): + return parent.internalPointer() + else: + return self + + def rowCount(self, _parent): + return self.child_count + + def headerData(self, section, orientation, role): + if role == Qt.TextAlignmentRole: + return self.columnAlignment(section) + if role != Qt.DisplayRole: + return None + if orientation != Qt.Horizontal: + return None + return self.columnHeader(section) + + def index(self, row, column, _parent): + return self.createIndex(row, column, self.child_items[row]) + + def DisplayData(self, item, index): + return item.getData(index.column()) + + def FetchIfNeeded(self, row): + if row > self.last_row_read: + self.last_row_read = row + if row + 10 >= self.child_count: + self.fetcher.Fetch(glb_chunk_sz) + + def columnAlignment(self, _column): + return Qt.AlignLeft + + def columnFont(self, _column): + return None + + def data(self, index, role): + if role == Qt.TextAlignmentRole: + return self.columnAlignment(index.column()) + if role == Qt.FontRole: + return self.columnFont(index.column()) + if role != Qt.DisplayRole: + return None + item = index.internalPointer() + return self.DisplayData(item, index) + +# Model cache + +model_cache: Any = weakref.WeakValueDictionary() +model_cache_lock = threading.Lock() + +def LookupCreateModel(model_name, create_fn): + model_cache_lock.acquire() + try: + model = model_cache[model_name] + except KeyError: + model = None + if model is None: + model = create_fn() + model_cache[model_name] = model + model_cache_lock.release() + return model + +def LookupModel(model_name): + model_cache_lock.acquire() + try: + model = model_cache[model_name] + except KeyError: + model = None + model_cache_lock.release() + return model + +# Find bar + +class FindBar(): + + def __init__(self, parent, finder, is_reg_expr=False): + self.finder = finder + self.context = [] + self.last_value = None + self.last_pattern = None + + label = QLabel("Find:") + label.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.textbox = QComboBox() + self.textbox.setEditable(True) + self.textbox.currentIndexChanged.connect(self.ValueChanged) + + self.progress = QProgressBar() + self.progress.setRange(0, 0) + self.progress.hide() + + if is_reg_expr: + self.pattern = QCheckBox("Regular Expression") + else: + self.pattern = QCheckBox("Pattern") + self.pattern.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.next_button = QToolButton() + self.next_button.setIcon(parent.style().standardIcon(QStyle.SP_ArrowDown)) + self.next_button.released.connect(lambda: self.NextPrev(1)) + + self.prev_button = QToolButton() + self.prev_button.setIcon(parent.style().standardIcon(QStyle.SP_ArrowUp)) + self.prev_button.released.connect(lambda: self.NextPrev(-1)) + + self.close_button = QToolButton() + self.close_button.setIcon(parent.style().standardIcon(QStyle.SP_DockWidgetCloseButton)) + self.close_button.released.connect(self.Deactivate) + + self.hbox = QHBoxLayout() + self.hbox.setContentsMargins(0, 0, 0, 0) + + self.hbox.addWidget(label) + self.hbox.addWidget(self.textbox) + self.hbox.addWidget(self.progress) + self.hbox.addWidget(self.pattern) + self.hbox.addWidget(self.next_button) + self.hbox.addWidget(self.prev_button) + self.hbox.addWidget(self.close_button) + + self.bar = QWidget() + self.bar.setLayout(self.hbox) + self.bar.hide() + + def Widget(self): + return self.bar + + def Activate(self): + self.bar.show() + self.textbox.lineEdit().selectAll() + self.textbox.setFocus() + + def Deactivate(self): + self.bar.hide() + + def Busy(self): + self.textbox.setEnabled(False) + self.pattern.hide() + self.next_button.hide() + self.prev_button.hide() + self.progress.show() + + def Idle(self): + self.textbox.setEnabled(True) + self.progress.hide() + self.pattern.show() + self.next_button.show() + self.prev_button.show() + + def Find(self, direction): + value = self.textbox.currentText() + pattern = self.pattern.isChecked() + self.last_value = value + self.last_pattern = pattern + self.finder.Find(value, direction, pattern, self.context) + + def ValueChanged(self): + _value = self.textbox.currentText() + pattern = self.pattern.isChecked() + index = self.textbox.currentIndex() + data = self.textbox.itemData(index) + # Store the pattern in the combo box to keep it with the text value + if data == None: + self.textbox.setItemData(index, pattern) + else: + self.pattern.setChecked(data) + self.Find(0) + + def NextPrev(self, direction): + value = self.textbox.currentText() + pattern = self.pattern.isChecked() + if value != self.last_value: + index = self.textbox.findText(value) + # Allow for a button press before the value has been added to the combo box + if index < 0: + index = self.textbox.count() + self.textbox.addItem(value, pattern) + self.textbox.setCurrentIndex(index) + return + else: + self.textbox.setItemData(index, pattern) + elif pattern != self.last_pattern: + # Keep the pattern recorded in the combo box up to date + index = self.textbox.currentIndex() + self.textbox.setItemData(index, pattern) + self.Find(direction) + + def NotFound(self): + QMessageBox.information(self.bar, "Find", "'" + self.textbox.currentText() + "' not found") + +# Context-sensitive call graph data model item base + +class CallGraphLevelItemBase(object): + def Select(self) -> None: + pass + def data(self, _column: int, _role: int) -> Any: + return None + + def __init__(self, glb, params, row, parent_item): + self.glb = glb + self.params = params + self.row = row + self.parent_item = parent_item + self.query_done = False + self.child_count = 0 + self.child_items = [] + if parent_item: + self.level = parent_item.level + 1 + else: + self.level = 0 + + def getChildItem(self, row): + return self.child_items[row] + + def getParentItem(self): + return self.parent_item + + def getRow(self): + return self.row + + def childCount(self): + if not self.query_done: + self.Select() + if not self.child_count: + return -1 + return self.child_count + + def hasChildren(self): + if not self.query_done: + return True + return self.child_count > 0 + + def getData(self, column): + return self.data[column] + +# Context-sensitive call graph data model level 2+ item base + +class CallGraphLevelTwoPlusItemBase(CallGraphLevelItemBase): + + def __init__(self, glb, params, row, comm_id, thread_id, call_path_id, time, insn_cnt, cyc_cnt, branch_count, parent_item): + super(CallGraphLevelTwoPlusItemBase, self).__init__(glb, params, row, parent_item) + self.comm_id = comm_id + self.thread_id = thread_id + self.call_path_id = call_path_id + self.insn_cnt = insn_cnt + self.cyc_cnt = cyc_cnt + self.branch_count = branch_count + self.time = time + + def Select(self): + self.query_done = True + query = QSqlQuery(self.glb.db) + if self.params.have_ipc: + ipc_str = ", SUM(insn_count), SUM(cyc_count)" + else: + ipc_str = "" + QueryExec(query, "SELECT call_path_id, name, short_name, COUNT(calls.id), SUM(return_time - call_time)" + ipc_str + ", SUM(branch_count)" + " FROM calls" + " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" + " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" + " INNER JOIN dsos ON symbols.dso_id = dsos.id" + " WHERE parent_call_path_id = " + str(self.call_path_id) + + " AND comm_id = " + str(self.comm_id) + + " AND thread_id = " + str(self.thread_id) + + " GROUP BY call_path_id, name, short_name" + " ORDER BY call_path_id") + while query.next(): + if self.params.have_ipc: + insn_cnt = int(query.value(5)) + cyc_cnt = int(query.value(6)) + branch_count = int(query.value(7)) + else: + insn_cnt = 0 + cyc_cnt = 0 + branch_count = int(query.value(5)) + child_item = CallGraphLevelThreeItem(self.glb, self.params, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), insn_cnt, cyc_cnt, branch_count, self) + self.child_items.append(child_item) + self.child_count += 1 + +# Context-sensitive call graph data model level three item + +class CallGraphLevelThreeItem(CallGraphLevelTwoPlusItemBase): + + def __init__(self, glb, params, row, comm_id, thread_id, call_path_id, name, dso, count, time, insn_cnt, cyc_cnt, branch_count, parent_item): + super(CallGraphLevelThreeItem, self).__init__(glb, params, row, comm_id, thread_id, call_path_id, time, insn_cnt, cyc_cnt, branch_count, parent_item) + dso = dsoname(dso) + if self.params.have_ipc: + insn_pcnt = PercentToOneDP(insn_cnt, parent_item.insn_cnt) + cyc_pcnt = PercentToOneDP(cyc_cnt, parent_item.cyc_cnt) + br_pcnt = PercentToOneDP(branch_count, parent_item.branch_count) + ipc = CalcIPC(cyc_cnt, insn_cnt) + self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(insn_cnt), insn_pcnt, str(cyc_cnt), cyc_pcnt, ipc, str(branch_count), br_pcnt ] + else: + self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ] + self.dbid = call_path_id + +# Context-sensitive call graph data model level two item + +class CallGraphLevelTwoItem(CallGraphLevelTwoPlusItemBase): + + def __init__(self, glb, params, row, comm_id, thread_id, pid, tid, parent_item): + super(CallGraphLevelTwoItem, self).__init__(glb, params, row, comm_id, thread_id, 1, 0, 0, 0, 0, parent_item) + if self.params.have_ipc: + self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", "", "", "", "", "", ""] + else: + self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""] + self.dbid = thread_id + + def Select(self): + super(CallGraphLevelTwoItem, self).Select() + for child_item in self.child_items: + self.time += child_item.time + self.insn_cnt += child_item.insn_cnt + self.cyc_cnt += child_item.cyc_cnt + self.branch_count += child_item.branch_count + for child_item in self.child_items: + child_item.data[4] = PercentToOneDP(child_item.time, self.time) + if self.params.have_ipc: + child_item.data[6] = PercentToOneDP(child_item.insn_cnt, self.insn_cnt) + child_item.data[8] = PercentToOneDP(child_item.cyc_cnt, self.cyc_cnt) + child_item.data[11] = PercentToOneDP(child_item.branch_count, self.branch_count) + else: + child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count) + +# Context-sensitive call graph data model level one item + +class CallGraphLevelOneItem(CallGraphLevelItemBase): + + def __init__(self, glb, params, row, comm_id, comm, parent_item): + super(CallGraphLevelOneItem, self).__init__(glb, params, row, parent_item) + if self.params.have_ipc: + self.data = [comm, "", "", "", "", "", "", "", "", "", "", ""] + else: + self.data = [comm, "", "", "", "", "", ""] + self.dbid = comm_id + + def Select(self): + self.query_done = True + query = QSqlQuery(self.glb.db) + QueryExec(query, "SELECT thread_id, pid, tid" + " FROM comm_threads" + " INNER JOIN threads ON thread_id = threads.id" + " WHERE comm_id = " + str(self.dbid)) + while query.next(): + child_item = CallGraphLevelTwoItem(self.glb, self.params, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self) + self.child_items.append(child_item) + self.child_count += 1 + +# Context-sensitive call graph data model root item + +class CallGraphRootItem(CallGraphLevelItemBase): + + def __init__(self, glb, params): + super(CallGraphRootItem, self).__init__(glb, params, 0, None) + self.dbid = 0 + self.query_done = True + if_has_calls = "" + if IsSelectable(glb.db, "comms", columns = "has_calls"): + if_has_calls = " WHERE has_calls = " + glb.dbref.TRUE + query = QSqlQuery(glb.db) + QueryExec(query, "SELECT id, comm FROM comms" + if_has_calls) + while query.next(): + if not query.value(0): + continue + child_item = CallGraphLevelOneItem(glb, params, self.child_count, query.value(0), query.value(1), self) + self.child_items.append(child_item) + self.child_count += 1 + +# Call graph model parameters + +class CallGraphModelParams(): + + def __init__(self, glb, _parent=None): + self.have_ipc = IsSelectable(glb.db, "calls", columns = "insn_count, cyc_count") + +# Context-sensitive call graph data model base + +class CallGraphModelBase(TreeModel): + + def __init__(self, glb, parent=None): + super(CallGraphModelBase, self).__init__(glb, CallGraphModelParams(glb), parent) + + def FindSelect(self, value, pattern, query): + if pattern: + # postgresql and sqlite pattern patching differences: + # postgresql LIKE is case sensitive but sqlite LIKE is not + # postgresql LIKE allows % and _ to be escaped with \ but sqlite LIKE does not + # postgresql supports ILIKE which is case insensitive + # sqlite supports GLOB (text only) which uses * and ? and is case sensitive + if not self.glb.dbref.is_sqlite3: + # Escape % and _ + s = value.replace("%", "\\%") + s = s.replace("_", "\\_") + # Translate * and ? into SQL LIKE pattern characters % and _ + if sys.version_info[0] == 3: + trans = str.maketrans("*?", "%_") + else: + trans = bytes.maketrans("*?", "%_") + match = " LIKE '" + str(s).translate(trans) + "'" + else: + match = " GLOB '" + str(value) + "'" + else: + match = " = '" + str(value) + "'" + self.DoFindSelect(query, match) + + def Found(self, query, found): + if found: + return self.FindPath(query) + return [] + + def FindValue(self, value, pattern, query, last_value, last_pattern): + if last_value == value and pattern == last_pattern: + found = query.first() + else: + self.FindSelect(value, pattern, query) + found = query.next() + return self.Found(query, found) + + def FindNext(self, query): + found = query.next() + if not found: + found = query.first() + return self.Found(query, found) + + def FindPrev(self, query): + found = query.previous() + if not found: + found = query.last() + return self.Found(query, found) + + def FindThread(self, c): + if c.direction == 0 or c.value != c.last_value or c.pattern != c.last_pattern: + ids = self.FindValue(c.value, c.pattern, c.query, c.last_value, c.last_pattern) + elif c.direction > 0: + ids = self.FindNext(c.query) + else: + ids = self.FindPrev(c.query) + return (True, ids) + + def Find(self, value, direction, pattern, context, callback): + class Context(): + def __init__(self, *x): + self.value, self.direction, self.pattern, self.query, self.last_value, self.last_pattern = x + def Update(self, *x): + self.value, self.direction, self.pattern, self.last_value, self.last_pattern = x + (self.value, self.pattern) + if len(context): + context[0].Update(value, direction, pattern) + else: + context.append(Context(value, direction, pattern, QSqlQuery(self.glb.db), None, None)) + # Use a thread so the UI is not blocked during the SELECT + thread = Thread(self.FindThread, context[0]) + thread.done.connect(lambda ids, t=thread, c=callback: self.FindDone(t, c, ids), Qt.QueuedConnection) + thread.start() + + def FindDone(self, _thread, callback, ids): + callback(ids) + +# Context-sensitive call graph data model + +class CallGraphModel(CallGraphModelBase): + + def GetRoot(self): + return CallGraphRootItem(self.glb, self.params) + + def columnCount(self, _parent=None): + if self.params.have_ipc: + return 12 + else: + return 7 + + def columnHeader(self, column): + if self.params.have_ipc: + headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Insn Cnt", "Insn Cnt (%)", "Cyc Cnt", "Cyc Cnt (%)", "IPC", "Branch Count ", "Branch Count (%) "] + else: + headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "] + return headers[column] + + def columnAlignment(self, column): + if self.params.have_ipc: + alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ] + else: + alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ] + return alignment[column] + + def DoFindSelect(self, query, match): + QueryExec(query, "SELECT call_path_id, comm_id, thread_id" + " FROM calls" + " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" + " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" + " WHERE calls.id <> 0" + " AND symbols.name" + match + + " GROUP BY comm_id, thread_id, call_path_id" + " ORDER BY comm_id, thread_id, call_path_id") + + def FindPath(self, query): + # Turn the query result into a list of ids that the tree view can walk + # to open the tree at the right place. + ids = [] + parent_id = query.value(0) + while parent_id: + ids.insert(0, parent_id) + q2 = QSqlQuery(self.glb.db) + QueryExec(q2, "SELECT parent_id" + " FROM call_paths" + " WHERE id = " + str(parent_id)) + if not q2.next(): + break + parent_id = q2.value(0) + # The call path root is not used + if ids[0] == 1: + del ids[0] + ids.insert(0, query.value(2)) + ids.insert(0, query.value(1)) + return ids + +# Call tree data model level 2+ item base + +class CallTreeLevelTwoPlusItemBase(CallGraphLevelItemBase): + + def __init__(self, glb, params, row, comm_id, thread_id, calls_id, call_time, time, insn_cnt, cyc_cnt, branch_count, parent_item): + super(CallTreeLevelTwoPlusItemBase, self).__init__(glb, params, row, parent_item) + self.comm_id = comm_id + self.thread_id = thread_id + self.calls_id = calls_id + self.call_time = call_time + self.time = time + self.insn_cnt = insn_cnt + self.cyc_cnt = cyc_cnt + self.branch_count = branch_count + + def Select(self): + self.query_done = True + if self.calls_id == 0: + comm_thread = " AND comm_id = " + str(self.comm_id) + " AND thread_id = " + str(self.thread_id) + else: + comm_thread = "" + if self.params.have_ipc: + ipc_str = ", insn_count, cyc_count" + else: + ipc_str = "" + query = QSqlQuery(self.glb.db) + QueryExec(query, "SELECT calls.id, name, short_name, call_time, return_time - call_time" + ipc_str + ", branch_count" + " FROM calls" + " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" + " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" + " INNER JOIN dsos ON symbols.dso_id = dsos.id" + " WHERE calls.parent_id = " + str(self.calls_id) + comm_thread + + " ORDER BY call_time, calls.id") + while query.next(): + if self.params.have_ipc: + insn_cnt = int(query.value(5)) + cyc_cnt = int(query.value(6)) + branch_count = int(query.value(7)) + else: + insn_cnt = 0 + cyc_cnt = 0 + branch_count = int(query.value(5)) + child_item = CallTreeLevelThreeItem(self.glb, self.params, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), insn_cnt, cyc_cnt, branch_count, self) + self.child_items.append(child_item) + self.child_count += 1 + +# Call tree data model level three item + +class CallTreeLevelThreeItem(CallTreeLevelTwoPlusItemBase): + + def __init__(self, glb, params, row, comm_id, thread_id, calls_id, name, dso, call_time, time, insn_cnt, cyc_cnt, branch_count, parent_item): + super(CallTreeLevelThreeItem, self).__init__(glb, params, row, comm_id, thread_id, calls_id, call_time, time, insn_cnt, cyc_cnt, branch_count, parent_item) + dso = dsoname(dso) + if self.params.have_ipc: + insn_pcnt = PercentToOneDP(insn_cnt, parent_item.insn_cnt) + cyc_pcnt = PercentToOneDP(cyc_cnt, parent_item.cyc_cnt) + br_pcnt = PercentToOneDP(branch_count, parent_item.branch_count) + ipc = CalcIPC(cyc_cnt, insn_cnt) + self.data = [ name, dso, str(call_time), str(time), PercentToOneDP(time, parent_item.time), str(insn_cnt), insn_pcnt, str(cyc_cnt), cyc_pcnt, ipc, str(branch_count), br_pcnt ] + else: + self.data = [ name, dso, str(call_time), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ] + self.dbid = calls_id + +# Call tree data model level two item + +class CallTreeLevelTwoItem(CallTreeLevelTwoPlusItemBase): + + def __init__(self, glb, params, row, comm_id, thread_id, pid, tid, parent_item): + super(CallTreeLevelTwoItem, self).__init__(glb, params, row, comm_id, thread_id, 0, 0, 0, 0, 0, 0, parent_item) + if self.params.have_ipc: + self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", "", "", "", "", "", ""] + else: + self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""] + self.dbid = thread_id + + def Select(self): + super(CallTreeLevelTwoItem, self).Select() + for child_item in self.child_items: + self.time += child_item.time + self.insn_cnt += child_item.insn_cnt + self.cyc_cnt += child_item.cyc_cnt + self.branch_count += child_item.branch_count + for child_item in self.child_items: + child_item.data[4] = PercentToOneDP(child_item.time, self.time) + if self.params.have_ipc: + child_item.data[6] = PercentToOneDP(child_item.insn_cnt, self.insn_cnt) + child_item.data[8] = PercentToOneDP(child_item.cyc_cnt, self.cyc_cnt) + child_item.data[11] = PercentToOneDP(child_item.branch_count, self.branch_count) + else: + child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count) + +# Call tree data model level one item + +class CallTreeLevelOneItem(CallGraphLevelItemBase): + + def __init__(self, glb, params, row, comm_id, comm, parent_item): + super(CallTreeLevelOneItem, self).__init__(glb, params, row, parent_item) + if self.params.have_ipc: + self.data = [comm, "", "", "", "", "", "", "", "", "", "", ""] + else: + self.data = [comm, "", "", "", "", "", ""] + self.dbid = comm_id + + def Select(self): + self.query_done = True + query = QSqlQuery(self.glb.db) + QueryExec(query, "SELECT thread_id, pid, tid" + " FROM comm_threads" + " INNER JOIN threads ON thread_id = threads.id" + " WHERE comm_id = " + str(self.dbid)) + while query.next(): + child_item = CallTreeLevelTwoItem(self.glb, self.params, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self) + self.child_items.append(child_item) + self.child_count += 1 + +# Call tree data model root item + +class CallTreeRootItem(CallGraphLevelItemBase): + + def __init__(self, glb, params): + super(CallTreeRootItem, self).__init__(glb, params, 0, None) + self.dbid = 0 + self.query_done = True + if_has_calls = "" + if IsSelectable(glb.db, "comms", columns = "has_calls"): + if_has_calls = " WHERE has_calls = " + glb.dbref.TRUE + query = QSqlQuery(glb.db) + QueryExec(query, "SELECT id, comm FROM comms" + if_has_calls) + while query.next(): + if not query.value(0): + continue + child_item = CallTreeLevelOneItem(glb, params, self.child_count, query.value(0), query.value(1), self) + self.child_items.append(child_item) + self.child_count += 1 + +# Call Tree data model + +class CallTreeModel(CallGraphModelBase): + + def GetRoot(self): + return CallTreeRootItem(self.glb, self.params) + + def columnCount(self, _parent=None): + if self.params.have_ipc: + return 12 + else: + return 7 + + def columnHeader(self, column): + if self.params.have_ipc: + headers = ["Call Path", "Object", "Call Time", "Time (ns) ", "Time (%) ", "Insn Cnt", "Insn Cnt (%)", "Cyc Cnt", "Cyc Cnt (%)", "IPC", "Branch Count ", "Branch Count (%) "] + else: + headers = ["Call Path", "Object", "Call Time", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "] + return headers[column] + + def columnAlignment(self, column): + if self.params.have_ipc: + alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ] + else: + alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ] + return alignment[column] + + def DoFindSelect(self, query, match): + QueryExec(query, "SELECT calls.id, comm_id, thread_id" + " FROM calls" + " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" + " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" + " WHERE calls.id <> 0" + " AND symbols.name" + match + + " ORDER BY comm_id, thread_id, call_time, calls.id") + + def FindPath(self, query): + # Turn the query result into a list of ids that the tree view can walk + # to open the tree at the right place. + ids = [] + parent_id = query.value(0) + while parent_id: + ids.insert(0, parent_id) + q2 = QSqlQuery(self.glb.db) + QueryExec(q2, "SELECT parent_id" + " FROM calls" + " WHERE id = " + str(parent_id)) + if not q2.next(): + break + parent_id = q2.value(0) + ids.insert(0, query.value(2)) + ids.insert(0, query.value(1)) + return ids + +# Vertical layout + +class HBoxLayout(QHBoxLayout): + + def __init__(self, *children): + super(HBoxLayout, self).__init__() + + self.layout().setContentsMargins(0, 0, 0, 0) + for child in children: + if child.isWidgetType(): + self.layout().addWidget(child) + else: + self.layout().addLayout(child) + +# Horizontal layout + +class VBoxLayout(QVBoxLayout): + + def __init__(self, *children): + super(VBoxLayout, self).__init__() + + self.layout().setContentsMargins(0, 0, 0, 0) + for child in children: + if child.isWidgetType(): + self.layout().addWidget(child) + else: + self.layout().addLayout(child) + +# Vertical layout widget + +class VBox(): + + def __init__(self, *children): + self.vbox = QWidget() + self.vbox.setLayout(VBoxLayout(*children)) + + def Widget(self): + return self.vbox + +# Tree window base + +class TreeWindowBase(QMdiSubWindow): + + def __init__(self, parent=None): + super(TreeWindowBase, self).__init__(parent) + + self.model = None + self.find_bar = None + + self.view = QTreeView() + self.view.setSelectionMode(QAbstractItemView.ContiguousSelection) + self.view.CopyCellsToClipboard = CopyTreeCellsToClipboard + + self.context_menu = TreeContextMenu(self.view) + + def DisplayFound(self, ids): + if not len(ids): + return False + parent = QModelIndex() + for dbid in ids: + found = False + n = self.model.rowCount(parent) + for row in range(n): + child = self.model.index(row, 0, parent) + if child.internalPointer().dbid == dbid: + found = True + self.view.setExpanded(parent, True) + self.view.setCurrentIndex(child) + parent = child + break + if not found: + break + return found + + def Find(self, value, direction, pattern, context): + self.view.setFocus() + self.find_bar.Busy() + self.model.Find(value, direction, pattern, context, self.FindDone) + + def FindDone(self, ids): + found = True + if not self.DisplayFound(ids): + found = False + self.find_bar.Idle() + if not found: + self.find_bar.NotFound() + + +# Context-sensitive call graph window + +class CallGraphWindow(TreeWindowBase): + + def __init__(self, glb, parent=None): + super(CallGraphWindow, self).__init__(parent) + + self.model = LookupCreateModel("Context-Sensitive Call Graph", lambda x=glb: CallGraphModel(x)) + + self.view.setModel(self.model) + + for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)): + self.view.setColumnWidth(c, w) + + self.find_bar = FindBar(self, self) + + self.vbox = VBox(self.view, self.find_bar.Widget()) + + self.setWidget(self.vbox.Widget()) + + AddSubWindow(glb.mainwindow.mdi_area, self, "Context-Sensitive Call Graph") + +# Call tree window + +class CallTreeWindow(TreeWindowBase): + + def __init__(self, glb, parent=None, thread_at_time=None): + super(CallTreeWindow, self).__init__(parent) + + self.model = LookupCreateModel("Call Tree", lambda x=glb: CallTreeModel(x)) + + self.view.setModel(self.model) + + for c, w in ((0, 230), (1, 100), (2, 100), (3, 70), (4, 70), (5, 100)): + self.view.setColumnWidth(c, w) + + self.find_bar = FindBar(self, self) + + self.vbox = VBox(self.view, self.find_bar.Widget()) + + self.setWidget(self.vbox.Widget()) + + AddSubWindow(glb.mainwindow.mdi_area, self, "Call Tree") + + if thread_at_time: + self.DisplayThreadAtTime(*thread_at_time) + + def DisplayThreadAtTime(self, comm_id, thread_id, time): + parent = QModelIndex() + for dbid in (comm_id, thread_id): + found = False + n = self.model.rowCount(parent) + for row in range(n): + child = self.model.index(row, 0, parent) + if child.internalPointer().dbid == dbid: + found = True + self.view.setExpanded(parent, True) + self.view.setCurrentIndex(child) + parent = child + break + if not found: + return + found = False + while True: + n = self.model.rowCount(parent) + if not n: + return + last_child = None + for row in range(n): + self.view.setExpanded(parent, True) + child = self.model.index(row, 0, parent) + child_call_time = child.internalPointer().call_time + if child_call_time < time: + last_child = child + elif child_call_time == time: + self.view.setCurrentIndex(child) + return + elif child_call_time > time: + break + if not last_child: + if not found: + child = self.model.index(0, 0, parent) + self.view.setExpanded(parent, True) + self.view.setCurrentIndex(child) + return + found = True + self.view.setExpanded(parent, True) + self.view.setCurrentIndex(last_child) + parent = last_child + +# ExecComm() gets the comm_id of the command string that was set when the process exec'd i.e. the program name + +def ExecComm(db, thread_id, time): + query = QSqlQuery(db) + QueryExec(query, "SELECT comm_threads.comm_id, comms.c_time, comms.exec_flag" + " FROM comm_threads" + " INNER JOIN comms ON comms.id = comm_threads.comm_id" + " WHERE comm_threads.thread_id = " + str(thread_id) + + " ORDER BY comms.c_time, comms.id") + first = None + last = None + while query.next(): + if first is None: + first = query.value(0) + if query.value(2) and Decimal(query.value(1)) <= Decimal(time): + last = query.value(0) + if not(last is None): + return last + return first + +# Container for (x, y) data + +class XY(): + def __init__(self, x=0, y=0): + self.x = x + self.y = y + + def __str__(self): + return "XY({}, {})".format(str(self.x), str(self.y)) + +# Container for sub-range data + +class Subrange(): + def __init__(self, lo=0, hi=0): + self.lo = lo + self.hi = hi + + def __str__(self): + return "Subrange({}, {})".format(str(self.lo), str(self.hi)) + +# Graph data region base class + +class GraphDataRegion(object): + + def __init__(self, key, title = "", ordinal = ""): + self.key = key + self.title = title + self.ordinal = ordinal + +# Function to sort GraphDataRegion + +def GraphDataRegionOrdinal(data_region): + return data_region.ordinal + +# Attributes for a graph region + +class GraphRegionAttribute(): + + def __init__(self, colour): + self.colour = colour + +# Switch graph data region represents a task + +class SwitchGraphDataRegion(GraphDataRegion): + + def __init__(self, key, exec_comm_id, pid, tid, comm, thread_id, comm_id): + super(SwitchGraphDataRegion, self).__init__(key) + + self.title = str(pid) + " / " + str(tid) + " " + comm + # Order graph legend within exec comm by pid / tid / time + self.ordinal = str(pid).rjust(16) + str(exec_comm_id).rjust(8) + str(tid).rjust(16) + self.exec_comm_id = exec_comm_id + self.pid = pid + self.tid = tid + self.comm = comm + self.thread_id = thread_id + self.comm_id = comm_id + +# Graph data point + +class GraphDataPoint(): + + def __init__(self, data, index, x, y, altx=None, alty=None, hregion=None, vregion=None): + self.data = data + self.index = index + self.x = x + self.y = y + self.altx = altx + self.alty = alty + self.hregion = hregion + self.vregion = vregion + +# Graph data (single graph) base class + +class GraphData(object): + + def __init__(self, collection, xbase=Decimal(0), ybase=Decimal(0)): + self.collection = collection + self.points = [] + self.xbase = xbase + self.ybase = ybase + self.title = "" + + def AddPoint(self, x, y, altx=None, alty=None, hregion=None, vregion=None): + index = len(self.points) + + x = float(Decimal(x) - self.xbase) + y = float(Decimal(y) - self.ybase) + + self.points.append(GraphDataPoint(self, index, x, y, altx, alty, hregion, vregion)) + + def XToData(self, x): + return Decimal(x) + self.xbase + + def YToData(self, y): + return Decimal(y) + self.ybase + +# Switch graph data (for one CPU) + +class SwitchGraphData(GraphData): + + def __init__(self, db, collection, cpu, xbase): + super(SwitchGraphData, self).__init__(collection, xbase) + + self.cpu = cpu + self.title = "CPU " + str(cpu) + self.SelectSwitches(db) + + def SelectComms(self, db, thread_id, last_comm_id, start_time, end_time): + query = QSqlQuery(db) + QueryExec(query, "SELECT id, c_time" + " FROM comms" + " WHERE c_thread_id = " + str(thread_id) + + " AND exec_flag = " + self.collection.glb.dbref.TRUE + + " AND c_time >= " + str(start_time) + + " AND c_time <= " + str(end_time) + + " ORDER BY c_time, id") + while query.next(): + comm_id = query.value(0) + if comm_id == last_comm_id: + continue + time = query.value(1) + hregion = self.HRegion(db, thread_id, comm_id, time) + self.AddPoint(time, 1000, None, None, hregion) + + def SelectSwitches(self, db): + last_time = None + last_comm_id = None + last_thread_id = None + query = QSqlQuery(db) + QueryExec(query, "SELECT time, thread_out_id, thread_in_id, comm_out_id, comm_in_id, flags" + " FROM context_switches" + " WHERE machine_id = " + str(self.collection.machine_id) + + " AND cpu = " + str(self.cpu) + + " ORDER BY time, id") + while query.next(): + flags = int(query.value(5)) + if flags & 1: + # Schedule-out: detect and add exec's + if last_thread_id == query.value(1) and last_comm_id is not None and last_comm_id != query.value(3): + self.SelectComms(db, last_thread_id, last_comm_id, last_time, query.value(0)) + continue + # Schedule-in: add data point + if len(self.points) == 0: + start_time = self.collection.glb.StartTime(self.collection.machine_id) + hregion = self.HRegion(db, query.value(1), query.value(3), start_time) + self.AddPoint(start_time, 1000, None, None, hregion) + time = query.value(0) + comm_id = query.value(4) + thread_id = query.value(2) + hregion = self.HRegion(db, thread_id, comm_id, time) + self.AddPoint(time, 1000, None, None, hregion) + last_time = time + last_comm_id = comm_id + last_thread_id = thread_id + + def NewHRegion(self, db, key, thread_id, comm_id, time): + exec_comm_id = ExecComm(db, thread_id, time) + query = QSqlQuery(db) + QueryExec(query, "SELECT pid, tid FROM threads WHERE id = " + str(thread_id)) + if query.next(): + pid = query.value(0) + tid = query.value(1) + else: + pid = -1 + tid = -1 + query = QSqlQuery(db) + QueryExec(query, "SELECT comm FROM comms WHERE id = " + str(comm_id)) + if query.next(): + comm = query.value(0) + else: + comm = "" + return SwitchGraphDataRegion(key, exec_comm_id, pid, tid, comm, thread_id, comm_id) + + def HRegion(self, db, thread_id, comm_id, time): + key = str(thread_id) + ":" + str(comm_id) + hregion = self.collection.LookupHRegion(key) + if hregion is None: + hregion = self.NewHRegion(db, key, thread_id, comm_id, time) + self.collection.AddHRegion(key, hregion) + return hregion + +# Graph data collection (multiple related graphs) base class + +class GraphDataCollection(object): + + def __init__(self, glb): + self.glb = glb + self.data = [] + self.hregions = {} + self.xrangelo = None + self.xrangehi = None + self.yrangelo = None + self.yrangehi = None + self.dp = XY(0, 0) + + def AddGraphData(self, data): + self.data.append(data) + + def LookupHRegion(self, key): + if key in self.hregions: + return self.hregions[key] + return None + + def AddHRegion(self, key, hregion): + self.hregions[key] = hregion + +# Switch graph data collection (SwitchGraphData for each CPU) + +class SwitchGraphDataCollection(GraphDataCollection): + + def __init__(self, glb, db, machine_id): + super(SwitchGraphDataCollection, self).__init__(glb) + + self.machine_id = machine_id + self.cpus = self.SelectCPUs(db) + + self.xrangelo = glb.StartTime(machine_id) + self.xrangehi = glb.FinishTime(machine_id) + + self.yrangelo = Decimal(0) + self.yrangehi = Decimal(1000) + + for cpu in self.cpus: + self.AddGraphData(SwitchGraphData(db, self, cpu, self.xrangelo)) + + def SelectCPUs(self, db): + cpus = [] + query = QSqlQuery(db) + QueryExec(query, "SELECT DISTINCT cpu" + " FROM context_switches" + " WHERE machine_id = " + str(self.machine_id)) + while query.next(): + cpus.append(int(query.value(0))) + return sorted(cpus) + +# Switch graph data graphics item displays the graphed data + +class SwitchGraphDataGraphicsItem(QGraphicsItem): + + def __init__(self, data, graph_width, graph_height, attrs, event_handler, parent=None): + super(SwitchGraphDataGraphicsItem, self).__init__(parent) + + self.data = data + self.graph_width = graph_width + self.graph_height = graph_height + self.attrs = attrs + self.event_handler = event_handler + self.setAcceptHoverEvents(True) + + def boundingRect(self): + return QRectF(0, 0, self.graph_width, self.graph_height) + + def PaintPoint(self, painter, last, x): + if not(last is None or last.hregion.pid == 0 or x < self.attrs.subrange.x.lo): + if last.x < self.attrs.subrange.x.lo: + x0 = self.attrs.subrange.x.lo + else: + x0 = last.x + if x > self.attrs.subrange.x.hi: + x1 = self.attrs.subrange.x.hi + else: + x1 = x - 1 + x0 = self.attrs.XToPixel(x0) + x1 = self.attrs.XToPixel(x1) + + y0 = self.attrs.YToPixel(last.y) + + colour = self.attrs.region_attributes[last.hregion.key].colour + + width = x1 - x0 + 1 + if width < 2: + painter.setPen(colour) + painter.drawLine(x0, self.graph_height - y0, x0, self.graph_height) + else: + painter.fillRect(x0, self.graph_height - y0, width, self.graph_height - 1, colour) + + def paint(self, painter, _option, _widget): + last = None + for point in self.data.points: + self.PaintPoint(painter, last, point.x) + if point.x > self.attrs.subrange.x.hi: + break + last = point + self.PaintPoint(painter, last, self.attrs.subrange.x.hi + 1) + + def BinarySearchPoint(self, target): + lower_pos = 0 + higher_pos = len(self.data.points) + while True: + pos = int((lower_pos + higher_pos) / 2) + val = self.data.points[pos].x + if target >= val: + lower_pos = pos + else: + higher_pos = pos + if higher_pos <= lower_pos + 1: + return lower_pos + + def XPixelToData(self, x): + x = self.attrs.PixelToX(x) + if x < self.data.points[0].x: + x = 0 + pos = 0 + low = True + else: + pos = self.BinarySearchPoint(x) + low = False + return (low, pos, self.data.XToData(x)) + + def EventToData(self, event): + no_data = (None,) * 4 + if len(self.data.points) < 1: + return no_data + x = event.pos().x() + if x < 0: + return no_data + _low0, pos0, time_from = self.XPixelToData(x) + low1, pos1, time_to = self.XPixelToData(x + 1) + hregions = set() + hregion_times = [] + if not low1: + for i in range(pos0, pos1 + 1): + hregion = self.data.points[i].hregion + hregions.add(hregion) + if i == pos0: + time = time_from + else: + time = self.data.XToData(self.data.points[i].x) + hregion_times.append((hregion, time)) + return (time_from, time_to, hregions, hregion_times) + + def hoverMoveEvent(self, event): + time_from, time_to, hregions, _hregion_times = self.EventToData(event) + if time_from is not None: + self.event_handler.PointEvent(self.data.cpu, time_from, time_to, hregions) + + def hoverLeaveEvent(self, _event): + self.event_handler.NoPointEvent() + + def mousePressEvent(self, event): + if event.button() != Qt.RightButton: + super(SwitchGraphDataGraphicsItem, self).mousePressEvent(event) + return + _time_from, _time_to, _hregions, hregion_times = self.EventToData(event) + if hregion_times: + self.event_handler.RightClickEvent(self.data.cpu, hregion_times, event.screenPos()) + +# X-axis graphics item + +class XAxisGraphicsItem(QGraphicsItem): + + def __init__(self, width, parent=None): + super(XAxisGraphicsItem, self).__init__(parent) + + self.width = width + self.max_mark_sz = 4 + self.height = self.max_mark_sz + 1 + + def boundingRect(self): + return QRectF(0, 0, self.width, self.height) + + def Step(self): + attrs = self.parentItem().attrs + subrange = attrs.subrange.x + t = subrange.hi - subrange.lo + s = (3.0 * t) / self.width + n = 1.0 + while s > n: + n = n * 10.0 + return n + + def PaintMarks(self, painter, at_y, lo, hi, step, i): + attrs = self.parentItem().attrs + x = lo + while x <= hi: + xp = attrs.XToPixel(x) + if i % 10: + if i % 5: + sz = 1 + else: + sz = 2 + else: + sz = self.max_mark_sz + i = 0 + painter.drawLine(xp, at_y, xp, at_y + sz) + x += step + i += 1 + + def paint(self, painter, _option, _widget): + # Using QPainter::drawLine(int x1, int y1, int x2, int y2) so x2 = width -1 + painter.drawLine(0, 0, self.width - 1, 0) + n = self.Step() + attrs = self.parentItem().attrs + subrange = attrs.subrange.x + if subrange.lo: + x_offset = n - (subrange.lo % n) + else: + x_offset = 0.0 + x = subrange.lo + x_offset + i = (x / n) % 10 + self.PaintMarks(painter, 0, x, subrange.hi, n, i) + + def ScaleDimensions(self): + n = self.Step() + attrs = self.parentItem().attrs + lo = attrs.subrange.x.lo + hi = (n * 10.0) + lo + width = attrs.XToPixel(hi) + if width > 500: + width = 0 + return (n, lo, hi, width) + + def PaintScale(self, painter, at_x, at_y): + n, lo, hi, width = self.ScaleDimensions() + if not width: + return + painter.drawLine(at_x, at_y, at_x + width, at_y) + self.PaintMarks(painter, at_y, lo, hi, n, 0) + + def ScaleWidth(self): + _n, _lo, _hi, width = self.ScaleDimensions() + return width + + def ScaleHeight(self): + return self.height + + def ScaleUnit(self): + return self.Step() * 10 + +# Scale graphics item base class + +class ScaleGraphicsItem(QGraphicsItem): + + def __init__(self, axis, parent=None): + super(ScaleGraphicsItem, self).__init__(parent) + self.axis = axis + + def boundingRect(self): + scale_width = self.axis.ScaleWidth() + if not scale_width: + return QRectF() + return QRectF(0, 0, self.axis.ScaleWidth() + 100, self.axis.ScaleHeight()) + + def paint(self, painter, _option, _widget): + scale_width = self.axis.ScaleWidth() + if not scale_width: + return + self.axis.PaintScale(painter, 0, 5) + x = scale_width + 4 + painter.drawText(QPointF(x, 10), self.Text()) + + def Unit(self): + return self.axis.ScaleUnit() + + def Text(self): + return "" + +# Switch graph scale graphics item + +class SwitchScaleGraphicsItem(ScaleGraphicsItem): + + def Text(self): + unit = self.Unit() + if unit >= 1000000000: + unit = int(unit / 1000000000) + us = "s" + elif unit >= 1000000: + unit = int(unit / 1000000) + us = "ms" + elif unit >= 1000: + unit = int(unit / 1000) + us = "us" + else: + unit = int(unit) + us = "ns" + return " = " + str(unit) + " " + us + +# Switch graph graphics item contains graph title, scale, x/y-axis, and the graphed data + +class SwitchGraphGraphicsItem(QGraphicsItem): + + def __init__(self, collection, data, attrs, event_handler, first, parent=None): + super(SwitchGraphGraphicsItem, self).__init__(parent) + self.collection = collection + self.data = data + self.attrs = attrs + self.event_handler = event_handler + + margin = 20 + title_width = 50 + + self.title_graphics = QGraphicsSimpleTextItem(data.title, self) + + self.title_graphics.setPos(margin, margin) + graph_width = attrs.XToPixel(attrs.subrange.x.hi) + 1 + graph_height = attrs.YToPixel(attrs.subrange.y.hi) + 1 + + self.graph_origin_x = margin + title_width + margin + self.graph_origin_y = graph_height + margin + + _x_axis_size = 1 + y_axis_size = 1 + self.yline = QGraphicsLineItem(0, 0, 0, graph_height, self) + + self.x_axis = XAxisGraphicsItem(graph_width, self) + self.x_axis.setPos(self.graph_origin_x, self.graph_origin_y + 1) + + if first: + self.scale_item = SwitchScaleGraphicsItem(self.x_axis, self) + self.scale_item.setPos(self.graph_origin_x, self.graph_origin_y + 10) + + self.yline.setPos(self.graph_origin_x - y_axis_size, self.graph_origin_y - graph_height) + + self.axis_point = QGraphicsLineItem(0, 0, 0, 0, self) + self.axis_point.setPos(self.graph_origin_x - 1, self.graph_origin_y +1) + + self.width = self.graph_origin_x + graph_width + margin + self.height = self.graph_origin_y + margin + + self.graph = SwitchGraphDataGraphicsItem(data, graph_width, graph_height, attrs, event_handler, self) + self.graph.setPos(self.graph_origin_x, self.graph_origin_y - graph_height) + + if parent and 'EnableRubberBand' in dir(parent): + parent.EnableRubberBand(self.graph_origin_x, self.graph_origin_x + graph_width - 1, self) + + def boundingRect(self): + return QRectF(0, 0, self.width, self.height) + + def paint(self, painter, option, widget): + pass + + def RBXToPixel(self, x): + return self.attrs.PixelToX(x - self.graph_origin_x) + + def RBXRangeToPixel(self, x0, x1): + return (self.RBXToPixel(x0), self.RBXToPixel(x1 + 1)) + + def RBPixelToTime(self, x): + if x < self.data.points[0].x: + return self.data.XToData(0) + return self.data.XToData(x) + + def RBEventTimes(self, x0, x1): + x0, x1 = self.RBXRangeToPixel(x0, x1) + time_from = self.RBPixelToTime(x0) + time_to = self.RBPixelToTime(x1) + return (time_from, time_to) + + def RBEvent(self, x0, x1): + time_from, time_to = self.RBEventTimes(x0, x1) + self.event_handler.RangeEvent(time_from, time_to) + + def RBMoveEvent(self, x0, x1): + if x1 < x0: + x0, x1 = x1, x0 + self.RBEvent(x0, x1) + + def RBReleaseEvent(self, x0, x1, selection_state): + if x1 < x0: + x0, x1 = x1, x0 + x0, x1 = self.RBXRangeToPixel(x0, x1) + self.event_handler.SelectEvent(x0, x1, selection_state) + +# Graphics item to draw a vertical bracket (used to highlight "forward" sub-range) + +class VerticalBracketGraphicsItem(QGraphicsItem): + + def __init__(self, parent=None): + super(VerticalBracketGraphicsItem, self).__init__(parent) + + self.width = 0 + self.height = 0 + self.hide() + + def SetSize(self, width, height): + self.width = width + 1 + self.height = height + 1 + + def boundingRect(self): + return QRectF(0, 0, self.width, self.height) + + def paint(self, painter, _option, _widget): + colour = QColor(255, 255, 0, 32) + painter.fillRect(0, 0, self.width, self.height, colour) + x1 = self.width - 1 + y1 = self.height - 1 + painter.drawLine(0, 0, x1, 0) + painter.drawLine(0, 0, 0, 3) + painter.drawLine(x1, 0, x1, 3) + painter.drawLine(0, y1, x1, y1) + painter.drawLine(0, y1, 0, y1 - 3) + painter.drawLine(x1, y1, x1, y1 - 3) + +# Graphics item to contain graphs arranged vertically + +class VertcalGraphSetGraphicsItem(QGraphicsItem): + + def __init__(self, collection, attrs, event_handler, child_class, parent=None): + super(VertcalGraphSetGraphicsItem, self).__init__(parent) + + self.collection = collection + + self.top = 10 + + self.width = 0 + self.height = self.top + + self.rubber_band = None + self.rb_enabled = False + self.rb_in_view = False + self.rb_xlo = 0 + self.rb_xhi = 0 + self.rb_event_handler = None + self.rb_origin = None + + first = True + for data in collection.data: + child = child_class(collection, data, attrs, event_handler, first, self) + child.setPos(0, self.height + 1) + rect = child.boundingRect() + if rect.right() > self.width: + self.width = rect.right() + self.height = self.height + rect.bottom() + 1 + first = False + + self.bracket = VerticalBracketGraphicsItem(self) + + def EnableRubberBand(self, xlo, xhi, rb_event_handler): + if self.rb_enabled: + return + self.rb_enabled = True + self.rb_in_view = False + self.setAcceptedMouseButtons(Qt.LeftButton) + self.rb_xlo = xlo + self.rb_xhi = xhi + self.rb_event_handler = rb_event_handler + + def mousePressEvent(self, event): + if self.rb_enabled: + self.MousePressEvent(event) + + def mouseMoveEvent(self, event): + if self.rb_enabled: + self.MouseMoveEvent(event) + + def mouseReleaseEvent(self, event): + if self.rb_enabled: + self.MouseReleaseEvent(event) + + def boundingRect(self): + return QRectF(0, 0, self.width, self.height) + + def paint(self, painter, option, widget): + pass + + def RubberBandParent(self): + scene = self.scene() + view = scene.views()[0] + viewport = view.viewport() + return viewport + + def RubberBandSetGeometry(self, rect): + scene_rectf = self.mapRectToScene(QRectF(rect)) + scene = self.scene() + view = scene.views()[0] + poly = view.mapFromScene(scene_rectf) + self.rubber_band.setGeometry(poly.boundingRect()) + + def SetSelection(self, selection_state): + if self.rubber_band: + if selection_state: + self.RubberBandSetGeometry(selection_state) + self.rubber_band.show() + else: + self.rubber_band.hide() + + def SetBracket(self, rect): + if rect: + x, y, width, height = rect.x(), rect.y(), rect.width(), rect.height() + self.bracket.setPos(x, y) + self.bracket.SetSize(width, height) + self.bracket.show() + else: + self.bracket.hide() + + def RubberBandX(self, event): + x = event.pos().toPoint().x() + if x < self.rb_xlo: + x = self.rb_xlo + elif x > self.rb_xhi: + x = self.rb_xhi + else: + self.rb_in_view = True + return x + + def RubberBandRect(self, x): + if self.rb_origin.x() <= x: + width = x - self.rb_origin.x() + rect = QRect(self.rb_origin, QSize(width, self.height)) + else: + width = self.rb_origin.x() - x + top_left = QPoint(self.rb_origin.x() - width, self.rb_origin.y()) + rect = QRect(top_left, QSize(width, self.height)) + return rect + + def MousePressEvent(self, event): + self.rb_in_view = False + x = self.RubberBandX(event) + self.rb_origin = QPoint(x, self.top) + if self.rubber_band is None: + self.rubber_band = QRubberBand(QRubberBand.Rectangle, self.RubberBandParent()) + self.RubberBandSetGeometry(QRect(self.rb_origin, QSize(0, self.height))) + if self.rb_in_view: + self.rubber_band.show() + self.rb_event_handler.RBMoveEvent(x, x) + else: + self.rubber_band.hide() + + def MouseMoveEvent(self, event): + x = self.RubberBandX(event) + rect = self.RubberBandRect(x) + self.RubberBandSetGeometry(rect) + if self.rb_in_view: + self.rubber_band.show() + self.rb_event_handler.RBMoveEvent(self.rb_origin.x(), x) + + def MouseReleaseEvent(self, event): + x = self.RubberBandX(event) + if self.rb_in_view: + selection_state = self.RubberBandRect(x) + else: + selection_state = None + self.rb_event_handler.RBReleaseEvent(self.rb_origin.x(), x, selection_state) + +# Switch graph legend data model + +class SwitchGraphLegendModel(QAbstractTableModel): + + def __init__(self, collection, region_attributes, parent=None): + super(SwitchGraphLegendModel, self).__init__(parent) + + self.region_attributes = region_attributes + + self.child_items = sorted(collection.hregions.values(), key=GraphDataRegionOrdinal) + self.child_count = len(self.child_items) + + self.highlight_set = set() + + self.column_headers = ("pid", "tid", "comm") + + def rowCount(self, _parent): + return self.child_count + + def headerData(self, section, orientation, role): + if role != Qt.DisplayRole: + return None + if orientation != Qt.Horizontal: + return None + return self.columnHeader(section) + + def index(self, row, column, _parent): + return self.createIndex(row, column, self.child_items[row]) + + def columnCount(self, _parent=None): + return len(self.column_headers) + + def columnHeader(self, column): + return self.column_headers[column] + + def data(self, index, role): + if role == Qt.BackgroundRole: + child = self.child_items[index.row()] + if child in self.highlight_set: + return self.region_attributes[child.key].colour + return None + if role == Qt.ForegroundRole: + child = self.child_items[index.row()] + if child in self.highlight_set: + return QColor(255, 255, 255) + return self.region_attributes[child.key].colour + if role != Qt.DisplayRole: + return None + hregion = self.child_items[index.row()] + col = index.column() + if col == 0: + return hregion.pid + if col == 1: + return hregion.tid + if col == 2: + return hregion.comm + return None + + def SetHighlight(self, row, _set_highlight): + child = self.child_items[row] + top_left = self.createIndex(row, 0, child) + bottom_right = self.createIndex(row, len(self.column_headers) - 1, child) + self.dataChanged.emit(top_left, bottom_right) + + def Highlight(self, highlight_set): + for row in range(self.child_count): + child = self.child_items[row] + if child in self.highlight_set: + if child not in highlight_set: + self.SetHighlight(row, False) + elif child in highlight_set: + self.SetHighlight(row, True) + self.highlight_set = highlight_set + +# Switch graph legend is a table + +class SwitchGraphLegend(QWidget): + + def __init__(self, collection, region_attributes, parent=None): + super(SwitchGraphLegend, self).__init__(parent) + + self.data_model = SwitchGraphLegendModel(collection, region_attributes) + + self.model = QSortFilterProxyModel() + self.model.setSourceModel(self.data_model) + + self.view = QTableView() + self.view.setModel(self.model) + self.view.setEditTriggers(QAbstractItemView.NoEditTriggers) + self.view.verticalHeader().setVisible(False) + self.view.sortByColumn(-1, Qt.AscendingOrder) + self.view.setSortingEnabled(True) + self.view.resizeColumnsToContents() + self.view.resizeRowsToContents() + + self.vbox = VBoxLayout(self.view) + self.setLayout(self.vbox) + + sz1 = self.view.columnWidth(0) + self.view.columnWidth(1) + self.view.columnWidth(2) + 2 + sz1 = sz1 + self.view.verticalScrollBar().sizeHint().width() + self.saved_size = sz1 + + def resizeEvent(self, event): + self.saved_size = self.size().width() + super(SwitchGraphLegend, self).resizeEvent(event) + + def Highlight(self, highlight_set): + self.data_model.Highlight(highlight_set) + self.update() + + def changeEvent(self, event): + if event.type() == QEvent.FontChange: + self.view.resizeRowsToContents() + self.view.resizeColumnsToContents() + # Need to resize rows again after column resize + self.view.resizeRowsToContents() + super(SwitchGraphLegend, self).changeEvent(event) + +# Random colour generation + +def RGBColourTooLight(r, g, _b): + if g > 230: + return True + if g <= 160: + return False + if r <= 180 and g <= 180: + return False + if r < 60: + return False + return True + +def GenerateColours(x): + cs = [0] + for i in range(1, x): + cs.append(int((255.0 / i) + 0.5)) + colours = [] + for r in cs: + for g in cs: + for b in cs: + # Exclude black and colours that look too light against a white background + if (r, g, b) == (0, 0, 0) or RGBColourTooLight(r, g, b): + continue + colours.append(QColor(r, g, b)) + return colours + +def GenerateNColours(n): + for x in range(2, n + 2): + colours = GenerateColours(x) + if len(colours) >= n: + return colours + return [] + +def GenerateNRandomColours(n, seed): + colours = GenerateNColours(n) + random.seed(seed) + random.shuffle(colours) + return colours + +# Graph attributes, in particular the scale and subrange that change when zooming + +class GraphAttributes(): + + def __init__(self, scale, subrange, region_attributes, dp): + self.scale = scale + self.subrange = subrange + self.region_attributes = region_attributes + # Rounding avoids errors due to finite floating point precision + self.dp = dp # data decimal places + self.Update() + + def XToPixel(self, x): + return int(round((x - self.subrange.x.lo) * self.scale.x, self.pdp.x)) + + def YToPixel(self, y): + return int(round((y - self.subrange.y.lo) * self.scale.y, self.pdp.y)) + + def PixelToXRounded(self, px): + return round((round(px, 0) / self.scale.x), self.dp.x) + self.subrange.x.lo + + def PixelToYRounded(self, py): + return round((round(py, 0) / self.scale.y), self.dp.y) + self.subrange.y.lo + + def PixelToX(self, px): + x = self.PixelToXRounded(px) + if self.pdp.x == 0: + rt = self.XToPixel(x) + if rt > px: + return x - 1 + return x + + def PixelToY(self, py): + y = self.PixelToYRounded(py) + if self.pdp.y == 0: + rt = self.YToPixel(y) + if rt > py: + return y - 1 + return y + + def ToPDP(self, dp, scale): + # Calculate pixel decimal places: + # (10 ** dp) is the minimum delta in the data + # scale it to get the minimum delta in pixels + # log10 gives the number of decimals places negatively + # subtrace 1 to divide by 10 + # round to the lower negative number + # change the sign to get the number of decimals positively + x = math.log10((10 ** dp) * scale) + if x < 0: + x -= 1 + x = -int(math.floor(x) - 0.1) + else: + x = 0 + return x + + def Update(self): + x = self.ToPDP(self.dp.x, self.scale.x) + y = self.ToPDP(self.dp.y, self.scale.y) + self.pdp = XY(x, y) # pixel decimal places + +# Switch graph splitter which divides the CPU graphs from the legend + +class SwitchGraphSplitter(QSplitter): + + def __init__(self, parent=None): + super(SwitchGraphSplitter, self).__init__(parent) + + self.first_time = False + + def resizeEvent(self, event): + if self.first_time: + self.first_time = False + sz1 = self.widget(1).view.columnWidth(0) + self.widget(1).view.columnWidth(1) + self.widget(1).view.columnWidth(2) + 2 + sz1 = sz1 + self.widget(1).view.verticalScrollBar().sizeHint().width() + sz0 = self.size().width() - self.handleWidth() - sz1 + self.setSizes([sz0, sz1]) + elif not(self.widget(1).saved_size is None): + sz1 = self.widget(1).saved_size + sz0 = self.size().width() - self.handleWidth() - sz1 + self.setSizes([sz0, sz1]) + super(SwitchGraphSplitter, self).resizeEvent(event) + +# Graph widget base class + +class GraphWidget(QWidget): + + graph_title_changed = Signal(object) + + def __init__(self, parent=None): + super(GraphWidget, self).__init__(parent) + + def GraphTitleChanged(self, title): + self.graph_title_changed.emit(title) + + def Title(self): + return "" + +# Display time in s, ms, us or ns + +def ToTimeStr(val): + val = Decimal(val) + if val >= 1000000000: + return "{} s".format((val / 1000000000).quantize(Decimal("0.000000001"))) + if val >= 1000000: + return "{} ms".format((val / 1000000).quantize(Decimal("0.000001"))) + if val >= 1000: + return "{} us".format((val / 1000).quantize(Decimal("0.001"))) + return "{} ns".format(val.quantize(Decimal("1"))) + +# Switch (i.e. context switch i.e. Time Chart by CPU) graph widget which contains the CPU graphs and the legend and control buttons + +class SwitchGraphWidget(GraphWidget): + + def __init__(self, glb, collection, parent=None): + super(SwitchGraphWidget, self).__init__(parent) + + self.glb = glb + self.collection = collection + + self.back_state = [] + self.forward_state = [] + self.selection_state = (None, None) + self.fwd_rect = None + self.start_time = self.glb.StartTime(collection.machine_id) + + i = 0 + hregions = collection.hregions.values() + colours = GenerateNRandomColours(len(hregions), 1013) + region_attributes = {} + for hregion in hregions: + if hregion.pid == 0 and hregion.tid == 0: + region_attributes[hregion.key] = GraphRegionAttribute(QColor(0, 0, 0)) + else: + region_attributes[hregion.key] = GraphRegionAttribute(colours[i]) + i = i + 1 + + # Default to entire range + xsubrange = Subrange(0.0, float(collection.xrangehi - collection.xrangelo) + 1.0) + ysubrange = Subrange(0.0, float(collection.yrangehi - collection.yrangelo) + 1.0) + subrange = XY(xsubrange, ysubrange) + + scale = self.GetScaleForRange(subrange) + + self.attrs = GraphAttributes(scale, subrange, region_attributes, collection.dp) + + self.item = VertcalGraphSetGraphicsItem(collection, self.attrs, self, SwitchGraphGraphicsItem) + + self.scene = QGraphicsScene() + self.scene.addItem(self.item) + + self.view = QGraphicsView(self.scene) + self.view.centerOn(0, 0) + self.view.setAlignment(Qt.AlignLeft | Qt.AlignTop) + + self.legend = SwitchGraphLegend(collection, region_attributes) + + self.splitter = SwitchGraphSplitter() + self.splitter.addWidget(self.view) + self.splitter.addWidget(self.legend) + + self.point_label = QLabel("") + self.point_label.setSizePolicy(QSizePolicy.Preferred, QSizePolicy.Fixed) + + self.back_button = QToolButton() + self.back_button.setIcon(self.style().standardIcon(QStyle.SP_ArrowLeft)) + self.back_button.setDisabled(True) + self.back_button.released.connect(self.Back) + + self.forward_button = QToolButton() + self.forward_button.setIcon(self.style().standardIcon(QStyle.SP_ArrowRight)) + self.forward_button.setDisabled(True) + self.forward_button.released.connect(self.Forward) + + self.zoom_button = QToolButton() + self.zoom_button.setText("Zoom") + self.zoom_button.setDisabled(True) + self.zoom_button.released.connect(self.Zoom) + + self.hbox = HBoxLayout(self.back_button, self.forward_button, self.zoom_button, self.point_label) + + self.vbox = VBoxLayout(self.splitter, self.hbox) + + self.setLayout(self.vbox) + + def GetScaleForRangeX(self, xsubrange): + # Default graph 1000 pixels wide + dflt = 1000.0 + r = xsubrange.hi - xsubrange.lo + return dflt / r + + def GetScaleForRangeY(self, ysubrange): + # Default graph 50 pixels high + dflt = 50.0 + r = ysubrange.hi - ysubrange.lo + return dflt / r + + def GetScaleForRange(self, subrange): + # Default graph 1000 pixels wide, 50 pixels high + xscale = self.GetScaleForRangeX(subrange.x) + yscale = self.GetScaleForRangeY(subrange.y) + return XY(xscale, yscale) + + def PointEvent(self, cpu, time_from, _time_to, hregions): + text = "CPU: " + str(cpu) + time_from = time_from.quantize(Decimal(1)) + rel_time_from = time_from - self.glb.StartTime(self.collection.machine_id) + text = text + " Time: " + str(time_from) + " (+" + ToTimeStr(rel_time_from) + ")" + self.point_label.setText(text) + self.legend.Highlight(hregions) + + def RightClickEvent(self, _cpu, hregion_times, pos): + if not IsSelectable(self.glb.db, "calls", "WHERE parent_id >= 0"): + return + menu = QMenu(self.view) + for hregion, time in hregion_times: + thread_at_time = (hregion.exec_comm_id, hregion.thread_id, time) + menu_text = "Show Call Tree for {} {}:{} at {}".format(hregion.comm, hregion.pid, hregion.tid, time) + menu.addAction(CreateAction(menu_text, "Show Call Tree", lambda a=None, args=thread_at_time: self.RightClickSelect(args), self.view)) + menu.exec_(pos) + + def RightClickSelect(self, args): + CallTreeWindow(self.glb, self.glb.mainwindow, thread_at_time=args) + + def NoPointEvent(self): + self.point_label.setText("") + self.legend.Highlight({}) + + def RangeEvent(self, time_from, time_to): + time_from = time_from.quantize(Decimal(1)) + time_to = time_to.quantize(Decimal(1)) + if time_to <= time_from: + self.point_label.setText("") + return + rel_time_from = time_from - self.start_time + rel_time_to = time_to - self.start_time + text = " Time: " + str(time_from) + " (+" + ToTimeStr(rel_time_from) + ") to: " + str(time_to) + " (+" + ToTimeStr(rel_time_to) + ")" + text = text + " duration: " + ToTimeStr(time_to - time_from) + self.point_label.setText(text) + + def BackState(self): + return (self.attrs.subrange, self.attrs.scale, self.selection_state, self.fwd_rect) + + def PushBackState(self): + state = copy.deepcopy(self.BackState()) + self.back_state.append(state) + self.back_button.setEnabled(True) + + def PopBackState(self): + self.attrs.subrange, self.attrs.scale, self.selection_state, self.fwd_rect = self.back_state.pop() + self.attrs.Update() + if not self.back_state: + self.back_button.setDisabled(True) + + def PushForwardState(self): + state = copy.deepcopy(self.BackState()) + self.forward_state.append(state) + self.forward_button.setEnabled(True) + + def PopForwardState(self): + self.attrs.subrange, self.attrs.scale, self.selection_state, self.fwd_rect = self.forward_state.pop() + self.attrs.Update() + if not self.forward_state: + self.forward_button.setDisabled(True) + + def Title(self): + time_from = self.collection.xrangelo + Decimal(self.attrs.subrange.x.lo) + time_to = self.collection.xrangelo + Decimal(self.attrs.subrange.x.hi) + rel_time_from = time_from - self.start_time + rel_time_to = time_to - self.start_time + title = "+" + ToTimeStr(rel_time_from) + " to +" + ToTimeStr(rel_time_to) + title = title + " (" + ToTimeStr(time_to - time_from) + ")" + return title + + def Update(self): + selected_subrange, selection_state = self.selection_state + self.item.SetSelection(selection_state) + self.item.SetBracket(self.fwd_rect) + self.zoom_button.setDisabled(selected_subrange is None) + self.GraphTitleChanged(self.Title()) + self.item.update(self.item.boundingRect()) + + def Back(self): + if not self.back_state: + return + self.PushForwardState() + self.PopBackState() + self.Update() + + def Forward(self): + if not self.forward_state: + return + self.PushBackState() + self.PopForwardState() + self.Update() + + def SelectEvent(self, x0, x1, selection_state): + if selection_state is None: + selected_subrange = None + else: + if x1 - x0 < 1.0: + x1 += 1.0 + selected_subrange = Subrange(x0, x1) + self.selection_state = (selected_subrange, selection_state) + self.zoom_button.setDisabled(selected_subrange is None) + + def Zoom(self): + selected_subrange, selection_state = self.selection_state + if selected_subrange is None: + return + self.fwd_rect = selection_state + self.item.SetSelection(None) + self.PushBackState() + self.attrs.subrange.x = selected_subrange + self.forward_state = [] + self.forward_button.setDisabled(True) + self.selection_state = (None, None) + self.fwd_rect = None + self.attrs.scale.x = self.GetScaleForRangeX(self.attrs.subrange.x) + self.attrs.Update() + self.Update() + +# Slow initialization - perform non-GUI initialization in a separate thread and put up a modal message box while waiting + +class SlowInitClass(): + + def __init__(self, glb, title, init_fn): + self.init_fn = init_fn + self.done = False + self.result = None + + self.msg_box = QMessageBox(glb.mainwindow) + self.msg_box.setText("Initializing " + title + ". Please wait.") + self.msg_box.setWindowTitle("Initializing " + title) + self.msg_box.setWindowIcon(glb.mainwindow.style().standardIcon(QStyle.SP_MessageBoxInformation)) + + self.init_thread = Thread(self.ThreadFn, glb) + self.init_thread.done.connect(self.Done, Qt.QueuedConnection) + + self.init_thread.start() + + def Done(self): + self.msg_box.done(0) + + def ThreadFn(self, glb): + conn_name = "SlowInitClass" + str(os.getpid()) + db, _dbname = glb.dbref.Open(conn_name) + self.result = self.init_fn(db) + self.done = True + return (True, 0) + + def Result(self): + while not self.done: + self.msg_box.exec_() + self.init_thread.wait() + return self.result + +def SlowInit(glb, title, init_fn): + init = SlowInitClass(glb, title, init_fn) + return init.Result() + +# Time chart by CPU window + +class TimeChartByCPUWindow(QMdiSubWindow): + + def __init__(self, glb, parent=None): + super(TimeChartByCPUWindow, self).__init__(parent) + + self.glb = glb + self.machine_id = glb.HostMachineId() + self.collection_name = "SwitchGraphDataCollection " + str(self.machine_id) + + collection = LookupModel(self.collection_name) + if collection is None: + collection = SlowInit(glb, "Time Chart", self.Init) + + self.widget = SwitchGraphWidget(glb, collection, self) + self.view = self.widget + + self.base_title = "Time Chart by CPU" + self.setWindowTitle(self.base_title + self.widget.Title()) + self.widget.graph_title_changed.connect(self.GraphTitleChanged) + + self.setWidget(self.widget) + + AddSubWindow(glb.mainwindow.mdi_area, self, self.windowTitle()) + + def Init(self, db): + return LookupCreateModel(self.collection_name, lambda : SwitchGraphDataCollection(self.glb, db, self.machine_id)) + + def GraphTitleChanged(self, title): + self.setWindowTitle(self.base_title + " : " + title) + +# Child data item finder + +class ChildDataItemFinder(): + + def __init__(self, root): + self.root = root + self.value, self.direction, self.pattern, self.last_value, self.last_pattern = (None,) * 5 + self.rows = [] + self.pos = 0 + + def FindSelect(self): + self.rows = [] + if self.pattern: + pattern = re.compile(self.value) + for child in self.root.child_items: + for column_data in child.data: + if re.search(pattern, str(column_data)) is not None: + self.rows.append(child.row) + break + else: + for child in self.root.child_items: + for column_data in child.data: + if self.value in str(column_data): + self.rows.append(child.row) + break + + def FindValue(self): + self.pos = 0 + if self.last_value != self.value or self.pattern != self.last_pattern: + self.FindSelect() + if not len(self.rows): + return -1 + return self.rows[self.pos] + + def FindThread(self): + if self.direction == 0 or self.value != self.last_value or self.pattern != self.last_pattern: + row = self.FindValue() + elif len(self.rows): + if self.direction > 0: + self.pos += 1 + if self.pos >= len(self.rows): + self.pos = 0 + else: + self.pos -= 1 + if self.pos < 0: + self.pos = len(self.rows) - 1 + row = self.rows[self.pos] + else: + row = -1 + return (True, row) + + def Find(self, value, direction, pattern, _context, callback): + self.value, self.direction, self.pattern, self.last_value, self.last_pattern = (value, direction,pattern, self.value, self.pattern) + # Use a thread so the UI is not blocked + thread = Thread(self.FindThread) + thread.done.connect(lambda row, t=thread, c=callback: self.FindDone(t, c, row), Qt.QueuedConnection) + thread.start() + + def FindDone(self, _thread, callback, row): + callback(row) + +# Number of database records to fetch in one go + +glb_chunk_sz = 10000 + +# Background process for SQL data fetcher + +class SQLFetcherProcess(): + + def __init__(self, dbref, sql, buffer, head, tail, fetch_count, fetching_done, process_target, wait_event, fetched_event, prep): + # Need a unique connection name + conn_name = "SQLFetcher" + str(os.getpid()) + self.db, _dbname = dbref.Open(conn_name) + self.sql = sql + self.buffer = buffer + self.head = head + self.tail = tail + self.fetch_count = fetch_count + self.fetching_done = fetching_done + self.process_target = process_target + self.wait_event = wait_event + self.fetched_event = fetched_event + self.prep = prep + self.query = QSqlQuery(self.db) + self.query_limit = 0 if "$$last_id$$" in sql else 2 + self.last_id = -1 + self.fetched = 0 + self.more = True + self.local_head = self.head.value + self.local_tail = self.tail.value + + def Select(self): + if self.query_limit: + if self.query_limit == 1: + return + self.query_limit -= 1 + stmt = self.sql.replace("$$last_id$$", str(self.last_id)) + QueryExec(self.query, stmt) + + def Next(self): + if not self.query.next(): + self.Select() + if not self.query.next(): + return None + self.last_id = self.query.value(0) + return self.prep(self.query) + + def WaitForTarget(self): + while True: + self.wait_event.clear() + target = self.process_target.value + if target > self.fetched or target < 0: + break + self.wait_event.wait() + return target + + def HasSpace(self, sz): + if self.local_tail <= self.local_head: + space = len(self.buffer) - self.local_head + if space > sz: + return True + if space >= glb_nsz: + # Use 0 (or space < glb_nsz) to mean there is no more at the top of the buffer + nd = pickle.dumps(0, pickle.HIGHEST_PROTOCOL) + self.buffer[self.local_head : self.local_head + len(nd)] = nd + self.local_head = 0 + if self.local_tail - self.local_head > sz: + return True + return False + + def WaitForSpace(self, sz): + if self.HasSpace(sz): + return + while True: + self.wait_event.clear() + self.local_tail = self.tail.value + if self.HasSpace(sz): + return + self.wait_event.wait() + + def AddToBuffer(self, obj): + d = pickle.dumps(obj, pickle.HIGHEST_PROTOCOL) + n = len(d) + nd = pickle.dumps(n, pickle.HIGHEST_PROTOCOL) + sz = n + glb_nsz + self.WaitForSpace(sz) + pos = self.local_head + self.buffer[pos : pos + len(nd)] = nd + self.buffer[pos + glb_nsz : pos + sz] = d + self.local_head += sz + + def FetchBatch(self, batch_size): + fetched = 0 + while batch_size > fetched: + obj = self.Next() + if obj is None: + self.more = False + break + self.AddToBuffer(obj) + fetched += 1 + if fetched: + self.fetched += fetched + with self.fetch_count.get_lock(): + self.fetch_count.value += fetched + self.head.value = self.local_head + self.fetched_event.set() + + def Run(self): + while self.more: + target = self.WaitForTarget() + if target < 0: + break + batch_size = min(glb_chunk_sz, target - self.fetched) + self.FetchBatch(batch_size) + self.fetching_done.value = True + self.fetched_event.set() + +def SQLFetcherFn(*x): + process = SQLFetcherProcess(*x) + process.Run() + +# SQL data fetcher + +class SQLFetcher(QObject): + + done = Signal(object) + + def __init__(self, glb, sql, prep, process_data, parent=None): + super(SQLFetcher, self).__init__(parent) + self.process_data = process_data + self.more = True + self.target = 0 + self.last_target = 0 + self.fetched = 0 + self.buffer_size = 16 * 1024 * 1024 + self.buffer = Array(c_char, self.buffer_size, lock=False) + self.head = Value(c_longlong) + self.tail = Value(c_longlong) + self.local_tail = 0 + self.fetch_count = Value(c_longlong) + self.fetching_done = Value(c_bool) + self.last_count = 0 + self.process_target = Value(c_longlong) + self.wait_event = Event() + self.fetched_event = Event() + glb.AddInstanceToShutdownOnExit(self) + self.process = Process(target=SQLFetcherFn, args=(glb.dbref, sql, self.buffer, self.head, self.tail, self.fetch_count, self.fetching_done, self.process_target, self.wait_event, self.fetched_event, prep)) + self.process.start() + self.thread = Thread(self.Thread) + self.thread.done.connect(self.ProcessData, Qt.QueuedConnection) + self.thread.start() + + def Shutdown(self): + # Tell the thread and process to exit + self.process_target.value = -1 + self.wait_event.set() + self.more = False + self.fetching_done.value = True + self.fetched_event.set() + + def Thread(self): + if not self.more: + return True, 0 + while True: + self.fetched_event.clear() + fetch_count = self.fetch_count.value + if fetch_count != self.last_count: + break + if self.fetching_done.value: + self.more = False + return True, 0 + self.fetched_event.wait() + count = fetch_count - self.last_count + self.last_count = fetch_count + self.fetched += count + return False, count + + def Fetch(self, nr): + if not self.more: + # -1 inidcates there are no more + return -1 + result = self.fetched + extra = result + nr - self.target + if extra > 0: + self.target += extra + # process_target < 0 indicates shutting down + if self.process_target.value >= 0: + self.process_target.value = self.target + self.wait_event.set() + return result + + def RemoveFromBuffer(self): + pos = self.local_tail + if len(self.buffer) - pos < glb_nsz: + pos = 0 + n = pickle.loads(self.buffer[pos : pos + glb_nsz]) + if n == 0: + pos = 0 + n = pickle.loads(self.buffer[0 : glb_nsz]) + pos += glb_nsz + obj = pickle.loads(self.buffer[pos : pos + n]) + self.local_tail = pos + n + return obj + + def ProcessData(self, count): + for _i in range(count): + obj = self.RemoveFromBuffer() + self.process_data(obj) + self.tail.value = self.local_tail + self.wait_event.set() + self.done.emit(count) + +# Fetch more records bar + +class FetchMoreRecordsBar(): + + def __init__(self, model, parent): + self.model = model + + self.label = QLabel("Number of records (x " + "{:,}".format(glb_chunk_sz) + ") to fetch:") + self.label.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.fetch_count = QSpinBox() + self.fetch_count.setRange(1, 1000000) + self.fetch_count.setValue(10) + self.fetch_count.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.fetch = QPushButton("Go!") + self.fetch.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + self.fetch.released.connect(self.FetchMoreRecords) + + self.progress = QProgressBar() + self.progress.setRange(0, 100) + self.progress.hide() + + self.done_label = QLabel("All records fetched") + self.done_label.hide() + + self.spacer = QLabel("") + + self.close_button = QToolButton() + self.close_button.setIcon(parent.style().standardIcon(QStyle.SP_DockWidgetCloseButton)) + self.close_button.released.connect(self.Deactivate) + + self.hbox = QHBoxLayout() + self.hbox.setContentsMargins(0, 0, 0, 0) + + self.hbox.addWidget(self.label) + self.hbox.addWidget(self.fetch_count) + self.hbox.addWidget(self.fetch) + self.hbox.addWidget(self.spacer) + self.hbox.addWidget(self.progress) + self.hbox.addWidget(self.done_label) + self.hbox.addWidget(self.close_button) + + self.bar = QWidget() + self.bar.setLayout(self.hbox) + self.bar.show() + + self.in_progress = False + self.start = 0 + self.model.progress.connect(self.Progress) + + self.done = False + + if not model.HasMoreRecords(): + self.Done() + + def Widget(self): + return self.bar + + def Activate(self): + self.bar.show() + self.fetch.setFocus() + + def Deactivate(self): + self.bar.hide() + + def Enable(self, enable): + self.fetch.setEnabled(enable) + self.fetch_count.setEnabled(enable) + + def Busy(self): + self.Enable(False) + self.fetch.hide() + self.spacer.hide() + self.progress.show() + + def Idle(self): + self.in_progress = False + self.Enable(True) + self.progress.hide() + self.fetch.show() + self.spacer.show() + + def Target(self): + return self.fetch_count.value() * glb_chunk_sz + + def Done(self): + self.done = True + self.Idle() + self.label.hide() + self.fetch_count.hide() + self.fetch.hide() + self.spacer.hide() + self.done_label.show() + + def Progress(self, count): + if self.in_progress: + if count: + percent = ((count - self.start) * 100) / self.Target() + if percent >= 100: + self.Idle() + else: + self.progress.setValue(percent) + if not count: + # Count value of zero means no more records + self.Done() + + def FetchMoreRecords(self): + if self.done: + return + self.progress.setValue(0) + self.Busy() + self.in_progress = True + self.start = self.model.FetchMoreRecords(self.Target()) + +# Brance data model level two item + +class BranchLevelTwoItem(): + + def __init__(self, row, col, text, parent_item): + self.row = row + self.parent_item = parent_item + self.data = [""] * (col + 1) + self.data[col] = text + self.level = 2 + + def getParentItem(self): + return self.parent_item + + def getRow(self): + return self.row + + def childCount(self): + return 0 + + def hasChildren(self): + return False + + def getData(self, column): + return self.data[column] + +# Brance data model level one item + +class BranchLevelOneItem(): + + def __init__(self, glb, row, data, parent_item): + self.glb = glb + self.row = row + self.parent_item = parent_item + self.child_count = 0 + self.child_items = [] + self.data = data[1:] + self.dbid = data[0] + self.level = 1 + self.query_done = False + self.br_col = len(self.data) - 1 + + def getChildItem(self, row): + return self.child_items[row] + + def getParentItem(self): + return self.parent_item + + def getRow(self): + return self.row + + def Select(self): + self.query_done = True + + if not self.glb.have_disassembler: + return + + query = QSqlQuery(self.glb.db) + + QueryExec(query, "SELECT cpu, to_dso_id, to_symbol_id, to_sym_offset, short_name, long_name, build_id, sym_start, to_ip" + " FROM samples" + " INNER JOIN dsos ON samples.to_dso_id = dsos.id" + " INNER JOIN symbols ON samples.to_symbol_id = symbols.id" + " WHERE samples.id = " + str(self.dbid))
Lines of this file are not shown. View the raw message.
tools/perf/scripts/python/exported-sql-viewer.py deleted +0 -5030
5,030 lines not on this page · raw message
The rest of this diff is not shown. View the raw message.
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
Part of the diff is not shown here. View the raw message.
Ian Rogers
reviewerPATCH v4 45/49 perf python: Move and clean up parallel-perf.py
In reply to Ian RogersMove parallel-perf.py from tools/perf/scripts/python/ to tools/perf/python/ as it is a standalone Python utility that invokes 'perf script' in parallel across time slices and CPUs. Update tools/perf/tests/shell/script.sh accordingly.
Also fix bugs and clean up the script to pass mypy and pylint without suppression comments:
- Fix Work.command() to return the shlex.quote()-escaped command string (previously sh_cmd was computed with shlex.quote() and discarded in favor of unquoted self.cmd).
- Close self.popen.stdout in the parent process after spawning the consumer subprocess in Work.start() when --pipe-to is used, ensuring the producer receives SIGPIPE if the consumer exits early and avoiding leaking the pipe file descriptor.
- Convert method and function names to snake_case, specify utf-8 file encodings, and add type annotations and docstrings.
--- tools/perf/python/parallel-perf.py | 1250 ++++++++++++++++++++ tools/perf/scripts/python/parallel-perf.py | 989 ---------------- tools/perf/tests/shell/script.sh | 4 +- 3 files changed, 1252 insertions(+), 991 deletions(-) create mode 100755 tools/perf/python/parallel-perf.py delete mode 100755 tools/perf/scripts/python/parallel-perf.py
tools/perf/python/parallel-perf.py new file +1250 -0
@@ -0,0 +1,1250 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +"""Parallel perf script.""" +# +# run a perf script command multiple times in parallel, using perf script +# options --cpu and --time so that each job processes a different chunk +# of the data. +# +# Copyright (c) 2024, Intel Corporation. + +import subprocess +import argparse +import pathlib +import shlex +import time +from typing import Any +import copy +import sys +import os +import re + +glb_prog_name = "parallel-perf.py" +glb_min_interval = 10.0 +glb_min_samples = 64 + + +class Verbosity(): + + def __init__(self, quiet: bool = False, verbose: bool = False, + debug: bool = False) -> None: + """__init__.""" + + self.normal = True + self.verbose = verbose + self.debug = debug + self.self_test = True + if self.debug: + self.verbose = True + if self.verbose: + quiet = False + if quiet: + self.normal = False + +# Manage work (start/wait/kill), as represented by a subprocess.Popen command + + +class Work(): + + def __init__(self, cmd: list[str], pipe_to: str, + output_dir: str = ".") -> None: + """__init__.""" + + self.popen: Any = None + self.consumer: Any = None + self.cmd = cmd + self.pipe_to = pipe_to + self.output_dir = output_dir + self.cmdout_name = f"{output_dir}/cmd.txt" + self.stdout_name = f"{output_dir}/out.txt" + self.stderr_name = f"{output_dir}/err.txt" + + def command(self): + """command.""" + + return " ".join(shlex.quote(x) for x in self.cmd) + + def stdout(self): + """stdout.""" + + return open(self.stdout_name, "w", encoding="utf-8") + + def stderr(self): + """stderr.""" + + return open(self.stderr_name, "w", encoding="utf-8") + + def create_output_dir(self): + """create_output_dir.""" + + pathlib.Path(self.output_dir).mkdir(parents=True, exist_ok=True) + + def start(self): + """start.""" + + if self.popen: + return + self.create_output_dir() + with open(self.cmdout_name, "w", encoding="utf-8") as f: + f.write(self.command()) + f.write("\n") + stdout = self.stdout() + stderr = self.stderr() + if self.pipe_to: + self.popen = subprocess.Popen( + self.cmd, stdout=subprocess.PIPE, stderr=stderr) + args = shlex.split(self.pipe_to) + self.consumer = subprocess.Popen( + args, stdin=self.popen.stdout, stdout=stdout, stderr=stderr) + # The consumer now owns the read end of the pipe. Close this + # process's copy so that the producer receives SIGPIPE if the + # consumer exits early, and so that the descriptor isn't leaked + # for the lifetime of this Work. + self.popen.stdout.close() + self.popen.stdout = None + else: + self.popen = subprocess.Popen( + self.cmd, stdout=stdout, stderr=stderr) + + def remove_empty_err_file(self): + """remove_empty_err_file.""" + + if os.path.exists(self.stderr_name): + if os.path.getsize(self.stderr_name) == 0: + os.unlink(self.stderr_name) + + def errors(self): + """errors.""" + + if os.path.exists(self.stderr_name): + if os.path.getsize(self.stderr_name) != 0: + return [f"Non-empty error file {self.stderr_name}"] + return [] + + def tidy_up(self): + """tidy_up.""" + + self.remove_empty_err_file() + + def raw_poll_wait(self, p, wait): + """raw_poll_wait.""" + + if wait: + return p.wait() + return p.poll() + + def poll(self, wait=False): + """poll.""" + + if not self.popen: + return None + result = self.raw_poll_wait(self.popen, wait) + if self.consumer: + res = result + result = self.raw_poll_wait(self.consumer, wait) + if result is not None and res is None: + self.popen.kill() + result = None + elif result == 0 and res is not None and res != 0: + result = res + if result is not None: + self.tidy_up() + return result + + def wait(self): + """wait.""" + + return self.poll(wait=True) + + def kill(self): + """kill.""" + + if not self.popen: + return + self.popen.kill() + if self.consumer: + self.consumer.kill() + + +def kill_work(worklist, _verbosity): + """kill_work.""" + + for w in worklist: + w.kill() + for w in worklist: + w.wait() + + +def number_of_cp_us(): + """number_of_cp_us.""" + + return os.sysconf("SC_NPROCESSORS_ONLN") + + +def nano_secs_to_secs_str(x): + """nano_secs_to_secs_str.""" + + if x is None: + return "" + x = str(x) + if len(x) < 10: + x = "0" * (10 - len(x)) + x + return x[:len(x) - 9] + "." + x[-9:] + + +def insert_option_after(cmd, option, after): + """insert_option_after.""" + + try: + pos = cmd.index(after) + cmd.insert(pos + 1, option) + except (OSError, ValueError, RuntimeError): + cmd.append(option) + + +def create_work_list(cmd, pipe_to, output_dir, cpus, time_ranges_by_cpu): + """create_work_list.""" + + max_len = len(str(cpus[-1])) + cpu_dir_fmt = f"cpu-%.{max_len}u" + worklist = [] + pos = 0 + for cpu in cpus: + if cpu >= 0: + cpu_dir = os.path.join(output_dir, cpu_dir_fmt % cpu) + cpu_option = f"--cpu={cpu}" + else: + cpu_dir = output_dir + cpu_option = None + + tr_dir_fmt = "time-range" + + if len(time_ranges_by_cpu) > 1: + time_ranges = time_ranges_by_cpu[pos] + tr_dir_fmt += f"-{pos}" + pos += 1 + else: + time_ranges = time_ranges_by_cpu[0] + + max_len = len(str(len(time_ranges))) + tr_dir_fmt += f"-%.{max_len}u" + + i = 0 + for r in time_ranges: + if r == [None, None]: + time_option = None + work_output_dir = cpu_dir + else: + time_option = "--time=" + \ + nano_secs_to_secs_str(r[0]) + "," + \ + nano_secs_to_secs_str(r[1]) + work_output_dir = os.path.join(cpu_dir, tr_dir_fmt % i) + i += 1 + work_cmd = list(cmd) + if time_option is not None: + insert_option_after(work_cmd, time_option, "script") + if cpu_option is not None: + insert_option_after(work_cmd, cpu_option, "script") + w = Work(work_cmd, pipe_to, work_output_dir) + worklist.append(w) + return worklist + + +def do_run_work(worklist: list[Work], nr_jobs: int, + _verbosity: Verbosity) -> bool: + """do_run_work.""" + + nr_to_do = len(worklist) + not_started = list(worklist) + running: list[Work] = [] + done: list[Work] = [] + chg = False + while True: + nr_done = len(done) + if chg and _verbosity.normal: + nr_run = len(running) + print( + f"\rThere are {nr_to_do} jobs: {nr_done} completed, {nr_run} running", + flush=True, end=" ") + if _verbosity.verbose: + print() + chg = False + if nr_done == nr_to_do: + break + while len(running) < nr_jobs and len(not_started): + w = not_started.pop(0) + running.append(w) + if _verbosity.verbose: + print("Starting:", w.command()) + w.start() + chg = True + if len(running): + time.sleep(0.1) + finished: list[Work] = [] + not_finished: list[Work] = [] + while len(running): + w = running.pop(0) + r = w.poll() + if r is None: + not_finished.append(w) + continue + if r == 0: + if _verbosity.verbose: + print("Finished:", w.command()) + finished.append(w) + chg = True + continue + if _verbosity.normal and not _verbosity.verbose: + print() + print("Job failed!\n return code:", r, + "\n command: ", w.command()) + if w.pipe_to: + print(" piped to: ", w.pipe_to) + print("Killing outstanding jobs") + kill_work(not_finished, _verbosity) + kill_work(running, _verbosity) + return False + running = not_finished + done += finished + errorlist: list[str] = [] + for w in worklist: + errorlist += w.errors() + if len(errorlist): + print("errors:") + for e in errorlist: + print(e) + elif _verbosity.normal: + print("\r", " "*50, "\rAll jobs finished successfully", flush=True) + return True + + +def run_work(worklist: list[Work], nr_jobs: int = number_of_cp_us(), + _verbosity: Verbosity = Verbosity()) -> bool: + """run_work.""" + try: + return do_run_work(worklist, nr_jobs, _verbosity) + except BaseException: + for w in worklist: + w.kill() + raise + + +def read_header(perf, file_name): + """read_header.""" + + cmd = [perf, "script", "--header-only", "--input", file_name] + with subprocess.Popen(cmd, stdout=subprocess.PIPE) as proc: + out = proc.stdout.read() if proc.stdout else b"" + return out.decode("utf-8") + + +def parse_header(hdr): + """parse_header.""" + + result = {} + lines = hdr.split("\n") + for line in lines: + if ":" in line and line[0] == "#": + pos = line.index(":") + name = line[1:pos-1].strip() + value = line[pos+1:].strip() + if name in result: + orig_name = name + nr = 2 + while True: + name = f"{orig_name} {nr}" + if name not in result: + break + nr += 1 + result[name] = value + return result + + +def header_field(hdr_dict, hdr_fld): + """header_field.""" + + if hdr_fld not in hdr_dict: + raise RuntimeError(f"'{hdr_fld}' missing from header information") + return hdr_dict[hdr_fld] + +# Represent the position of an option within a command string +# and provide the option value and/or remove the option + + +class OptPos(): + + def init(self, opt_element=-1, value_element=-1, opt_pos=-1, value_pos=-1, error=None): + """init.""" + + self.opt_element = opt_element # list element that contains option + self.value_element = value_element # list element that contains option value + self.opt_pos = opt_pos # string position of option + self.value_pos = value_pos # string position of value + self.error = error # error message string + + def __init__(self, args, short_name, long_name, default=None): + """__init__.""" + + self.args = list(args) + self.default = default + n = 2 + len(long_name) + m = len(short_name) + pos = -1 + for opt in args: + pos += 1 + if m and opt[:2] == f"-{short_name}": + if len(opt) == 2: + if pos + 1 < len(args): + self.init(pos, pos + 1, 0, 0) + else: + self.init(error=f"-{short_name} option missing value") + else: + self.init(pos, pos, 0, 2) + return + if opt[:n] == f"--{long_name}": + if len(opt) == n: + if pos + 1 < len(args): + self.init(pos, pos + 1, 0, 0) + else: + self.init(error=f"--{long_name} option missing value") + elif opt[n] == "=": + self.init(pos, pos, 0, n + 1) + else: + self.init(error=f"--{long_name} option expected '='") + return + if m and opt[:1] == "-" and opt[:2] != "--" and short_name in opt: + ipos = opt.index(short_name) + if "-" in opt[1:]: + hpos = opt[1:].index("-") + if hpos < ipos: + continue + if ipos + 1 == len(opt): + if pos + 1 < len(args): + self.init(pos, pos + 1, ipos, 0) + else: + self.init(error=f"-{short_name} option missing value") + else: + self.init(pos, pos, ipos, ipos + 1) + return + self.init() + + def value(self): + """value.""" + + if self.opt_element >= 0: + if self.opt_element != self.value_element: + return self.args[self.value_element] + else: + return self.args[self.value_element][self.value_pos:] + return self.default + + def remove(self, args): + """remove.""" + + if self.opt_element == -1: + return + if self.opt_element != self.value_element: + del args[self.value_element] + if self.opt_pos: + args[self.opt_element] = args[self.opt_element][:self.opt_pos] + else: + del args[self.opt_element] + + +def determine_input_file_name(cmd): + """determine_input_file_name.""" + + p = OptPos(cmd, "i", "input", "perf.data") + if p.error: + raise RuntimeError(f"perf command {p.error}") + file_name = p.value() + if not os.path.exists(file_name): + raise RuntimeError(f"perf command input file '{file_name}' not found") + return file_name + + +def read_option(args, short_name, long_name, err_prefix, remove=False): + """read_option.""" + + p = OptPos(args, short_name, long_name) + if p.error: + raise RuntimeError(f"{err_prefix}{p.error}") + value = p.value() + if remove: + p.remove(args) + return value + + +def extract_option(args, short_name, long_name, err_prefix): + """extract_option.""" + + return read_option(args, short_name, long_name, err_prefix, True) + + +def read_perf_option(args, short_name, long_name): + """read_perf_option.""" + + return read_option(args, short_name, long_name, "perf command ") + + +def extract_perf_option(args, short_name, long_name): + """extract_perf_option.""" + + return extract_option(args, short_name, long_name, "perf command ") + + +def perf_double_quick_commands(cmd, file_name): + """perf_double_quick_commands.""" + + cpu_str = read_perf_option(cmd, "C", "cpu") + time_str = read_perf_option(cmd, "", "time") + # Use double-quick sampling to determine trace data density + times_cmd = ["perf", "script", "--ns", + "--input", file_name, "--itrace=qqi"] + if cpu_str is not None and cpu_str != "": + times_cmd.append(f"--cpu={cpu_str}") + if time_str is not None and time_str != "": + times_cmd.append(f"--time={time_str}") + cnts_cmd = list(times_cmd) + cnts_cmd.append("-Fcpu") + times_cmd.append("-Fcpu,time") + return cnts_cmd, times_cmd + + +class CPUTimeRange(): + def __init__(self, cpu): + """__init__.""" + + self.cpu = cpu + self.sample_cnt = 0 + self.time_ranges = None + self.interval = 0 + self.interval_remaining = 0 + self.remaining = 0 + self.tr_pos = 0 + + +def calc_time_ranges_by_cpu(line, cpu, cpu_time_ranges, max_time): + """calc_time_ranges_by_cpu.""" + + cpu_time_range = cpu_time_ranges[cpu] + cpu_time_range.remaining -= 1 + cpu_time_range.interval_remaining -= 1 + if cpu_time_range.remaining == 0: + cpu_time_range.time_ranges[cpu_time_range.tr_pos][1] = max_time + return + if cpu_time_range.interval_remaining == 0: + ts = time_val(line[1][:-1], 0) + time_ranges = cpu_time_range.time_ranges + time_ranges[cpu_time_range.tr_pos][1] = ts - 1 + time_ranges.append([ts, max_time]) + cpu_time_range.tr_pos += 1 + cpu_time_range.interval_remaining = cpu_time_range.interval + + +def count_samples_by_cpu(_line: list[str], cpu: int, + cpu_time_ranges: list[Any]) -> None: + """count_samples_by_cpu.""" + + try: + cpu_time_ranges[cpu].sample_cnt += 1 + except (OSError, ValueError, RuntimeError, IndexError): + print("exception") + print("cpu", cpu) + print("len(cpu_time_ranges)", len(cpu_time_ranges)) + raise + + +def process_command_output_lines(cmd, per_cpu, fn, *x): + """process_command_output_lines.""" + + # Assume CPU number is at beginning of line and enclosed by [] + pat = re.compile(r"\s*\[[0-9]+\]") + p = subprocess.Popen(cmd, stdout=subprocess.PIPE) + while True: + line = p.stdout.readline() + if line: + line = line.decode("utf-8") + if pat.match(line): + line = line.split() + if per_cpu: + # Assumes CPU number is enclosed by [] + cpu = int(line[0][1:-1]) + else: + cpu = 0 + fn(line, cpu, *x) + else: + break + p.wait() + + +def intersect_time_ranges(new_time_ranges, time_ranges): + """intersect_time_ranges.""" + + pos = 0 + new_pos = 0 + # Can assume len(time_ranges) != 0 and len(new_time_ranges) != 0 + # Note also, there *must* be at least one intersection. + while pos < len(time_ranges) and new_pos < len(new_time_ranges): + # new end < old start => no intersection, remove new + if new_time_ranges[new_pos][1] < time_ranges[pos][0]: + del new_time_ranges[new_pos] + continue + # new start > old end => no intersection, check next + if new_time_ranges[new_pos][0] > time_ranges[pos][1]: + pos += 1 + if pos < len(time_ranges): + continue + # no next, so remove remaining + while new_pos < len(new_time_ranges): + del new_time_ranges[new_pos] + return + # Found an intersection + # new start < old start => adjust new start = old start + if new_time_ranges[new_pos][0] < time_ranges[pos][0]: + new_time_ranges[new_pos][0] = time_ranges[pos][0] + # new end > old end => keep the overlap, insert the remainder + if new_time_ranges[new_pos][1] > time_ranges[pos][1]: + r = [time_ranges[pos][1] + 1, new_time_ranges[new_pos][1]] + new_time_ranges[new_pos][1] = time_ranges[pos][1] + new_pos += 1 + new_time_ranges.insert(new_pos, r) + continue + # new [start, end] is within old [start, end] + new_pos += 1 + + +def split_time_ranges_by_trace_data_density( + time_ranges, cpus, nr, cmd, file_name, per_cpu, min_size, min_interval, _verbosity +): + """split_time_ranges_by_trace_data_density.""" + + if _verbosity.normal: + print("\rAnalyzing...", flush=True, end=" ") + if _verbosity.verbose: + print() + cnts_cmd, times_cmd = perf_double_quick_commands(cmd, file_name) + + nr_cpus = cpus[-1] + 1 if per_cpu else 1 + if per_cpu: + nr_cpus = cpus[-1] + 1 + cpu_time_ranges = [CPUTimeRange(cpu) for cpu in range(nr_cpus)] + else: + nr_cpus = 1 + cpu_time_ranges = [CPUTimeRange(-1)] + + if _verbosity.debug: + print("nr_cpus", nr_cpus) + print("cnts_cmd", cnts_cmd) + print("times_cmd", times_cmd) + + # Count the number of "double quick" samples per CPU + process_command_output_lines( + cnts_cmd, per_cpu, count_samples_by_cpu, cpu_time_ranges) + + tot = 0 + mx = 0 + for cpu_time_range in cpu_time_ranges: + cnt = cpu_time_range.sample_cnt + tot += cnt + if cnt > mx: + mx = cnt + if _verbosity.debug: + print("cpu:", cpu_time_range.cpu, "sample_cnt", cnt) + + if min_size < 1: + min_size = 1 + + if mx < min_size: + # Too little data to be worth splitting + if _verbosity.debug: + print("Too little data to split by time") + if nr == 0: + nr = 1 + return [split_time_ranges_into_n(time_ranges, nr, min_interval)] + + if nr: + divisor = nr + min_size = 1 + else: + divisor = number_of_cp_us() + + interval = int(round(tot / divisor, 0)) + if interval < min_size: + interval = min_size + + if _verbosity.debug: + print("divisor", divisor) + print("min_size", min_size) + print("interval", interval) + + min_time = time_ranges[0][0] + max_time = time_ranges[-1][1] + + for cpu_time_range in cpu_time_ranges: + cnt = cpu_time_range.sample_cnt + if cnt == 0: + cpu_time_range.time_ranges = copy.deepcopy(time_ranges) + continue + # Adjust target interval for CPU to give approximately equal interval sizes + # Determine number of intervals, rounding to nearest integer + n = int(round(cnt / interval, 0)) + if n < 1: + n = 1 + # Determine interval size, rounding up + d, m = divmod(cnt, n) + if m: + d += 1 + cpu_time_range.interval = d + cpu_time_range.interval_remaining = d + cpu_time_range.remaining = cnt + # init. time ranges for each CPU with the start time + cpu_time_range.time_ranges = [[min_time, max_time]] + + # Set time ranges so that the same number of "double quick" samples + # will fall into each time range. + process_command_output_lines( + times_cmd, per_cpu, calc_time_ranges_by_cpu, cpu_time_ranges, max_time) + + for cpu_time_range in cpu_time_ranges: + if cpu_time_range.sample_cnt: + intersect_time_ranges(cpu_time_range.time_ranges, time_ranges) + + return [cpu_time_ranges[cpu].time_ranges for cpu in cpus] + + +def split_single_time_range_into_n(time_range, n): + """split_single_time_range_into_n.""" + + if n <= 1: + return [time_range] + start = time_range[0] + end = time_range[1] + duration = int((end - start + 1) / n) + if duration < 1: + return [time_range] + time_ranges = [] + for _i in range(n): + time_ranges.append([start, start + duration - 1]) + start += duration + time_ranges[-1][1] = end + return time_ranges + + +def time_range_duration(r): + """time_range_duration.""" + + return r[1] - r[0] + 1 + + +def total_duration(time_ranges): + """total_duration.""" + + duration = 0 + for r in time_ranges: + duration += time_range_duration(r) + return duration + + +def split_time_ranges_by_interval(time_ranges, interval): + """split_time_ranges_by_interval.""" + + new_ranges = [] + for r in time_ranges: + duration = time_range_duration(r) + n = duration / interval + n = int(round(n, 0)) + new_ranges += split_single_time_range_into_n(r, n) + return new_ranges + + +def split_time_ranges_into_n(time_ranges, n, min_interval): + """split_time_ranges_into_n.""" + + if n <= len(time_ranges): + return time_ranges + duration = total_duration(time_ranges) + interval = duration / n + if interval < min_interval: + interval = min_interval + return split_time_ranges_by_interval(time_ranges, interval) + + +def recombine_time_ranges(tr): + """recombine_time_ranges.""" + + new_tr = copy.deepcopy(tr) + i = 1 + while i < len(new_tr): + # if prev end + 1 == cur start, combine them + if new_tr[i - 1][1] + 1 == new_tr[i][0]: + new_tr[i][0] = new_tr[i - 1][0] + del new_tr[i - 1] + else: + i += 1 + return new_tr + + +def open_time_range_ends(time_ranges, min_time, max_time): + """open_time_range_ends.""" + + if time_ranges[0][0] <= min_time: + time_ranges[0][0] = None + if time_ranges[-1][1] >= max_time: + time_ranges[-1][1] = None + + +def bad_time_str(time_str): + """bad_time_str.""" + + raise RuntimeError( + f"perf command bad time option: '{time_str}'\n" + "Check also 'time of first sample' and 'time of last sample' " + "in perf script --header-only" + ) + + +def validate_time_ranges(time_ranges, time_str): + """validate_time_ranges.""" + + n = len(time_ranges) + for i in range(n): + start = time_ranges[i][0] + end = time_ranges[i][1] + if i != 0 and start <= time_ranges[i - 1][1]: + bad_time_str(time_str) + if start > end: + bad_time_str(time_str) + + +def time_val(s, dflt): + """time_val.""" + + s = s.strip() + if s == "": + return dflt + a = s.split(".") + if len(a) > 2: + raise RuntimeError(f"Bad time value'{s}'") + x = int(a[0]) + if x < 0: + raise RuntimeError("Negative time not allowed") + x *= 1000000000 + if len(a) > 1: + x += int((a[1] + "000000000")[:9]) + return x + + +def bad_cpu_str(cpu_str): + """bad_cpu_str.""" + + raise RuntimeError( + f"perf command bad cpu option: '{cpu_str}'\n" + "Check also 'nrcpus avail' in perf script --header-only" + ) + + +def parse_time_str(time_str, min_time, max_time): + """parse_time_str.""" + + if time_str is None or time_str == "": + return [[min_time, max_time]] + time_ranges = [] + for r in time_str.split(): + a = r.split(",") + if len(a) != 2: + bad_time_str(time_str) + try: + start = time_val(a[0], min_time) + end = time_val(a[1], max_time) + except (OSError, ValueError, RuntimeError): + bad_time_str(time_str) + time_ranges.append([start, end]) + validate_time_ranges(time_ranges, time_str) + return time_ranges + + +def parse_cpu_str(cpu_str, nr_cpus): + """parse_cpu_str.""" + + if cpu_str is None or cpu_str == "": + return [-1] + cpus = [] + for r in cpu_str.split(","): + a = r.split("-") + if len(a) < 1 or len(a) > 2: + bad_cpu_str(cpu_str) + try: + start = int(a[0].strip()) + if len(a) > 1: + end = int(a[1].strip()) + else: + end = start + except (OSError, ValueError, RuntimeError): + bad_cpu_str(cpu_str) + if start < 0 or end < 0 or end < start or end >= nr_cpus: + bad_cpu_str(cpu_str) + cpus.extend(range(start, end + 1)) + cpus = list(set(cpus)) # remove duplicates + cpus.sort() + return cpus + + +class ParallelPerf(): + + def __init__(self, a): + """init.""" + self.nr = 0 + self.jobs = 0 + self.file_name = None + self.hdr = None + self.hdr_dict = None + self.cmd_line = None + self.min_time = None + self.max_time = None + self.time_str = None + self.time_ranges = None + self.cpu_str = None + self.cpus = None + self.split_time_ranges_for_each_cpu = None + self.worklist = None + self.per_cpu = None + self.interval = None + self.min_size = None + self.min_interval = None + self.pipe_to = None + self.output_dir = None + self.cmd = getattr(a, 'cmd', None) + self.no_per_cpu = getattr(a, 'no_per_cpu', False) + self.dry_run = getattr(a, 'dry_run', False) + self._verbosity = getattr(a, "_verbosity", Verbosity()) + + for arg_name in vars(a): + setattr(self, arg_name, getattr(a, arg_name)) + self.orig_nr = self.nr + self.orig_cmd = list(self.cmd) + self.perf = self.cmd[0] + if os.path.exists(self.output_dir): + raise RuntimeError(f"Output '{self.output_dir}' already exists") + if self.jobs < 0 or self.nr < 0 or self.interval < 0: + raise RuntimeError( + "Bad options (negative values): try -h option for help") + if self.nr != 0 and self.interval != 0: + raise RuntimeError( + "Cannot specify number of time subdivisions and time interval") + if self.jobs == 0: + self.jobs = number_of_cp_us() + if self.nr == 0 and self.interval == 0: + if self.per_cpu: + self.nr = 1 + else: + self.nr = self.jobs + + def init(self): + """init.""" + + if self._verbosity.debug: + print("cmd", self.cmd) + self.file_name = determine_input_file_name(self.cmd) + self.hdr = read_header(self.perf, self.file_name) + self.hdr_dict = parse_header(self.hdr) + self.cmd_line = header_field(self.hdr_dict, "cmdline") + + def extract_time_info(self): + """extract_time_info.""" + + self.min_time = time_val(header_field( + self.hdr_dict, "time of first sample"), 0) + self.max_time = time_val(header_field( + self.hdr_dict, "time of last sample"), 0) + self.time_str = extract_perf_option(self.cmd, "", "time") + self.time_ranges = parse_time_str( + self.time_str, self.min_time, self.max_time) + if self._verbosity.debug: + print("time_ranges", self.time_ranges) + + def extract_cpu_info(self): + """extract_cpu_info.""" + + if self.per_cpu: + nr_cpus = int(header_field(self.hdr_dict, "nrcpus avail")) + self.cpu_str = extract_perf_option(self.cmd, "C", "cpu") + if self.cpu_str is None or self.cpu_str == "": + self.cpus = [x for x in range(nr_cpus)] + else: + self.cpus = parse_cpu_str(self.cpu_str, nr_cpus) + else: + self.cpu_str = None + self.cpus = [-1] + if self._verbosity.debug: + print("cpus", self.cpus) + + def is_intel_pt(self): + """is_intel_pt.""" + + return self.cmd_line.find("intel_pt") >= 0 + + def split_time_ranges(self): + """split_time_ranges.""" + + if self.is_intel_pt() and self.interval == 0: + self.split_time_ranges_for_each_cpu = ( + split_time_ranges_by_trace_data_density( + self.time_ranges, self.cpus, self.orig_nr, + self.orig_cmd, self.file_name, self.per_cpu, + self.min_size, self.min_interval, self._verbosity + ) + ) + elif self.nr: + self.split_time_ranges_for_each_cpu = [split_time_ranges_into_n( + self.time_ranges, self.nr, self.min_interval)] + else: + self.split_time_ranges_for_each_cpu = [ + split_time_ranges_by_interval(self.time_ranges, self.interval)] + + def check_time_ranges(self): + """check_time_ranges.""" + + for tr in self.split_time_ranges_for_each_cpu: + # Re-combined time ranges should be the same + new_tr = recombine_time_ranges(tr) + if new_tr != self.time_ranges: + if self._verbosity.debug: + print("tr", tr) + print("new_tr", new_tr) + raise RuntimeError("Self test failed!") + + def open_time_range_ends(self): + """open_time_range_ends.""" + + for time_ranges in self.split_time_ranges_for_each_cpu: + open_time_range_ends(time_ranges, self.min_time, self.max_time) + + def create_work_list(self): + """create_work_list.""" + + self.worklist = create_work_list( + self.cmd, self.pipe_to, self.output_dir, self.cpus, self.split_time_ranges_for_each_cpu) + + def perf_data_recorded_per_cpu(self): + """perf_data_recorded_per_cpu.""" + + if "--per-thread" in self.cmd_line.split(): + return False + return True + + def default_to_per_cpu(self): + """default_to_per_cpu.""" + + # --no-per-cpu option takes precedence + if self.no_per_cpu: + return False + if not self.perf_data_recorded_per_cpu(): + return False + # Default to per-cpu for Intel PT data that was recorded per-cpu, + # because decoding can be done for each CPU separately. + if self.is_intel_pt(): + return True + return False + + def config(self): + """config.""" + + self.init() + self.extract_time_info() + if not self.per_cpu: + self.per_cpu = self.default_to_per_cpu() + if self._verbosity.debug: + print("per_cpu", self.per_cpu) + self.extract_cpu_info() + self.split_time_ranges() + if self._verbosity.self_test: + self.check_time_ranges() + # Prefer open-ended time range to starting / ending with min_time / max_time resp. + self.open_time_range_ends() + self.create_work_list() + + def run(self): + """run.""" + + if self.dry_run: + print(len(self.worklist), "jobs:") + for w in self.worklist: + print(w.command()) + return True + result = run_work(self.worklist, self.jobs, _verbosity=self._verbosity) + if self._verbosity.verbose: + print(glb_prog_name, "done") + return result + + +def run_parallel_perf(a): + """run_parallel_perf.""" + + pp = ParallelPerf(a) + pp.config() + return pp.run() + + +def main(args): + """main.""" + + ap = argparse.ArgumentParser( + prog=glb_prog_name, formatter_class=argparse.RawDescriptionHelpFormatter, + description=""" +run a perf script command multiple times in parallel, using perf script options +--cpu and --time so that each job processes a different chunk of the data. +""", + epilog=""" +Follow the options by '--' and then the perf script command e.g. + + $ perf record -a -- sleep 10 + $ parallel-perf.py --nr=4 -- perf script --ns + All jobs finished successfully + $ tree parallel-perf-output/ + parallel-perf-output/ + ├── time-range-0 + │ ├── cmd.txt + │ └── out.txt + ├── time-range-1 + │ ├── cmd.txt + │ └── out.txt + ├── time-range-2 + │ ├── cmd.txt + │ └── out.txt + └── time-range-3 + ├── cmd.txt + └── out.txt + $ find parallel-perf-output -name cmd.txt | sort | xargs grep -H . + parallel-perf-output/time-range-0/cmd.txt:perf script --time=,9466.504461499 --ns + parallel-perf-output/time-range-1/cmd.txt:perf script --time=9466.504461500,9469.005396999 --ns + parallel-perf-output/time-range-2/cmd.txt:perf script --time=9469.005397000,9471.506332499 --ns + parallel-perf-output/time-range-3/cmd.txt:perf script --time=9471.506332500, --ns + +Any perf script command can be used, including the use of perf script options +--dlfilter and --script, so that the benefit of running parallel jobs +naturally extends to them also. + +If option --pipe-to is used, standard output is first piped through that +command. Beware, if the command fails (e.g. grep with no matches), it will be +considered a fatal error. + +Final standard output is redirected to files named out.txt in separate +subdirectories under the output directory. Similarly, standard error is +written to files named err.txt. In addition, files named cmd.txt contain the +corresponding perf script command. After processing, err.txt files are removed +if they are empty. + +If any job exits with a non-zero exit code, then all jobs are killed and no +more are started. A message is printed if any job results in a non-empty +err.txt file. + +There is a separate output subdirectory for each time range. If the --per-cpu +option is used, these are further grouped under cpu-n subdirectories, e.g. + + $ parallel-perf.py --per-cpu --nr=2 -- perf script --ns --cpu=0,1 + All jobs finished successfully + $ tree parallel-perf-output + parallel-perf-output/ + ├── cpu-0 + │ ├── time-range-0 + │ │ ├── cmd.txt + │ │ └── out.txt + │ └── time-range-1 + │ ├── cmd.txt + │ └── out.txt + └── cpu-1 + ├── time-range-0 + │ ├── cmd.txt + │ └── out.txt + └── time-range-1 + ├── cmd.txt + └── out.txt + $ find parallel-perf-output -name cmd.txt | sort | xargs grep -H . + parallel-perf-output/cpu-0/time-range-0/cmd.txt:perf script --cpu=0 --time=,9469.005396999 --ns + parallel-perf-output/cpu-0/time-range-1/cmd.txt:perf script --cpu=0 --time=9469.005397000, --ns + parallel-perf-output/cpu-1/time-range-0/cmd.txt:perf script --cpu=1 --time=,9469.005396999 --ns + parallel-perf-output/cpu-1/time-range-1/cmd.txt:perf script --cpu=1 --time=9469.005397000, --ns + +Subdivisions of time range, and cpus if the --per-cpu option is used, are +expressed by the --time and --cpu perf script options respectively. If the +supplied perf script command has a --time option, then that time range is +subdivided, otherwise the time range given by 'time of first sample' to +'time of last sample' is used (refer perf script --header-only). Similarly, the +supplied perf script command may provide a --cpu option, and only those CPUs +will be processed. + +To prevent time intervals becoming too small, the --min-interval option can +be used. + +Note there is special handling for processing Intel PT traces. If an interval is +not specified and the perf record command contained the intel_pt event, then the +time range will be subdivided in order to produce subdivisions that contain +approximately the same amount of trace data. That is accomplished by counting +double-quick (--itrace=qqi) samples, and choosing time ranges that encompass +approximately the same number of samples. In that case, time ranges may not be +the same for each CPU processed. For Intel PT, --per-cpu is the default, but +that can be overridden by --no-per-cpu. Note, for Intel PT, double-quick +decoding produces 1 sample for each PSB synchronization packet, which in turn +come after a certain number of bytes output, determined by psb_period (refer +perf Intel PT documentation). The minimum number of double-quick samples that +will define a time range can be set by the --min_size option, which defaults to +64. +""") + ap.add_argument("-o", "--output-dir", default="parallel-perf-output", + help="output directory (default 'parallel-perf-output')") + ap.add_argument("-j", "--jobs", type=int, default=0, + help="maximum number of jobs to run in parallel at one time " + "(default is the number of CPUs)") + ap.add_argument("-n", "--nr", type=int, default=0, + help="number of time subdivisions (default is the number of jobs)") + ap.add_argument("-i", "--interval", type=float, default=0, + help="subdivide the time range using this time interval " + "(in seconds e.g. 0.1 for a tenth of a second)") + ap.add_argument("-c", "--per-cpu", action="store_true", + help="process data for each CPU in parallel") + ap.add_argument("-m", "--min-interval", type=float, default=glb_min_interval, + help=f"minimum interval (default {glb_min_interval} seconds)") + ap.add_argument("-p", "--pipe-to", + help="command to pipe output to (optional)") + ap.add_argument("-N", "--no-per-cpu", action="store_true", + help="do not process data for each CPU in parallel") + ap.add_argument("-b", "--min_size", type=int, default=glb_min_samples, + help="minimum data size (for Intel PT in PSBs)") + ap.add_argument("-D", "--dry-run", action="store_true", + help="do not run any jobs, just show the perf script commands") + ap.add_argument("-q", "--quiet", action="store_true", + help="do not print any messages except errors") + ap.add_argument("-v", "--verbose", action="store_true", + help="print more messages") + ap.add_argument("-d", "--debug", action="store_true", + help="print debugging messages") + cmd_line = list(args) + try: + split_pos = cmd_line.index("--") + cmd = cmd_line[split_pos + 1:] + args = cmd_line[:split_pos] + except (OSError, ValueError, RuntimeError): + cmd = None + args = cmd_line + a = ap.parse_args(args=args[1:]) + a.cmd = cmd + setattr(a, "_verbosity", Verbosity(a.quiet, a.verbose, a.debug)) + try: + if not a.cmd: + if a.cmd is None and len(args) <= 1: + ap.print_help() + return True + raise RuntimeError( + "command line must contain '--' before perf command") + return run_parallel_perf(a) + except (OSError, ValueError, RuntimeError, KeyboardInterrupt) as e: + print("Fatal error: ", str(e)) + if a.debug: + raise + return False + + +if __name__ == "__main__": + if not main(sys.argv): + sys.exit(1)
tools/perf/scripts/python/parallel-perf.py deleted +0 -989
989 lines not on this page · raw message
tools/perf/tests/shell/script.sh +2 -2
@@ -1,6 +1,6 @@ #!/bin/bash -# perf script tests # SPDX-License-Identifier: GPL-2.0 +# perf script tests set -e
@@ -76,7 +76,7 @@ test_parallel_perf() err=2 return fi - pp=$(dirname "$0")/../../scripts/python/parallel-perf.py + pp=$(dirname "$0")/../../python/parallel-perf.py if [ ! -f "${pp}" ] ; then echo "SKIP: parallel-perf.py script not found " err=2
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
[email protected]
AI reviewRe: [PATCH v4 45/49] perf python: Move and clean up parallel-perf.py
Sashiko has reviewed this patch and found no issues. It looks great!
Quoted 17 lines
Move
parallel-perf.pyfromtools/perf/scripts/python/totools/perf/python/as it is a standalone Python utility that invokes 'perf script' in parallel across time slices and CPUs. Updatetools/perf/tests/shell/script.shaccordingly.Also fix bugs and clean up the script to pass mypy and pylint without suppression comments:
- FixWork.command()to return the shlex.quote()-escaped command string (previouslysh_cmdwas computed withshlex.quote()and discarded in favor of unquoted self.cmd).
- Close self.popen.stdout in the parent process after spawning the consumer subprocess inWork.start()when --pipe-to is used, ensuring the producer receives SIGPIPE if the consumer exits early and avoiding leaking the pipe file descriptor.
- Convert method and function names tosnake_case, specify utf-8 file encodings, and add type annotations and docstrings.
Quoted 2 lines
Assisted-by Antigravity:gemini-3.1-proSigned-off-by Ian Rogers <[email protected]>
Sashiko has reviewed this patch and found no issues. It looks great!
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=45
Ian Rogers
reviewerPATCH v4 46/49 perf: Remove libpython support and legacy Python scripts
In reply to Ian RogersRemove embedded Python interpreter support (libpython) from perf, as all Python scripts have been migrated to standalone scripts using the perf Python extension module.
Changes include:
- Remove libpython detection and build flags from Makefile.config.
- Remove legacy Python script installation rules from Makefile.perf.
- Delete tools/perf/util/scripting-engines/trace-event-python.c and tools/perf/scripts/python/Perf-Trace-Util/Context.c.
- Remove Python scripting engine registration from trace-event-scripting.c.
- Remove libpython from the supported features list in builtin-check.c and Documentation/perf-check.txt.
- Delete the legacy Python scripts and bin wrappers in tools/perf/scripts/python/ and update shell tests.
--- tools/perf/Documentation/perf-check.txt | 1 - tools/perf/Makefile.config | 26 +- tools/perf/Makefile.perf | 7 +- tools/perf/builtin-check.c | 2 +- tools/perf/scripts/Build | 27 - .../perf/scripts/python/Perf-Trace-Util/Build | 4 - .../scripts/python/Perf-Trace-Util/Context.c | 225 -- .../Perf-Trace-Util/lib/Perf/Trace/Core.py | 116 - .../lib/Perf/Trace/EventClass.py | 97 - .../lib/Perf/Trace/SchedGui.py | 184 -- .../Perf-Trace-Util/lib/Perf/Trace/Util.py | 92 - .../scripts/python/arm-cs-trace-disasm.py | 356 --- .../python/bin/compaction-times-record | 2 - .../python/bin/compaction-times-report | 4 - .../python/bin/event_analyzing_sample-record | 8 - .../python/bin/event_analyzing_sample-report | 3 - .../python/bin/export-to-postgresql-record | 8 - .../python/bin/export-to-postgresql-report | 29 - .../python/bin/export-to-sqlite-record | 8 - .../python/bin/export-to-sqlite-report | 29 - .../python/bin/failed-syscalls-by-pid-record | 3 - .../python/bin/failed-syscalls-by-pid-report | 10 - .../perf/scripts/python/bin/flamegraph-record | 2 - .../perf/scripts/python/bin/flamegraph-report | 3 - .../python/bin/futex-contention-record | 2 - .../python/bin/futex-contention-report | 4 - tools/perf/scripts/python/bin/gecko-record | 2 - tools/perf/scripts/python/bin/gecko-report | 7 - .../scripts/python/bin/intel-pt-events-record | 13 - .../scripts/python/bin/intel-pt-events-report | 3 - .../scripts/python/bin/mem-phys-addr-record | 19 - .../scripts/python/bin/mem-phys-addr-report | 3 - .../scripts/python/bin/net_dropmonitor-record | 2 - .../scripts/python/bin/net_dropmonitor-report | 4 - .../scripts/python/bin/netdev-times-record | 8 - .../scripts/python/bin/netdev-times-report | 5 - .../scripts/python/bin/powerpc-hcalls-record | 2 - .../scripts/python/bin/powerpc-hcalls-report | 2 - .../scripts/python/bin/sched-migration-record | 2 - .../scripts/python/bin/sched-migration-report | 3 - tools/perf/scripts/python/bin/sctop-record | 3 - tools/perf/scripts/python/bin/sctop-report | 24 - .../scripts/python/bin/stackcollapse-record | 8 - .../scripts/python/bin/stackcollapse-report | 3 - .../python/bin/syscall-counts-by-pid-record | 3 - .../python/bin/syscall-counts-by-pid-report | 10 - .../scripts/python/bin/syscall-counts-record | 3 - .../scripts/python/bin/syscall-counts-report | 10 - .../scripts/python/bin/task-analyzer-record | 2 - .../scripts/python/bin/task-analyzer-report | 3 - tools/perf/scripts/python/check-perf-trace.py | 84 - tools/perf/scripts/python/compaction-times.py | 311 --- .../scripts/python/event_analyzing_sample.py | 192 -- .../scripts/python/export-to-postgresql.py | 1114 -------- tools/perf/scripts/python/export-to-sqlite.py | 799 ------ .../scripts/python/failed-syscalls-by-pid.py | 79 - tools/perf/scripts/python/flamegraph.py | 267 -- tools/perf/scripts/python/futex-contention.py | 57 - tools/perf/scripts/python/gecko.py | 395 --- tools/perf/scripts/python/intel-pt-events.py | 494 ---- tools/perf/scripts/python/libxed.py | 107 - tools/perf/scripts/python/mem-phys-addr.py | 127 - tools/perf/scripts/python/net_dropmonitor.py | 78 - tools/perf/scripts/python/netdev-times.py | 473 ---- tools/perf/scripts/python/powerpc-hcalls.py | 335 --- tools/perf/scripts/python/sched-migration.py | 462 ---- tools/perf/scripts/python/sctop.py | 89 - tools/perf/scripts/python/stackcollapse.py | 127 - tools/perf/scripts/python/stat-cpi.py | 79 - .../scripts/python/syscall-counts-by-pid.py | 75 - tools/perf/scripts/python/syscall-counts.py | 65 - tools/perf/scripts/python/task-analyzer.py | 934 ------- tools/perf/tests/shell/script.sh | 42 - tools/perf/tests/shell/script_python.sh | 113 - tools/perf/util/scripting-engines/Build | 4 - .../scripting-engines/trace-event-python.c | 2335 ----------------- tools/perf/util/trace-event-scripting.c | 9 - 77 files changed, 4 insertions(+), 10638 deletions(-) delete mode 100644 tools/perf/scripts/python/Perf-Trace-Util/Build delete mode 100644 tools/perf/scripts/python/Perf-Trace-Util/Context.c delete mode 100644 tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py delete mode 100755 tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py delete mode 100644 tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py delete mode 100644 tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py delete mode 100755 tools/perf/scripts/python/arm-cs-trace-disasm.py delete mode 100644 tools/perf/scripts/python/bin/compaction-times-record delete mode 100644 tools/perf/scripts/python/bin/compaction-times-report delete mode 100644 tools/perf/scripts/python/bin/event_analyzing_sample-record delete mode 100644 tools/perf/scripts/python/bin/event_analyzing_sample-report delete mode 100644 tools/perf/scripts/python/bin/export-to-postgresql-record delete mode 100644 tools/perf/scripts/python/bin/export-to-postgresql-report delete mode 100644 tools/perf/scripts/python/bin/export-to-sqlite-record delete mode 100644 tools/perf/scripts/python/bin/export-to-sqlite-report delete mode 100644 tools/perf/scripts/python/bin/failed-syscalls-by-pid-record delete mode 100644 tools/perf/scripts/python/bin/failed-syscalls-by-pid-report delete mode 100755 tools/perf/scripts/python/bin/flamegraph-record delete mode 100755 tools/perf/scripts/python/bin/flamegraph-report delete mode 100644 tools/perf/scripts/python/bin/futex-contention-record delete mode 100644 tools/perf/scripts/python/bin/futex-contention-report delete mode 100644 tools/perf/scripts/python/bin/gecko-record delete mode 100755 tools/perf/scripts/python/bin/gecko-report delete mode 100644 tools/perf/scripts/python/bin/intel-pt-events-record delete mode 100644 tools/perf/scripts/python/bin/intel-pt-events-report delete mode 100644 tools/perf/scripts/python/bin/mem-phys-addr-record delete mode 100644 tools/perf/scripts/python/bin/mem-phys-addr-report delete mode 100755 tools/perf/scripts/python/bin/net_dropmonitor-record delete mode 100755 tools/perf/scripts/python/bin/net_dropmonitor-report delete mode 100644 tools/perf/scripts/python/bin/netdev-times-record delete mode 100644 tools/perf/scripts/python/bin/netdev-times-report delete mode 100644 tools/perf/scripts/python/bin/powerpc-hcalls-record delete mode 100644 tools/perf/scripts/python/bin/powerpc-hcalls-report delete mode 100644 tools/perf/scripts/python/bin/sched-migration-record delete mode 100644 tools/perf/scripts/python/bin/sched-migration-report delete mode 100644 tools/perf/scripts/python/bin/sctop-record delete mode 100644 tools/perf/scripts/python/bin/sctop-report delete mode 100755 tools/perf/scripts/python/bin/stackcollapse-record delete mode 100755 tools/perf/scripts/python/bin/stackcollapse-report delete mode 100644 tools/perf/scripts/python/bin/syscall-counts-by-pid-record delete mode 100644 tools/perf/scripts/python/bin/syscall-counts-by-pid-report delete mode 100644 tools/perf/scripts/python/bin/syscall-counts-record delete mode 100644 tools/perf/scripts/python/bin/syscall-counts-report delete mode 100755 tools/perf/scripts/python/bin/task-analyzer-record delete mode 100755 tools/perf/scripts/python/bin/task-analyzer-report delete mode 100644 tools/perf/scripts/python/check-perf-trace.py delete mode 100644 tools/perf/scripts/python/compaction-times.py delete mode 100644 tools/perf/scripts/python/event_analyzing_sample.py delete mode 100644 tools/perf/scripts/python/export-to-postgresql.py delete mode 100644 tools/perf/scripts/python/export-to-sqlite.py delete mode 100644 tools/perf/scripts/python/failed-syscalls-by-pid.py delete mode 100755 tools/perf/scripts/python/flamegraph.py delete mode 100644 tools/perf/scripts/python/futex-contention.py delete mode 100644 tools/perf/scripts/python/gecko.py delete mode 100644 tools/perf/scripts/python/intel-pt-events.py delete mode 100644 tools/perf/scripts/python/libxed.py delete mode 100644 tools/perf/scripts/python/mem-phys-addr.py delete mode 100755 tools/perf/scripts/python/net_dropmonitor.py delete mode 100644 tools/perf/scripts/python/netdev-times.py delete mode 100644 tools/perf/scripts/python/powerpc-hcalls.py delete mode 100644 tools/perf/scripts/python/sched-migration.py delete mode 100644 tools/perf/scripts/python/sctop.py delete mode 100755 tools/perf/scripts/python/stackcollapse.py delete mode 100644 tools/perf/scripts/python/stat-cpi.py delete mode 100644 tools/perf/scripts/python/syscall-counts-by-pid.py delete mode 100644 tools/perf/scripts/python/syscall-counts.py delete mode 100755 tools/perf/scripts/python/task-analyzer.py delete mode 100755 tools/perf/tests/shell/script_python.sh delete mode 100644 tools/perf/util/scripting-engines/trace-event-python.c
tools/perf/Documentation/perf-check.txt +0 -1
@@ -60,7 +60,6 @@ feature:: libopencsd / HAVE_CSTRACE_SUPPORT libperl / HAVE_LIBPERL_SUPPORT libpfm4 / HAVE_LIBPFM - libpython / HAVE_LIBPYTHON_SUPPORT libslang / HAVE_SLANG_SUPPORT libtraceevent / HAVE_LIBTRACEEVENT libunwind / HAVE_LIBUNWIND_SUPPORT
tools/perf/Makefile.config +1 -25
@@ -800,27 +800,6 @@ ifdef GTK4 endif endif -ifdef LIBPERL - PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null) - PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS)) - PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) - PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null) - PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS)) - PERL_EMBED_CCOPTS := $(filter-out -flto% -ffat-lto-objects, $(PERL_EMBED_CCOPTS)) - PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS)) - FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) - - $(call feature_check,libperl) - ifneq ($(feature-libperl), 1) - $(error Missing perl devel files. Please install perl-ExtUtils-Embed/libperl-dev) - else - LDFLAGS += $(PERL_EMBED_LDFLAGS) - EXTLIBS += $(PERL_EMBED_LIBADD) - CFLAGS += -DHAVE_LIBPERL_SUPPORT - $(call detected,CONFIG_LIBPERL) - endif -endif - ifeq ($(feature-timerfd), 1) CFLAGS += -DHAVE_TIMERFD_SUPPORT else
@@ -851,8 +830,7 @@ else ifneq ($(feature-libpython), 1) $(call disable-python,No 'Python.h' was found: disables Python support - please install python-devel/python-dev) else - LDFLAGS += $(PYTHON_EMBED_LDFLAGS) - EXTLIBS += $(PYTHON_EMBED_LIBADD) + CFLAGS += -DHAVE_LIBPYTHON_SUPPORT PYTHON_SETUPTOOLS_INSTALLED := $(shell $(PYTHON) -c 'import setuptools;' 2> /dev/null && echo "yes" || echo "no") ifeq ($(PYTHON_SETUPTOOLS_INSTALLED), yes) PYTHON_EXTENSION_SUFFIX := $(shell $(PYTHON) -c 'from importlib import machinery; print(machinery.EXTENSION_SUFFIXES[0])')
@@ -863,8 +841,6 @@ else else $(warning Missing python setuptools, the python binding won't be built, please install python3-setuptools or equivalent) endif - CFLAGS += -DHAVE_LIBPYTHON_SUPPORT - $(call detected,CONFIG_LIBPYTHON) ifeq ($(filter -fPIC,$(CFLAGS)),) # Building a shared library requires position independent code. CFLAGS += -fPIC
tools/perf/Makefile.perf +2 -5
@@ -902,11 +902,8 @@ ifdef LIBPERL endif ifndef NO_LIBPYTHON $(call QUIET_INSTALL, python-scripts) \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'; \ - $(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \ - $(INSTALL) scripts/python/*.py -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \ - $(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin' + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \ + $(INSTALL) python/*.py -m 644 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python' $(call QUIET_INSTALL, python-scripts-standalone) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/python' && \ $(INSTALL) python/*.py -m 755 -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/python' && \
tools/perf/builtin-check.c +1 -1
@@ -52,8 +52,8 @@ struct feature_status supported_features[] = {FEATURE_STATUS ("libnuma" ,HAVE_LIBNUMA_SUPPORT ),FEATURE_STATUS ("libopencsd" ,HAVE_CSTRACE_SUPPORT ),FEATURE_STATUS_TIP ("libperl" ,HAVE_LIBPERL_SUPPORT ,"Deprecated, use LIBPERL=1 and install perl-ExtUtils-Embed/libperl-dev to build with it" ), +FEATURE_STATUS ("python-module" ,HAVE_LIBPYTHON_SUPPORT ),FEATURE_STATUS ("libpfm4" ,HAVE_LIBPFM ), -FEATURE_STATUS ("libpython" ,HAVE_LIBPYTHON_SUPPORT ),FEATURE_STATUS ("libslang" ,HAVE_SLANG_SUPPORT ),FEATURE_STATUS ("libtraceevent" ,HAVE_LIBTRACEEVENT ), FEATURE_STATUS_TIP("libunwind", HAVE_LIBUNWIND_SUPPORT, "Deprecated, use LIBUNWIND=1 and install libunwind-dev[el] to build with it"),
tools/perf/scripts/Build +0 -27
@@ -1,30 +1,3 @@ ifeq ($(CONFIG_LIBTRACEEVENT),y) perf-util-$(CONFIG_LIBPERL) += perl/Perf-Trace-Util/ endif -perf-util-$(CONFIG_LIBPYTHON) += python/Perf-Trace-Util/ - -ifdef MYPY - PY_TESTS := $(shell find python -type f -name '*.py') - MYPY_TEST_LOGS := $(PY_TESTS:python/%=python/%.mypy_log) -else - MYPY_TEST_LOGS := -endif - -$(OUTPUT)%.mypy_log: % - $(call rule_mkdir) - $(Q)$(call echo-cmd,test)mypy "$<" > $@ || (cat $@ && rm $@ && false) - -perf-y += $(MYPY_TEST_LOGS) - -ifdef PYLINT - PY_TESTS := $(shell find python -type f -name '*.py') - PYLINT_TEST_LOGS := $(PY_TESTS:python/%=python/%.pylint_log) -else - PYLINT_TEST_LOGS := -endif - -$(OUTPUT)%.pylint_log: % - $(call rule_mkdir) - $(Q)$(call echo-cmd,test)pylint "$<" > $@ || (cat $@ && rm $@ && false) - -perf-y += $(PYLINT_TEST_LOGS)
tools/perf/scripts/python/Perf-Trace-Util/Build deleted +0 -4
@@ -1,4 +0,0 @@ -perf-util-y += Context.o - -# -Wno-declaration-after-statement: The python headers have mixed code with declarations (decls after asserts, for instance) -CFLAGS_Context.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs -Wno-declaration-after-statement
tools/perf/scripts/python/Perf-Trace-Util/Context.c deleted +0 -225
225 lines not on this page · raw message
tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py deleted +0 -116
116 lines not on this page · raw message
tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py deleted +0 -97
97 lines not on this page · raw message
tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py deleted +0 -184
184 lines not on this page · raw message
tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py deleted +0 -92
92 lines not on this page · raw message
tools/perf/scripts/python/arm-cs-trace-disasm.py deleted +0 -356
356 lines not on this page · raw message
tools/perf/scripts/python/bin/compaction-times-record deleted +0 -2
@@ -1,2 +0,0 @@ -#!/bin/bash -perf record -e compaction:mm_compaction_begin -e compaction:mm_compaction_end -e compaction:mm_compaction_migratepages -e compaction:mm_compaction_isolate_migratepages -e compaction:mm_compaction_isolate_freepages $@
tools/perf/scripts/python/bin/compaction-times-report deleted +0 -4
@@ -1,4 +0,0 @@ -#!/bin/bash -#description: display time taken by mm compaction -#args: [-h] [-u] [-p|-pv] [-t | [-m] [-fs] [-ms]] [pid|pid-range|comm-regex] -perf script -s "$PERF_EXEC_PATH"/scripts/python/compaction-times.py $@
tools/perf/scripts/python/bin/event_analyzing_sample-record deleted +0 -8
@@ -1,8 +0,0 @@ -#!/bin/bash - -# -# event_analyzing_sample.py can cover all type of perf samples including -# the tracepoints, so no special record requirements, just record what -# you want to analyze. -# -perf record $@
tools/perf/scripts/python/bin/event_analyzing_sample-report deleted +0 -3
@@ -1,3 +0,0 @@ -#!/bin/bash -# description: analyze all perf samples -perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/event_analyzing_sample.py
tools/perf/scripts/python/bin/export-to-postgresql-record deleted +0 -8
@@ -1,8 +0,0 @@ -#!/bin/bash - -# -# export perf data to a postgresql database. Can cover -# perf ip samples (excluding the tracepoints). No special -# record requirements, just record what you want to export. -# -perf record $@
tools/perf/scripts/python/bin/export-to-postgresql-report deleted +0 -29
@@ -1,29 +0,0 @@ -#!/bin/bash -# description: export perf data to a postgresql database -# args: [database name] [columns] [calls] -n_args=0 -for i in "$@" -do - if expr match "$i" "-" > /dev/null ; then - break - fi - n_args=$(( $n_args + 1 )) -done -if [ "$n_args" -gt 3 ] ; then - echo "usage: export-to-postgresql-report [database name] [columns] [calls]" - exit -fi -if [ "$n_args" -gt 2 ] ; then - dbname=$1 - columns=$2 - calls=$3 - shift 3 -elif [ "$n_args" -gt 1 ] ; then - dbname=$1 - columns=$2 - shift 2 -elif [ "$n_args" -gt 0 ] ; then - dbname=$1 - shift -fi -perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-postgresql.py $dbname $columns $calls
tools/perf/scripts/python/bin/export-to-sqlite-record deleted +0 -8
@@ -1,8 +0,0 @@ -#!/bin/bash - -# -# export perf data to a sqlite3 database. Can cover -# perf ip samples (excluding the tracepoints). No special -# record requirements, just record what you want to export. -# -perf record $@
tools/perf/scripts/python/bin/export-to-sqlite-report deleted +0 -29
@@ -1,29 +0,0 @@ -#!/bin/bash -# description: export perf data to a sqlite3 database -# args: [database name] [columns] [calls] -n_args=0 -for i in "$@" -do - if expr match "$i" "-" > /dev/null ; then - break - fi - n_args=$(( $n_args + 1 )) -done -if [ "$n_args" -gt 3 ] ; then - echo "usage: export-to-sqlite-report [database name] [columns] [calls]" - exit -fi -if [ "$n_args" -gt 2 ] ; then - dbname=$1 - columns=$2 - calls=$3 - shift 3 -elif [ "$n_args" -gt 1 ] ; then - dbname=$1 - columns=$2 - shift 2 -elif [ "$n_args" -gt 0 ] ; then - dbname=$1 - shift -fi -perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-sqlite.py $dbname $columns $calls
tools/perf/scripts/python/bin/failed-syscalls-by-pid-record deleted +0 -3
@@ -1,3 +0,0 @@ -#!/bin/bash -(perf record -e raw_syscalls:sys_exit $@ || \ - perf record -e syscalls:sys_exit $@) 2> /dev/null
tools/perf/scripts/python/bin/failed-syscalls-by-pid-report deleted +0 -10
@@ -1,10 +0,0 @@ -#!/bin/bash -# description: system-wide failed syscalls, by pid -# args: [comm] -if [ $# -gt 0 ] ; then - if ! expr match "$1" "-" > /dev/null ; then - comm=$1 - shift - fi -fi -perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/failed-syscalls-by-pid.py $comm
tools/perf/scripts/python/bin/flamegraph-record deleted +0 -2
@@ -1,2 +0,0 @@ -#!/bin/bash -perf record -g "$@"
tools/perf/scripts/python/bin/flamegraph-report deleted +0 -3
@@ -1,3 +0,0 @@ -#!/bin/bash -# description: create flame graphs -perf script -s "$PERF_EXEC_PATH"/scripts/python/flamegraph.py "$@"
tools/perf/scripts/python/bin/futex-contention-record deleted +0 -2
@@ -1,2 +0,0 @@ -#!/bin/bash -perf record -e syscalls:sys_enter_futex -e syscalls:sys_exit_futex $@
tools/perf/scripts/python/bin/futex-contention-report deleted +0 -4
@@ -1,4 +0,0 @@ -#!/bin/bash -# description: futext contention measurement - -perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/futex-contention.py
tools/perf/scripts/python/bin/gecko-record deleted +0 -2
@@ -1,2 +0,0 @@ -#!/bin/bash -perf record -F 99 -g "$@"
tools/perf/scripts/python/bin/gecko-report deleted +0 -7
@@ -1,7 +0,0 @@ -#!/bin/bash -# description: create firefox gecko profile json format from perf.data -if [ "$*" = "-i -" ]; then -perf script -s "$PERF_EXEC_PATH"/scripts/python/gecko.py -else -perf script -s "$PERF_EXEC_PATH"/scripts/python/gecko.py -- "$@" -fi
tools/perf/scripts/python/bin/intel-pt-events-record deleted +0 -13
@@ -1,13 +0,0 @@ -#!/bin/bash - -# -# print Intel PT Events including Power Events and PTWRITE. The intel_pt PMU -# event needs to be specified with appropriate config terms. -# -if ! echo "$@" | grep -q intel_pt ; then - echo "Options must include the Intel PT event e.g. -e intel_pt/pwr_evt,ptw/" - echo "and for power events it probably needs to be system wide i.e. -a option" - echo "For example: -a -e intel_pt/pwr_evt,branch=0/ sleep 1" - exit 1 -fi -perf record $@
tools/perf/scripts/python/bin/intel-pt-events-report deleted +0 -3
@@ -1,3 +0,0 @@ -#!/bin/bash -# description: print Intel PT Events including Power Events and PTWRITE -perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/intel-pt-events.py
tools/perf/scripts/python/bin/mem-phys-addr-record deleted +0 -19
@@ -1,19 +0,0 @@ -#!/bin/bash - -# -# Profiling physical memory by all retired load instructions/uops event -# MEM_INST_RETIRED.ALL_LOADS or MEM_UOPS_RETIRED.ALL_LOADS -# - -load=`perf list | grep mem_inst_retired.all_loads` -if [ -z "$load" ]; then - load=`perf list | grep mem_uops_retired.all_loads` -fi -if [ -z "$load" ]; then - echo "There is no event to count all retired load instructions/uops." - exit 1 -fi - -arg=$(echo $load | tr -d ' ') -arg="$arg:P" -perf record --phys-data -e $arg $@
tools/perf/scripts/python/bin/mem-phys-addr-report deleted +0 -3
@@ -1,3 +0,0 @@ -#!/bin/bash -# description: resolve physical address samples -perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/mem-phys-addr.py
tools/perf/scripts/python/bin/net_dropmonitor-record deleted +0 -2
@@ -1,2 +0,0 @@ -#!/bin/bash -perf record -e skb:kfree_skb $@
tools/perf/scripts/python/bin/net_dropmonitor-report deleted +0 -4
@@ -1,4 +0,0 @@ -#!/bin/bash -# description: display a table of dropped frames - -perf script -s "$PERF_EXEC_PATH"/scripts/python/net_dropmonitor.py $@
tools/perf/scripts/python/bin/netdev-times-record deleted +0 -8
@@ -1,8 +0,0 @@ -#!/bin/bash -perf record -e net:net_dev_xmit -e net:net_dev_queue \ - -e net:netif_receive_skb -e net:netif_rx \ - -e skb:consume_skb -e skb:kfree_skb \ - -e skb:skb_copy_datagram_iovec -e napi:napi_poll \ - -e irq:irq_handler_entry -e irq:irq_handler_exit \ - -e irq:softirq_entry -e irq:softirq_exit \ - -e irq:softirq_raise $@
tools/perf/scripts/python/bin/netdev-times-report deleted +0 -5
@@ -1,5 +0,0 @@ -#!/bin/bash -# description: display a process of packet and processing time -# args: [tx] [rx] [dev=] [debug] - -perf script -s "$PERF_EXEC_PATH"/scripts/python/netdev-times.py $@
tools/perf/scripts/python/bin/powerpc-hcalls-record deleted +0 -2
@@ -1,2 +0,0 @@ -#!/bin/bash -perf record -e "{powerpc:hcall_entry,powerpc:hcall_exit}" $@
tools/perf/scripts/python/bin/powerpc-hcalls-report deleted +0 -2
@@ -1,2 +0,0 @@ -#!/bin/bash -perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/powerpc-hcalls.py
tools/perf/scripts/python/bin/sched-migration-record deleted +0 -2
@@ -1,2 +0,0 @@ -#!/bin/bash -perf record -m 16384 -e sched:sched_wakeup -e sched:sched_wakeup_new -e sched:sched_switch -e sched:sched_migrate_task $@
tools/perf/scripts/python/bin/sched-migration-report deleted +0 -3
@@ -1,3 +0,0 @@ -#!/bin/bash -# description: sched migration overview -perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/sched-migration.py
tools/perf/scripts/python/bin/sctop-record deleted +0 -3
@@ -1,3 +0,0 @@ -#!/bin/bash -(perf record -e raw_syscalls:sys_enter $@ || \ - perf record -e syscalls:sys_enter $@) 2> /dev/null
tools/perf/scripts/python/bin/sctop-report deleted +0 -24
@@ -1,24 +0,0 @@ -#!/bin/bash -# description: syscall top -# args: [comm] [interval] -n_args=0 -for i in "$@" -do - if expr match "$i" "-" > /dev/null ; then - break - fi - n_args=$(( $n_args + 1 )) -done -if [ "$n_args" -gt 2 ] ; then - echo "usage: sctop-report [comm] [interval]" - exit -fi -if [ "$n_args" -gt 1 ] ; then - comm=$1 - interval=$2 - shift 2 -elif [ "$n_args" -gt 0 ] ; then - interval=$1 - shift -fi -perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/sctop.py $comm $interval
tools/perf/scripts/python/bin/stackcollapse-record deleted +0 -8
@@ -1,8 +0,0 @@ -#!/bin/sh - -# -# stackcollapse.py can cover all type of perf samples including -# the tracepoints, so no special record requirements, just record what -# you want to analyze. -# -perf record "$@"
tools/perf/scripts/python/bin/stackcollapse-report deleted +0 -3
@@ -1,3 +0,0 @@ -#!/bin/sh -# description: produce callgraphs in short form for scripting use -perf script -s "$PERF_EXEC_PATH"/scripts/python/stackcollapse.py "$@"
tools/perf/scripts/python/bin/syscall-counts-by-pid-record deleted +0 -3
@@ -1,3 +0,0 @@ -#!/bin/bash -(perf record -e raw_syscalls:sys_enter $@ || \ - perf record -e syscalls:sys_enter $@) 2> /dev/null
tools/perf/scripts/python/bin/syscall-counts-by-pid-report deleted +0 -10
@@ -1,10 +0,0 @@ -#!/bin/bash -# description: system-wide syscall counts, by pid -# args: [comm] -if [ $# -gt 0 ] ; then - if ! expr match "$1" "-" > /dev/null ; then - comm=$1 - shift - fi -fi -perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/syscall-counts-by-pid.py $comm
tools/perf/scripts/python/bin/syscall-counts-record deleted +0 -3
@@ -1,3 +0,0 @@ -#!/bin/bash -(perf record -e raw_syscalls:sys_enter $@ || \ - perf record -e syscalls:sys_enter $@) 2> /dev/null
tools/perf/scripts/python/bin/syscall-counts-report deleted +0 -10
@@ -1,10 +0,0 @@ -#!/bin/bash -# description: system-wide syscall counts -# args: [comm] -if [ $# -gt 0 ] ; then - if ! expr match "$1" "-" > /dev/null ; then - comm=$1 - shift - fi -fi -perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/syscall-counts.py $comm
tools/perf/scripts/python/bin/task-analyzer-record deleted +0 -2
@@ -1,2 +0,0 @@ -#!/bin/bash -perf record -e sched:sched_switch -e sched:sched_migrate_task "$@"
tools/perf/scripts/python/bin/task-analyzer-report deleted +0 -3
@@ -1,3 +0,0 @@ -#!/bin/bash -# description: analyze timings of tasks -perf script -s "$PERF_EXEC_PATH"/scripts/python/task-analyzer.py -- "$@"
tools/perf/scripts/python/check-perf-trace.py deleted +0 -84
84 lines not on this page · raw message
tools/perf/scripts/python/compaction-times.py deleted +0 -311
311 lines not on this page · raw message
tools/perf/scripts/python/event_analyzing_sample.py deleted +0 -192
192 lines not on this page · raw message
tools/perf/scripts/python/export-to-postgresql.py deleted +0 -1114
977 lines not on this page · raw message
tools/perf/scripts/python/export-to-sqlite.py deleted +0 -799
799 lines not on this page · raw message
tools/perf/scripts/python/failed-syscalls-by-pid.py deleted +0 -79
79 lines not on this page · raw message
tools/perf/scripts/python/flamegraph.py deleted +0 -267
267 lines not on this page · raw message
tools/perf/scripts/python/futex-contention.py deleted +0 -57
57 lines not on this page · raw message
tools/perf/scripts/python/gecko.py deleted +0 -395
395 lines not on this page · raw message
tools/perf/scripts/python/intel-pt-events.py deleted +0 -494
494 lines not on this page · raw message
tools/perf/scripts/python/libxed.py deleted +0 -107
107 lines not on this page · raw message
tools/perf/scripts/python/mem-phys-addr.py deleted +0 -127
127 lines not on this page · raw message
tools/perf/scripts/python/net_dropmonitor.py deleted +0 -78
78 lines not on this page · raw message
tools/perf/scripts/python/netdev-times.py deleted +0 -473
473 lines not on this page · raw message
tools/perf/scripts/python/powerpc-hcalls.py deleted +0 -335
335 lines not on this page · raw message
tools/perf/scripts/python/sched-migration.py deleted +0 -462
462 lines not on this page · raw message
tools/perf/scripts/python/sctop.py deleted +0 -89
89 lines not on this page · raw message
tools/perf/scripts/python/stackcollapse.py deleted +0 -127
127 lines not on this page · raw message
tools/perf/scripts/python/stat-cpi.py deleted +0 -79
79 lines not on this page · raw message
tools/perf/scripts/python/syscall-counts-by-pid.py deleted +0 -75
75 lines not on this page · raw message
tools/perf/scripts/python/syscall-counts.py deleted +0 -65
65 lines not on this page · raw message
tools/perf/scripts/python/task-analyzer.py deleted +0 -934
934 lines not on this page · raw message
tools/perf/tests/shell/script.sh +0 -42
42 lines not on this page · raw message
tools/perf/tests/shell/script_python.sh deleted +0 -113
113 lines not on this page · raw message
tools/perf/util/scripting-engines/Build +0 -4
Lines of this file are not shown. View the raw message.
tools/perf/util/scripting-engines/trace-event-python.c deleted +0 -2335
2,335 lines not on this page · raw message
tools/perf/util/trace-event-scripting.c +0 -9
Lines of this file are not shown. View the raw message.
The rest of this diff is not shown. View the raw message.
Signature · 1 line
2.56.0.rc1.315.gc6ed9934b7-goog
Part of the diff is not shown here. View the raw message.