perf report/annotate: Support average IPC and IPC coverage for function

Commit-ID:  9d2a4fa18816c8a7c4df5873755b92956f6a7128
Gitweb:     https://git.kernel.org/tip/9d2a4fa18816c8a7c4df5873755b92956f6a7128
Author:     Jin Yao <[email protected]>
AuthorDate: Fri, 30 Nov 2018 21:54:54 +0800
Committer:  Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Fri, 30 Nov 2018 17:14:52 -0300

perf annotate: Compute average IPC and IPC coverage per symbol

Add support to 'perf report' annotate view or 'perf annotate --stdio2' to aggregate the IPC derived from timed LBRs per symbol. We compute the average IPC and the IPC coverage percentage.

For example:

  $ perf annotate --stdio2

Percent IPC Cycle (Average IPC: 2.30, IPC Coverage: 54.8%)

                          Disassembly of section .text:

                          000000000003aac0 <random@@GLIBC_2.2.5>:
    8.32  3.28              sub    $0x18,%rsp
          3.28              mov    $0x1,%esi
          3.28              xor    %eax,%eax
          3.28              cmpl   $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
   11.57  3.28     1      ↓ je     20
                            lock   cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
                          ↓ jne    29
                          ↓ jmp    43
   11.57  1.10        20:   cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
    0.00  1.10     1      ↓ je     43
                      29:   lea    __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
                            sub    $0x80,%rsp
                          → callq  __lll_lock_wait_private
                            add    $0x80,%rsp
    0.00  3.00        43:   lea    __ctype_b@GLIBC_2.2.5+0x38,%rdi
          3.00              lea    0xc(%rsp),%rsi
    8.49  3.00     1      → callq  __random_r
    7.91  1.94              cmpl   $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
    0.00  1.94     1      ↓ je     68
                            lock   decl   __abort_msg@@GLIBC_PRIVATE+0x8a0
                          ↓ jne    70
                          ↓ jmp    8a
    0.00  2.00        68:   decl   __abort_msg@@GLIBC_PRIVATE+0x8a0
   21.56  2.00     1      ↓ je     8a
                      70:   lea    __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
                            sub    $0x80,%rsp
                          → callq  __lll_unlock_wake_private
                            add    $0x80,%rsp
   21.56  2.90        8a:   movslq 0xc(%rsp),%rax
          2.90              add    $0x18,%rsp
    9.03  2.90     1      ← retq

It shows for this symbol the average IPC is 2.30 and the IPC coverage is 54.8%.

---
 tools/perf/util/annotate.c | 41 ++++++++++++++++++++++++++++++++++++++---
 tools/perf/util/annotate.h |  5 +++++
 2 files changed, 43 insertions(+), 3 deletions(-)

index 6936daf89ddd..4b2b1b09b8f1 100644
@@ -1000,6 +1000,7 @@ static unsigned annotation__count_insn(struct annotation *notes, u64 start, u64
 static void annotation__count_and_fill(struct annotation *notes, u64 start, u64 end, struct cyc_hist *ch)
 {
 	unsigned n_insn;
+	unsigned int cover_insn = 0;
 	u64 offset;
 
 	n_insn = annotation__count_insn(notes, start, end);

@@ -1013,21 +1014,34 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 		for (offset = start; offset <= end; offset++) {
 			struct annotation_line *al = notes->offsets[offset];
 
-			if (al)
+			if (al && al->ipc == 0.0) {
 				al->ipc = ipc;
+				cover_insn++;
+			}
+		}
+
+		if (cover_insn) {
+			notes->hit_cycles += ch->cycles;
+			notes->hit_insn += n_insn * ch->num;
+			notes->cover_insn += cover_insn;
 		}
 	}
 }
 
 void annotation__compute_ipc(struct annotation *notes, size_t size)
 {
-	u64 offset;
+	s64 offset;
 
 	if (!notes->src || !notes->src->cycles_hist)
 		return;
 
+	notes->total_insn = annotation__count_insn(notes, 0, size - 1);
+	notes->hit_cycles = 0;
+	notes->hit_insn = 0;
+	notes->cover_insn = 0;
+
 	pthread_mutex_lock(&notes->lock);
-	for (offset = 0; offset < size; ++offset) {
+	for (offset = size - 1; offset >= 0; --offset) {
 		struct cyc_hist *ch;
 
 		ch = &notes->src->cycles_hist[offset];

@@ -2563,6 +2577,22 @@ call_like:
 	disasm_line__scnprintf(dl, bf, size, !notes->options->use_offset);
 }
 
+static void ipc_coverage_string(char *bf, int size, struct annotation *notes)
+{
+	double ipc = 0.0, coverage = 0.0;
+
+	if (notes->hit_cycles)
+		ipc = notes->hit_insn / ((double)notes->hit_cycles);
+
+	if (notes->total_insn) {
+		coverage = notes->cover_insn * 100.0 /
+			((double)notes->total_insn);
+	}
+
+	scnprintf(bf, size, "(Average IPC: %.2f, IPC Coverage: %.1f%%)",
+		  ipc, coverage);
+}
+
 static void __annotation_line__write(struct annotation_line *al, struct annotation *notes,
 				     bool first_line, bool current_entry, bool change_color, int width,
 				     void *obj, unsigned int percent_type,

@@ -2658,6 +2688,11 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 					    ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
 					    "Cycle(min/max)");
 		}
+
+		if (show_title && !*al->line) {
+			ipc_coverage_string(bf, sizeof(bf), notes);
+			obj__printf(obj, "%*s", ANNOTATION__AVG_IPC_WIDTH, bf);
+		}
 	}
 
 	obj__printf(obj, " ");

index 5399ba2321bb..fb6463730ba4 100644
@@ -64,6 +64,7 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
 #define ANNOTATION__IPC_WIDTH 6
 #define ANNOTATION__CYCLES_WIDTH 6
 #define ANNOTATION__MINMAX_CYCLES_WIDTH 19
+#define ANNOTATION__AVG_IPC_WIDTH 36
 
 struct annotation_options {
 	bool hide_src_code,

@@ -262,6 +263,10 @@ struct annotation {
 	pthread_mutex_t		lock;
 	u64			max_coverage;
 	u64			start;
+	u64			hit_cycles;
+	u64			hit_insn;
+	unsigned int		total_insn;
+	unsigned int		cover_insn;
 	struct annotation_options *options;
 	struct annotation_line	**offsets;
 	int			nr_events;

Commit-ID:  ace4f8faea54f62521e349f70b49797e48873e1f
Gitweb:     https://git.kernel.org/tip/ace4f8faea54f62521e349f70b49797e48873e1f
Author:     Jin Yao <[email protected]>
AuthorDate: Fri, 30 Nov 2018 21:54:54 +0800
Committer:  Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Mon, 17 Dec 2018 14:55:32 -0300

perf annotate: Compute average IPC and IPC coverage per symbol

Add support to 'perf report' annotate view or 'perf annotate --stdio2' to aggregate the IPC derived from timed LBRs per symbol. We compute the average IPC and the IPC coverage percentage.

For example:

  $ perf annotate --stdio2

Percent IPC Cycle (Average IPC: 2.30, IPC Coverage: 54.8%)

                          Disassembly of section .text:

                          000000000003aac0 <random@@GLIBC_2.2.5>:
    8.32  3.28              sub    $0x18,%rsp
          3.28              mov    $0x1,%esi
          3.28              xor    %eax,%eax
          3.28              cmpl   $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
   11.57  3.28     1      ↓ je     20
                            lock   cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
                          ↓ jne    29
                          ↓ jmp    43
   11.57  1.10        20:   cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
    0.00  1.10     1      ↓ je     43
                      29:   lea    __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
                            sub    $0x80,%rsp
                          → callq  __lll_lock_wait_private
                            add    $0x80,%rsp
    0.00  3.00        43:   lea    __ctype_b@GLIBC_2.2.5+0x38,%rdi
          3.00              lea    0xc(%rsp),%rsi
    8.49  3.00     1      → callq  __random_r
    7.91  1.94              cmpl   $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
    0.00  1.94     1      ↓ je     68
                            lock   decl   __abort_msg@@GLIBC_PRIVATE+0x8a0
                          ↓ jne    70
                          ↓ jmp    8a
    0.00  2.00        68:   decl   __abort_msg@@GLIBC_PRIVATE+0x8a0
   21.56  2.00     1      ↓ je     8a
                      70:   lea    __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
                            sub    $0x80,%rsp
                          → callq  __lll_unlock_wake_private
                            add    $0x80,%rsp
   21.56  2.90        8a:   movslq 0xc(%rsp),%rax
          2.90              add    $0x18,%rsp
    9.03  2.90     1      ← retq

It shows for this symbol the average IPC is 2.30 and the IPC coverage is 54.8%.

---
 tools/perf/util/annotate.c | 41 ++++++++++++++++++++++++++++++++++++++---
 tools/perf/util/annotate.h |  5 +++++
 2 files changed, 43 insertions(+), 3 deletions(-)

index 6936daf89ddd..4b2b1b09b8f1 100644
@@ -1000,6 +1000,7 @@ static unsigned annotation__count_insn(struct annotation *notes, u64 start, u64
 static void annotation__count_and_fill(struct annotation *notes, u64 start, u64 end, struct cyc_hist *ch)
 {
 	unsigned n_insn;
+	unsigned int cover_insn = 0;
 	u64 offset;
 
 	n_insn = annotation__count_insn(notes, start, end);

@@ -1013,21 +1014,34 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 		for (offset = start; offset <= end; offset++) {
 			struct annotation_line *al = notes->offsets[offset];
 
-			if (al)
+			if (al && al->ipc == 0.0) {
 				al->ipc = ipc;
+				cover_insn++;
+			}
+		}
+
+		if (cover_insn) {
+			notes->hit_cycles += ch->cycles;
+			notes->hit_insn += n_insn * ch->num;
+			notes->cover_insn += cover_insn;
 		}
 	}
 }
 
 void annotation__compute_ipc(struct annotation *notes, size_t size)
 {
-	u64 offset;
+	s64 offset;
 
 	if (!notes->src || !notes->src->cycles_hist)
 		return;
 
+	notes->total_insn = annotation__count_insn(notes, 0, size - 1);
+	notes->hit_cycles = 0;
+	notes->hit_insn = 0;
+	notes->cover_insn = 0;
+
 	pthread_mutex_lock(&notes->lock);
-	for (offset = 0; offset < size; ++offset) {
+	for (offset = size - 1; offset >= 0; --offset) {
 		struct cyc_hist *ch;
 
 		ch = &notes->src->cycles_hist[offset];

@@ -2563,6 +2577,22 @@ call_like:
 	disasm_line__scnprintf(dl, bf, size, !notes->options->use_offset);
 }
 
+static void ipc_coverage_string(char *bf, int size, struct annotation *notes)
+{
+	double ipc = 0.0, coverage = 0.0;
+
+	if (notes->hit_cycles)
+		ipc = notes->hit_insn / ((double)notes->hit_cycles);
+
+	if (notes->total_insn) {
+		coverage = notes->cover_insn * 100.0 /
+			((double)notes->total_insn);
+	}
+
+	scnprintf(bf, size, "(Average IPC: %.2f, IPC Coverage: %.1f%%)",
+		  ipc, coverage);
+}
+
 static void __annotation_line__write(struct annotation_line *al, struct annotation *notes,
 				     bool first_line, bool current_entry, bool change_color, int width,
 				     void *obj, unsigned int percent_type,

@@ -2658,6 +2688,11 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 					    ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
 					    "Cycle(min/max)");
 		}
+
+		if (show_title && !*al->line) {
+			ipc_coverage_string(bf, sizeof(bf), notes);
+			obj__printf(obj, "%*s", ANNOTATION__AVG_IPC_WIDTH, bf);
+		}
 	}
 
 	obj__printf(obj, " ");

index 5399ba2321bb..fb6463730ba4 100644
@@ -64,6 +64,7 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
 #define ANNOTATION__IPC_WIDTH 6
 #define ANNOTATION__CYCLES_WIDTH 6
 #define ANNOTATION__MINMAX_CYCLES_WIDTH 19
+#define ANNOTATION__AVG_IPC_WIDTH 36
 
 struct annotation_options {
 	bool hide_src_code,

@@ -262,6 +263,10 @@ struct annotation {
 	pthread_mutex_t		lock;
 	u64			max_coverage;
 	u64			start;
+	u64			hit_cycles;
+	u64			hit_insn;
+	unsigned int		total_insn;
+	unsigned int		cover_insn;
 	struct annotation_options *options;
 	struct annotation_line	**offsets;
 	int			nr_events;

Commit-ID:  41405354bd534857a02448c14df4454bf8abe432
Gitweb:     https://git.kernel.org/tip/41405354bd534857a02448c14df4454bf8abe432
Author:     Jin Yao <[email protected]>
AuthorDate: Fri, 30 Nov 2018 21:54:55 +0800
Committer:  Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Fri, 30 Nov 2018 17:14:52 -0300

perf annotate: Create a annotate2 flag in struct symbol

We often use the symbol__annotate2() to annotate a specified symbol. While annotating may take some time, so in order to avoid annotating the same symbol repeatedly, the patch creates a new flag to indicate the symbol has been annotated.

---
 tools/perf/util/annotate.c | 1 +
 tools/perf/util/symbol.h   | 1 +
 2 files changed, 2 insertions(+)

index 4b2b1b09b8f1..f69d8e177fa3 100644
@@ -2798,6 +2798,7 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *ev
 	notes->nr_events = nr_pcnt;
 
 	annotation__update_column_widths(notes);
+	sym->annotate2 = true;
 
 	return 0;
 

index d026d215bdc6..14d9d438e7e2 100644
@@ -63,6 +63,7 @@ struct symbol {
 	u8		ignore:1;
 	u8		inlined:1;
 	u8		arch_sym;
+	bool		annotate2;
 	char		name[0];
 };
 

Commit-ID:  246fda09c127e689780d32ef72f2e870615ece3f
Gitweb:     https://git.kernel.org/tip/246fda09c127e689780d32ef72f2e870615ece3f
Author:     Jin Yao <[email protected]>
AuthorDate: Fri, 30 Nov 2018 21:54:55 +0800
Committer:  Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Mon, 17 Dec 2018 14:55:40 -0300

perf annotate: Create a annotate2 flag in struct symbol

We often use the symbol__annotate2() to annotate a specified symbol. While annotating may take some time, so in order to avoid annotating the same symbol repeatedly, the patch creates a new flag to indicate the symbol has been annotated.

---
 tools/perf/util/annotate.c | 1 +
 tools/perf/util/symbol.h   | 1 +
 2 files changed, 2 insertions(+)

index 4b2b1b09b8f1..f69d8e177fa3 100644
@@ -2798,6 +2798,7 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *ev
 	notes->nr_events = nr_pcnt;
 
 	annotation__update_column_widths(notes);
+	sym->annotate2 = true;
 
 	return 0;
 

index d026d215bdc6..14d9d438e7e2 100644
@@ -63,6 +63,7 @@ struct symbol {
 	u8		ignore:1;
 	u8		inlined:1;
 	u8		arch_sym;
+	bool		annotate2;
 	char		name[0];
 };
 

Commit-ID:  8eced1d1581499203caa785b9b60bdcfdab5dcce
Gitweb:     https://git.kernel.org/tip/8eced1d1581499203caa785b9b60bdcfdab5dcce
Author:     Jin Yao <[email protected]>
AuthorDate: Fri, 30 Nov 2018 21:54:56 +0800
Committer:  Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Fri, 30 Nov 2018 17:14:52 -0300

perf report: Display average IPC and IPC coverage per symbol

Support displaying the average IPC and IPC coverage per symbol in 'perf report' --tui and --stdio modes.

For example,

 $ perf record -b ...
 $ perf report -s symbol

 Overhead  Symbol                           IPC   [IPC Coverage]
   39.60%  [.] __random                     2.30  [ 54.8%]
   18.02%  [.] main                         0.43  [ 54.3%]
   14.21%  [.] compute_flag                 2.29  [100.0%]
   14.16%  [.] rand                         0.36  [100.0%]
    7.06%  [.] __random_r                   2.57  [ 70.5%]
    6.85%  [.] rand@plt                     0.00  [  0.0%]

Jiri Olsa <[email protected]> provided the patch to support the --stdio mode. I merged Jiri's code in this patch.

  $ perf report -s symbol --stdio

    # Overhead  Symbol                       IPC   [IPC Coverage]
    # ........  ...........................  ....................
    #
      39.60%  [.] __random                   2.30  [ 54.8%]
      18.02%  [.] main                       0.43  [ 54.3%]
      14.21%  [.] compute_flag               2.29  [100.0%]
      14.16%  [.] rand                       0.36  [100.0%]
       7.06%  [.] __random_r                 2.57  [ 70.5%]
       6.85%  [.] rand@plt                   0.00  [  0.0%]
       0.02%  [k] run_timer_softirq          1.60  [ 57.2%]

The columns "IPC" and "[IPC Coverage]" are automatically enabled when the sort-key "symbol" is specified. If the perf.data file doesn't contain timed LBR information, columns are filled with "-".

For example,

  # Overhead  Symbol                       IPC   [IPC Coverage]
  # ........  ...........................  ....................
  #
      46.57%  [.] main                     -      -
      17.60%  [.] rand                     -      -
      15.84%  [.] __random_r               -      -
      11.90%  [.] __random                 -      -
       6.50%  [.] compute_flag             -      -
       1.59%  [.] rand@plt                 -      -
       0.00%  [.] _dl_relocate_object      -      -
       0.00%  [k] tlb_flush_mmu            -      -
       0.00%  [k] perf_event_mmap          -      -
       0.00%  [k] native_sched_clock       -      -
       0.00%  [k] intel_pmu_handle_irq_v4  -      -
       0.00%  [k] native_write_msr         -      -

v3:
---
Removed the sortkey 'ipc' from command-line. The columns "IPC" and "[IPC Coverage]" are automatically enabled when "symbol" is specified.

v2:
---
Merge in Jiri's patch to support stdio mode

---
 tools/perf/builtin-report.c | 26 ++++++++++++++++---
 tools/perf/util/hist.h      |  1 +
 tools/perf/util/sort.c      | 61 +++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/sort.h      |  2 ++
 4 files changed, 87 insertions(+), 3 deletions(-)

index 257c9c18cb7e..4958095be4fc 100644
@@ -85,6 +85,7 @@ struct report {
 	int			socket_filter;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 	struct branch_type_stat	brtype_stat;
+	bool			symbol_ipc;
 };
 
 static int report__config(const char *var, const char *value, void *cb)

@@ -129,7 +130,7 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter,
 	struct mem_info *mi;
 	struct branch_info *bi;
 
-	if (!ui__has_annotation())
+	if (!ui__has_annotation() && !rep->symbol_ipc)
 		return 0;
 
 	hist__account_cycles(sample->branch_stack, al, sample,

@@ -174,7 +175,7 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter,
 	struct perf_evsel *evsel = iter->evsel;
 	int err;
 
-	if (!ui__has_annotation())
+	if (!ui__has_annotation() && !rep->symbol_ipc)
 		return 0;
 
 	hist__account_cycles(sample->branch_stack, al, sample,

@@ -1133,6 +1134,7 @@ int cmd_report(int argc, const char **argv)
 		.mode  = PERF_DATA_MODE_READ,
 	};
 	int ret = hists__init();
+	char sort_tmp[128];
 
 	if (ret < 0)
 		return ret;

@@ -1284,6 +1286,24 @@ repeat:
 	else
 		use_browser = 0;
 
+	if (sort_order && strstr(sort_order, "ipc")) {
+		parse_options_usage(report_usage, options, "s", 1);
+		goto error;
+	}
+
+	if (sort_order && strstr(sort_order, "symbol")) {
+		if (sort__mode == SORT_MODE__BRANCH) {
+			snprintf(sort_tmp, sizeof(sort_tmp), "%s,%s",
+				 sort_order, "ipc_lbr");
+			report.symbol_ipc = true;
+		} else {
+			snprintf(sort_tmp, sizeof(sort_tmp), "%s,%s",
+				 sort_order, "ipc_null");
+		}
+
+		sort_order = sort_tmp;
+	}
+
 	if (setup_sorting(session->evlist) < 0) {
 		if (sort_order)
 			parse_options_usage(report_usage, options, "s", 1);

@@ -1311,7 +1331,7 @@ repeat:
 	 * so don't allocate extra space that won't be used in the stdio
 	 * implementation.
 	 */
-	if (ui__has_annotation()) {
+	if (ui__has_annotation() || report.symbol_ipc) {
 		ret = symbol__annotation_init();
 		if (ret < 0)
 			goto error;

index 3badd7f1e1b8..664b5eda8d51 100644
@@ -62,6 +62,7 @@ enum hist_column {
 	HISTC_TRACE,
 	HISTC_SYM_SIZE,
 	HISTC_DSO_SIZE,
+	HISTC_SYMBOL_IPC,
 	HISTC_NR_COLS, /* Last entry */
 };
 

index a97cf8e6be86..130fe37fe2df 100644
@@ -229,6 +229,7 @@ enum sort_type {
 	SORT_SYM_SIZE,
 	SORT_DSO_SIZE,
 	SORT_CGROUP_ID,
+	SORT_SYM_IPC_NULL,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,

@@ -242,6 +243,7 @@ enum sort_type {
 	SORT_CYCLES,
 	SORT_SRCLINE_FROM,
 	SORT_SRCLINE_TO,
+	SORT_SYM_IPC,
 
 	/* memory mode specific sort keys */
 	__SORT_MEMORY_MODE,

Commit-ID:  ec6ae74fe8f00c7df018628ada9d33190de72efa
Gitweb:     https://git.kernel.org/tip/ec6ae74fe8f00c7df018628ada9d33190de72efa
Author:     Jin Yao <[email protected]>
AuthorDate: Fri, 30 Nov 2018 21:54:56 +0800
Committer:  Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Mon, 17 Dec 2018 14:55:44 -0300

perf report: Display average IPC and IPC coverage per symbol

Support displaying the average IPC and IPC coverage per symbol in 'perf report' --tui and --stdio modes.

For example,

 $ perf record -b ...
 $ perf report -s symbol

 Overhead  Symbol                           IPC   [IPC Coverage]
   39.60%  [.] __random                     2.30  [ 54.8%]
   18.02%  [.] main                         0.43  [ 54.3%]
   14.21%  [.] compute_flag                 2.29  [100.0%]
   14.16%  [.] rand                         0.36  [100.0%]
    7.06%  [.] __random_r                   2.57  [ 70.5%]
    6.85%  [.] rand@plt                     0.00  [  0.0%]

Jiri Olsa <[email protected]> provided the patch to support the --stdio mode. I merged Jiri's code in this patch.

  $ perf report -s symbol --stdio

    # Overhead  Symbol                       IPC   [IPC Coverage]
    # ........  ...........................  ....................
    #
      39.60%  [.] __random                   2.30  [ 54.8%]
      18.02%  [.] main                       0.43  [ 54.3%]
      14.21%  [.] compute_flag               2.29  [100.0%]
      14.16%  [.] rand                       0.36  [100.0%]
       7.06%  [.] __random_r                 2.57  [ 70.5%]
       6.85%  [.] rand@plt                   0.00  [  0.0%]
       0.02%  [k] run_timer_softirq          1.60  [ 57.2%]

The columns "IPC" and "[IPC Coverage]" are automatically enabled when the sort-key "symbol" is specified. If the perf.data file doesn't contain timed LBR information, columns are filled with "-".

For example,

  # Overhead  Symbol                       IPC   [IPC Coverage]
  # ........  ...........................  ....................
  #
      46.57%  [.] main                     -      -
      17.60%  [.] rand                     -      -
      15.84%  [.] __random_r               -      -
      11.90%  [.] __random                 -      -
       6.50%  [.] compute_flag             -      -
       1.59%  [.] rand@plt                 -      -
       0.00%  [.] _dl_relocate_object      -      -
       0.00%  [k] tlb_flush_mmu            -      -
       0.00%  [k] perf_event_mmap          -      -
       0.00%  [k] native_sched_clock       -      -
       0.00%  [k] intel_pmu_handle_irq_v4  -      -
       0.00%  [k] native_write_msr         -      -

v3:
---
Removed the sortkey 'ipc' from command-line. The columns "IPC" and "[IPC Coverage]" are automatically enabled when "symbol" is specified.

v2:
---
Merge in Jiri's patch to support stdio mode

---
 tools/perf/builtin-report.c | 26 ++++++++++++++++---
 tools/perf/util/hist.h      |  1 +
 tools/perf/util/sort.c      | 61 +++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/sort.h      |  2 ++
 4 files changed, 87 insertions(+), 3 deletions(-)

index 257c9c18cb7e..4958095be4fc 100644
@@ -85,6 +85,7 @@ struct report {
 	int			socket_filter;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 	struct branch_type_stat	brtype_stat;
+	bool			symbol_ipc;
 };
 
 static int report__config(const char *var, const char *value, void *cb)

@@ -129,7 +130,7 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter,
 	struct mem_info *mi;
 	struct branch_info *bi;
 
-	if (!ui__has_annotation())
+	if (!ui__has_annotation() && !rep->symbol_ipc)
 		return 0;
 
 	hist__account_cycles(sample->branch_stack, al, sample,

@@ -174,7 +175,7 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter,
 	struct perf_evsel *evsel = iter->evsel;
 	int err;
 
-	if (!ui__has_annotation())
+	if (!ui__has_annotation() && !rep->symbol_ipc)
 		return 0;
 
 	hist__account_cycles(sample->branch_stack, al, sample,

@@ -1133,6 +1134,7 @@ int cmd_report(int argc, const char **argv)
 		.mode  = PERF_DATA_MODE_READ,
 	};
 	int ret = hists__init();
+	char sort_tmp[128];
 
 	if (ret < 0)
 		return ret;

@@ -1284,6 +1286,24 @@ repeat:
 	else
 		use_browser = 0;
 
+	if (sort_order && strstr(sort_order, "ipc")) {
+		parse_options_usage(report_usage, options, "s", 1);
+		goto error;
+	}
+
+	if (sort_order && strstr(sort_order, "symbol")) {
+		if (sort__mode == SORT_MODE__BRANCH) {
+			snprintf(sort_tmp, sizeof(sort_tmp), "%s,%s",
+				 sort_order, "ipc_lbr");
+			report.symbol_ipc = true;
+		} else {
+			snprintf(sort_tmp, sizeof(sort_tmp), "%s,%s",
+				 sort_order, "ipc_null");
+		}
+
+		sort_order = sort_tmp;
+	}
+
 	if (setup_sorting(session->evlist) < 0) {
 		if (sort_order)
 			parse_options_usage(report_usage, options, "s", 1);

@@ -1311,7 +1331,7 @@ repeat:
 	 * so don't allocate extra space that won't be used in the stdio
 	 * implementation.
 	 */
-	if (ui__has_annotation()) {
+	if (ui__has_annotation() || report.symbol_ipc) {
 		ret = symbol__annotation_init();
 		if (ret < 0)
 			goto error;

index 3badd7f1e1b8..664b5eda8d51 100644
@@ -62,6 +62,7 @@ enum hist_column {
 	HISTC_TRACE,
 	HISTC_SYM_SIZE,
 	HISTC_DSO_SIZE,
+	HISTC_SYMBOL_IPC,
 	HISTC_NR_COLS, /* Last entry */
 };
 

index a97cf8e6be86..130fe37fe2df 100644
@@ -229,6 +229,7 @@ enum sort_type {
 	SORT_SYM_SIZE,
 	SORT_DSO_SIZE,
 	SORT_CGROUP_ID,
+	SORT_SYM_IPC_NULL,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,

@@ -242,6 +243,7 @@ enum sort_type {
 	SORT_CYCLES,
 	SORT_SRCLINE_FROM,
 	SORT_SRCLINE_TO,
+	SORT_SYM_IPC,
 
 	/* memory mode specific sort keys */
 	__SORT_MEMORY_MODE,

Commit-ID:  eb58157b92bfdddc5257f9a170edd3db96e96748
Gitweb:     https://git.kernel.org/tip/eb58157b92bfdddc5257f9a170edd3db96e96748
Author:     Jin Yao <[email protected]>
AuthorDate: Fri, 30 Nov 2018 21:54:57 +0800
Committer:  Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Fri, 30 Nov 2018 17:14:52 -0300

perf report: Documentation average IPC and IPC coverage

Add explanations for new columns "IPC" and "IPC coverage" in perf documentation.

v5:
---
Update the description according to Ingo's comments.

---
 tools/perf/Documentation/perf-report.txt | 8 ++++++++
 1 file changed, 8 insertions(+)

index 474a4941f65d..ed2bf37ab132 100644
@@ -126,6 +126,14 @@ OPTIONS
 	And default sort keys are changed to comm, dso_from, symbol_from, dso_to
 	and symbol_to, see '--branch-stack'.
 
+	When the sort key symbol is specified, columns "IPC" and "IPC Coverage"
+	are enabled automatically. Column "IPC" reports the average IPC per function
+	and column "IPC coverage" reports the percentage of instructions with
+	sampled IPC in this function. IPC means Instruction Per Cycle. If it's low,
+	it indicates there may be a performance bottleneck when the function is
+	executed, such as a memory access bottleneck. If a function has high overhead
+	and low IPC, it's worth further analyzing it to optimize its performance.
+
 	If the --mem-mode option is used, the following sort keys are also available
 	(incompatible with --branch-stack):
 	symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline.

Commit-ID:  239ca3e78609378a1ed5d9db1c7db629a71c2857
Gitweb:     https://git.kernel.org/tip/239ca3e78609378a1ed5d9db1c7db629a71c2857
Author:     Jin Yao <[email protected]>
AuthorDate: Fri, 30 Nov 2018 21:54:57 +0800
Committer:  Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Mon, 17 Dec 2018 14:55:49 -0300

perf report: Documentation average IPC and IPC coverage

Add explanations for new columns "IPC" and "IPC coverage" in perf documentation.

v5:
---
Update the description according to Ingo's comments.

---
 tools/perf/Documentation/perf-report.txt | 8 ++++++++
 1 file changed, 8 insertions(+)

index 474a4941f65d..ed2bf37ab132 100644
@@ -126,6 +126,14 @@ OPTIONS
 	And default sort keys are changed to comm, dso_from, symbol_from, dso_to
 	and symbol_to, see '--branch-stack'.
 
+	When the sort key symbol is specified, columns "IPC" and "IPC Coverage"
+	are enabled automatically. Column "IPC" reports the average IPC per function
+	and column "IPC coverage" reports the percentage of instructions with
+	sampled IPC in this function. IPC means Instruction Per Cycle. If it's low,
+	it indicates there may be a performance bottleneck when the function is
+	executed, such as a memory access bottleneck. If a function has high overhead
+	and low IPC, it's worth further analyzing it to optimize its performance.
+
 	If the --mem-mode option is used, the following sort keys are also available
 	(incompatible with --branch-stack):
 	symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline.