perf: Improve cgroup profiling (v6)
Namhyung Kim
maintainercover perf: Improve cgroup profiling (v6)
Hello,
This work is to improve cgroup profiling in perf. Currently it only supports profiling tasks in a specific cgroup and there's no way to identify which cgroup the current sample belongs to. So I added PERF_SAMPLE_CGROUP to add cgroup id into each sample. It's a 64-bit integer having file handle of the cgroup. And kernel also generates PERF_RECORD_CGROUP event for new groups to correlate the cgroup id and cgroup name (path in the cgroup filesystem). The cgroup id can be read from userspace by name_to_handle_at() system call so it can synthesize the CGROUP event for existing groups.
So why do we want this? Systems running a large number of jobs in different cgroups want to profiling such jobs precisely. This includes container hosting systems widely used today. Currently perf supports namespace tracking but the systems may not use (cgroup) namespace for their jobs. Also it'd be more intuitive to see cgroup names (as they're given by user or sysadmin) rather than numeric cgroup/namespace id even if they use the namespaces.
From Stephane Eranian:
Quoted 6 lines
In data centers you care about attributing samples to a job not such much to a process. A job may have multiple processes which may come and go. The cgroup on the other hand stays around for the entire lifetime of the job. It is much easier to map a cgroup name to a particular job than it is to map a pid back to a job name, especially for offline post-processing.
Note that this only works for "perf_event" cgroups (obviously) so if users are still using cgroup-v1 interface, they need to have same hierarchy for subsystem(s) want to profile with it.
* Changes from v5:
- add ACKs for the kernel changes
- fix sort column alignment when no cgroup is available
* Changes from v4:
- use CONFIG_CGROUP_PERF
- move cgroup tree to perf_env
- move cgroup fs utility function to tools/lib/api/fs
- use a local buffer and check its size for cgroup systhesis
* Changes from v3:
- staticize perf_event_cgroup()
- fix sample parsing test
* Changes from v2:
- remove path_len from cgroup_event
- bail out if kernel doesn't support cgroup sampling
- add some description in the Kconfig
* Changes from v1:
- use new cgroup id (= file handle)
The code is available at perf/cgroup-v6 branch in
git://git.kernel.org/pub/scm/linux/kernel/git/namhyung/linux-perf.git
The testing result looks something like this:
[root@qemu build]# ./perf record --all-cgroups ./cgtest
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.009 MB perf.data (150 samples) ]
[root@qemu build]# ./perf report -s cgroup,comm --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 150 of event 'cpu-clock:pppH'
# Event count (approx.): 37500000
#
# Overhead cgroup Command
# ........ .......... .......
#
32.00% /sub/cgrp2 looper2
28.00% /sub/cgrp1 looper1
25.33% /sub looper0
4.00% / cgtest
4.00% /sub cgtest
3.33% /sub/cgrp2 cgtest
2.67% /sub/cgrp1 cgtest
0.67% / looper0The test program (cgtest) follows.
Thanks,
Namhyung
-------8<-----------------------------------------8<---------------- #define _GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include <sched.h>
#include <errno.h>
#include <sys/stat.h>
#include <sys/wait.h>
#include <sys/prctl.h>
#include <sys/mount.h>
char cgbase[] = "/sys/fs/cgroup/perf_event";
void mkcgrp(char *name) {
char buf[256];
snprintf(buf, sizeof(buf), "%s%s", cgbase, name); if (mkdir(buf, 0755) < 0)
perror("mkdir");
}void rmcgrp(char *name) {
char buf[256];
snprintf(buf, sizeof(buf), "%s%s", cgbase, name); if (rmdir(buf) < 0)
perror("rmdir");
}void setcgrp(char *name) {
char buf[256];
int fd;
snprintf(buf, sizeof(buf), "%s%s/tasks", cgbase, name);
fd = open(buf, O_WRONLY);
if (fd > 0) {
if (write(fd, "0\n", 2) != 2)
perror("write");
close(fd); }
}
void create_sub_cgroup(int idx) {
char buf[128];
snprintf(buf, sizeof(buf), "/sub/cgrp%d", idx);
mkcgrp(buf);
}
void remove_sub_cgroup(int idx) {
char buf[128];
snprintf(buf, sizeof(buf), "/sub/cgrp%d", idx);
rmcgrp(buf);
}
void set_sub_cgroup(int idx) {
char buf[128];
snprintf(buf, sizeof(buf), "/sub/cgrp%d", idx);
setcgrp(buf);
}
void set_task_name(int idx) {
char buf[16];
snprintf(buf, sizeof(buf), "looper%d", idx);
prctl(PR_SET_NAME, buf, 0, 0, 0);
}
void loop(unsigned max) {
volatile unsigned int count = 1;
while (count++ != max) {
asm volatile ("pause"); }
}
void worker(int idx, unsigned cnt, int new_ns) {
int oldns;
create_sub_cgroup(idx);
set_sub_cgroup(idx);
if (new_ns) {
if (unshare(CLONE_NEWCGROUP) < 0)
perror("unshare");#if 0 /* FIXME */
if (unshare(CLONE_NEWNS) < 0)
perror("unshare");
if (mount("none", "/sys", NULL, MS_REMOUNT | MS_REC | MS_SLAVE, NULL) < 0)
perror("mount --make-rslave");
sleep(1);
if (umount("/sys/fs/cgroup/perf_event") < 0)
perror("umount");
if (mount("cgroup", "/sys/fs/cgroup/perf_event", "cgroup",
MS_NODEV | MS_NOEXEC | MS_NOSUID, "perf_event") < 0)
perror("mount again");#endif
}
if (fork() == 0) {
set_task_name(idx);
loop(cnt);
exit(0); }
wait(NULL);
}
int main(int argc, char *argv[])
{
int i, nr = 2;
int new_ns = 1;
unsigned cnt = 1000000;
int fd;
if (argc > 1)
nr = atoi(argv[1]);
if (argc > 2)
cnt = atoi(argv[2]);
if (argc > 3)
new_ns = atoi(argv[3]);
mkcgrp("/sub");
setcgrp("/sub");
for (i = 0; i < nr; i++) {
if (fork() == 0) {
worker(i+1, cnt, new_ns);
exit(0);
}
}
set_task_name(0);
loop(cnt);
for (i = 0; i < nr; i++)
wait(NULL);
for (i = 0; i < nr; i++)
remove_sub_cgroup(i+1);
setcgrp("/");
rmcgrp("/sub"); return 0;
} -------8<-----------------------------------------8<----------------
Namhyung Kim (9):
perf/core: Add PERF_RECORD_CGROUP event
perf/core: Add PERF_SAMPLE_CGROUP feature
perf tools: Basic support for CGROUP event
perf tools: Maintain cgroup hierarchy
perf report: Add 'cgroup' sort key
perf record: Support synthesizing cgroup events
perf record: Add --all-cgroups option
perf top: Add --all-cgroups option
perf script: Add --show-cgroup-events option
include/linux/perf_event.h | 1 + include/uapi/linux/perf_event.h | 16 ++- init/Kconfig | 3 +- kernel/events/core.c | 133 ++++++++++++++++++++++ tools/include/uapi/linux/perf_event.h | 16 ++- tools/lib/perf/include/perf/event.h | 7 ++ tools/perf/Documentation/perf-record.txt | 5 +- tools/perf/Documentation/perf-report.txt | 1 + tools/perf/Documentation/perf-script.txt | 3 + tools/perf/Documentation/perf-top.txt | 4 + tools/perf/builtin-diff.c | 1 + tools/perf/builtin-record.c | 10 ++ tools/perf/builtin-report.c | 1 + tools/perf/builtin-script.c | 41 +++++++ tools/perf/builtin-top.c | 9 ++ tools/perf/tests/sample-parsing.c | 6 +- tools/perf/util/cgroup.c | 80 +++++++++++++ tools/perf/util/cgroup.h | 17 ++- tools/perf/util/env.c | 2 + tools/perf/util/env.h | 6 + tools/perf/util/event.c | 18 +++ tools/perf/util/event.h | 6 + tools/perf/util/evsel.c | 17 ++- tools/perf/util/evsel.h | 1 + tools/perf/util/hist.c | 13 +++ tools/perf/util/hist.h | 1 + tools/perf/util/machine.c | 19 ++++ tools/perf/util/machine.h | 3 + tools/perf/util/perf_event_attr_fprintf.c | 2 + tools/perf/util/record.h | 1 + tools/perf/util/session.c | 4 + tools/perf/util/sort.c | 37 ++++++ tools/perf/util/sort.h | 2 + tools/perf/util/synthetic-events.c | 121 ++++++++++++++++++++ tools/perf/util/synthetic-events.h | 1 + tools/perf/util/tool.h | 2 + 36 files changed, 598 insertions(+), 12 deletions(-)
Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
Namhyung Kim
maintainerPATCH 1/9 perf/core: Add PERF_RECORD_CGROUP event
To support cgroup tracking, add CGROUP event to save a link between cgroup path and id number. This is needed since cgroups can go away when userspace tries to read the cgroup info (from the id) later. The attr.cgroup bit was also added to enable cgroup tracking from userspace.
This event will be generated when a new cgroup becomes active. Userspace might need to synthesize those events for existing cgroups.
--- include/uapi/linux/perf_event.h | 13 +++- kernel/events/core.c | 111 ++++++++++++++++++++++++++++++++ 2 files changed, 123 insertions(+), 1 deletion(-)
include/uapi/linux/perf_event.h +12 -1
@@ -381,7 +381,8 @@ struct perf_event_attr { ksymbol : 1, /* include ksymbol events */ bpf_event : 1, /* include bpf events */ aux_output : 1, /* generate AUX records instead of events */ - __reserved_1 : 32; + cgroup : 1, /* include cgroup events */ + __reserved_1 : 31;union {__u32 wakeup_events;/* wakeup every n events */
@@ -1012,6 +1013,16 @@ enum perf_event_type {*/ PERF_RECORD_BPF_EVENT =18 , +/* +* struct { +* struct perf_event_header header; +* u64 id; +* char path[]; +* struct sample_id sample_id; +* }; +*/ +PERF_RECORD_CGROUP =19 , + PERF_RECORD_MAX, /* non-ABI */ };
kernel/events/core.c +111 -0
147 lines not on this page · raw message
Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
[tip: perf/urgent] perf/core: Add PERF_RECORD_CGROUP event
The following commit has been merged into the perf/urgent branch of tip:
The following commit has been merged into the perf/urgent branch of tip:
Commit-ID: 96aaab686505c449e24d76e76507290dcc30e008 Gitweb: https://git.kernel.org/tip/96aaab686505c449e24d76e76507290dcc30e008 Author: Namhyung Kim <[email protected]> AuthorDate: Wed, 25 Mar 2020 21:45:28 +09:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Fri, 27 Mar 2020 10:39:11 -03:00
perf/core: Add PERF_RECORD_CGROUP event
To support cgroup tracking, add CGROUP event to save a link between cgroup path and id number. This is needed since cgroups can go away when userspace tries to read the cgroup info (from the id) later.
The attr.cgroup bit was also added to enable cgroup tracking from userspace.
This event will be generated when a new cgroup becomes active. Userspace might need to synthesize those events for existing cgroups.
Committer testing:
Quoted 1 line
From the resulting kernel, using
/sys/kernel/btf/vmlinux:
$ pahole perf_event_attr | grep -w cgroup -B5 -A1 __u64 write_backward:1; /* 40:27 8 */ __u64 namespaces:1; /* 40:28 8 */ __u64 ksymbol:1; /* 40:29 8 */ __u64 bpf_event:1; /* 40:30 8 */ __u64 aux_output:1; /* 40:31 8 */ __u64 cgroup:1; /* 40:32 8 */ __u64 __reserved_1:31; /* 40:33 8 */ $
--- include/uapi/linux/perf_event.h | 13 +++- kernel/events/core.c | 111 +++++++++++++++++++++++++++++++- 2 files changed, 123 insertions(+), 1 deletion(-)
include/uapi/linux/perf_event.h +12 -1
@@ -381,7 +381,8 @@ struct perf_event_attr { ksymbol : 1, /* include ksymbol events */ bpf_event : 1, /* include bpf events */ aux_output : 1, /* generate AUX records instead of events */ - __reserved_1 : 32; + cgroup : 1, /* include cgroup events */ + __reserved_1 : 31;union {__u32 wakeup_events;/* wakeup every n events */
@@ -1012,6 +1013,16 @@ enum perf_event_type {*/ PERF_RECORD_BPF_EVENT =18 , +/* +* struct { +* struct perf_event_header header; +* u64 id; +* char path[]; +* struct sample_id sample_id; +* }; +*/ +PERF_RECORD_CGROUP =19 , + PERF_RECORD_MAX, /* non-ABI */ };
kernel/events/core.c +111 -0
147 lines not on this page · raw message
Namhyung Kim
maintainerPATCH 2/9 perf/core: Add PERF_SAMPLE_CGROUP feature
In reply to Namhyung KimThe PERF_SAMPLE_CGROUP bit is to save (perf_event) cgroup information in the sample. It will add a 64-bit id to identify current cgroup and it's the file handle in the cgroup file system. Userspace should use this information with PERF_RECORD_CGROUP event to match which cgroup it belongs.
I put it before PERF_SAMPLE_AUX for simplicity since it just needs a 64-bit word. But if we want bigger samples, I can work on that direction too.
--- include/linux/perf_event.h | 1 + include/uapi/linux/perf_event.h | 3 ++- init/Kconfig | 3 ++- kernel/events/core.c | 22 ++++++++++++++++++++++ 4 files changed, 27 insertions(+), 2 deletions(-)
include/linux/perf_event.h +1 -0
@@ -1020,6 +1020,7 @@ struct perf_sample_data {u64 stack_user_size;u64 phys_addr; +u64 cgroup; }____cacheline_aligned ;/* default value for data source */
include/uapi/linux/perf_event.h +2 -1
@@ -142,8 +142,9 @@ enum perf_event_sample_format {PERF_SAMPLE_REGS_INTR =1U <<18 ,PERF_SAMPLE_PHYS_ADDR =1U <<19 ,PERF_SAMPLE_AUX =1U <<20 , +PERF_SAMPLE_CGROUP =1U <<21 , -PERF_SAMPLE_MAX =1U <<21 ,/* non-ABI */ +PERF_SAMPLE_MAX =1U <<22 ,/* non-ABI */ __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ };
init/Kconfig +2 -1
@@ -1027,7 +1027,8 @@ config CGROUP_PERF help This option extends the perf per-cpu mode to restrict monitoring to threads which belong to the cgroup specified and run on the - designated cpu. + designated cpu. Or this can be used to have cgroup ID in samples + so that it can monitor performance events among cgroups. Say N if unsure.
kernel/events/core.c +22 -0
@@ -1862,6 +1862,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)if (sample_type &PERF_SAMPLE_PHYS_ADDR ) size +=sizeof (data->phys_addr); +if (sample_type &PERF_SAMPLE_CGROUP ) + size +=sizeof (data->cgroup); + event->header_size = size; }
@@ -6867,6 +6870,9 @@ void perf_output_sample(struct perf_output_handle *handle,if (sample_type &PERF_SAMPLE_PHYS_ADDR )perf_output_put (handle, data->phys_addr); +if (sample_type &PERF_SAMPLE_CGROUP ) +perf_output_put (handle, data->cgroup); +if (sample_type &PERF_SAMPLE_AUX ) {perf_output_put (handle, data->aux_size);
@@ -7066,6 +7072,16 @@ void perf_prepare_sample(struct perf_event_header *header,if (sample_type &PERF_SAMPLE_PHYS_ADDR ) data->phys_addr =perf_virt_to_phys (data->addr); +#ifdef CONFIG_CGROUP_PERF +if (sample_type &PERF_SAMPLE_CGROUP ) { +struct cgroup *cgrp; + +/* protected by RCU */ + cgrp =task_css_check (current, perf_event_cgrp_id,1 )->cgroup; + data->cgroup =cgroup_id (cgrp); + } +#endif +if (sample_type &PERF_SAMPLE_AUX ) {u64 size;
@@ -11264,6 +11280,12 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,if (attr->sample_type &PERF_SAMPLE_REGS_INTR ) ret =perf_reg_validate (attr->sample_regs_intr); + +#ifndef CONFIG_CGROUP_PERF +if (attr->sample_type &PERF_SAMPLE_CGROUP ) +return -EINVAL ; +#endif + out:return ret;
Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
[tip: perf/urgent] perf/core: Add PERF_SAMPLE_CGROUP feature
The following commit has been merged into the perf/urgent branch of tip:
The following commit has been merged into the perf/urgent branch of tip:
Commit-ID: 6546b19f95acc986807de981402bbac6b3a94b0f Gitweb: https://git.kernel.org/tip/6546b19f95acc986807de981402bbac6b3a94b0f Author: Namhyung Kim <[email protected]> AuthorDate: Wed, 25 Mar 2020 21:45:29 +09:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Fri, 27 Mar 2020 10:41:44 -03:00
perf/core: Add PERF_SAMPLE_CGROUP feature
The PERF_SAMPLE_CGROUP bit is to save (perf_event) cgroup information in the sample. It will add a 64-bit id to identify current cgroup and it's the file handle in the cgroup file system. Userspace should use this information with PERF_RECORD_CGROUP event to match which cgroup it belongs.
I put it before PERF_SAMPLE_AUX for simplicity since it just needs a 64-bit word. But if we want bigger samples, I can work on that direction too.
Committer testing:
$ pahole perf_sample_data | grep -w cgroup -B5 -A5 /* --- cacheline 4 boundary (256 bytes) was 56 bytes ago --- */ struct perf_regs regs_intr; /* 312 16 */ /* --- cacheline 5 boundary (320 bytes) was 8 bytes ago --- */ u64 stack_user_size; /* 328 8 */ u64 phys_addr; /* 336 8 */ u64 cgroup; /* 344 8 */
/* size: 384, cachelines: 6, members: 22 */ /* padding: 32 */ }; $
--- include/linux/perf_event.h | 1 + include/uapi/linux/perf_event.h | 3 ++- init/Kconfig | 3 ++- kernel/events/core.c | 22 ++++++++++++++++++++++ 4 files changed, 27 insertions(+), 2 deletions(-)
include/linux/perf_event.h +1 -0
@@ -1020,6 +1020,7 @@ struct perf_sample_data {u64 stack_user_size;u64 phys_addr; +u64 cgroup; }____cacheline_aligned ;/* default value for data source */
include/uapi/linux/perf_event.h +2 -1
@@ -142,8 +142,9 @@ enum perf_event_sample_format {PERF_SAMPLE_REGS_INTR =1U <<18 ,PERF_SAMPLE_PHYS_ADDR =1U <<19 ,PERF_SAMPLE_AUX =1U <<20 , +PERF_SAMPLE_CGROUP =1U <<21 , -PERF_SAMPLE_MAX =1U <<21 ,/* non-ABI */ +PERF_SAMPLE_MAX =1U <<22 ,/* non-ABI */ __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ };
init/Kconfig +2 -1
@@ -1027,7 +1027,8 @@ config CGROUP_PERF help This option extends the perf per-cpu mode to restrict monitoring to threads which belong to the cgroup specified and run on the - designated cpu. + designated cpu. Or this can be used to have cgroup ID in samples + so that it can monitor performance events among cgroups. Say N if unsure.
kernel/events/core.c +22 -0
@@ -1862,6 +1862,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)if (sample_type &PERF_SAMPLE_PHYS_ADDR ) size +=sizeof (data->phys_addr); +if (sample_type &PERF_SAMPLE_CGROUP ) + size +=sizeof (data->cgroup); + event->header_size = size; }
@@ -6867,6 +6870,9 @@ void perf_output_sample(struct perf_output_handle *handle,if (sample_type &PERF_SAMPLE_PHYS_ADDR )perf_output_put (handle, data->phys_addr); +if (sample_type &PERF_SAMPLE_CGROUP ) +perf_output_put (handle, data->cgroup); +if (sample_type &PERF_SAMPLE_AUX ) {perf_output_put (handle, data->aux_size);
@@ -7066,6 +7072,16 @@ void perf_prepare_sample(struct perf_event_header *header,if (sample_type &PERF_SAMPLE_PHYS_ADDR ) data->phys_addr =perf_virt_to_phys (data->addr); +#ifdef CONFIG_CGROUP_PERF +if (sample_type &PERF_SAMPLE_CGROUP ) { +struct cgroup *cgrp; + +/* protected by RCU */ + cgrp =task_css_check (current, perf_event_cgrp_id,1 )->cgroup; + data->cgroup =cgroup_id (cgrp); + } +#endif +if (sample_type &PERF_SAMPLE_AUX ) {u64 size;
@@ -11264,6 +11280,12 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,if (attr->sample_type &PERF_SAMPLE_REGS_INTR ) ret =perf_reg_validate (attr->sample_regs_intr); + +#ifndef CONFIG_CGROUP_PERF +if (attr->sample_type &PERF_SAMPLE_CGROUP ) +return -EINVAL ; +#endif + out:return ret;
Namhyung Kim
maintainerPATCH 3/9 perf tools: Basic support for CGROUP event
In reply to Namhyung KimImplement basic functionality to support cgroup tracking. Each cgroup can be identified by inode number which can be read from userspace too. The actual cgroup processing will come in the later patch.
--- tools/include/uapi/linux/perf_event.h | 16 ++++++++++++++-- tools/lib/perf/include/perf/event.h | 7 +++++++ tools/perf/builtin-diff.c | 1 + tools/perf/builtin-report.c | 1 + tools/perf/tests/sample-parsing.c | 6 +++++- tools/perf/util/event.c | 18 ++++++++++++++++++ tools/perf/util/event.h | 6 ++++++ tools/perf/util/evsel.c | 6 ++++++ tools/perf/util/machine.c | 12 ++++++++++++ tools/perf/util/machine.h | 3 +++ tools/perf/util/perf_event_attr_fprintf.c | 2 ++ tools/perf/util/session.c | 4 ++++ tools/perf/util/synthetic-events.c | 8 ++++++++ tools/perf/util/tool.h | 1 + 14 files changed, 88 insertions(+), 3 deletions(-)
tools/include/uapi/linux/perf_event.h +14 -2
@@ -142,8 +142,9 @@ enum perf_event_sample_format {PERF_SAMPLE_REGS_INTR =1U <<18 ,PERF_SAMPLE_PHYS_ADDR =1U <<19 ,PERF_SAMPLE_AUX =1U <<20 , +PERF_SAMPLE_CGROUP =1U <<21 , -PERF_SAMPLE_MAX =1U <<21 ,/* non-ABI */ +PERF_SAMPLE_MAX =1U <<22 ,/* non-ABI */ __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ };
@@ -381,7 +382,8 @@ struct perf_event_attr { ksymbol : 1, /* include ksymbol events */ bpf_event : 1, /* include bpf events */ aux_output : 1, /* generate AUX records instead of events */ - __reserved_1 : 32; + cgroup : 1, /* include cgroup events */ + __reserved_1 : 31;union {__u32 wakeup_events;/* wakeup every n events */
@@ -1012,6 +1014,16 @@ enum perf_event_type {*/ PERF_RECORD_BPF_EVENT =18 , +/* +* struct { +* struct perf_event_header header; +* u64 id; +* char path[]; +* struct sample_id sample_id; +* }; +*/ +PERF_RECORD_CGROUP =19 , + PERF_RECORD_MAX, /* non-ABI */ };
tools/lib/perf/include/perf/event.h +7 -0
@@ -105,6 +105,12 @@ struct perf_record_bpf_event {__u8 tag[BPF_TAG_SIZE ];// prog tag }; +struct perf_record_cgroup { +struct perf_event_header header; +__u64 id; +char path[PATH_MAX ]; +}; +struct perf_record_sample {struct perf_event_header header;__u64 array[];
@@ -352,6 +358,7 @@ union perf_event {struct perf_record_mmap2 mmap2;struct perf_record_comm comm;struct perf_record_namespaces namespaces; +struct perf_record_cgroup cgroup;struct perf_record_fork fork;struct perf_record_lost lost;struct perf_record_lost_samples lost_samples;
tools/perf/builtin-diff.c +1 -0
@@ -455,6 +455,7 @@ static struct perf_diff pdiff = { .fork = perf_event__process_fork, .lost = perf_event__process_lost, .namespaces = perf_event__process_namespaces, + .cgroup = perf_event__process_cgroup, .ordered_events = true, .ordering_requires_timestamps = true, },
tools/perf/builtin-report.c +1 -0
@@ -1105,6 +1105,7 @@ int cmd_report(int argc, const char **argv) .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, .namespaces = perf_event__process_namespaces, + .cgroup = perf_event__process_cgroup, .exit = perf_event__process_exit, .fork = perf_event__process_fork, .lost = perf_event__process_lost,
tools/perf/tests/sample-parsing.c +5 -1
@@ -151,6 +151,9 @@ static bool samples_same(const struct perf_sample *s1,if (type &PERF_SAMPLE_PHYS_ADDR )COMP (phys_addr); +if (type &PERF_SAMPLE_CGROUP ) +COMP (cgroup); +if (type &PERF_SAMPLE_AUX ) {COMP (aux_sample.size); if (memcmp(s1->aux_sample.data, s2->aux_sample.data,
@@ -230,6 +233,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) .regs = regs, }, .phys_addr = 113, + .cgroup = 114, .aux_sample = { .size = sizeof(aux_data), .data = (void *)aux_data,
@@ -336,7 +340,7 @@ int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_u* were added. Please actually update the test rather than just change * the condition below. */ -if (PERF_SAMPLE_MAX >PERF_SAMPLE_AUX <<1 ) { +if (PERF_SAMPLE_MAX >PERF_SAMPLE_CGROUP <<1 ) {pr_debug ("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n" );return -1 ; }
tools/perf/util/event.c +18 -0
@@ -54,6 +54,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_NAMESPACES] = "NAMESPACES", [PERF_RECORD_KSYMBOL] = "KSYMBOL", [PERF_RECORD_BPF_EVENT] = "BPF_EVENT", + [PERF_RECORD_CGROUP] = "CGROUP", [PERF_RECORD_HEADER_ATTR] = "ATTR", [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
@@ -180,6 +181,12 @@ size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp)return ret; } +size_t perf_event__fprintf_cgroup (union perf_event *event,FILE *fp) +{ +return fprintf (fp," cgroup: %" PRI_lu64" %s\n" , + event->cgroup.id, event->cgroup.path); +} + int perf_event__process_comm(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample,
@@ -196,6 +203,14 @@ int perf_event__process_namespaces(struct perf_tool *tool __maybe_unused,return machine__process_namespaces_event (machine, event, sample); } +int perf_event__process_cgroup (struct perf_tool *tool__maybe_unused , +union perf_event *event, +struct perf_sample *sample, +struct machine *machine) +{ +return machine__process_cgroup_event (machine, event, sample); +} + int perf_event__process_lost(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample,
@@ -417,6 +432,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)case PERF_RECORD_NAMESPACES : ret +=perf_event__fprintf_namespaces (event, fp);break ; +case PERF_RECORD_CGROUP : + ret +=perf_event__fprintf_cgroup (event, fp); +break ;case PERF_RECORD_MMAP2 : ret +=perf_event__fprintf_mmap2 (event, fp);break ;
tools/perf/util/event.h +6 -0
@@ -135,6 +135,7 @@ struct perf_sample {u32 raw_size;u64 data_src;u64 phys_addr; +u64 cgroup;u32 flags;u16 insn_len;u8 cpumode;
@@ -322,6 +323,10 @@ int perf_event__process_namespaces(struct perf_tool *tool,union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_event__process_cgroup (struct perf_tool *tool, +union perf_event *event, +struct perf_sample *sample, +struct machine *machine); int perf_event__process_mmap(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample,
@@ -377,6 +382,7 @@ size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);size_t perf_event__fprintf_thread_map (union perf_event *event,FILE *fp);size_t perf_event__fprintf_cpu_map (union perf_event *event,FILE *fp);size_t perf_event__fprintf_namespaces (union perf_event *event,FILE *fp); +size_t perf_event__fprintf_cgroup (union perf_event *event,FILE *fp);size_t perf_event__fprintf_ksymbol (union perf_event *event,FILE *fp);size_t perf_event__fprintf_bpf (union perf_event *event,FILE *fp);size_t perf_event__fprintf (union perf_event *event,FILE *fp);
tools/perf/util/evsel.c +6 -0
@@ -2267,6 +2267,12 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event, array++; } + data->cgroup =0 ; +if (type &PERF_SAMPLE_CGROUP ) { + data->cgroup = *array; + array++; + } +if (type &PERF_SAMPLE_AUX ) {OVERFLOW_CHECK_u64 (array); sz = *array++;
tools/perf/util/machine.c +12 -0
@@ -654,6 +654,16 @@ int machine__process_namespaces_event(struct machine *machine __maybe_unused,return err; } +int machine__process_cgroup_event (struct machine *machine__maybe_unused , +union perf_event *event, +struct perf_sample *sample__maybe_unused ) +{ +if (dump_trace) +perf_event__fprintf_cgroup (event, stdout); + +return 0 ; +} +int machine__process_lost_event (struct machine *machine__maybe_unused ,union perf_event *event,struct perf_sample *sample__maybe_unused ) {
@@ -1878,6 +1888,8 @@ int machine__process_event(struct machine *machine, union perf_event *event, ret =machine__process_mmap_event (machine, event, sample);break ;case PERF_RECORD_NAMESPACES : ret =machine__process_namespaces_event (machine, event, sample);break ; +case PERF_RECORD_CGROUP : + ret =machine__process_cgroup_event (machine, event, sample);break ;case PERF_RECORD_MMAP2 : ret =machine__process_mmap2_event (machine, event, sample);break ;case PERF_RECORD_FORK :
tools/perf/util/machine.h +3 -0
@@ -128,6 +128,9 @@ int machine__process_switch_event(struct machine *machine,int machine__process_namespaces_event (struct machine *machine,union perf_event *event,struct perf_sample *sample); +int machine__process_cgroup_event (struct machine *machine, +union perf_event *event, +struct perf_sample *sample);int machine__process_mmap_event (struct machine *machine,union perf_event *event,struct perf_sample *sample); int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
tools/perf/util/perf_event_attr_fprintf.c +2 -0
@@ -35,6 +35,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)bit_name (BRANCH_STACK ),bit_name (REGS_USER ),bit_name (STACK_USER ),bit_name (IDENTIFIER ),bit_name (REGS_INTR ),bit_name (DATA_SRC ),bit_name (WEIGHT ),bit_name (PHYS_ADDR ),bit_name (AUX ), +bit_name (CGROUP ), { .name = NULL, } };#undef bit_name
@@ -132,6 +133,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,PRINT_ATTRf (ksymbol, p_unsigned);PRINT_ATTRf (bpf_event, p_unsigned);PRINT_ATTRf (aux_output, p_unsigned); +PRINT_ATTRf (cgroup, p_unsigned);PRINT_ATTRn ("{ wakeup_events, wakeup_watermark }" , wakeup_events, p_unsigned);PRINT_ATTRf (bp_type, p_unsigned);
tools/perf/util/session.c +4 -0
@@ -471,6 +471,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->comm = process_event_stub;if (tool->namespaces ==NULL ) tool->namespaces = process_event_stub; +if (tool->cgroup ==NULL ) + tool->cgroup = process_event_stub;if (tool->fork ==NULL ) tool->fork = process_event_stub;if (tool->exit ==NULL )
@@ -1436,6 +1438,8 @@ static int machines__deliver_event(struct machines *machines,return tool->comm (tool, event, sample, machine);case PERF_RECORD_NAMESPACES :return tool->namespaces (tool, event, sample, machine); +case PERF_RECORD_CGROUP : +return tool->cgroup (tool, event, sample, machine);case PERF_RECORD_FORK :return tool->fork (tool, event, sample, machine);case PERF_RECORD_EXIT :
tools/perf/util/synthetic-events.c +8 -0
@@ -1230,6 +1230,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,if (type &PERF_SAMPLE_PHYS_ADDR ) result +=sizeof (u64); +if (type &PERF_SAMPLE_CGROUP ) + result +=sizeof (u64); +if (type &PERF_SAMPLE_AUX ) { result +=sizeof (u64); result += sample->aux_sample.size;
@@ -1404,6 +1407,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo array++; } +if (type &PERF_SAMPLE_CGROUP ) { + *array = sample->cgroup; + array++; + } +if (type &PERF_SAMPLE_AUX ) { sz = sample->aux_sample.size; *array++ = sz;
tools/perf/util/tool.h +1 -0
@@ -46,6 +46,7 @@ struct perf_tool { mmap2, comm, namespaces, + cgroup, fork, exit, lost,
Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
Re: [PATCH 3/9] perf tools: Basic support for CGROUP event
Em Wed, Mar 25, 2020 at 09:45:30PM +0900, Namhyung Kim escreveu:
Quoted 9 lines
Implement basic functionality to support cgroup tracking. Each cgroup can be identified by inode number which can be read from userspace too. The actual cgroup processing will come in the later patch.
Cc Adrian Hunter <[email protected]>[fix perf test failure on sampling parsing]Reported-by kernel test robot <[email protected]>Signed-off-by Namhyung Kim <[email protected]>---
I'm just separating the UAPI header from the rest of this patch, as has been usual,
- Arnaldo
Quoted 363 lines
tools/include/uapi/linux/perf_event.h | 16 ++++++++++++++-- tools/lib/perf/include/perf/event.h | 7 +++++++ tools/perf/builtin-diff.c | 1 + tools/perf/builtin-report.c | 1 + tools/perf/tests/sample-parsing.c | 6 +++++- tools/perf/util/event.c | 18 ++++++++++++++++++ tools/perf/util/event.h | 6 ++++++ tools/perf/util/evsel.c | 6 ++++++ tools/perf/util/machine.c | 12 ++++++++++++ tools/perf/util/machine.h | 3 +++ tools/perf/util/perf_event_attr_fprintf.c | 2 ++ tools/perf/util/session.c | 4 ++++ tools/perf/util/synthetic-events.c | 8 ++++++++ tools/perf/util/tool.h | 1 + 14 files changed, 88 insertions(+), 3 deletions(-)tools/include/uapi/linux/perf_event.h +14
-2@@ -142,8 +142,9 @@ enum perf_event_sample_format {PERF_SAMPLE_REGS_INTR =1U <<18 ,PERF_SAMPLE_PHYS_ADDR =1U <<19 ,PERF_SAMPLE_AUX =1U <<20 , +PERF_SAMPLE_CGROUP =1U <<21 , -PERF_SAMPLE_MAX =1U <<21 ,/* non-ABI */ +PERF_SAMPLE_MAX =1U <<22 ,/* non-ABI */ __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ };@@ -381,7 +382,8 @@ struct perf_event_attr { ksymbol : 1, /* include ksymbol events */ bpf_event : 1, /* include bpf events */ aux_output : 1, /* generate AUX records instead of events */ - __reserved_1 : 32; + cgroup : 1, /* include cgroup events */ + __reserved_1 : 31;union {__u32 wakeup_events;/* wakeup every n events */ @@ -1012,6 +1014,16 @@ enum perf_event_type {*/ PERF_RECORD_BPF_EVENT =18 , +/* +* struct { +* struct perf_event_header header; +* u64 id; +* char path[]; +* struct sample_id sample_id; +* }; +*/ +PERF_RECORD_CGROUP =19 , + PERF_RECORD_MAX, /* non-ABI */ };tools/lib/perf/include/perf/event.h +7
-0@@ -105,6 +105,12 @@ struct perf_record_bpf_event {__u8 tag[BPF_TAG_SIZE ];// prog tag }; +struct perf_record_cgroup { +struct perf_event_header header; +__u64 id; +char path[PATH_MAX ]; +}; +struct perf_record_sample {struct perf_event_header header;__u64 array[];@@ -352,6 +358,7 @@ union perf_event {struct perf_record_mmap2 mmap2;struct perf_record_comm comm;struct perf_record_namespaces namespaces; +struct perf_record_cgroup cgroup;struct perf_record_fork fork;struct perf_record_lost lost;struct perf_record_lost_samples lost_samples;tools/perf/builtin-diff.c +1
-0@@ -455,6 +455,7 @@ static struct perf_diff pdiff = { .fork = perf_event__process_fork, .lost = perf_event__process_lost, .namespaces = perf_event__process_namespaces, + .cgroup = perf_event__process_cgroup, .ordered_events = true, .ordering_requires_timestamps = true, },tools/perf/builtin-report.c +1
-0@@ -1105,6 +1105,7 @@ int cmd_report(int argc, const char **argv) .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, .namespaces = perf_event__process_namespaces, + .cgroup = perf_event__process_cgroup, .exit = perf_event__process_exit, .fork = perf_event__process_fork, .lost = perf_event__process_lost,tools/perf/tests/sample-parsing.c +5
-1@@ -151,6 +151,9 @@ static bool samples_same(const struct perf_sample *s1,if (type &PERF_SAMPLE_PHYS_ADDR )COMP (phys_addr); +if (type &PERF_SAMPLE_CGROUP ) +COMP (cgroup); +if (type &PERF_SAMPLE_AUX ) {COMP (aux_sample.size); if (memcmp(s1->aux_sample.data, s2->aux_sample.data,@@ -230,6 +233,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) .regs = regs, }, .phys_addr = 113, + .cgroup = 114, .aux_sample = { .size = sizeof(aux_data), .data = (void *)aux_data,@@ -336,7 +340,7 @@ int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_u* were added. Please actually update the test rather than just change * the condition below. */ -if (PERF_SAMPLE_MAX >PERF_SAMPLE_AUX <<1 ) { +if (PERF_SAMPLE_MAX >PERF_SAMPLE_CGROUP <<1 ) {pr_debug ("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n" );return -1 ; }tools/perf/util/event.c +18
-0@@ -54,6 +54,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_NAMESPACES] = "NAMESPACES", [PERF_RECORD_KSYMBOL] = "KSYMBOL", [PERF_RECORD_BPF_EVENT] = "BPF_EVENT", + [PERF_RECORD_CGROUP] = "CGROUP", [PERF_RECORD_HEADER_ATTR] = "ATTR", [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",@@ -180,6 +181,12 @@ size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp)return ret; } +size_t perf_event__fprintf_cgroup (union perf_event *event,FILE *fp) +{ +return fprintf (fp," cgroup: %" PRI_lu64" %s\n" , + event->cgroup.id, event->cgroup.path); +} + int perf_event__process_comm(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample,@@ -196,6 +203,14 @@ int perf_event__process_namespaces(struct perf_tool *tool __maybe_unused,return machine__process_namespaces_event (machine, event, sample); } +int perf_event__process_cgroup (struct perf_tool *tool__maybe_unused , +union perf_event *event, +struct perf_sample *sample, +struct machine *machine) +{ +return machine__process_cgroup_event (machine, event, sample); +} + int perf_event__process_lost(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample,@@ -417,6 +432,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)case PERF_RECORD_NAMESPACES : ret +=perf_event__fprintf_namespaces (event, fp);break ; +case PERF_RECORD_CGROUP : + ret +=perf_event__fprintf_cgroup (event, fp); +break ;case PERF_RECORD_MMAP2 : ret +=perf_event__fprintf_mmap2 (event, fp);break ;tools/perf/util/event.h +6
-0@@ -135,6 +135,7 @@ struct perf_sample {u32 raw_size;u64 data_src;u64 phys_addr; +u64 cgroup;u32 flags;u16 insn_len;u8 cpumode;@@ -322,6 +323,10 @@ int perf_event__process_namespaces(struct perf_tool *tool,union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_event__process_cgroup (struct perf_tool *tool, +union perf_event *event, +struct perf_sample *sample, +struct machine *machine); int perf_event__process_mmap(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample,@@ -377,6 +382,7 @@ size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);size_t perf_event__fprintf_thread_map (union perf_event *event,FILE *fp);size_t perf_event__fprintf_cpu_map (union perf_event *event,FILE *fp);size_t perf_event__fprintf_namespaces (union perf_event *event,FILE *fp); +size_t perf_event__fprintf_cgroup (union perf_event *event,FILE *fp);size_t perf_event__fprintf_ksymbol (union perf_event *event,FILE *fp);size_t perf_event__fprintf_bpf (union perf_event *event,FILE *fp);size_t perf_event__fprintf (union perf_event *event,FILE *fp);tools/perf/util/evsel.c +6
-0@@ -2267,6 +2267,12 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event, array++; } + data->cgroup =0 ; +if (type &PERF_SAMPLE_CGROUP ) { + data->cgroup = *array; + array++; + } +if (type &PERF_SAMPLE_AUX ) {OVERFLOW_CHECK_u64 (array); sz = *array++;tools/perf/util/machine.c +12
-0@@ -654,6 +654,16 @@ int machine__process_namespaces_event(struct machine *machine __maybe_unused,return err; } +int machine__process_cgroup_event (struct machine *machine__maybe_unused , +union perf_event *event, +struct perf_sample *sample__maybe_unused ) +{ +if (dump_trace) +perf_event__fprintf_cgroup (event, stdout); + +return 0 ; +} +int machine__process_lost_event (struct machine *machine__maybe_unused ,union perf_event *event,struct perf_sample *sample__maybe_unused ) {@@ -1878,6 +1888,8 @@ int machine__process_event(struct machine *machine, union perf_event *event, ret =machine__process_mmap_event (machine, event, sample);break ;case PERF_RECORD_NAMESPACES : ret =machine__process_namespaces_event (machine, event, sample);break ; +case PERF_RECORD_CGROUP : + ret =machine__process_cgroup_event (machine, event, sample);break ;case PERF_RECORD_MMAP2 : ret =machine__process_mmap2_event (machine, event, sample);break ;case PERF_RECORD_FORK :tools/perf/util/machine.h +3
-0@@ -128,6 +128,9 @@ int machine__process_switch_event(struct machine *machine,int machine__process_namespaces_event (struct machine *machine,union perf_event *event,struct perf_sample *sample); +int machine__process_cgroup_event (struct machine *machine, +union perf_event *event, +struct perf_sample *sample);int machine__process_mmap_event (struct machine *machine,union perf_event *event,struct perf_sample *sample); int machine__process_mmap2_event(struct machine *machine, union perf_event *event,tools/perf/util/perf_event_attr_fprintf.c +2
-0@@ -35,6 +35,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)bit_name (BRANCH_STACK ),bit_name (REGS_USER ),bit_name (STACK_USER ),bit_name (IDENTIFIER ),bit_name (REGS_INTR ),bit_name (DATA_SRC ),bit_name (WEIGHT ),bit_name (PHYS_ADDR ),bit_name (AUX ), +bit_name (CGROUP ), { .name = NULL, } };#undef bit_name@@ -132,6 +133,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,PRINT_ATTRf (ksymbol, p_unsigned);PRINT_ATTRf (bpf_event, p_unsigned);PRINT_ATTRf (aux_output, p_unsigned); +PRINT_ATTRf (cgroup, p_unsigned);PRINT_ATTRn ("{ wakeup_events, wakeup_watermark }" , wakeup_events, p_unsigned);PRINT_ATTRf (bp_type, p_unsigned);tools/perf/util/session.c +4
-0@@ -471,6 +471,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->comm = process_event_stub;if (tool->namespaces ==NULL ) tool->namespaces = process_event_stub; +if (tool->cgroup ==NULL ) + tool->cgroup = process_event_stub;if (tool->fork ==NULL ) tool->fork = process_event_stub;if (tool->exit ==NULL )@@ -1436,6 +1438,8 @@ static int machines__deliver_event(struct machines *machines,return tool->comm (tool, event, sample, machine);case PERF_RECORD_NAMESPACES :return tool->namespaces (tool, event, sample, machine); +case PERF_RECORD_CGROUP : +return tool->cgroup (tool, event, sample, machine);case PERF_RECORD_FORK :return tool->fork (tool, event, sample, machine);case PERF_RECORD_EXIT :tools/perf/util/synthetic-events.c +8
-0@@ -1230,6 +1230,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,if (type &PERF_SAMPLE_PHYS_ADDR ) result +=sizeof (u64); +if (type &PERF_SAMPLE_CGROUP ) + result +=sizeof (u64); +if (type &PERF_SAMPLE_AUX ) { result +=sizeof (u64); result += sample->aux_sample.size;@@ -1404,6 +1407,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo array++; } +if (type &PERF_SAMPLE_CGROUP ) { + *array = sample->cgroup; + array++; + } +if (type &PERF_SAMPLE_AUX ) { sz = sample->aux_sample.size; *array++ = sz;tools/perf/util/tool.h +1
-0@@ -46,6 +46,7 @@ struct perf_tool { mmap2, comm, namespaces, + cgroup, fork, exit, lost,Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
Signature · 1 line
- Arnaldo
[tip: perf/urgent] perf tools: Basic support for CGROUP event
In reply to Namhyung KimThe following commit has been merged into the perf/urgent branch of tip:
The following commit has been merged into the perf/urgent branch of tip:
Commit-ID: ba78c1c5461c2fc2f57b777e971b3a9ec0df5666 Gitweb: https://git.kernel.org/tip/ba78c1c5461c2fc2f57b777e971b3a9ec0df5666 Author: Namhyung Kim <[email protected]> AuthorDate: Wed, 25 Mar 2020 21:45:30 +09:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Fri, 03 Apr 2020 09:37:55 -03:00
perf tools: Basic support for CGROUP event
Implement basic functionality to support cgroup tracking. Each cgroup can be identified by inode number which can be read from userspace too. The actual cgroup processing will come in the later patch.
--- tools/lib/perf/include/perf/event.h | 7 +++++++ tools/perf/builtin-diff.c | 1 + tools/perf/builtin-report.c | 1 + tools/perf/tests/sample-parsing.c | 6 +++++- tools/perf/util/event.c | 18 ++++++++++++++++++ tools/perf/util/event.h | 6 ++++++ tools/perf/util/evsel.c | 6 ++++++ tools/perf/util/machine.c | 12 ++++++++++++ tools/perf/util/machine.h | 3 +++ tools/perf/util/perf_event_attr_fprintf.c | 2 ++ tools/perf/util/session.c | 4 ++++ tools/perf/util/synthetic-events.c | 8 ++++++++ tools/perf/util/tool.h | 1 + 13 files changed, 74 insertions(+), 1 deletion(-)
tools/lib/perf/include/perf/event.h +7 -0
@@ -105,6 +105,12 @@ struct perf_record_bpf_event {__u8 tag[BPF_TAG_SIZE ];// prog tag }; +struct perf_record_cgroup { +struct perf_event_header header; +__u64 id; +char path[PATH_MAX ]; +}; +struct perf_record_sample {struct perf_event_header header;__u64 array[];
@@ -352,6 +358,7 @@ union perf_event {struct perf_record_mmap2 mmap2;struct perf_record_comm comm;struct perf_record_namespaces namespaces; +struct perf_record_cgroup cgroup;struct perf_record_fork fork;struct perf_record_lost lost;struct perf_record_lost_samples lost_samples;
tools/perf/builtin-diff.c +1 -0
@@ -455,6 +455,7 @@ static struct perf_diff pdiff = { .fork = perf_event__process_fork, .lost = perf_event__process_lost, .namespaces = perf_event__process_namespaces, + .cgroup = perf_event__process_cgroup, .ordered_events = true, .ordering_requires_timestamps = true, },
tools/perf/builtin-report.c +1 -0
@@ -1105,6 +1105,7 @@ int cmd_report(int argc, const char **argv) .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, .namespaces = perf_event__process_namespaces, + .cgroup = perf_event__process_cgroup, .exit = perf_event__process_exit, .fork = perf_event__process_fork, .lost = perf_event__process_lost,
tools/perf/tests/sample-parsing.c +5 -1
@@ -151,6 +151,9 @@ static bool samples_same(const struct perf_sample *s1,if (type &PERF_SAMPLE_PHYS_ADDR )COMP (phys_addr); +if (type &PERF_SAMPLE_CGROUP ) +COMP (cgroup); +if (type &PERF_SAMPLE_AUX ) {COMP (aux_sample.size); if (memcmp(s1->aux_sample.data, s2->aux_sample.data,
@@ -230,6 +233,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) .regs = regs, }, .phys_addr = 113, + .cgroup = 114, .aux_sample = { .size = sizeof(aux_data), .data = (void *)aux_data,
@@ -336,7 +340,7 @@ int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_u* were added. Please actually update the test rather than just change * the condition below. */ -if (PERF_SAMPLE_MAX >PERF_SAMPLE_AUX <<1 ) { +if (PERF_SAMPLE_MAX >PERF_SAMPLE_CGROUP <<1 ) {pr_debug ("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n" );return -1 ; }
tools/perf/util/event.c +18 -0
@@ -54,6 +54,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_NAMESPACES] = "NAMESPACES", [PERF_RECORD_KSYMBOL] = "KSYMBOL", [PERF_RECORD_BPF_EVENT] = "BPF_EVENT", + [PERF_RECORD_CGROUP] = "CGROUP", [PERF_RECORD_HEADER_ATTR] = "ATTR", [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
@@ -180,6 +181,12 @@ size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp)return ret; } +size_t perf_event__fprintf_cgroup (union perf_event *event,FILE *fp) +{ +return fprintf (fp," cgroup: %" PRI_lu64" %s\n" , + event->cgroup.id, event->cgroup.path); +} + int perf_event__process_comm(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample,
@@ -196,6 +203,14 @@ int perf_event__process_namespaces(struct perf_tool *tool __maybe_unused,return machine__process_namespaces_event (machine, event, sample); } +int perf_event__process_cgroup (struct perf_tool *tool__maybe_unused , +union perf_event *event, +struct perf_sample *sample, +struct machine *machine) +{ +return machine__process_cgroup_event (machine, event, sample); +} + int perf_event__process_lost(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample,
@@ -417,6 +432,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)case PERF_RECORD_NAMESPACES : ret +=perf_event__fprintf_namespaces (event, fp);break ; +case PERF_RECORD_CGROUP : + ret +=perf_event__fprintf_cgroup (event, fp); +break ;case PERF_RECORD_MMAP2 : ret +=perf_event__fprintf_mmap2 (event, fp);break ;
tools/perf/util/event.h +6 -0
@@ -135,6 +135,7 @@ struct perf_sample {u32 raw_size;u64 data_src;u64 phys_addr; +u64 cgroup;u32 flags;u16 insn_len;u8 cpumode;
@@ -322,6 +323,10 @@ int perf_event__process_namespaces(struct perf_tool *tool,union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_event__process_cgroup (struct perf_tool *tool, +union perf_event *event, +struct perf_sample *sample, +struct machine *machine); int perf_event__process_mmap(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample,
@@ -377,6 +382,7 @@ size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);size_t perf_event__fprintf_thread_map (union perf_event *event,FILE *fp);size_t perf_event__fprintf_cpu_map (union perf_event *event,FILE *fp);size_t perf_event__fprintf_namespaces (union perf_event *event,FILE *fp); +size_t perf_event__fprintf_cgroup (union perf_event *event,FILE *fp);size_t perf_event__fprintf_ksymbol (union perf_event *event,FILE *fp);size_t perf_event__fprintf_bpf (union perf_event *event,FILE *fp);size_t perf_event__fprintf (union perf_event *event,FILE *fp);
tools/perf/util/evsel.c +6 -0
@@ -2267,6 +2267,12 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event, array++; } + data->cgroup =0 ; +if (type &PERF_SAMPLE_CGROUP ) { + data->cgroup = *array; + array++; + } +if (type &PERF_SAMPLE_AUX ) {OVERFLOW_CHECK_u64 (array); sz = *array++;
tools/perf/util/machine.c +12 -0
@@ -654,6 +654,16 @@ int machine__process_namespaces_event(struct machine *machine __maybe_unused,return err; } +int machine__process_cgroup_event (struct machine *machine__maybe_unused , +union perf_event *event, +struct perf_sample *sample__maybe_unused ) +{ +if (dump_trace) +perf_event__fprintf_cgroup (event, stdout); + +return 0 ; +} +int machine__process_lost_event (struct machine *machine__maybe_unused ,union perf_event *event,struct perf_sample *sample__maybe_unused ) {
@@ -1878,6 +1888,8 @@ int machine__process_event(struct machine *machine, union perf_event *event, ret =machine__process_mmap_event (machine, event, sample);break ;case PERF_RECORD_NAMESPACES : ret =machine__process_namespaces_event (machine, event, sample);break ; +case PERF_RECORD_CGROUP : + ret =machine__process_cgroup_event (machine, event, sample);break ;case PERF_RECORD_MMAP2 : ret =machine__process_mmap2_event (machine, event, sample);break ;case PERF_RECORD_FORK :
tools/perf/util/machine.h +3 -0
@@ -128,6 +128,9 @@ int machine__process_switch_event(struct machine *machine,int machine__process_namespaces_event (struct machine *machine,union perf_event *event,struct perf_sample *sample); +int machine__process_cgroup_event (struct machine *machine, +union perf_event *event, +struct perf_sample *sample);int machine__process_mmap_event (struct machine *machine,union perf_event *event,struct perf_sample *sample); int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
tools/perf/util/perf_event_attr_fprintf.c +2 -0
@@ -35,6 +35,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)bit_name (BRANCH_STACK ),bit_name (REGS_USER ),bit_name (STACK_USER ),bit_name (IDENTIFIER ),bit_name (REGS_INTR ),bit_name (DATA_SRC ),bit_name (WEIGHT ),bit_name (PHYS_ADDR ),bit_name (AUX ), +bit_name (CGROUP ), { .name = NULL, } };#undef bit_name
@@ -132,6 +133,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,PRINT_ATTRf (ksymbol, p_unsigned);PRINT_ATTRf (bpf_event, p_unsigned);PRINT_ATTRf (aux_output, p_unsigned); +PRINT_ATTRf (cgroup, p_unsigned);PRINT_ATTRn ("{ wakeup_events, wakeup_watermark }" , wakeup_events, p_unsigned);PRINT_ATTRf (bp_type, p_unsigned);
tools/perf/util/session.c +4 -0
@@ -471,6 +471,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->comm = process_event_stub;if (tool->namespaces ==NULL ) tool->namespaces = process_event_stub; +if (tool->cgroup ==NULL ) + tool->cgroup = process_event_stub;if (tool->fork ==NULL ) tool->fork = process_event_stub;if (tool->exit ==NULL )
@@ -1436,6 +1438,8 @@ static int machines__deliver_event(struct machines *machines,return tool->comm (tool, event, sample, machine);case PERF_RECORD_NAMESPACES :return tool->namespaces (tool, event, sample, machine); +case PERF_RECORD_CGROUP : +return tool->cgroup (tool, event, sample, machine);case PERF_RECORD_FORK :return tool->fork (tool, event, sample, machine);case PERF_RECORD_EXIT :
tools/perf/util/synthetic-events.c +8 -0
@@ -1230,6 +1230,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,if (type &PERF_SAMPLE_PHYS_ADDR ) result +=sizeof (u64); +if (type &PERF_SAMPLE_CGROUP ) + result +=sizeof (u64); +if (type &PERF_SAMPLE_AUX ) { result +=sizeof (u64); result += sample->aux_sample.size;
@@ -1404,6 +1407,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo array++; } +if (type &PERF_SAMPLE_CGROUP ) { + *array = sample->cgroup; + array++; + } +if (type &PERF_SAMPLE_AUX ) { sz = sample->aux_sample.size; *array++ = sz;
tools/perf/util/tool.h +1 -0
@@ -46,6 +46,7 @@ struct perf_tool { mmap2, comm, namespaces, + cgroup, fork, exit, lost,
Namhyung Kim
maintainerPATCH 4/9 perf tools: Maintain cgroup hierarchy
In reply to Namhyung KimEach cgroup is kept in the perf_env's cgroup_tree sorted by the cgroup id. Hist entries have cgroup id can compare it directly and later it can be used to find a group name using this tree.
--- tools/perf/util/cgroup.c | 80 +++++++++++++++++++++++++++++++++++++++ tools/perf/util/cgroup.h | 17 +++++++-- tools/perf/util/env.c | 2 + tools/perf/util/env.h | 6 +++ tools/perf/util/machine.c | 9 ++++- 5 files changed, 109 insertions(+), 5 deletions(-)
tools/perf/util/cgroup.c +80 -0
@@ -191,3 +191,83 @@ int parse_cgroups(const struct option *opt, const char *str, }return 0 ; } + +static struct cgroup *__cgroup__findnew (struct rb_root *root,uint64_t id, +bool create,const char *path) +{ +struct rb_node **p = &root->rb_node; +struct rb_node *parent =NULL ; +struct cgroup *cgrp; + +while (*p !=NULL ) { + parent = *p; + cgrp = rb_entry(parent, struct cgroup, node); + +if (cgrp->id == id) +return cgrp; + +if (cgrp->id < id) + p = &(*p)->rb_left; +else + p = &(*p)->rb_right; + } + +if (!create) +return NULL ; + + cgrp =malloc (sizeof (*cgrp)); +if (cgrp ==NULL ) +return NULL ; + + cgrp->name =strdup (path); +if (cgrp->name ==NULL ) { +free (cgrp); +return NULL ; + } + + cgrp->fd =-1 ; + cgrp->id = id; +refcount_set (&cgrp->refcnt,1 ); + +rb_link_node (&cgrp->node, parent, p); +rb_insert_color (&cgrp->node, root); + +return cgrp; +} + +struct cgroup *cgroup__findnew (struct perf_env *env,uint64_t id, +const char *path) +{ +struct cgroup *cgrp; + +down_write (&env->cgroups.lock); + cgrp =__cgroup__findnew (&env->cgroups.tree, id, true, path); +up_write (&env->cgroups.lock); +return cgrp; +} + +struct cgroup *cgroup__find (struct perf_env *env,uint64_t id) +{ +struct cgroup *cgrp; + +down_read (&env->cgroups.lock); + cgrp =__cgroup__findnew (&env->cgroups.tree, id, false,NULL ); +up_read (&env->cgroups.lock); +return cgrp; +} + +void perf_env__purge_cgroups (struct perf_env *env) +{ +struct rb_node *node; +struct cgroup *cgrp; + +down_write (&env->cgroups.lock); +while (!RB_EMPTY_ROOT (&env->cgroups.tree)) { + node =rb_first (&env->cgroups.tree); + cgrp = rb_entry(node, struct cgroup, node); + +rb_erase (node, &env->cgroups.tree); +cgroup__put (cgrp); + } +up_write (&env->cgroups.lock); +}
tools/perf/util/cgroup.h +13 -4
@@ -3,16 +3,19 @@#define __CGROUP_H__#include <linux/refcount.h> +#include <linux/rbtree.h> +#include "util/env.h" struct option ;struct cgroup { -char *name; -int fd; -refcount_t refcnt; +struct rb_node node; +u64 id; +char *name; +int fd; +refcount_t refcnt; }; -extern int nr_cgroups;/* number of explicit cgroups defined */ struct cgroup *cgroup__get (struct cgroup *cgroup);
@@ -26,4 +29,10 @@ void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup);int parse_cgroups (const struct option *opt,const char *str,int unset); +struct cgroup *cgroup__findnew (struct perf_env *env,uint64_t id, +const char *path); +struct cgroup *cgroup__find (struct perf_env *env,uint64_t id); + +void perf_env__purge_cgroups (struct perf_env *env); +#endif /* __CGROUP_H__ */
tools/perf/util/env.c +2 -0
@@ -6,6 +6,7 @@#include <linux/ctype.h> #include <linux/zalloc.h> #include "bpf-event.h" +#include "cgroup.h" #include <errno.h> #include <sys/utsname.h> #include <bpf/libbpf.h>
@@ -168,6 +169,7 @@ void perf_env__exit(struct perf_env *env)int i;perf_env__purge_bpf (env); +perf_env__purge_cgroups (env);zfree (&env->hostname);zfree (&env->os_release);zfree (&env->version);
tools/perf/util/env.h +6 -0
@@ -88,6 +88,12 @@ struct perf_env {u32 btfs_cnt; } bpf_progs; +/* same reason as above (for perf-top) */ +struct { +struct rw_semaphore lock; +struct rb_root tree; + } cgroups; +/* For fast cpu to numa node lookup via perf_env__numa_node */ int *numa_map;int nr_numa_map;
tools/perf/util/machine.c +8 -1
@@ -33,6 +33,7 @@#include "asm/bug.h" #include "bpf-event.h" #include <internal/lib.h> // page_size +#include "cgroup.h" #include <linux/ctype.h> #include <symbol/kallsyms.h>
@@ -654,13 +655,19 @@ int machine__process_namespaces_event(struct machine *machine __maybe_unused,return err; } -int machine__process_cgroup_event (struct machine *machine__maybe_unused , +int machine__process_cgroup_event (struct machine *machine,union perf_event *event,struct perf_sample *sample__maybe_unused ) { +struct cgroup *cgrp; +if (dump_trace)perf_event__fprintf_cgroup (event, stdout); + cgrp =cgroup__findnew (machine->env, event->cgroup.id, event->cgroup.path); +if (cgrp ==NULL ) +return -ENOMEM ; +return 0 ; }
Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
Re: [PATCH 4/9] perf tools: Maintain cgroup hierarchy
Em Wed, Mar 25, 2020 at 09:45:31PM +0900, Namhyung Kim escreveu:
Quoted 3 lines
Each cgroup is kept in the perf_env's
cgroup_treesorted by the cgroup id. Hist entries have cgroup id can compare it directly and later it can be used to find a group name using this tree.
This one breaks the 'perf test python' test, I fixed it adding this patch before your series:
From ea3c4ab73cb2ea2960bba6894560b1ef91e69737 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <[email protected]>
Date: Fri, 3 Apr 2020 09:29:52 -0300
Subject: [PATCH 1/1] perf python: Include rwsem.c in the pythong biding
We'll need it for the cgroup patches, and its better to have it in a separate patch in case we need to later revert the cgroup patches.
I.e. without this we have:
[root@five ~]# perf test -v python
19: 'import perf' in python :
--- start ---
test child forked, pid 148447
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
ImportError: /tmp/build/perf/python/perf.cpython-37m-x86_64-linux-gnu.so: undefined symbol: down_write test child finished with -1
---- end ----
'import perf' in python: FAILED!
[root@five ~]#
--- tools/perf/util/python-ext-sources | 1 + 1 file changed, 1 insertion(+)
tools/perf/util/python-ext-sources +1 -0
@@ -34,3 +34,4 @@ util/string.c util/symbol_fprintf.c util/units.c util/affinity.c +util/rwsem.c
Signature · 1 line
2.25.1
Namhyung Kim
maintainerRe: [PATCH 4/9] perf tools: Maintain cgroup hierarchy
Hi Arnaldo,
Quoted 8 lines · Arnaldo Carvalho de Melo
Em Wed, Mar 25, 2020 at 09:45:31PM +0900, Namhyung Kim escreveu:
Quoted 3 lines
Each cgroup is kept in the perf_env's
cgroup_treesorted by the cgroup id. Hist entries have cgroup id can compare it directly and later it can be used to find a group name using this tree.This one breaks the 'perf test python' test, I fixed it adding this patch before your series:
Thanks a lot for fixing this and taking care of the whole thing! Namhyung
Quoted 45 lines
From
ea3c4ab73cb2ea2960bba6894560b1ef91e69737Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <[email protected]>
Date: Fri, 3 Apr 2020 09:29:52 -0300
Subject: [PATCH 1/1] perf python: Includerwsem.cin the pythong bidingWe'll need it for the cgroup patches, and its better to have it in a separate patch in case we need to later revert the cgroup patches.
I.e. without this we have:
[root@five ~]# perf test -v python
19: 'import perf' in python :
--- start ---
test child forked, pid 148447
Traceback (most recent call last):File "<stdin>", line 1, in <module>ImportError:
/tmp/build/perf/python/perf.cpython-37m-x86_64-linux-gnu.so: undefined symbol:down_writetest child finished with -1
---- end ----
'import perf' in python: FAILED!
[root@five ~]#Cc Adrian Hunter <[email protected]>Cc Alexander Shishkin <[email protected]>Cc Jiri Olsa <[email protected]>Cc Mark Rutland <[email protected]>Cc Namhyung Kim <[email protected]>Cc Peter Zijlstra <[email protected]>Signed-off-by Arnaldo Carvalho de Melo <[email protected]>--- tools/perf/util/python-ext-sources | 1 + 1 file changed, 1 insertion(+)tools/perf/util/python-ext-sources +1
-1@@ -34,3 +34,4 @@ util/string.c util/symbol_fprintf.c util/units.c util/affinity.c +util/rwsem.c --2.25.1
[tip: perf/urgent] perf python: Include rwsem.c in the pythong biding
In reply to Arnaldo Carvalho de MeloThe following commit has been merged into the perf/urgent branch of tip:
The following commit has been merged into the perf/urgent branch of tip:
Commit-ID: 460c3ed999d700fa84c953f83141f580ef456b3c Gitweb: https://git.kernel.org/tip/460c3ed999d700fa84c953f83141f580ef456b3c Author: Arnaldo Carvalho de Melo <[email protected]> AuthorDate: Fri, 03 Apr 2020 09:29:52 -03:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Fri, 03 Apr 2020 09:37:55 -03:00
perf python: Include rwsem.c in the pythong biding
We'll need it for the cgroup patches, and its better to have it in a separate patch in case we need to later revert the cgroup patches.
I.e. without this we have:
[root@five ~]# perf test -v python
19: 'import perf' in python :
--- start ---
test child forked, pid 148447
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
ImportError: /tmp/build/perf/python/perf.cpython-37m-x86_64-linux-gnu.so: undefined symbol: down_write test child finished with -1
---- end ----
'import perf' in python: FAILED!
[root@five ~]#
--- tools/perf/util/python-ext-sources | 1 + 1 file changed, 1 insertion(+)
tools/perf/util/python-ext-sources +1 -0
@@ -34,3 +34,4 @@ util/string.c util/symbol_fprintf.c util/units.c util/affinity.c +util/rwsem.c
[tip: perf/urgent] perf cgroup: Maintain cgroup hierarchy
In reply to Namhyung KimThe following commit has been merged into the perf/urgent branch of tip:
The following commit has been merged into the perf/urgent branch of tip:
Commit-ID: d1277aa36bff4bfc1a187a469fc6a6a1d17cf59c Gitweb: https://git.kernel.org/tip/d1277aa36bff4bfc1a187a469fc6a6a1d17cf59c Author: Namhyung Kim <[email protected]> AuthorDate: Wed, 25 Mar 2020 21:45:31 +09:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Fri, 03 Apr 2020 09:37:55 -03:00
perf cgroup: Maintain cgroup hierarchy
Each cgroup is kept in the perf_env's cgroup_tree sorted by the cgroup id. Hist entries have cgroup id can compare it directly and later it can be used to find a group name using this tree.
--- tools/perf/util/cgroup.c | 80 ++++++++++++++++++++++++++++++++++++++- tools/perf/util/cgroup.h | 17 ++++++-- tools/perf/util/env.c | 2 +- tools/perf/util/env.h | 6 +++- tools/perf/util/machine.c | 9 +++- 5 files changed, 109 insertions(+), 5 deletions(-)
tools/perf/util/cgroup.c +80 -0
@@ -191,3 +191,83 @@ int parse_cgroups(const struct option *opt, const char *str, }return 0 ; } + +static struct cgroup *__cgroup__findnew (struct rb_root *root,uint64_t id, +bool create,const char *path) +{ +struct rb_node **p = &root->rb_node; +struct rb_node *parent =NULL ; +struct cgroup *cgrp; + +while (*p !=NULL ) { + parent = *p; + cgrp = rb_entry(parent, struct cgroup, node); + +if (cgrp->id == id) +return cgrp; + +if (cgrp->id < id) + p = &(*p)->rb_left; +else + p = &(*p)->rb_right; + } + +if (!create) +return NULL ; + + cgrp =malloc (sizeof (*cgrp)); +if (cgrp ==NULL ) +return NULL ; + + cgrp->name =strdup (path); +if (cgrp->name ==NULL ) { +free (cgrp); +return NULL ; + } + + cgrp->fd =-1 ; + cgrp->id = id; +refcount_set (&cgrp->refcnt,1 ); + +rb_link_node (&cgrp->node, parent, p); +rb_insert_color (&cgrp->node, root); + +return cgrp; +} + +struct cgroup *cgroup__findnew (struct perf_env *env,uint64_t id, +const char *path) +{ +struct cgroup *cgrp; + +down_write (&env->cgroups.lock); + cgrp =__cgroup__findnew (&env->cgroups.tree, id, true, path); +up_write (&env->cgroups.lock); +return cgrp; +} + +struct cgroup *cgroup__find (struct perf_env *env,uint64_t id) +{ +struct cgroup *cgrp; + +down_read (&env->cgroups.lock); + cgrp =__cgroup__findnew (&env->cgroups.tree, id, false,NULL ); +up_read (&env->cgroups.lock); +return cgrp; +} + +void perf_env__purge_cgroups (struct perf_env *env) +{ +struct rb_node *node; +struct cgroup *cgrp; + +down_write (&env->cgroups.lock); +while (!RB_EMPTY_ROOT (&env->cgroups.tree)) { + node =rb_first (&env->cgroups.tree); + cgrp = rb_entry(node, struct cgroup, node); + +rb_erase (node, &env->cgroups.tree); +cgroup__put (cgrp); + } +up_write (&env->cgroups.lock); +}
tools/perf/util/cgroup.h +13 -4
@@ -3,16 +3,19 @@#define __CGROUP_H__#include <linux/refcount.h> +#include <linux/rbtree.h> +#include "util/env.h" struct option ;struct cgroup { -char *name; -int fd; -refcount_t refcnt; +struct rb_node node; +u64 id; +char *name; +int fd; +refcount_t refcnt; }; -extern int nr_cgroups;/* number of explicit cgroups defined */ struct cgroup *cgroup__get (struct cgroup *cgroup);
@@ -26,4 +29,10 @@ void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup);int parse_cgroups (const struct option *opt,const char *str,int unset); +struct cgroup *cgroup__findnew (struct perf_env *env,uint64_t id, +const char *path); +struct cgroup *cgroup__find (struct perf_env *env,uint64_t id); + +void perf_env__purge_cgroups (struct perf_env *env); +#endif /* __CGROUP_H__ */
tools/perf/util/env.c +2 -0
@@ -6,6 +6,7 @@#include <linux/ctype.h> #include <linux/zalloc.h> #include "bpf-event.h" +#include "cgroup.h" #include <errno.h> #include <sys/utsname.h> #include <bpf/libbpf.h>
@@ -168,6 +169,7 @@ void perf_env__exit(struct perf_env *env)int i;perf_env__purge_bpf (env); +perf_env__purge_cgroups (env);zfree (&env->hostname);zfree (&env->os_release);zfree (&env->version);
tools/perf/util/env.h +6 -0
@@ -88,6 +88,12 @@ struct perf_env {u32 btfs_cnt; } bpf_progs; +/* same reason as above (for perf-top) */ +struct { +struct rw_semaphore lock; +struct rb_root tree; + } cgroups; +/* For fast cpu to numa node lookup via perf_env__numa_node */ int *numa_map;int nr_numa_map;
tools/perf/util/machine.c +8 -1
@@ -33,6 +33,7 @@#include "asm/bug.h" #include "bpf-event.h" #include <internal/lib.h> // page_size +#include "cgroup.h" #include <linux/ctype.h> #include <symbol/kallsyms.h>
@@ -654,13 +655,19 @@ int machine__process_namespaces_event(struct machine *machine __maybe_unused,return err; } -int machine__process_cgroup_event (struct machine *machine__maybe_unused , +int machine__process_cgroup_event (struct machine *machine,union perf_event *event,struct perf_sample *sample__maybe_unused ) { +struct cgroup *cgrp; +if (dump_trace)perf_event__fprintf_cgroup (event, stdout); + cgrp =cgroup__findnew (machine->env, event->cgroup.id, event->cgroup.path); +if (cgrp ==NULL ) +return -ENOMEM ; +return 0 ; }
Namhyung Kim
maintainerPATCH 5/9 perf report: Add 'cgroup' sort key
In reply to Namhyung KimThe cgroup sort key is to show cgroup membership of each task. Currently it shows full path in the cgroupfs (not relative to the root of cgroup namespace) since it'd be more intuitive IMHO. Otherwise root cgroup in different namespaces will all show same name - "/".
The cgroup sort key should come before cgroup_id otherwise sort_dimension__add() will match it to cgroup_id as it only matches with the given substring.
For example it will look like following. Note that record patch adding --all-cgroups patch will come later.
$ perf record -a --namespace --all-cgroups cgtest [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.208 MB perf.data (4090 samples) ]
$ perf report -s cgroup_id,cgroup,pid
...
# Overhead cgroup id (dev/inode) Cgroup Pid:Command
# ........ ..................... .......... ...............
#
93.96% 0/0x0 / 0:swapper
1.25% 3/0xeffffffb / 278:looper0
0.86% 3/0xf000015f /sub/cgrp1 280:cgtest
0.37% 3/0xf0000160 /sub/cgrp2 281:cgtest
0.34% 3/0xf0000163 /sub/cgrp3 282:cgtest
0.22% 3/0xeffffffb /sub 278:looper0
0.20% 3/0xeffffffb / 280:cgtest
0.15% 3/0xf0000163 /sub/cgrp3 285:looper3--- tools/perf/Documentation/perf-report.txt | 1 + tools/perf/util/hist.c | 13 +++++++++ tools/perf/util/hist.h | 1 + tools/perf/util/sort.c | 37 ++++++++++++++++++++++++ tools/perf/util/sort.h | 2 ++ 5 files changed, 54 insertions(+)
tools/perf/Documentation/perf-report.txt +1 -0
@@ -95,6 +95,7 @@ OPTIONS abort cost. This is the global weight. - local_weight: Local weight version of the weight above. - cgroup_id: ID derived from cgroup namespace device and inode numbers. + - cgroup: cgroup pathname in the cgroupfs. - transaction: Transaction abort flags. - overhead: Overhead percentage of sample - overhead_sys: Overhead percentage of sample running in system mode
tools/perf/util/hist.c +13 -0
@@ -10,6 +10,7 @@#include "mem-events.h" #include "session.h" #include "namespaces.h" +#include "cgroup.h" #include "sort.h" #include "units.h" #include "evlist.h"
@@ -194,6 +195,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)hists__set_unres_dso_col_len (hists,HISTC_MEM_DADDR_DSO ); } +hists__new_col_len (hists,HISTC_CGROUP ,6 );hists__new_col_len (hists,HISTC_CGROUP_ID ,20 );hists__new_col_len (hists,HISTC_CPU ,3 );hists__new_col_len (hists,HISTC_SOCKET ,6 );
@@ -222,6 +224,16 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)if (h->trace_output)hists__new_col_len (hists,HISTC_TRACE ,strlen (h->trace_output)); + +if (h->cgroup) { +const char *cgrp_name ="unknown" ; +struct cgroup *cgrp =cgroup__find (h->ms.maps->machine->env, + h->cgroup); +if (cgrp !=NULL ) + cgrp_name = cgrp->name; + +hists__new_col_len (hists,HISTC_CGROUP ,strlen (cgrp_name)); + } }void hists__output_recalc_col_len (struct hists *hists,int max_rows)
@@ -691,6 +703,7 @@ __hists__add_entry(struct hists *hists, .dev = ns ? ns->link_info[CGROUP_NS_INDEX].dev : 0, .ino = ns ? ns->link_info[CGROUP_NS_INDEX].ino : 0, }, + .cgroup = sample->cgroup, .ms = { .maps = al->maps, .map = al->map,
tools/perf/util/hist.h +1 -0
@@ -38,6 +38,7 @@ enum hist_column {HISTC_THREAD ,HISTC_COMM ,HISTC_CGROUP_ID , +HISTC_CGROUP ,HISTC_PARENT ,HISTC_CPU , HISTC_SOCKET,
tools/perf/util/sort.c +37 -0
@@ -12,6 +12,7 @@#include "cacheline.h" #include "comm.h" #include "map.h" +#include "maps.h" #include "symbol.h" #include "map_symbol.h" #include "branch.h"
@@ -25,6 +26,8 @@#include "mem-events.h" #include "annotate.h" #include "time-utils.h" +#include "cgroup.h" +#include "machine.h" #include <linux/kernel.h> #include <linux/string.h>
@@ -634,6 +637,39 @@ struct sort_entry sort_cgroup_id = { .se_width_idx = HISTC_CGROUP_ID, }; +/* --sort cgroup */ + +static int64_t +sort__cgroup_cmp (struct hist_entry *left,struct hist_entry *right) +{ +return right->cgroup - left->cgroup; +} + +static int hist_entry__cgroup_snprintf (struct hist_entry *he, +char *bf,size_t size, +unsigned int width__maybe_unused ) +{ +const char *cgrp_name ="N/A" ; + +if (he->cgroup) { +struct cgroup *cgrp =cgroup__find (he->ms.maps->machine->env, + he->cgroup); +if (cgrp !=NULL ) + cgrp_name = cgrp->name; +else + cgrp_name ="unknown" ; + } + +return repsep_snprintf (bf, size,"%s" , cgrp_name); +} + +struct sort_entry sort_cgroup = { + .se_header ="Cgroup" , + .se_cmp = sort__cgroup_cmp, + .se_snprintf = hist_entry__cgroup_snprintf, + .se_width_idx =HISTC_CGROUP , +}; +/* --sort socket */ static int64_t
@@ -1660,6 +1696,7 @@ static struct sort_dimension common_sort_dimensions[] = {DIM (SORT_TRACE ,"trace" , sort_trace),DIM (SORT_SYM_SIZE ,"symbol_size" , sort_sym_size),DIM (SORT_DSO_SIZE ,"dso_size" , sort_dso_size), +DIM (SORT_CGROUP ,"cgroup" , sort_cgroup),DIM (SORT_CGROUP_ID ,"cgroup_id" , sort_cgroup_id),DIM (SORT_SYM_IPC_NULL ,"ipc_null" , sort_sym_ipc_null), DIM(SORT_TIME, "time", sort_time),
tools/perf/util/sort.h +2 -0
@@ -101,6 +101,7 @@ struct hist_entry {struct thread *thread;struct comm *comm;struct namespace_id cgroup_id; +u64 cgroup;u64 ip;u64 transaction;s32 socket;
@@ -224,6 +225,7 @@ enum sort_type {SORT_TRACE ,SORT_SYM_SIZE ,SORT_DSO_SIZE , +SORT_CGROUP ,SORT_CGROUP_ID ,SORT_SYM_IPC_NULL , SORT_TIME,
Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
[tip: perf/urgent] perf report: Add 'cgroup' sort key
The following commit has been merged into the perf/urgent branch of tip:
The following commit has been merged into the perf/urgent branch of tip:
Commit-ID: b629f3e9d01b4e4ad4e84c8f76fad514967a83da Gitweb: https://git.kernel.org/tip/b629f3e9d01b4e4ad4e84c8f76fad514967a83da Author: Namhyung Kim <[email protected]> AuthorDate: Wed, 25 Mar 2020 21:45:32 +09:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Fri, 03 Apr 2020 09:37:55 -03:00
perf report: Add 'cgroup' sort key
The cgroup sort key is to show cgroup membership of each task. Currently it shows full path in the cgroupfs (not relative to the root of cgroup namespace) since it'd be more intuitive IMHO. Otherwise root cgroup in different namespaces will all show same name - "/".
The cgroup sort key should come before cgroup_id otherwise sort_dimension__add() will match it to cgroup_id as it only matches with the given substring.
For example it will look like following. Note that record patch adding --all-cgroups patch will come later.
$ perf record -a --namespace --all-cgroups cgtest [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.208 MB perf.data (4090 samples) ]
$ perf report -s cgroup_id,cgroup,pid
...
# Overhead cgroup id (dev/inode) Cgroup Pid:Command
# ........ ..................... .......... ...............
#
93.96% 0/0x0 / 0:swapper
1.25% 3/0xeffffffb / 278:looper0
0.86% 3/0xf000015f /sub/cgrp1 280:cgtest
0.37% 3/0xf0000160 /sub/cgrp2 281:cgtest
0.34% 3/0xf0000163 /sub/cgrp3 282:cgtest
0.22% 3/0xeffffffb /sub 278:looper0
0.20% 3/0xeffffffb / 280:cgtest
0.15% 3/0xf0000163 /sub/cgrp3 285:looper3--- tools/perf/Documentation/perf-report.txt | 1 +- tools/perf/util/hist.c | 13 ++++++++- tools/perf/util/hist.h | 1 +- tools/perf/util/sort.c | 37 +++++++++++++++++++++++- tools/perf/util/sort.h | 2 +- 5 files changed, 54 insertions(+)
tools/perf/Documentation/perf-report.txt +1 -0
@@ -95,6 +95,7 @@ OPTIONS abort cost. This is the global weight. - local_weight: Local weight version of the weight above. - cgroup_id: ID derived from cgroup namespace device and inode numbers. + - cgroup: cgroup pathname in the cgroupfs. - transaction: Transaction abort flags. - overhead: Overhead percentage of sample - overhead_sys: Overhead percentage of sample running in system mode
tools/perf/util/hist.c +13 -0
@@ -10,6 +10,7 @@#include "mem-events.h" #include "session.h" #include "namespaces.h" +#include "cgroup.h" #include "sort.h" #include "units.h" #include "evlist.h"
@@ -194,6 +195,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)hists__set_unres_dso_col_len (hists,HISTC_MEM_DADDR_DSO ); } +hists__new_col_len (hists,HISTC_CGROUP ,6 );hists__new_col_len (hists,HISTC_CGROUP_ID ,20 );hists__new_col_len (hists,HISTC_CPU ,3 );hists__new_col_len (hists,HISTC_SOCKET ,6 );
@@ -222,6 +224,16 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)if (h->trace_output)hists__new_col_len (hists,HISTC_TRACE ,strlen (h->trace_output)); + +if (h->cgroup) { +const char *cgrp_name ="unknown" ; +struct cgroup *cgrp =cgroup__find (h->ms.maps->machine->env, + h->cgroup); +if (cgrp !=NULL ) + cgrp_name = cgrp->name; + +hists__new_col_len (hists,HISTC_CGROUP ,strlen (cgrp_name)); + } }void hists__output_recalc_col_len (struct hists *hists,int max_rows)
@@ -691,6 +703,7 @@ __hists__add_entry(struct hists *hists, .dev = ns ? ns->link_info[CGROUP_NS_INDEX].dev : 0, .ino = ns ? ns->link_info[CGROUP_NS_INDEX].ino : 0, }, + .cgroup = sample->cgroup, .ms = { .maps = al->maps, .map = al->map,
tools/perf/util/hist.h +1 -0
@@ -38,6 +38,7 @@ enum hist_column {HISTC_THREAD ,HISTC_COMM ,HISTC_CGROUP_ID , +HISTC_CGROUP ,HISTC_PARENT ,HISTC_CPU , HISTC_SOCKET,
tools/perf/util/sort.c +37 -0
@@ -12,6 +12,7 @@#include "cacheline.h" #include "comm.h" #include "map.h" +#include "maps.h" #include "symbol.h" #include "map_symbol.h" #include "branch.h"
@@ -25,6 +26,8 @@#include "mem-events.h" #include "annotate.h" #include "time-utils.h" +#include "cgroup.h" +#include "machine.h" #include <linux/kernel.h> #include <linux/string.h>
@@ -634,6 +637,39 @@ struct sort_entry sort_cgroup_id = { .se_width_idx = HISTC_CGROUP_ID, }; +/* --sort cgroup */ + +static int64_t +sort__cgroup_cmp (struct hist_entry *left,struct hist_entry *right) +{ +return right->cgroup - left->cgroup; +} + +static int hist_entry__cgroup_snprintf (struct hist_entry *he, +char *bf,size_t size, +unsigned int width__maybe_unused ) +{ +const char *cgrp_name ="N/A" ; + +if (he->cgroup) { +struct cgroup *cgrp =cgroup__find (he->ms.maps->machine->env, + he->cgroup); +if (cgrp !=NULL ) + cgrp_name = cgrp->name; +else + cgrp_name ="unknown" ; + } + +return repsep_snprintf (bf, size,"%s" , cgrp_name); +} + +struct sort_entry sort_cgroup = { + .se_header ="Cgroup" , + .se_cmp = sort__cgroup_cmp, + .se_snprintf = hist_entry__cgroup_snprintf, + .se_width_idx =HISTC_CGROUP , +}; +/* --sort socket */ static int64_t
@@ -1660,6 +1696,7 @@ static struct sort_dimension common_sort_dimensions[] = {DIM (SORT_TRACE ,"trace" , sort_trace),DIM (SORT_SYM_SIZE ,"symbol_size" , sort_sym_size),DIM (SORT_DSO_SIZE ,"dso_size" , sort_dso_size), +DIM (SORT_CGROUP ,"cgroup" , sort_cgroup),DIM (SORT_CGROUP_ID ,"cgroup_id" , sort_cgroup_id),DIM (SORT_SYM_IPC_NULL ,"ipc_null" , sort_sym_ipc_null), DIM(SORT_TIME, "time", sort_time),
tools/perf/util/sort.h +2 -0
@@ -101,6 +101,7 @@ struct hist_entry {struct thread *thread;struct comm *comm;struct namespace_id cgroup_id; +u64 cgroup;u64 ip;u64 transaction;s32 socket;
@@ -224,6 +225,7 @@ enum sort_type {SORT_TRACE ,SORT_SYM_SIZE ,SORT_DSO_SIZE , +SORT_CGROUP ,SORT_CGROUP_ID ,SORT_SYM_IPC_NULL , SORT_TIME,
Namhyung Kim
maintainerPATCH 6/9 perf record: Support synthesizing cgroup events
In reply to Namhyung KimSynthesize cgroup events by iterating cgroup filesystem directories. The cgroup event only saves the portion of cgroup path after the mount point and the cgroup id (which actually is a file handle).
--- tools/perf/builtin-record.c | 5 ++ tools/perf/util/synthetic-events.c | 113 +++++++++++++++++++++++++++++ tools/perf/util/synthetic-events.h | 1 + tools/perf/util/tool.h | 1 + 4 files changed, 120 insertions(+)
tools/perf/builtin-record.c +5 -0
@@ -1397,6 +1397,11 @@ static int record__synthesize(struct record *rec, bool tail)if (err <0 )pr_warning ("Couldn't synthesize bpf events.\n" ); + err =perf_event__synthesize_cgroups (tool, process_synthesized_event, + machine); +if (err <0 ) +pr_warning ("Couldn't synthesize cgroup events.\n" ); + err =__machine__synthesize_threads (machine, tool, &opts->target, rec->evlist->core.threads, process_synthesized_event, opts->sample_address,1 );
tools/perf/util/synthetic-events.c +113 -0
125 lines not on this page · raw message
tools/perf/util/synthetic-events.h +1 -0
@@ -45,6 +45,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handlint perf_event__synthesize_mmap_events (struct perf_tool *tool,union perf_event *event,pid_t pid,pid_t tgid,perf_event__handler_t process,struct machine *machine,bool mmap_data);int perf_event__synthesize_modules (struct perf_tool *tool,perf_event__handler_t process,struct machine *machine);int perf_event__synthesize_namespaces (struct perf_tool *tool,union perf_event *event,pid_t pid,pid_t tgid,perf_event__handler_t process,struct machine *machine); +int perf_event__synthesize_cgroups (struct perf_tool *tool,perf_event__handler_t process,struct machine *machine);int perf_event__synthesize_sample (union perf_event *event,u64 type,u64 read_format,const struct perf_sample *sample);int perf_event__synthesize_stat_config (struct perf_tool *tool,struct perf_stat_config *config,perf_event__handler_t process,struct machine *machine);int perf_event__synthesize_stat_events (struct perf_stat_config *config,struct perf_tool *tool,struct evlist *evlist,perf_event__handler_t process,bool attrs);
tools/perf/util/tool.h +1 -0
@@ -79,6 +79,7 @@ struct perf_tool {bool ordered_events;bool ordering_requires_timestamps;bool namespace_events; +bool cgroup_events;bool no_warn;enum show_feature_header show_feat_hdr; };
Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
Re: [PATCH 6/9] perf record: Support synthesizing cgroup events
Em Wed, Mar 25, 2020 at 09:45:33PM +0900, Namhyung Kim escreveu:
Quoted 3 lines
Synthesize cgroup events by iterating cgroup filesystem directories. The cgroup event only saves the portion of cgroup path after the mount point and the cgroup id (which actually is a file handle).
Breaks the build on alpine linux (musl libc):
CC /tmp/build/perf/util/srccode.o
CC /tmp/build/perf/util/synthetic-events.outil/synthetic-events.c: In function 'perf_event__synthesize_cgroup':util/synthetic-events.c:427:22: error: field 'fh' has incomplete type
struct file_handle fh;
^
util/synthetic-events.c:441:6: error: implicit declaration of function 'name_to_handle_at' [-Werror=implicit-function-declaration]
if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0) < 0) {
^util/synthetic-events.c:441:2: error: nested extern declaration of 'name_to_handle_at' [-Werror=nested-externs]
if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0) < 0) {
^
CC /tmp/build/perf/util/data.o
cc1: all warnings being treated as errors
mv: can't rename '/tmp/build/perf/util/.synthetic-events.o.tmp': No such file or directory
I'm trying to fix
Quoted 182 lines
Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/builtin-record.c | 5 ++ tools/perf/util/synthetic-events.c | 113 +++++++++++++++++++++++++++++ tools/perf/util/synthetic-events.h | 1 + tools/perf/util/tool.h | 1 + 4 files changed, 120 insertions(+)tools/perf/builtin-record.c +5
-0@@ -1397,6 +1397,11 @@ static int record__synthesize(struct record *rec, bool tail)if (err <0 )pr_warning ("Couldn't synthesize bpf events.\n" ); + err =perf_event__synthesize_cgroups (tool, process_synthesized_event, + machine); +if (err <0 ) +pr_warning ("Couldn't synthesize cgroup events.\n" ); + err =__machine__synthesize_threads (machine, tool, &opts->target, rec->evlist->core.threads, process_synthesized_event, opts->sample_address,1 );tools/perf/util/synthetic-events.c +113
-0@@ -16,6 +16,7 @@#include "util/synthetic-events.h" #include "util/target.h" #include "util/time-utils.h" +#include "util/cgroup.h" #include <linux/bitops.h> #include <linux/kernel.h> #include <linux/string.h> @@ -414,6 +415,118 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,return rc; } +static int perf_event__synthesize_cgroup (struct perf_tool *tool, +union perf_event *event, +char *path,size_t mount_len, +perf_event__handler_t process, +struct machine *machine) +{ +size_t event_size =sizeof (event->cgroup) -sizeof (event->cgroup.path); +size_t path_len =strlen (path) - mount_len +1 ; +struct { +struct file_handle fh; +uint64_t cgroup_id; + } handle; +int mount_id; + +while (path_len %sizeof (u64)) + path[mount_len + path_len++] ='\0' ; + +memset (&event->cgroup,0 , event_size); + + event->cgroup.header.type =PERF_RECORD_CGROUP ; + event->cgroup.header.size = event_size + path_len + machine->id_hdr_size; + + handle.fh.handle_bytes =sizeof (handle.cgroup_id); +if (name_to_handle_at (AT_FDCWD , path, &handle.fh, &mount_id,0 ) <0 ) { +pr_debug ("stat failed: %s\n" , path); +return -1 ; + } + + event->cgroup.id = handle.cgroup_id; +strncpy (event->cgroup.path, path + mount_len, path_len); +memset (event->cgroup.path + path_len,0 , machine->id_hdr_size); + +if (perf_tool__process_synth_event (tool, event, machine, process) <0 ) { +pr_debug ("process synth event failed\n" ); +return -1 ; + } + +return 0 ; +} + +static int perf_event__walk_cgroup_tree (struct perf_tool *tool, +union perf_event *event, +char *path,size_t mount_len, +perf_event__handler_t process, +struct machine *machine) +{ +size_t pos =strlen (path); +DIR *d; +struct dirent *dent; +int ret =0 ; + +if (perf_event__synthesize_cgroup (tool, event, path, mount_len, + process, machine) <0 ) +return -1 ; + + d =opendir (path); +if (d ==NULL ) { +pr_debug ("failed to open directory: %s\n" , path); +return -1 ; + } + +while ((dent =readdir (d)) !=NULL ) { +if (dent->d_type !=DT_DIR ) +continue ; +if (!strcmp (dent->d_name,"." ) || + !strcmp (dent->d_name,".." )) +continue ; + +/* any sane path should be less than PATH_MAX */ +if (strlen (path) +strlen (dent->d_name) +1 >=PATH_MAX ) +continue ; + +if (path[pos -1 ] !='/' ) +strcat (path,"/" ); +strcat (path, dent->d_name); + + ret =perf_event__walk_cgroup_tree (tool, event, path, + mount_len, process, machine); +if (ret <0 ) +break ; + + path[pos] ='\0' ; + } + +closedir (d); +return ret; +} + +int perf_event__synthesize_cgroups (struct perf_tool *tool, +perf_event__handler_t process, +struct machine *machine) +{ +union perf_event event; +char cgrp_root[PATH_MAX ]; +size_t mount_len;/* length of mount point in the path */ + +if (cgroupfs_find_mountpoint (cgrp_root,PATH_MAX ,"perf_event" ) <0 ) { +pr_debug ("cannot find cgroup mount point\n" ); +return -1 ; + } + + mount_len =strlen (cgrp_root); +/* make sure the path starts with a slash (after mount point) */ +strcat (cgrp_root,"/" ); + +if (perf_event__walk_cgroup_tree (tool, &event, cgrp_root, mount_len, + process, machine) <0 ) +return -1 ; + +return 0 ; +} +int perf_event__synthesize_modules (struct perf_tool *tool,perf_event__handler_t process,struct machine *machine) {tools/perf/util/synthetic-events.h +1
-0@@ -45,6 +45,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handlint perf_event__synthesize_mmap_events (struct perf_tool *tool,union perf_event *event,pid_t pid,pid_t tgid,perf_event__handler_t process,struct machine *machine,bool mmap_data);int perf_event__synthesize_modules (struct perf_tool *tool,perf_event__handler_t process,struct machine *machine);int perf_event__synthesize_namespaces (struct perf_tool *tool,union perf_event *event,pid_t pid,pid_t tgid,perf_event__handler_t process,struct machine *machine); +int perf_event__synthesize_cgroups (struct perf_tool *tool,perf_event__handler_t process,struct machine *machine);int perf_event__synthesize_sample (union perf_event *event,u64 type,u64 read_format,const struct perf_sample *sample);int perf_event__synthesize_stat_config (struct perf_tool *tool,struct perf_stat_config *config,perf_event__handler_t process,struct machine *machine);int perf_event__synthesize_stat_events (struct perf_stat_config *config,struct perf_tool *tool,struct evlist *evlist,perf_event__handler_t process,bool attrs);tools/perf/util/tool.h +1
-0@@ -79,6 +79,7 @@ struct perf_tool {bool ordered_events;bool ordering_requires_timestamps;bool namespace_events; +bool cgroup_events;bool no_warn;enum show_feature_header show_feat_hdr; };Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
Signature · 1 line
- Arnaldo
Re: [PATCH 6/9] perf record: Support synthesizing cgroup events
Em Mon, Mar 30, 2020 at 01:30:58PM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 24 lines
Em Wed, Mar 25, 2020 at 09:45:33PM +0900, Namhyung Kim escreveu:
Quoted 3 lines
Synthesize cgroup events by iterating cgroup filesystem directories. The cgroup event only saves the portion of cgroup path after the mount point and the cgroup id (which actually is a file handle).
Breaks the build on alpine linux (musl libc):
CC
/tmp/build/perf/util/srccode.o
CC/tmp/build/perf/util/synthetic-events.outil/synthetic-events.c: In function 'perf_event__synthesize_cgroup':util/synthetic-events.c:427:22: error: field 'fh' has incomplete typestruct file_handle fh; ^ util/synthetic-events.c:441:6: error: implicit declaration of function 'name_to_handle_at' [-Werror=implicit-function-declaration] if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0) < 0) { ^
util/synthetic-events.c:441:2: error: nested extern declaration of 'name_to_handle_at' [-Werror=nested-externs]
if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0)< 0) {
^
CC/tmp/build/perf/util/data.o
cc1: all warnings being treated as errors
mv: can't rename '/tmp/build/perf/util/.synthetic-events.o.tmp': No such file or directory
Quoted 1 line
I'm trying to fix
musl libc up to 1.2.21 (IIRC) lacks name_to_handle_at and its structs, then from the one that is in alpine linux 3.10 the error changes to:
CC /tmp/build/perf/util/cloexec.outil/synthetic-events.c:427:22: error: field 'fh' with variable sized type 'struct file_handle' not at the end of a struct or class is a GNU
extension [-Werror,-Wgnu-variable-sized-type-not-at-end]
struct file_handle fh;
^1 error generated.
mv: can't rename '/tmp/build/perf/util/.synthetic-events.o.tmp': No such file or directory make[4]: *** [/git/linux/tools/build/Makefile.build:97: /tmp/build/perf/util/synthetic-events.o] Error 1 make[4]: *** Waiting for unfinished jobs....
make[3]: *** [/git/linux/tools/build/Makefile.build:139: util] Error 2
make[2]: *** [Makefile.perf:617: /tmp/build/perf/perf-in.o] Error 2
make[1]: *** [Makefile.perf:225: sub-make] Error 2
make: *** [Makefile:70: all] Error 2
make: Leaving directory '/git/linux/tools/perf'
+ exit 1
[root@quaco ~]#
So probably we'll need a feature test to catch this and do some workaround or disable the feature on such systems, providing some warning.
I left the container build tests running to see if some other system has problems with this, perhaps the ones with uCLibc or some older glibc, we'll see.
So far all the alpine versions failed with the above problems and ALT Linux p8 and p9 built without problems.
- Arnaldo
Re: [PATCH 6/9] perf record: Support synthesizing cgroup events
Em Mon, Mar 30, 2020 at 01:43:12PM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 51 lines
Em Mon, Mar 30, 2020 at 01:30:58PM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 24 lines
Em Wed, Mar 25, 2020 at 09:45:33PM +0900, Namhyung Kim escreveu:
Quoted 3 lines
Synthesize cgroup events by iterating cgroup filesystem directories. The cgroup event only saves the portion of cgroup path after the mount point and the cgroup id (which actually is a file handle).
Breaks the build on alpine linux (musl libc):
CC
/tmp/build/perf/util/srccode.o
CC/tmp/build/perf/util/synthetic-events.outil/synthetic-events.c: In function 'perf_event__synthesize_cgroup':util/synthetic-events.c:427:22: error: field 'fh' has incomplete typestruct file_handle fh; ^ util/synthetic-events.c:441:6: error: implicit declaration of function 'name_to_handle_at' [-Werror=implicit-function-declaration] if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0) < 0) { ^
util/synthetic-events.c:441:2: error: nested extern declaration of 'name_to_handle_at' [-Werror=nested-externs]
if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0)< 0) {
^
CC/tmp/build/perf/util/data.o
cc1: all warnings being treated as errors
mv: can't rename '/tmp/build/perf/util/.synthetic-events.o.tmp': No such file or directoryQuoted 1 line
I'm trying to fix
musl libc up to 1.2.21 (IIRC) lacks
name_to_handle_atand its structs, then from the one that is in alpine linux 3.10 the error changes to:CC
/tmp/build/perf/util/cloexec.outil/synthetic-events.c:427:22: error: field 'fh' with variable sized type 'structfile_handle' not at the end of a struct or class is a GNUextension [-Werror,-Wgnu-variable-sized-type-not-at-end] struct file_handle fh; ^1 error generated.
mv: can't rename '/tmp/build/perf/util/.synthetic-events.o.tmp': No such file or directory make[4]: *** [/git/linux/tools/build/Makefile.build:97:/tmp/build/perf/util/synthetic-events.o] Error 1 make[4]: *** Waiting for unfinished jobs....
make[3]: *** [/git/linux/tools/build/Makefile.build:139: util] Error 2
make[2]: *** [Makefile.perf:617:/tmp/build/perf/perf-in.o] Error 2
make[1]: *** [Makefile.perf:225: sub-make] Error 2
make: *** [Makefile:70: all] Error 2
make: Leaving directory '/git/linux/tools/perf'
+ exit 1
[root@quaco ~]#So probably we'll need a feature test to catch this and do some workaround or disable the feature on such systems, providing some warning.
Quoted 6 lines
I left the container build tests running to see if some other system has problems with this, perhaps the ones with uCLibc or some older glibc, we'll see.
So far all the alpine versions failed with the above problems and ALT Linux p8 and p9 built without problems.
13 129.90 amazonlinux:1 : Ok gcc (GCC) 7.2.1 20170915 (Red Hat 7.2.1-2), clang version 3.6.2 (tags/RELEASE_362/final) 14 192.36 amazonlinux:2 : Ok gcc (GCC) 7.3.1 20180712 (Red Hat 7.3.1-6), clang version 7.0.1 (Amazon Linux 2 7.0.1-1.amzn2.0.2) 15 16.02 android-ndk:r12b-arm : FAIL arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease) 16 16.35 android-ndk:r15c-arm : FAIL arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease) 17 13.42 centos:5 : FAIL gcc (GCC) 4.1.2 20080704 (Red Hat 4.1.2-55) 18 18.39 centos:6 : FAIL gcc (GCC) 4.4.7 20120313 (Red Hat 4.4.7-23) 19 54.36 centos:7 : Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-39) 20 215.20 centos:8 : Ok gcc (GCC) 8.3.1 20190507 (Red Hat 8.3.1-4), clang version 8.0.1 (Red Hat 8.0.1-1.module_el8.1.0+215+a01033fb) 21 54.41 clearlinux:latest : Ok gcc (Clear Linux OS for Intel Architecture) 9.2.1 20200214 gcc_9_2_0_release-615-g7866f9ebf1, clang version 9.0.1 22 139.44 debian:8 : Ok gcc (Debian 4.9.2-10+deb8u2) 4.9.2, Debian clang version 3.5.0-10 (tags/RELEASE_350/final) (based on LLVM 3.5.0) 23 153.99 debian:9 : Ok gcc (Debian 6.3.0-18+deb9u1) 6.3.0 20170516, clang version 3.8.1-24 (tags/RELEASE_381/final) 24 157.00 debian:10 : Ok gcc (Debian 8.3.0-6) 8.3.0, clang version 7.0.1-8 (tags/RELEASE_701/final) 25 170.15 debian:experimental : Ok gcc (Debian 9.2.1-28) 9.2.1 20200203, clang version 8.0.1-7 (tags/RELEASE_801/final) 26 28.45 debian:experimental-x-arm64 : FAIL aarch64-linux-gnu-gcc (Debian 8.3.0-19) 8.3.0
This one was something else, and I bet the other arm64 were the same
thing:
CC /tmp/build/perf/tests/parse-events.oarch/arm64/util/machine.c: In function 'arch__symbols__fixup_end':arch/arm64/util/machine.c:19:7: error: implicit declaration of function 'strchr' [-Werror=implicit-function-declaration]
if ((strchr(p->name, '[') && strchr(c->name, '[') == NULL) ||
^~~~~~
arch/arm64/util/machine.c:19:7: error: incompatible implicit declaration of built-in function 'strchr' [-Werror] arch/arm64/util/machine.c:19:7: note: include '<string.h>' or provide a declaration of 'strchr' arch/arm64/util/machine.c:6:1:
+#include <string.h>
arch/arm64/util/machine.c:19:7:
if ((strchr(p->name, '[') && strchr(c->name, '[') == NULL) ||
^~~~~~
cc1: all warnings being treated as errors
mv: cannot stat '/tmp/build/perf/arch/arm64/util/.machine.o.tmp': No such file or directory make[6]: *** [/git/linux/tools/build/Makefile.build:97: /tmp/build/perf/arch/arm64/util/machine.o] Error 1
27 60.23 debian:experimental-x-mips : Ok mips-linux-gnu-gcc (Debian 8.3.0-19) 8.3.0 28 54.38 debian:experimental-x-mips64 : Ok mips64-linux-gnuabi64-gcc (Debian 9.2.1-24) 9.2.1 20200117 29 60.29 debian:experimental-x-mipsel : Ok mipsel-linux-gnu-gcc (Debian 9.2.1-8) 9.2.1 20190909 30 51.92 fedora:20 : Ok gcc (GCC) 4.8.3 20140911 (Red Hat 4.8.3-7) 31 54.05 fedora:22 : Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6), clang version 3.5.0 (tags/RELEASE_350/final) 32 142.15 fedora:23 : Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6), clang version 3.7.0 (tags/RELEASE_370/final) 33 160.24 fedora:24 : Ok gcc (GCC) 6.3.1 20161221 (Red Hat 6.3.1-1), clang version 3.8.1 (tags/RELEASE_381/final) 34 20.46 fedora:24-x-ARC-uClibc : FAIL arc-linux-gcc (ARCompact ISA Linux uClibc toolchain 2017.09-rc2) 7.1.1 20170710 35 161.31 fedora:25 : Ok gcc (GCC) 6.4.1 20170727 (Red Hat 6.4.1-1), clang version 3.9.1 (tags/RELEASE_391/final) 36 182.38 fedora:26 : Ok gcc (GCC) 7.3.1 20180130 (Red Hat 7.3.1-2), clang version 4.0.1 (tags/RELEASE_401/final) 37 178.68 fedora:27 : Ok gcc (GCC) 7.3.1 20180712 (Red Hat 7.3.1-6), clang version 5.0.2 (tags/RELEASE_502/final) 38 199.12 fedora:28 : Ok gcc (GCC) 8.3.1 20190223 (Red Hat 8.3.1-2), clang version 6.0.1 (tags/RELEASE_601/final) 39 209.86 fedora:29 : Ok gcc (GCC) 8.3.1 20190223 (Red Hat 8.3.1-2), clang version 7.0.1 (Fedora 7.0.1-6.fc29) 40 213.17 fedora:30 : Ok gcc (GCC) 9.2.1 20190827 (Red Hat 9.2.1-1), clang version 8.0.0 (Fedora 8.0.0-3.fc30) 41 53.64 fedora:30-x-ARC-glibc : Ok arc-linux-gcc (ARC HS GNU/Linux glibc toolchain 2019.03-rc1) 8.3.1 20190225 42 20.78 fedora:30-x-ARC-uClibc : FAIL arc-linux-gcc (ARCv2 ISA Linux uClibc toolchain 2019.03-rc1) 8.3.1 20190225
Same thing as with fedora:24-x-ARC-uClibc:
CC /tmp/build/perf/util/tsc.outil/synthetic-events.c: In function 'perf_event__synthesize_cgroup':util/synthetic-events.c:427:22: error: field 'fh' has incomplete type
struct file_handle fh;
^~
util/synthetic-events.c:441:6: error: implicit declaration of function 'name_to_handle_at' [-Werror=implicit-function-declaration]
if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0) < 0) {
^~~~~~~~~~~~~~~~~util/synthetic-events.c:441:6: error: nested extern declaration of 'name_to_handle_at' [-Werror=nested-externs]
CC /tmp/build/perf/util/cloexec.o
CC /tmp/build/perf/util/call-path.o
cc1: all warnings being treated as errors
43 215.94 fedora:31 : Ok gcc (GCC) 9.2.1 20190827 (Red Hat 9.2.1-1), clang version 9.0.1 (Fedora 9.0.1-2.fc31) 44 181.57 fedora:32 : Ok gcc (GCC) 10.0.1 20200216 (Red Hat 10.0.1-0.8), clang version 10.0.0 (Fedora 10.0.0-0.1.rc2.fc32) 45 185.19 fedora:rawhide : Ok gcc (GCC) 10.0.1 20200216 (Red Hat 10.0.1-0.8), clang version 10.0.0 (Fedora 10.0.0-0.3.rc2.fc33) 46 62.84 gentoo-stage3-amd64:latest : Ok gcc (Gentoo 9.2.0-r2 p3) 9.2.0 47 139.89 mageia:5 : Ok gcc (GCC) 4.9.2, clang version 3.5.2 (tags/RELEASE_352/final) 48 165.42 mageia:6 : Ok gcc (Mageia 5.5.0-1.mga6) 5.5.0, clang version 3.9.1 (tags/RELEASE_391/final) 49 217.63 mageia:7 : Ok gcc (Mageia 8.3.1-0.20190524.1.mga7) 8.3.1 20190524, clang version 8.0.0 (Mageia 8.0.0-1.mga7) 50 221.42 manjaro:latest : Ok gcc (GCC) 9.2.0, clang version 9.0.0 (tags/RELEASE_900/final) 51 219.95 openmandriva:cooker : Ok gcc (GCC) 10.0.0 20200216 (OpenMandriva), clang version 10.0.0 52 188.84 opensuse:15.0 : Ok gcc (SUSE Linux) 7.4.1 20190424 [gcc-7-branch revision 270538], clang version 5.0.1 (tags/RELEASE_501/final 312548) 53 206.42 opensuse:15.1 : Ok gcc (SUSE Linux) 7.5.0, clang version 7.0.1 (tags/RELEASE_701/final 349238) 54 205.61 opensuse:15.2 : Ok gcc (SUSE Linux) 7.5.0, clang version 7.0.1 (tags/RELEASE_701/final 349238) 55 183.74 opensuse:42.3 : Ok gcc (SUSE Linux) 4.8.5, clang version 3.8.0 (tags/RELEASE_380/final 262553) 56 195.58 opensuse:tumbleweed : Ok gcc (SUSE Linux) 9.2.1 20200128 [revision 83f65674e78d97d27537361de1a9d74067ff228d], clang version 9.0.1 57 18.33 oraclelinux:6 : FAIL gcc (GCC) 4.4.7 20120313 (Red Hat 4.4.7-23.0.1) 58 52.69 oraclelinux:7 : Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-39.0.3) 59 218.36 oraclelinux:8 : Ok gcc (GCC) 8.3.1 20190507 (Red Hat 8.3.1-4.5.0.5), clang version 8.0.1 (Red Hat 8.0.1-1.0.1.module+el8.1.0+5428+345cee14) 60 45.57 ubuntu:12.04 : Ok gcc (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3, Ubuntu clang version 3.0-6ubuntu3 (tags/RELEASE_30/final) (based on LLVM 3.0) 61 54.51 ubuntu:14.04 : Ok gcc (Ubuntu 4.8.4-2ubuntu1~14.04.4) 4.8.4 62 151.39 ubuntu:16.04 : Ok gcc (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609, clang version 3.8.0-2ubuntu4 (tags/RELEASE_380/final) 63 47.30 ubuntu:16.04-x-arm : Ok arm-linux-gnueabihf-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 64 24.91 ubuntu:16.04-x-arm64 : FAIL aarch64-linux-gnu-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609
Same thing as with debian experimental cross build, will fix this one
CC /tmp/build/perf/bench/mem-functions.o
CC /tmp/build/perf/tests/parse-events.oarch/arm64/util/machine.c: In function 'arch__symbols__fixup_end':arch/arm64/util/machine.c:19:7: error: implicit declaration of function 'strchr' [-Werror=implicit-function-declaration]
if ((strchr(p->name, '[') && strchr(c->name, '[') == NULL) ||
^
arch/arm64/util/machine.c:19:7: error: incompatible implicit declaration of built-in function 'strchr' [-Werror] arch/arm64/util/machine.c:19:7: note: include '<string.h>' or provide a declaration of 'strchr'
cc1: all warnings being treated as errors
MKDIR /tmp/build/perf/ui/
mv: cannot stat '/tmp/build/perf/arch/arm64/util/.machine.o.tmp': No such file or directory /git/linux/tools/build/Makefile.build:96: recipe for target '/tmp/build/perf/arch/arm64/util/machine.o' failed make[6]: *** [/tmp/build/perf/arch/arm64/util/machine.o] Error 1
CC /tmp/build/perf/ui/setup.o
/git/linux/tools/build/Makefile.build:139: recipe for target 'util' failed
make[5]: *** [util] Error 2
/git/linux/tools/build/Makefile.build:139: recipe for target 'arm64' failed
make[4]: *** [arm64] Error 2
/git/linux/tools/build/Makefile.build:139: recipe for target 'arch' failed
make[3]: *** [arch] Error 2
make[3]: *** Waiting for unfinished jobs....
65 47.00 ubuntu:16.04-x-powerpc : Ok powerpc-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 66 48.04 ubuntu:16.04-x-powerpc64 : Ok powerpc64-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 67 47.52 ubuntu:16.04-x-powerpc64el : Ok powerpc64le-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 68 46.10 ubuntu:16.04-x-s390 : Ok s390x-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 69 182.60 ubuntu:18.04 : Ok gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0, clang version 6.0.0-1ubuntu2 (tags/RELEASE_600/final) 70 50.66 ubuntu:18.04-x-arm : Ok arm-linux-gnueabihf-gcc (Ubuntu/Linaro 7.4.0-1ubuntu1~18.04.1) 7.4.0 71 26.81 ubuntu:18.04-x-arm64 : FAIL aarch64-linux-gnu-gcc (Ubuntu/Linaro 7.4.0-1ubuntu1~18.04.1) 7.4.0 72 38.36 ubuntu:18.04-x-m68k : Ok m68k-linux-gnu-gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0 73 50.79 ubuntu:18.04-x-powerpc : Ok powerpc-linux-gnu-gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0 74 57.69 ubuntu:18.04-x-powerpc64 : Ok powerpc64-linux-gnu-gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0 75 56.70 ubuntu:18.04-x-powerpc64el : Ok powerpc64le-linux-gnu-gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0 76 147.10 ubuntu:18.04-x-riscv64 : Ok riscv64-linux-gnu-gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0 77 43.49 ubuntu:18.04-x-s390 : Ok s390x-linux-gnu-gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0 78 52.88 ubuntu:18.04-x-sh4 : Ok sh4-linux-gnu-gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0 79 45.57 ubuntu:18.04-x-sparc64 : Ok sparc64-linux-gnu-gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0 80 168.41 ubuntu:18.10 : Ok gcc (Ubuntu 8.3.0-6ubuntu1~18.10.1) 8.3.0, clang version 7.0.0-3 (tags/RELEASE_700/final) 81 177.55 ubuntu:19.04 : Ok gcc (Ubuntu 8.3.0-6ubuntu1) 8.3.0, clang version 8.0.0-3 (tags/RELEASE_800/final) 82 45.12 ubuntu:19.04-x-alpha : Ok alpha-linux-gnu-gcc (Ubuntu 8.3.0-6ubuntu1) 8.3.0 83 28.06 ubuntu:19.04-x-arm64 : FAIL aarch64-linux-gnu-gcc (Ubuntu/Linaro 8.3.0-6ubuntu1) 8.3.0 84 43.21 ubuntu:19.04-x-hppa : Ok hppa-linux-gnu-gcc (Ubuntu 8.3.0-6ubuntu1) 8.3.0 85 147.65 ubuntu:19.10 : FAIL gcc (Ubuntu 9.2.1-9ubuntu2) 9.2.1 20191008, clang version 9.0.0-2 (tags/RELEASE_900/final)
This should be something else, will check.
Namhyung Kim
maintainerRe: [PATCH 6/9] perf record: Support synthesizing cgroup events
In reply to Arnaldo Carvalho de MeloHi Arnaldo,
Quoted 52 lines · Arnaldo Carvalho de Melo
Em Mon, Mar 30, 2020 at 01:30:58PM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 24 lines
Em Wed, Mar 25, 2020 at 09:45:33PM +0900, Namhyung Kim escreveu:
Quoted 3 lines
Synthesize cgroup events by iterating cgroup filesystem directories. The cgroup event only saves the portion of cgroup path after the mount point and the cgroup id (which actually is a file handle).
Breaks the build on alpine linux (musl libc):
CC
/tmp/build/perf/util/srccode.o
CC/tmp/build/perf/util/synthetic-events.outil/synthetic-events.c: In function 'perf_event__synthesize_cgroup':util/synthetic-events.c:427:22: error: field 'fh' has incomplete typestruct file_handle fh; ^ util/synthetic-events.c:441:6: error: implicit declaration of function 'name_to_handle_at' [-Werror=implicit-function-declaration] if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0) < 0) { ^
util/synthetic-events.c:441:2: error: nested extern declaration of 'name_to_handle_at' [-Werror=nested-externs]
if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0)< 0) {
^
CC/tmp/build/perf/util/data.o
cc1: all warnings being treated as errors
mv: can't rename '/tmp/build/perf/util/.synthetic-events.o.tmp': No such file or directoryQuoted 1 line
I'm trying to fix
musl libc up to 1.2.21 (IIRC) lacks
name_to_handle_atand its structs, then from the one that is in alpine linux 3.10 the error changes to:CC
/tmp/build/perf/util/cloexec.outil/synthetic-events.c:427:22: error: field 'fh' with variable sized type 'structfile_handle' not at the end of a struct or class is a GNUextension [-Werror,-Wgnu-variable-sized-type-not-at-end] struct file_handle fh; ^1 error generated.
mv: can't rename '/tmp/build/perf/util/.synthetic-events.o.tmp': No such file or directory make[4]: *** [/git/linux/tools/build/Makefile.build:97:/tmp/build/perf/util/synthetic-events.o] Error 1 make[4]: *** Waiting for unfinished jobs....
make[3]: *** [/git/linux/tools/build/Makefile.build:139: util] Error 2
make[2]: *** [Makefile.perf:617:/tmp/build/perf/perf-in.o] Error 2
make[1]: *** [Makefile.perf:225: sub-make] Error 2
make: *** [Makefile:70: all] Error 2
make: Leaving directory '/git/linux/tools/perf'
+ exit 1
[root@quaco ~]#So probably we'll need a feature test to catch this and do some workaround or disable the feature on such systems, providing some warning.
Quoted 6 lines
I left the container build tests running to see if some other system has problems with this, perhaps the ones with uCLibc or some older glibc, we'll see.
So far all the alpine versions failed with the above problems and ALT Linux p8 and p9 built without problems.
Hmm.. right, the CONFIG_FHANDLE can be turned off or old systems lack support. I'll send a patch for the feature test soon.
Thanks
Namhyung
Namhyung Kim
maintainerPATCH 1/1 perf tools: Add file-handle feature test
The file handle (FHANDLE) support is configurable so some systems might not have it. So add a config feature item to check it on build time and reject cgroup tracking based on that.
--- tools/build/Makefile.feature | 3 ++- tools/build/feature/Makefile | 6 +++++- tools/build/feature/test-file-handle.c | 14 ++++++++++++++ tools/perf/Makefile.config | 4 ++++ tools/perf/builtin-record.c | 8 +++++++- tools/perf/builtin-top.c | 8 +++++++- tools/perf/util/synthetic-events.c | 9 +++++++++ 7 files changed, 48 insertions(+), 4 deletions(-) create mode 100644 tools/build/feature/test-file-handle.c
tools/build/Makefile.feature +2 -1
@@ -72,7 +72,8 @@ FEATURE_TESTS_BASIC := \ setns \ libaio \ libzstd \ - disassembler-four-args + disassembler-four-args \ + file-handle # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list # of all feature tests
tools/build/feature/Makefile +5 -1
@@ -67,7 +67,8 @@ FILES= \ test-llvm.bin \ test-llvm-version.bin \ test-libaio.bin \ - test-libzstd.bin + test-libzstd.bin \ + test-file-handle.bin FILES := $(addprefix $(OUTPUT),$(FILES))
@@ -321,6 +322,9 @@ FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) $(OUTPUT)test-libzstd.bin: $(BUILD) -lzstd +$(OUTPUT)test-file-handle.bin: + $(BUILD) + ############################### clean:
tools/build/feature/test-file-handle.c new file +14 -0
@@ -0,0 +1,14 @@ +#define _GNU_SOURCE +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> + +int main (void ) +{ +struct file_handle fh; +int mount_id; + +name_to_handle_at (AT_FDCWD ,"/" , &fh, &mount_id,0 ); +return 0 ; +} +
tools/perf/Makefile.config +4 -0
@@ -348,6 +348,10 @@ ifeq ($(feature-gettid), 1) CFLAGS += -DHAVE_GETTID endif +ifeq ($(feature-file-handle), 1) + CFLAGS += -DHAVE_FILE_HANDLE +endif + ifdef NO_LIBELF NO_DWARF := 1 NO_DEMANGLE := 1
tools/perf/builtin-record.c +7 -1
@@ -1433,8 +1433,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)if (rec->opts.record_namespaces) tool->namespace_events = true; -if (rec->opts.record_cgroup) +if (rec->opts.record_cgroup) { +#ifdef HAVE_FILE_HANDLE tool->cgroup_events = true; +#else +pr_err ("cgroup tracking is not supported\n" ); +return -1 ; +#endif + }if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {signal (SIGUSR2 , snapshot_sig_handler);
tools/perf/builtin-top.c +7 -1
@@ -1246,8 +1246,14 @@ static int __cmd_top(struct perf_top *top)if (opts->record_namespaces) top->tool.namespace_events = true; -if (opts->record_cgroup) +if (opts->record_cgroup) { +#ifdef HAVE_FILE_HANDLE top->tool.cgroup_events = true; +#else +pr_err ("cgroup tracking is not supported.\n" ); +return -1 ; +#endif + } ret = perf_event__synthesize_bpf_events(top->session, perf_event__process, &top->session->machines.host,
tools/perf/util/synthetic-events.c +9 -0
@@ -415,6 +415,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,return rc; } +#ifdef HAVE_FILE_HANDLE static int perf_event__synthesize_cgroup(struct perf_tool *tool, union perf_event *event, char *path, size_t mount_len,
@@ -526,6 +527,14 @@ int perf_event__synthesize_cgroups(struct perf_tool *tool, return 0; } +#else +int perf_event__synthesize_cgroups (struct perf_tool *tool, +perf_event__handler_t process, +struct machine *machine) +{ +return -1 ; +} +#endif int perf_event__synthesize_modules (struct perf_tool *tool,perf_event__handler_t process,struct machine *machine)
Signature · 1 line
2.26.0.rc2.310.g2932bb562d-goog
Re: [PATCH] perf tools: Add file-handle feature test
Em Thu, Apr 02, 2020 at 10:52:49AM +0900, Namhyung Kim escreveu:
Quoted 3 lines
The file handle (FHANDLE) support is configurable so some systems might not have it. So add a config feature item to check it on build time and reject cgroup tracking based on that.
Ok, I'll break this patch in two, add the feature test first, then fold the usage of HAVE_FILE_HANDLE with the patch that uses it, so that we keep the codebase bisectable,
Thanks!
- Arnaldo
Quoted 156 lines
Reported-by Arnaldo Carvalho de Melo <[email protected]>Signed-off-by Namhyung Kim <[email protected]>--- tools/build/Makefile.feature | 3 ++- tools/build/feature/Makefile | 6 +++++- tools/build/feature/test-file-handle.c | 14 ++++++++++++++ tools/perf/Makefile.config | 4 ++++ tools/perf/builtin-record.c | 8 +++++++- tools/perf/builtin-top.c | 8 +++++++- tools/perf/util/synthetic-events.c | 9 +++++++++ 7 files changed, 48 insertions(+), 4 deletions(-) create mode 100644 tools/build/feature/test-file-handle.ctools/build/Makefile.feature +2
-1@@ -72,7 +72,8 @@ FEATURE_TESTS_BASIC := \ setns \ libaio \ libzstd \ - disassembler-four-args + disassembler-four-args \ + file-handle # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list # of all feature teststools/build/feature/Makefile +5
-1@@ -67,7 +67,8 @@ FILES= \ test-llvm.bin \ test-llvm-version.bin \ test-libaio.bin \ - test-libzstd.bin + test-libzstd.bin \ + test-file-handle.bin FILES := $(addprefix $(OUTPUT),$(FILES))@@ -321,6 +322,9 @@ FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) $(OUTPUT)test-libzstd.bin: $(BUILD) -lzstd +$(OUTPUT)test-file-handle.bin: + $(BUILD) + ############################### clean:tools/build/feature/test-file-handle.c new file +14
-0@@ -0,0 +1,14 @@ +#define _GNU_SOURCE +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> + +int main (void ) +{ +struct file_handle fh; +int mount_id; + +name_to_handle_at (AT_FDCWD ,"/" , &fh, &mount_id,0 ); +return 0 ; +} +tools/perf/Makefile.config +4
-0@@ -348,6 +348,10 @@ ifeq ($(feature-gettid), 1) CFLAGS += -DHAVE_GETTID endif +ifeq ($(feature-file-handle), 1) + CFLAGS += -DHAVE_FILE_HANDLE +endif + ifdef NO_LIBELF NO_DWARF := 1 NO_DEMANGLE := 1tools/perf/builtin-record.c +7
-1@@ -1433,8 +1433,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)if (rec->opts.record_namespaces) tool->namespace_events = true; -if (rec->opts.record_cgroup) +if (rec->opts.record_cgroup) { +#ifdef HAVE_FILE_HANDLE tool->cgroup_events = true; +#else +pr_err ("cgroup tracking is not supported\n" ); +return -1 ; +#endif + }if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {signal (SIGUSR2 , snapshot_sig_handler);tools/perf/builtin-top.c +7
-1@@ -1246,8 +1246,14 @@ static int __cmd_top(struct perf_top *top)if (opts->record_namespaces) top->tool.namespace_events = true; -if (opts->record_cgroup) +if (opts->record_cgroup) { +#ifdef HAVE_FILE_HANDLE top->tool.cgroup_events = true; +#else +pr_err ("cgroup tracking is not supported.\n" ); +return -1 ; +#endif + } ret = perf_event__synthesize_bpf_events(top->session, perf_event__process, &top->session->machines.host,tools/perf/util/synthetic-events.c +9
-0@@ -415,6 +415,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,return rc; } +#ifdef HAVE_FILE_HANDLE static int perf_event__synthesize_cgroup(struct perf_tool *tool, union perf_event *event, char *path, size_t mount_len,@@ -526,6 +527,14 @@ int perf_event__synthesize_cgroups(struct perf_tool *tool, return 0; } +#else +int perf_event__synthesize_cgroups (struct perf_tool *tool, +perf_event__handler_t process, +struct machine *machine) +{ +return -1 ; +} +#endif int perf_event__synthesize_modules (struct perf_tool *tool,perf_event__handler_t process,struct machine *machine)Signature · 1 line
2.26.0.rc2.310.g2932bb562d-goog
Signature · 1 line
- Arnaldo
Re: [PATCH] perf tools: Add file-handle feature test
Em Thu, Apr 02, 2020 at 12:37:48PM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 10 lines
Em Thu, Apr 02, 2020 at 10:52:49AM +0900, Namhyung Kim escreveu:
Quoted 3 lines
The file handle (FHANDLE) support is configurable so some systems might not have it. So add a config feature item to check it on build time and reject cgroup tracking based on that.
Ok, I'll break this patch in two, add the feature test first, then fold the usage of
HAVE_FILE_HANDLEwith the patch that uses it, so that we keep the codebase bisectable,Thanks!
Also had to do this here and in the other similar places:
tools/perf/util/synthetic-events.c +3 -3
@@ -528,9 +528,9 @@ int perf_event__synthesize_cgroups(struct perf_tool *tool, return 0; }#else -int perf_event__synthesize_cgroups (struct perf_tool *tool, -perf_event__handler_t process, -struct machine *machine) +int perf_event__synthesize_cgroups (struct perf_tool *tool__maybe_unused , +perf_event__handler_t process__maybe_unused , +struct machine *machine__maybe_unused ) {return -1 ; }
Re: [PATCH] perf tools: Add file-handle feature test
In reply to Arnaldo Carvalho de MeloEm Thu, Apr 02, 2020 at 12:37:48PM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 9 lines
Em Thu, Apr 02, 2020 at 10:52:49AM +0900, Namhyung Kim escreveu:
Quoted 3 lines
The file handle (FHANDLE) support is configurable so some systems might not have it. So add a config feature item to check it on build time and reject cgroup tracking based on that.
Ok, I'll break this patch in two, add the feature test first, then fold the usage of
HAVE_FILE_HANDLEwith the patch that uses it, so that we keep the codebase bisectable,
Quoted 14 lines
Quoted 4 lines
+++
b/tools/build/feature/test-file-handle.c(quoted diff) +2
-0@@ -0,0 +1,14 @@ +#define _GNU_SOURCE +#include <sys/types.h>Review line 12
Quoted 10 lines
(quoted diff) +10
-0+#include <sys/stat.h> +#include <fcntl.h> + +int main(void) +{ + struct file_handle fh; + int mount_id; + + name_to_handle_at(AT_FDCWD, "/", &fh, &mount_id, 0); + return 0;
Also had to do it just like you use in your patches, see patch below, to cover this case as well:
CC /tmp/build/perf/util/synthetic-events.o
CC /tmp/build/perf/util/data.o
CC /tmp/build/perf/util/tsc.o
CC /tmp/build/perf/util/cloexec.o
util/synthetic-events.c:428:22: error: field 'fh' with CC /tmp/build/perf/util/call-path.o
variable sized type 'struct file_handle' not at the end of a struct or class is a GNU
extension [-Werror,-Wgnu-variable-sized-type-not-at-end]
struct file_handle fh;
^1 error generated.
mv: can't rename '/tmp/build/perf/util/.synthetic-events.o.tmp': No such file or directory make[4]: *** [/git/linux/tools/build/Makefile.build:97: /tmp/build/perf/util/synthetic-events.o] Error 1 make[4]: *** Waiting for unfinished jobs....
This is on Alpine Linux 3.11 onwards, musl libc.
- Arnaldo
tools/build/feature/test-file-handle.c +5 -2
@@ -5,9 +5,12 @@int main (void ) { -struct file_handle fh; +struct { +struct file_handle fh; +uint64_t cgroup_id; + } handle;int mount_id; -name_to_handle_at (AT_FDCWD ,"/" , &fh, &mount_id,0 ); +name_to_handle_at (AT_FDCWD ,"/" , &handle.fh, &mount_id,0 );return 0 ; }
[tip: perf/urgent] perf tools: Add file-handle feature test
In reply to Namhyung KimThe following commit has been merged into the perf/urgent branch of tip:
The following commit has been merged into the perf/urgent branch of tip:
Commit-ID: 49f550ea87c73671ee4d5e08820e0976894dd610 Gitweb: https://git.kernel.org/tip/49f550ea87c73671ee4d5e08820e0976894dd610 Author: Namhyung Kim <[email protected]> AuthorDate: Thu, 02 Apr 2020 10:52:49 +09:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Fri, 03 Apr 2020 09:37:55 -03:00
perf tools: Add file-handle feature test
The file handle (FHANDLE) support is configurable so some systems might not have it. So add a config feature item to check it on build time so that we don't add the cgroup tracking feature based on that.
Committer notes:
Had to make the test use the same construct as its later use in synthetic-events.c, in the next patch in this series. i.e. make it be:
struct {
struct file_handle fh;
uint64_t cgroup_id;
} handle;To cope with:
CC /tmp/build/perf/util/cloexec.o
util/synthetic-events.c:428:22: error: field 'fh' with CC /tmp/build/perf/util/call-path.o
variable sized type 'struct file_handle' not at the end of a struct or class is a GNU
extension [-Werror,-Wgnu-variable-sized-type-not-at-end]
struct file_handle fh;
^1 error generated.
Deal with this at some point, i.e. investigate if the right thing is to remove that -Wgnu-variable-sized-type-not-at-end from our CFLAGS, for now do the test the same way as it is used looks more sensible.
--- tools/build/Makefile.feature | 3 ++- tools/build/feature/Makefile | 6 +++++- tools/build/feature/test-file-handle.c | 17 +++++++++++++++++ tools/perf/Makefile.config | 4 ++++ 4 files changed, 28 insertions(+), 2 deletions(-) create mode 100644 tools/build/feature/test-file-handle.c
tools/build/Makefile.feature +2 -1
@@ -72,7 +72,8 @@ FEATURE_TESTS_BASIC := \ setns \ libaio \ libzstd \ - disassembler-four-args + disassembler-four-args \ + file-handle # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list # of all feature tests
tools/build/feature/Makefile +5 -1
@@ -67,7 +67,8 @@ FILES= \ test-llvm.bin \ test-llvm-version.bin \ test-libaio.bin \ - test-libzstd.bin + test-libzstd.bin \ + test-file-handle.bin FILES := $(addprefix $(OUTPUT),$(FILES))
@@ -321,6 +322,9 @@ $(OUTPUT)test-libaio.bin: $(OUTPUT)test-libzstd.bin: $(BUILD) -lzstd +$(OUTPUT)test-file-handle.bin: + $(BUILD) + ############################### clean:
tools/build/feature/test-file-handle.c new file +17 -0
@@ -0,0 +1,17 @@ +#define _GNU_SOURCE +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <inttypes.h> + +int main (void ) +{ +struct { +struct file_handle fh; +uint64_t cgroup_id; + } handle; +int mount_id; + +name_to_handle_at (AT_FDCWD ,"/" , &handle.fh, &mount_id,0 ); +return 0 ; +}
tools/perf/Makefile.config +4 -0
@@ -348,6 +348,10 @@ ifeq ($(feature-gettid), 1) CFLAGS += -DHAVE_GETTID endif +ifeq ($(feature-file-handle), 1) + CFLAGS += -DHAVE_FILE_HANDLE +endif + ifdef NO_LIBELF NO_DWARF := 1 NO_DEMANGLE := 1
[tip: perf/urgent] perf record: Support synthesizing cgroup events
In reply to Namhyung KimThe following commit has been merged into the perf/urgent branch of tip:
The following commit has been merged into the perf/urgent branch of tip:
Commit-ID: ab64069f1a6604a43daec5fc4a4294b0b77a8b93 Gitweb: https://git.kernel.org/tip/ab64069f1a6604a43daec5fc4a4294b0b77a8b93 Author: Namhyung Kim <[email protected]> AuthorDate: Wed, 25 Mar 2020 21:45:33 +09:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Fri, 03 Apr 2020 09:37:55 -03:00
perf record: Support synthesizing cgroup events
Synthesize cgroup events by iterating cgroup filesystem directories. The cgroup event only saves the portion of cgroup path after the mount point and the cgroup id (which actually is a file handle).
--- tools/perf/builtin-record.c | 5 +- tools/perf/util/synthetic-events.c | 122 ++++++++++++++++++++++++++++- tools/perf/util/synthetic-events.h | 1 +- tools/perf/util/tool.h | 1 +- 4 files changed, 129 insertions(+)
tools/perf/builtin-record.c +5 -0
@@ -1397,6 +1397,11 @@ static int record__synthesize(struct record *rec, bool tail)if (err <0 )pr_warning ("Couldn't synthesize bpf events.\n" ); + err =perf_event__synthesize_cgroups (tool, process_synthesized_event, + machine); +if (err <0 ) +pr_warning ("Couldn't synthesize cgroup events.\n" ); + err =__machine__synthesize_threads (machine, tool, &opts->target, rec->evlist->core.threads, process_synthesized_event, opts->sample_address,1 );
tools/perf/util/synthetic-events.c +122 -0
134 lines not on this page · raw message
tools/perf/util/synthetic-events.h +1 -0
@@ -45,6 +45,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handlint perf_event__synthesize_mmap_events (struct perf_tool *tool,union perf_event *event,pid_t pid,pid_t tgid,perf_event__handler_t process,struct machine *machine,bool mmap_data);int perf_event__synthesize_modules (struct perf_tool *tool,perf_event__handler_t process,struct machine *machine);int perf_event__synthesize_namespaces (struct perf_tool *tool,union perf_event *event,pid_t pid,pid_t tgid,perf_event__handler_t process,struct machine *machine); +int perf_event__synthesize_cgroups (struct perf_tool *tool,perf_event__handler_t process,struct machine *machine);int perf_event__synthesize_sample (union perf_event *event,u64 type,u64 read_format,const struct perf_sample *sample);int perf_event__synthesize_stat_config (struct perf_tool *tool,struct perf_stat_config *config,perf_event__handler_t process,struct machine *machine);int perf_event__synthesize_stat_events (struct perf_stat_config *config,struct perf_tool *tool,struct evlist *evlist,perf_event__handler_t process,bool attrs);
tools/perf/util/tool.h +1 -0
@@ -79,6 +79,7 @@ struct perf_tool {bool ordered_events;bool ordering_requires_timestamps;bool namespace_events; +bool cgroup_events;bool no_warn;enum show_feature_header show_feat_hdr; };
Namhyung Kim
maintainerPATCH 7/9 perf record: Add --all-cgroups option
In reply to Namhyung KimThe --all-cgroups option is to enable cgroup profiling support. It tells kernel to record CGROUP events in the ring buffer so that perf report can identify task/cgroup association later.
--- tools/perf/Documentation/perf-record.txt | 5 ++++- tools/perf/builtin-record.c | 5 +++++ tools/perf/util/evsel.c | 11 ++++++++++- tools/perf/util/evsel.h | 1 + tools/perf/util/record.h | 1 + 5 files changed, 21 insertions(+), 2 deletions(-)
tools/perf/Documentation/perf-record.txt +4 -1
@@ -385,7 +385,10 @@ displayed with the weight and local_weight sort keys. This currently works for abort events and some memory events in precise mode on modern Intel CPUs. --namespaces:: -Record events of type PERF_RECORD_NAMESPACES. +Record events of type PERF_RECORD_NAMESPACES. This enables 'cgroup_id' sort key. + +--all-cgroups:: +Record events of type PERF_RECORD_CGROUP. This enables 'cgroup' sort key. --transaction:: Record transaction flags for transaction related events.
tools/perf/builtin-record.c +5 -0
@@ -1433,6 +1433,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)if (rec->opts.record_namespaces) tool->namespace_events = true; +if (rec->opts.record_cgroup) + tool->cgroup_events = true; +if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {signal (SIGUSR2 , snapshot_sig_handler);if (rec->opts.auxtrace_snapshot_mode)
@@ -2363,6 +2366,8 @@ static struct option __record_options[] = { "per thread proc mmap processing timeout in ms"),OPT_BOOLEAN (0 ,"namespaces" , &record.opts.record_namespaces,"Record namespaces events" ), +OPT_BOOLEAN (0 ,"all-cgroups" , &record.opts.record_cgroup, +"Record cgroup events" ),OPT_BOOLEAN (0 ,"switch-events" , &record.opts.record_switch_events,"Record context switch events" ), OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel,
tools/perf/util/evsel.c +10 -1
@@ -1104,6 +1104,11 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,if (opts->record_namespaces) attr->namespaces = track; +if (opts->record_cgroup) { + attr->cgroup = track && !perf_missing_features.cgroup; +perf_evsel__set_sample_bit (evsel,CGROUP ); + } +if (opts->record_switch_events) attr->context_switch = track;
@@ -1789,7 +1794,11 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,* Must probe features in the order they were added to the * perf_event_attr interface. */ -if (!perf_missing_features.branch_hw_idx && +if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) { + perf_missing_features.cgroup = true; +pr_debug2_peo ("Kernel has no cgroup sampling support, bailing out\n" ); + goto out_close; + }else if (!perf_missing_features.branch_hw_idx && (evsel->core.attr.branch_sample_type &PERF_SAMPLE_BRANCH_HW_INDEX )) { perf_missing_features.branch_hw_idx = true;pr_debug2 ("switching off branch HW index support\n" );
tools/perf/util/evsel.h +1 -0
@@ -120,6 +120,7 @@ struct perf_missing_features {bool bpf;bool aux_output;bool branch_hw_idx; +bool cgroup; };extern struct perf_missing_features perf_missing_features;
tools/perf/util/record.h +1 -0
@@ -34,6 +34,7 @@ struct record_opts {bool auxtrace_snapshot_on_exit;bool auxtrace_sample_mode;bool record_namespaces; +bool record_cgroup;bool record_switch_events;bool all_kernel;bool all_user;
Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
[tip: perf/urgent] perf record: Add --all-cgroups option
The following commit has been merged into the perf/urgent branch of tip:
The following commit has been merged into the perf/urgent branch of tip:
Commit-ID: 8fb4b67939e169fca68174e9ac7be79fe9a04498 Gitweb: https://git.kernel.org/tip/8fb4b67939e169fca68174e9ac7be79fe9a04498 Author: Namhyung Kim <[email protected]> AuthorDate: Wed, 25 Mar 2020 21:45:34 +09:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Fri, 03 Apr 2020 09:37:55 -03:00
perf record: Add --all-cgroups option
The --all-cgroups option is to enable cgroup profiling support. It tells kernel to record CGROUP events in the ring buffer so that perf report can identify task/cgroup association later.
[root@seventh ~]# perf record --all-cgroups --namespaces /wb/cgtest
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.042 MB perf.data (558 samples) ]
[root@seventh ~]# perf report --stdio -s cgroup_id,cgroup,pid
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 558 of event 'cycles'
# Event count (approx.): 458017341
#
# Overhead cgroup id (dev/inode) Cgroup Pid:Command
# ........ ..................... .......... ...............
#
33.15% 4/0xeffffffb /sub 9615:looper0
32.83% 4/0xf00002f5 /sub/cgrp2 9620:looper2
32.79% 4/0xf00002f4 /sub/cgrp1 9619:looper1
0.35% 4/0xf00002f5 /sub/cgrp2 9618:cgtest
0.34% 4/0xf00002f4 /sub/cgrp1 9617:cgtest
0.32% 4/0xeffffffb / 9615:looper0
0.11% 4/0xeffffffb /sub 9617:cgtest
0.10% 4/0xeffffffb /sub 9618:cgtest #
# (Tip: Sample related events with: perf record -e '{cycles,instructions}:S') #
[root@seventh ~]#
--- tools/perf/Documentation/perf-record.txt | 5 ++++- tools/perf/builtin-record.c | 11 +++++++++++ tools/perf/util/evsel.c | 11 ++++++++++- tools/perf/util/evsel.h | 1 + tools/perf/util/record.h | 1 + 5 files changed, 27 insertions(+), 2 deletions(-)
tools/perf/Documentation/perf-record.txt +4 -1
@@ -391,7 +391,10 @@ displayed with the weight and local_weight sort keys. This currently works for abort events and some memory events in precise mode on modern Intel CPUs. --namespaces:: -Record events of type PERF_RECORD_NAMESPACES. +Record events of type PERF_RECORD_NAMESPACES. This enables 'cgroup_id' sort key. + +--all-cgroups:: +Record events of type PERF_RECORD_CGROUP. This enables 'cgroup' sort key. --transaction:: Record transaction flags for transaction related events.
tools/perf/builtin-record.c +11 -0
@@ -1433,6 +1433,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)if (rec->opts.record_namespaces) tool->namespace_events = true; +if (rec->opts.record_cgroup) { +#ifdef HAVE_FILE_HANDLE + tool->cgroup_events = true; +#else +pr_err ("cgroup tracking is not supported\n" ); +return -1 ; +#endif + } +if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {signal (SIGUSR2 , snapshot_sig_handler);if (rec->opts.auxtrace_snapshot_mode)
@@ -2363,6 +2372,8 @@ static struct option __record_options[] = { "per thread proc mmap processing timeout in ms"),OPT_BOOLEAN (0 ,"namespaces" , &record.opts.record_namespaces,"Record namespaces events" ), +OPT_BOOLEAN (0 ,"all-cgroups" , &record.opts.record_cgroup, +"Record cgroup events" ),OPT_BOOLEAN (0 ,"switch-events" , &record.opts.record_switch_events,"Record context switch events" ), OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel,
tools/perf/util/evsel.c +10 -1
@@ -1104,6 +1104,11 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,if (opts->record_namespaces) attr->namespaces = track; +if (opts->record_cgroup) { + attr->cgroup = track && !perf_missing_features.cgroup; +perf_evsel__set_sample_bit (evsel,CGROUP ); + } +if (opts->record_switch_events) attr->context_switch = track;
@@ -1789,7 +1794,11 @@ try_fallback:* Must probe features in the order they were added to the * perf_event_attr interface. */ -if (!perf_missing_features.branch_hw_idx && +if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) { + perf_missing_features.cgroup = true; +pr_debug2_peo ("Kernel has no cgroup sampling support, bailing out\n" ); + goto out_close; + }else if (!perf_missing_features.branch_hw_idx && (evsel->core.attr.branch_sample_type &PERF_SAMPLE_BRANCH_HW_INDEX )) { perf_missing_features.branch_hw_idx = true;pr_debug2 ("switching off branch HW index support\n" );
tools/perf/util/evsel.h +1 -0
@@ -120,6 +120,7 @@ struct perf_missing_features {bool bpf;bool aux_output;bool branch_hw_idx; +bool cgroup; };extern struct perf_missing_features perf_missing_features;
tools/perf/util/record.h +1 -0
@@ -34,6 +34,7 @@ struct record_opts {bool auxtrace_snapshot_on_exit;bool auxtrace_sample_mode;bool record_namespaces; +bool record_cgroup;bool record_switch_events;bool all_kernel;bool all_user;
Namhyung Kim
maintainerPATCH 8/9 perf top: Add --all-cgroups option
In reply to Namhyung KimThe --all-cgroups option is to enable cgroup profiling support. It tells kernel to record CGROUP events in the ring buffer so that perf report can identify task/cgroup association later.
--- tools/perf/Documentation/perf-top.txt | 4 ++++ tools/perf/builtin-top.c | 9 +++++++++ 2 files changed, 13 insertions(+)
tools/perf/Documentation/perf-top.txt +4 -0
@@ -272,6 +272,10 @@ Default is to monitor all CPUS. Record events of type PERF_RECORD_NAMESPACES and display it with the 'cgroup_id' sort key. +--all-cgroups:: + Record events of type PERF_RECORD_CGROUP and display it with the + 'cgroup' sort key. + --switch-on EVENT_NAME:: Only consider events after this event is found.
tools/perf/builtin-top.c +9 -0
@@ -1246,6 +1246,8 @@ static int __cmd_top(struct perf_top *top)if (opts->record_namespaces) top->tool.namespace_events = true; +if (opts->record_cgroup) + top->tool.cgroup_events = true; ret = perf_event__synthesize_bpf_events(top->session, perf_event__process, &top->session->machines.host,
@@ -1253,6 +1255,11 @@ static int __cmd_top(struct perf_top *top)if (ret <0 )pr_debug ("Couldn't synthesize BPF events: Pre-existing BPF programs won't have symbols resolved.\n" ); + ret =perf_event__synthesize_cgroups (&top->tool, perf_event__process, + &top->session->machines.host); +if (ret <0 ) +pr_debug ("Couldn't synthesize cgroup events.\n" ); +machine__synthesize_threads (&top->session->machines.host, &opts->target, top->evlist->core.threads, false, top->nr_threads_synthesize);
@@ -1545,6 +1552,8 @@ int cmd_top(int argc, const char **argv) "number of thread to run event synthesize"),OPT_BOOLEAN (0 ,"namespaces" , &opts->record_namespaces,"Record namespaces events" ), +OPT_BOOLEAN (0 ,"all-cgroups" , &opts->record_cgroup, +"Record cgroup events" ),OPTS_EVSWITCH (&top.evswitch), OPT_END() };
Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
Re: [PATCH 8/9] perf top: Add --all-cgroups option
Em Wed, Mar 25, 2020 at 09:45:35PM +0900, Namhyung Kim escreveu:
Quoted 3 lines
The --all-cgroups option is to enable cgroup profiling support. It tells kernel to record CGROUP events in the ring buffer so that perf report can identify task/cgroup association later.
s/report/top/g in this case, and I added:
Committer testing:
Use:
# perf top --all-cgroups -s cgroup_id,cgroup,pid- Arnaldo
Quoted 58 lines
Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/Documentation/perf-top.txt | 4 ++++ tools/perf/builtin-top.c | 9 +++++++++ 2 files changed, 13 insertions(+)tools/perf/Documentation/perf-top.txt +4
-0@@ -272,6 +272,10 @@ Default is to monitor all CPUS. Record events of type PERF_RECORD_NAMESPACES and display it with the 'cgroup_id' sort key. +--all-cgroups:: + Record events of type PERF_RECORD_CGROUP and display it with the + 'cgroup' sort key. + --switch-on EVENT_NAME:: Only consider events after this event is found.tools/perf/builtin-top.c +9
-0@@ -1246,6 +1246,8 @@ static int __cmd_top(struct perf_top *top)if (opts->record_namespaces) top->tool.namespace_events = true; +if (opts->record_cgroup) + top->tool.cgroup_events = true; ret = perf_event__synthesize_bpf_events(top->session, perf_event__process, &top->session->machines.host,@@ -1253,6 +1255,11 @@ static int __cmd_top(struct perf_top *top)if (ret <0 )pr_debug ("Couldn't synthesize BPF events: Pre-existing BPF programs won't have symbols resolved.\n" ); + ret =perf_event__synthesize_cgroups (&top->tool, perf_event__process, + &top->session->machines.host); +if (ret <0 ) +pr_debug ("Couldn't synthesize cgroup events.\n" ); +machine__synthesize_threads (&top->session->machines.host, &opts->target, top->evlist->core.threads, false, top->nr_threads_synthesize);@@ -1545,6 +1552,8 @@ int cmd_top(int argc, const char **argv) "number of thread to run event synthesize"),OPT_BOOLEAN (0 ,"namespaces" , &opts->record_namespaces,"Record namespaces events" ), +OPT_BOOLEAN (0 ,"all-cgroups" , &opts->record_cgroup, +"Record cgroup events" ),OPTS_EVSWITCH (&top.evswitch), OPT_END() };Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
Signature · 1 line
- Arnaldo
[tip: perf/urgent] perf top: Add --all-cgroups option
In reply to Namhyung KimThe following commit has been merged into the perf/urgent branch of tip:
The following commit has been merged into the perf/urgent branch of tip:
Commit-ID: f382842fa0244ae1e2c28c8377732c85ec1fe7a9 Gitweb: https://git.kernel.org/tip/f382842fa0244ae1e2c28c8377732c85ec1fe7a9 Author: Namhyung Kim <[email protected]> AuthorDate: Wed, 25 Mar 2020 21:45:35 +09:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Fri, 03 Apr 2020 09:37:55 -03:00
perf top: Add --all-cgroups option
The --all-cgroups option is to enable cgroup profiling support. It tells kernel to record CGROUP events in the ring buffer so that 'perf top' can identify task/cgroup association later.
Committer testing:
Use:
# perf top --all-cgroups -s cgroup_id,cgroup,pid
--- tools/perf/Documentation/perf-top.txt | 4 ++++ tools/perf/builtin-top.c | 15 +++++++++++++++ 2 files changed, 19 insertions(+)
tools/perf/Documentation/perf-top.txt +4 -0
@@ -272,6 +272,10 @@ Default is to monitor all CPUS. Record events of type PERF_RECORD_NAMESPACES and display it with the 'cgroup_id' sort key. +--all-cgroups:: + Record events of type PERF_RECORD_CGROUP and display it with the + 'cgroup' sort key. + --switch-on EVENT_NAME:: Only consider events after this event is found.
tools/perf/builtin-top.c +15 -0
@@ -1246,6 +1246,14 @@ static int __cmd_top(struct perf_top *top)if (opts->record_namespaces) top->tool.namespace_events = true; +if (opts->record_cgroup) { +#ifdef HAVE_FILE_HANDLE + top->tool.cgroup_events = true; +#else +pr_err ("cgroup tracking is not supported.\n" ); +return -1 ; +#endif + } ret = perf_event__synthesize_bpf_events(top->session, perf_event__process, &top->session->machines.host,
@@ -1253,6 +1261,11 @@ static int __cmd_top(struct perf_top *top)if (ret <0 )pr_debug ("Couldn't synthesize BPF events: Pre-existing BPF programs won't have symbols resolved.\n" ); + ret =perf_event__synthesize_cgroups (&top->tool, perf_event__process, + &top->session->machines.host); +if (ret <0 ) +pr_debug ("Couldn't synthesize cgroup events.\n" ); +machine__synthesize_threads (&top->session->machines.host, &opts->target, top->evlist->core.threads, false, top->nr_threads_synthesize);
@@ -1545,6 +1558,8 @@ int cmd_top(int argc, const char **argv) "number of thread to run event synthesize"),OPT_BOOLEAN (0 ,"namespaces" , &opts->record_namespaces,"Record namespaces events" ), +OPT_BOOLEAN (0 ,"all-cgroups" , &opts->record_cgroup, +"Record cgroup events" ),OPTS_EVSWITCH (&top.evswitch), OPT_END() };
Namhyung Kim
maintainerPATCH 9/9 perf script: Add --show-cgroup-events option
In reply to Namhyung KimThe --show-cgroup-events option is to print CGROUP events in the output like others.
--- tools/perf/Documentation/perf-script.txt | 3 ++ tools/perf/builtin-script.c | 41 ++++++++++++++++++++++++ 2 files changed, 44 insertions(+)
tools/perf/Documentation/perf-script.txt +3 -0
@@ -319,6 +319,9 @@ OPTIONS --show-bpf-events Display bpf events i.e. events of type PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT. +--show-cgroup-events + Display cgroup events i.e. events of type PERF_RECORD_CGROUP. + --demangle:: Demangle symbol names to human readable form. It's enabled by default, disable with --no-demangle.
tools/perf/builtin-script.c +41 -0
71 lines not on this page · raw message
Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
Re: [PATCH 9/9] perf script: Add --show-cgroup-events option
Em Wed, Mar 25, 2020 at 09:45:36PM +0900, Namhyung Kim escreveu:
Quoted 2 lines
The --show-cgroup-events option is to print CGROUP events in the output like others.
Added this to the comment:
Committer testing:
[root@seventh ~]# perf record --all-cgroups --namespaces /wb/cgtest
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.039 MB perf.data (487 samples) ]
[root@seventh ~]# perf script --show-cgroup-events | grep PERF_RECORD_CGROUP -B2 -A2
swapper 0 0.000000: PERF_RECORD_CGROUP cgroup: 1 /
perf 12145 11200.440730: 1 cycles: ffffffffb900d58b __intel_pmu_enable_all.constprop.0+0x3b (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
perf 12145 11200.440733: 1 cycles: ffffffffb900d58b __intel_pmu_enable_all.constprop.0+0x3b (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
--
cgtest 12145 11200.440739: 193472 cycles: ffffffffb90f6fbc commit_creds+0x1fc (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
cgtest 12145 11200.440790: 2691608 cycles: 7fa2cb43019b _dl_sysdep_start+0x7cb (/usr/lib64/ld-2.29.so)
cgtest 12145 11200.440962: PERF_RECORD_CGROUP cgroup: 83 /sub
cgtest 12147 11200.441054: 1 cycles: ffffffffb900d58b __intel_pmu_enable_all.constprop.0+0x3b (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
cgtest 12147 11200.441057: 1 cycles: ffffffffb900d58b __intel_pmu_enable_all.constprop.0+0x3b (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
--
cgtest 12148 11200.441103: 10227 cycles: ffffffffb9a0153d end_repeat_nmi+0x48 (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
cgtest 12148 11200.441106: 273295 cycles: ffffffffb99ecbc7 copy_page+0x7 (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
cgtest 12147 11200.441133: PERF_RECORD_CGROUP cgroup: 88 /sub/cgrp1
cgtest 12147 11200.441143: 2788845 cycles: ffffffffb94676c2 security_genfs_sid+0x102 (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
cgtest 12148 11200.441162: PERF_RECORD_CGROUP cgroup: 93 /sub/cgrp2
cgtest 12148 11200.441182: 2669546 cycles: 401020 _init+0x20 (/wb/cgtest)
cgtest 12149 11200.441247: 1 cycles: ffffffffb900d58b __intel_pmu_enable_all.constprop.0+0x3b (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
[root@seventh ~]#Thanks, series applied and tested, seems to work :-)
Now to trampolines...
- Arnaldo
Quoted 103 lines
Signed-off-by Namhyung Kim <[email protected]>--- tools/perf/Documentation/perf-script.txt | 3 ++ tools/perf/builtin-script.c | 41 ++++++++++++++++++++++++ 2 files changed, 44 insertions(+)tools/perf/Documentation/perf-script.txt +3
-0@@ -319,6 +319,9 @@ OPTIONS --show-bpf-events Display bpf events i.e. events of type PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT. +--show-cgroup-events + Display cgroup events i.e. events of type PERF_RECORD_CGROUP. + --demangle:: Demangle symbol names to human readable form. It's enabled by default, disable with --no-demangle.tools/perf/builtin-script.c +41
-0@@ -1685,6 +1685,7 @@ struct perf_script {bool show_lost_events;bool show_round_events;bool show_bpf_events; +bool show_cgroup_events;bool allocated;bool per_event_dump;struct evswitch evswitch;@@ -2203,6 +2204,41 @@ static int process_namespaces_event(struct perf_tool *tool,return ret; } +static int process_cgroup_event (struct perf_tool *tool, +union perf_event *event, +struct perf_sample *sample, +struct machine *machine) +{ +struct thread *thread; + struct perf_script *script = container_of(tool, struct perf_script, tool); +struct perf_session *session = script->session; +struct evsel *evsel =perf_evlist__id2evsel (session->evlist, sample->id); +int ret =-1 ; + + thread =machine__findnew_thread (machine, sample->pid, sample->tid); +if (thread ==NULL ) { +pr_debug ("problem processing CGROUP event, skipping it.\n" ); +return -1 ; + } + +if (perf_event__process_cgroup (tool, event, sample, machine) <0 ) + goto out; + +if (!evsel->core.attr.sample_id_all) { + sample->cpu =0 ; + sample->time =0 ; + } +if (!filter_cpu (sample)) { +perf_sample__fprintf_start (sample, thread, evsel, +PERF_RECORD_CGROUP , stdout); +perf_event__fprintf (event, stdout); + } + ret =0 ; +out: +thread__put (thread); +return ret; +} + static int process_fork_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample,@@ -2542,6 +2578,8 @@ static int __cmd_script(struct perf_script *script) script->tool.context_switch = process_switch_event;if (script->show_namespace_events) script->tool.namespaces = process_namespaces_event; +if (script->show_cgroup_events) + script->tool.cgroup = process_cgroup_event;if (script->show_lost_events) script->tool.lost = process_lost_event;if (script->show_round_events) {@@ -3467,6 +3505,7 @@ int cmd_script(int argc, const char **argv) .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, .namespaces = perf_event__process_namespaces, + .cgroup = perf_event__process_cgroup, .exit = perf_event__process_exit, .fork = perf_event__process_fork, .attr = process_attr,@@ -3567,6 +3606,8 @@ int cmd_script(int argc, const char **argv) "Show context switch events (if recorded)"),OPT_BOOLEAN ('\0' ,"show-namespace-events" , &script.show_namespace_events,"Show namespace events (if recorded)" ), +OPT_BOOLEAN ('\0' ,"show-cgroup-events" , &script.show_cgroup_events, +"Show cgroup events (if recorded)" ),OPT_BOOLEAN ('\0' ,"show-lost-events" , &script.show_lost_events,"Show lost events (if recorded)" ), OPT_BOOLEAN('\0', "show-round-events", &script.show_round_events,Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
Signature · 1 line
- Arnaldo
[tip: perf/urgent] perf script: Add --show-cgroup-events option
In reply to Namhyung KimThe following commit has been merged into the perf/urgent branch of tip:
The following commit has been merged into the perf/urgent branch of tip:
Commit-ID: 160d4af97b831c87e680c607c639d55ae027087f Gitweb: https://git.kernel.org/tip/160d4af97b831c87e680c607c639d55ae027087f Author: Namhyung Kim <[email protected]> AuthorDate: Wed, 25 Mar 2020 21:45:36 +09:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Fri, 03 Apr 2020 09:37:55 -03:00
perf script: Add --show-cgroup-events option
The --show-cgroup-events option is to print CGROUP events in the output like others.
Committer testing:
[root@seventh ~]# perf record --all-cgroups --namespaces /wb/cgtest
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.039 MB perf.data (487 samples) ]
[root@seventh ~]# perf script --show-cgroup-events | grep PERF_RECORD_CGROUP -B2 -A2
swapper 0 0.000000: PERF_RECORD_CGROUP cgroup: 1 /
perf 12145 11200.440730: 1 cycles: ffffffffb900d58b __intel_pmu_enable_all.constprop.0+0x3b (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
perf 12145 11200.440733: 1 cycles: ffffffffb900d58b __intel_pmu_enable_all.constprop.0+0x3b (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
--
cgtest 12145 11200.440739: 193472 cycles: ffffffffb90f6fbc commit_creds+0x1fc (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
cgtest 12145 11200.440790: 2691608 cycles: 7fa2cb43019b _dl_sysdep_start+0x7cb (/usr/lib64/ld-2.29.so)
cgtest 12145 11200.440962: PERF_RECORD_CGROUP cgroup: 83 /sub
cgtest 12147 11200.441054: 1 cycles: ffffffffb900d58b __intel_pmu_enable_all.constprop.0+0x3b (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
cgtest 12147 11200.441057: 1 cycles: ffffffffb900d58b __intel_pmu_enable_all.constprop.0+0x3b (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
--
cgtest 12148 11200.441103: 10227 cycles: ffffffffb9a0153d end_repeat_nmi+0x48 (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
cgtest 12148 11200.441106: 273295 cycles: ffffffffb99ecbc7 copy_page+0x7 (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
cgtest 12147 11200.441133: PERF_RECORD_CGROUP cgroup: 88 /sub/cgrp1
cgtest 12147 11200.441143: 2788845 cycles: ffffffffb94676c2 security_genfs_sid+0x102 (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
cgtest 12148 11200.441162: PERF_RECORD_CGROUP cgroup: 93 /sub/cgrp2
cgtest 12148 11200.441182: 2669546 cycles: 401020 _init+0x20 (/wb/cgtest)
cgtest 12149 11200.441247: 1 cycles: ffffffffb900d58b __intel_pmu_enable_all.constprop.0+0x3b (/lib/modules/5.6.0-rc6-00008-gfe2413eefd7f/build/vmlinux)
[root@seventh ~]#--- tools/perf/Documentation/perf-script.txt | 3 ++- tools/perf/builtin-script.c | 41 +++++++++++++++++++++++- 2 files changed, 44 insertions(+)
tools/perf/Documentation/perf-script.txt +3 -0
@@ -319,6 +319,9 @@ OPTIONS --show-bpf-events Display bpf events i.e. events of type PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT. +--show-cgroup-events + Display cgroup events i.e. events of type PERF_RECORD_CGROUP. + --demangle:: Demangle symbol names to human readable form. It's enabled by default, disable with --no-demangle.
tools/perf/builtin-script.c +41 -0
71 lines not on this page · raw message
Em Wed, Mar 25, 2020 at 09:45:27PM +0900, Namhyung Kim escreveu:
Quoted 11 lines
Hello,
This work is to improve cgroup profiling in perf. Currently it only supports profiling tasks in a specific cgroup and there's no way to identify which cgroup the current sample belongs to. So I added
PERF_SAMPLE_CGROUPto add cgroup id into each sample. It's a 64-bit integer having file handle of the cgroup. And kernel also generatesPERF_RECORD_CGROUPevent for new groups to correlate the cgroup id and cgroup name (path in the cgroup filesystem). The cgroup id can be read from userspace byname_to_handle_at()system call so it can synthesize the CGROUP event for existing groups.
Thanks for the refresh, I'll test this today and all going well push to Ingo soon,
- Arnaldo
Quoted 297 lines
So why do we want this? Systems running a large number of jobs in different cgroups want to profiling such jobs precisely. This includes container hosting systems widely used today. Currently perf supports namespace tracking but the systems may not use (cgroup) namespace for their jobs. Also it'd be more intuitive to see cgroup names (as they're given by user or sysadmin) rather than numeric cgroup/namespace id even if they use the namespaces.
From Stephane Eranian:
Quoted 6 lines
In data centers you care about attributing samples to a job not such much to a process. A job may have multiple processes which may come and go. The cgroup on the other hand stays around for the entire lifetime of the job. It is much easier to map a cgroup name to a particular job than it is to map a pid back to a job name, especially for offline post-processing.
Note that this only works for "
perf_event" cgroups (obviously) so if users are still using cgroup-v1 interface, they need to have same hierarchy for subsystem(s) want to profile with it.* Changes from v5:
- add ACKs for the kernel changes
- fix sort column alignment when no cgroup is available* Changes from v4:
- useCONFIG_CGROUP_PERF
- move cgroup tree toperf_env
- move cgroup fs utility function totools/lib/api/fs
- use a local buffer and check its size for cgroup systhesis* Changes from v3:
- staticizeperf_event_cgroup()
- fix sample parsing test* Changes from v2:
- removepath_lenfromcgroup_event
- bail out if kernel doesn't support cgroup sampling
- add some description in theKconfig* Changes from v1:
- use new cgroup id (= file handle)The code is available at perf/cgroup-v6 branch in
git://git.kernel.org/pub/scm/linux/kernel/git/namhyung/linux-perf.gitThe testing result looks something like this:
[root@qemu build]# ./perf record --all-cgroups ./cgtest
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.009 MB perf.data (150 samples) ][root@qemu build]# ./perf report -s cgroup,comm --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 150 of event 'cpu-clock:pppH' # Event count (approx.): 37500000 # # Overhead cgroup Command # ........ .......... ....... # 32.00% /sub/cgrp2 looper2 28.00% /sub/cgrp1 looper1 25.33% /sub looper0 4.00% / cgtest 4.00% /sub cgtest 3.33% /sub/cgrp2 cgtest 2.67% /sub/cgrp1 cgtest 0.67% / looper0The test program (cgtest) follows.
Thanks,
NamhyungCc Tejun Heo <[email protected]>Cc Li Zefan <[email protected]>Cc Johannes Weiner <[email protected]>Cc Adrian Hunter <[email protected]>-------8<-----------------------------------------8<---------------- #define
_GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include <sched.h>
#include <errno.h>
#include <sys/stat.h>
#include <sys/wait.h>
#include <sys/prctl.h>
#include <sys/mount.h>char cgbase[] = "
/sys/fs/cgroup/perf_event";void
mkcgrp(char *name){
char buf[256];
snprintf(buf, sizeof(buf), "%s%s", cgbase, name); if (mkdir(buf, 0755)< 0)perror("mkdir"); }void
rmcgrp(char *name){
char buf[256];
snprintf(buf, sizeof(buf), "%s%s", cgbase, name); if (rmdir(buf) < 0)perror("rmdir"); }void
setcgrp(char *name){
char buf[256];
int fd;snprintf(buf, sizeof(buf), "%s%s/tasks", cgbase, name);fd =
open(buf, O_WRONLY);if (fd > 0) { if (write(fd, "0\n", 2) != 2) perror("write"); close(fd);}
}void
create_sub_cgroup(int idx){
char buf[128];
snprintf(buf, sizeof(buf), "/sub/cgrp%d", idx);
mkcgrp(buf);
}void
remove_sub_cgroup(int idx){
char buf[128];
snprintf(buf, sizeof(buf), "/sub/cgrp%d", idx);
rmcgrp(buf);
}void
set_sub_cgroup(int idx){
char buf[128];
snprintf(buf, sizeof(buf), "/sub/cgrp%d", idx);
setcgrp(buf);
}void
set_task_name(int idx){
char buf[16];
snprintf(buf, sizeof(buf), "looper%d", idx);
prctl(PR_SET_NAME, buf, 0, 0, 0);
}void loop(unsigned max) {
volatile unsigned int count = 1;while (count++ != max) { asm volatile ("pause");}
}void
worker(int idx, unsigned cnt, int new_ns){
int oldns;create_sub_cgroup(idx); set_sub_cgroup(idx); if (new_ns) { if (unshare(CLONE_NEWCGROUP) < 0) perror("unshare");#if 0 /* FIXME */ if (unshare(CLONE_NEWNS) < 0) perror("unshare"); if (mount("none", "/sys", NULL, MS_REMOUNT | MS_REC | MS_SLAVE, NULL) < 0) perror("mount --make-rslave"); sleep(1); if (umount("/sys/fs/cgroup/perf_event") < 0) perror("umount"); if (mount("cgroup", "/sys/fs/cgroup/perf_event", "cgroup", MS_NODEV | MS_NOEXEC | MS_NOSUID, "perf_event") < 0) perror("mount again");#endif
}if (fork() == 0) { set_task_name(idx); loop(cnt); exit(0);}
wait(NULL);
}int
main(int argc, char *argv[])
{
int i, nr = 2;
intnew_ns= 1;
unsigned cnt = 1000000;
int fd;if (argc > 1) nr = atoi(argv[1]); if (argc > 2) cnt = atoi(argv[2]); if (argc > 3) new_ns = atoi(argv[3]); mkcgrp("/sub"); setcgrp("/sub"); for (i = 0; i < nr; i++) { if (fork() == 0) { worker(i+1, cnt, new_ns); exit(0); } } set_task_name(0); loop(cnt); for (i = 0; i < nr; i++) wait(NULL); for (i = 0; i < nr; i++) remove_sub_cgroup(i+1); setcgrp("/"); rmcgrp("/sub");return 0;
} -------8<-----------------------------------------8<----------------Namhyung Kim (9):
perf/core: AddPERF_RECORD_CGROUPevent
perf/core: AddPERF_SAMPLE_CGROUPfeature
perf tools: Basic support for CGROUP event
perf tools: Maintain cgroup hierarchy
perf report: Add 'cgroup' sort key
perf record: Support synthesizing cgroup events
perf record: Add --all-cgroups option
perf top: Add --all-cgroups option
perf script: Add --show-cgroup-events optioninclude/linux/perf_event.h | 1 + include/uapi/linux/perf_event.h | 16 ++- init/Kconfig | 3 +- kernel/events/core.c | 133 ++++++++++++++++++++++ tools/include/uapi/linux/perf_event.h | 16 ++- tools/lib/perf/include/perf/event.h | 7 ++ tools/perf/Documentation/perf-record.txt | 5 +- tools/perf/Documentation/perf-report.txt | 1 + tools/perf/Documentation/perf-script.txt | 3 + tools/perf/Documentation/perf-top.txt | 4 + tools/perf/builtin-diff.c | 1 + tools/perf/builtin-record.c | 10 ++ tools/perf/builtin-report.c | 1 + tools/perf/builtin-script.c | 41 +++++++ tools/perf/builtin-top.c | 9 ++ tools/perf/tests/sample-parsing.c | 6 +- tools/perf/util/cgroup.c | 80 +++++++++++++ tools/perf/util/cgroup.h | 17 ++- tools/perf/util/env.c | 2 + tools/perf/util/env.h | 6 + tools/perf/util/event.c | 18 +++ tools/perf/util/event.h | 6 + tools/perf/util/evsel.c | 17 ++- tools/perf/util/evsel.h | 1 + tools/perf/util/hist.c | 13 +++ tools/perf/util/hist.h | 1 + tools/perf/util/machine.c | 19 ++++ tools/perf/util/machine.h | 3 + tools/perf/util/perf_event_attr_fprintf.c | 2 + tools/perf/util/record.h | 1 + tools/perf/util/session.c | 4 + tools/perf/util/sort.c | 37 ++++++ tools/perf/util/sort.h | 2 + tools/perf/util/synthetic-events.c | 121 ++++++++++++++++++++ tools/perf/util/synthetic-events.h | 1 + tools/perf/util/tool.h | 2 + 36 files changed, 598 insertions(+), 12 deletions(-)Signature · 1 line
2.25.1.696.g5e7596f4ac-goog
Signature · 1 line
- Arnaldo
Namhyung Kim
maintainerHi Arnaldo,
Quoted 14 lines · Arnaldo Carvalho de Melo
Em Wed, Mar 25, 2020 at 09:45:27PM +0900, Namhyung Kim escreveu:
Quoted 11 lines
Hello,
This work is to improve cgroup profiling in perf. Currently it only supports profiling tasks in a specific cgroup and there's no way to identify which cgroup the current sample belongs to. So I added
PERF_SAMPLE_CGROUPto add cgroup id into each sample. It's a 64-bit integer having file handle of the cgroup. And kernel also generatesPERF_RECORD_CGROUPevent for new groups to correlate the cgroup id and cgroup name (path in the cgroup filesystem). The cgroup id can be read from userspace byname_to_handle_at()system call so it can synthesize the CGROUP event for existing groups.
Quoted 2 lines
Thanks for the refresh, I'll test this today and all going well push to Ingo soon,
Thanks for doing this!
Namhyung