Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
大约 1 年 前同步成功

通知 158
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 24 12月, 2011 3 次提交
  3. 20 12月, 2011 1 次提交
    • A
      perf record: Add ability to record event period · 3e76ac78
      由 Andrew Vagin 提交于 
      The problem is that when SAMPLE_PERIOD is not set, the kernel generates
a number of samples in proportion to an event's period. Number of these
samples may be too big and the kernel throttles all samples above a
defined limit.

E.g.: I want to trace when a process sleeps. I created a process which
sleeps for 1ms and for 4ms.  perf got 100 events in both cases.

swapper 0 [000] 1141.371830: sched_stat_sleep: comm=foo pid=1801 delay=1386750 [ns]
swapper 0 [000] 1141.369444: sched_stat_sleep: comm=foo pid=1801 delay=4499585 [ns]

In the first case a kernel want to send 4499585 events and in the second
case it wants to send 1386750 events.  perf-reports shows that process
sleeps in both places equal time.

Instead of this we can get only one sample with an attribute period. As
result we have less data transferring between kernel and user-space and
we avoid throttling of samples.

The patch "events: Don't divide events if it has field period" added a
kernel part of this functionality.
Acked-by: NArun Sharma <asharma@fb.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: devel@openvz.org
Link: http://lkml.kernel.org/r/1324391565-1369947-1-git-send-email-avagin@openvz.orgSigned-off-by: NAndrew Vagin <avagin@openvz.org>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      3e76ac78
  5. 29 11月, 2011 1 次提交
  7. 28 11月, 2011 8 次提交
  9. 26 10月, 2011 2 次提交
  11. 08 10月, 2011 1 次提交
    • S
      perf tools: Make perf.data more self-descriptive (v8) · fbe96f29
      由 Stephane Eranian 提交于 
      The goal of this patch is to include more information about the host
environment into the perf.data so it is more self-descriptive. Overtime,
profiles are captured on various machines and it becomes hard to track
what was recorded, on what machine and when.

This patch provides a way to solve this by extending the perf.data file
with basic information about the host machine. To add those extensions,
we leverage the feature bits capabilities of the perf.data format.  The
change is backward compatible with existing perf.data files.

We define the following useful new extensions:
 - HEADER_HOSTNAME: the hostname
 - HEADER_OSRELEASE: the kernel release number
 - HEADER_ARCH: the hw architecture
 - HEADER_CPUDESC: generic CPU description
 - HEADER_NRCPUS: number of online/avail cpus
 - HEADER_CMDLINE: perf command line
 - HEADER_VERSION: perf version
 - HEADER_TOPOLOGY: cpu topology
 - HEADER_EVENT_DESC: full event description (attrs)
 - HEADER_CPUID: easy-to-parse low level CPU identication

The small granularity for the entries is to make it easier to extend
without breaking backward compatiblity. Many entries are provided as
ASCII strings.

Perf report/script have been modified to print the basic information as
easy-to-parse ASCII strings. Extended information about CPU and NUMA
topology may be requested with the -I option.

Thanks to David Ahern for reviewing and testing the many versions of
this patch.

 $ perf report --stdio
 # ========
 # captured on : Mon Sep 26 15:22:14 2011
 # hostname : quad
 # os release : 3.1.0-rc4-tip
 # perf version : 3.1.0-rc4
 # arch : x86_64
 # nrcpus online : 4
 # nrcpus avail : 4
 # cpudesc : Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz
 # cpuid : GenuineIntel,6,15,11
 # total memory : 8105360 kB
 # cmdline : /home/eranian/perfmon/official/tip/build/tools/perf/perf record date
 # event : name = cycles, type = 0, config = 0x0, config1 = 0x0, config2 = 0x0, excl_usr = 0, excl_kern = 0, id = { 29, 30, 31,
 # HEADER_CPU_TOPOLOGY info available, use -I to display
 # HEADER_NUMA_TOPOLOGY info available, use -I to display
 # ========
 #
 ...

 $ perf report --stdio -I
 # ========
 # captured on : Mon Sep 26 15:22:14 2011
 # hostname : quad
 # os release : 3.1.0-rc4-tip
 # perf version : 3.1.0-rc4
 # arch : x86_64
 # nrcpus online : 4
 # nrcpus avail : 4
 # cpudesc : Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz
 # cpuid : GenuineIntel,6,15,11
 # total memory : 8105360 kB
 # cmdline : /home/eranian/perfmon/official/tip/build/tools/perf/perf record date
 # event : name = cycles, type = 0, config = 0x0, config1 = 0x0, config2 = 0x0, excl_usr = 0, excl_kern = 0, id = { 29, 30, 31,
 # sibling cores   : 0-3
 # sibling threads : 0
 # sibling threads : 1
 # sibling threads : 2
 # sibling threads : 3
 # node0 meminfo  : total = 8320608 kB, free = 7571024 kB
 # node0 cpu list : 0-3
 # ========
 #
 ...
Reviewed-by: NDavid Ahern <dsahern@gmail.com>
Tested-by: NDavid Ahern <dsahern@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Andi Kleen <ak@linux.intel.com>
Link: http://lkml.kernel.org/r/20110930134040.GA5575@quadSigned-off-by: NStephane Eranian <eranian@google.com>
[ committer notes: Use --show-info in the tools as was in the docs, rename
  perf_header_fprintf_info to perf_file_section__fprintf_info, fixup
  conflict with f69b64f7 "perf: Support setting the disassembler style" ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      fbe96f29
  13. 30 9月, 2011 1 次提交
  15. 24 9月, 2011 1 次提交
  17. 18 8月, 2011 1 次提交
  19. 25 7月, 2011 1 次提交
  21. 21 7月, 2011 1 次提交
  23. 28 5月, 2011 1 次提交
  25. 26 5月, 2011 1 次提交
    • A
      perf symbols: Handle /proc/sys/kernel/kptr_restrict · ec80fde7
      由 Arnaldo Carvalho de Melo 提交于 
      Perf uses /proc/modules to figure out where kernel modules are loaded.

With the advent of kptr_restrict, non root users get zeroes for all module
start addresses.

So check if kptr_restrict is non zero and don't generate the syntethic
PERF_RECORD_MMAP events for them.

Warn the user about it in perf record and in perf report.

In perf report the reference relocation symbol being zero means that
kptr_restrict was set, thus /proc/kallsyms has only zeroed addresses, so don't
use it to fixup symbol addresses when using a valid kallsyms (in the buildid
cache) or vmlinux (in the vmlinux path) build-id located automatically or
specified by the user.

Provide an explanation about it in 'perf report' if kernel samples were taken,
checking if a suitable vmlinux or kallsyms was found/specified.

Restricted /proc/kallsyms don't go to the buildid cache anymore.

Example:

 [acme@emilia ~]$ perf record -F 100000 sleep 1

 WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted, check
 /proc/sys/kernel/kptr_restrict.

 Samples in kernel functions may not be resolved if a suitable vmlinux file is
 not found in the buildid cache or in the vmlinux path.

 Samples in kernel modules won't be resolved at all.

 If some relocation was applied (e.g. kexec) symbols may be misresolved even
 with a suitable vmlinux or kallsyms file.

 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.005 MB perf.data (~231 samples) ]
 [acme@emilia ~]$

 [acme@emilia ~]$ perf report --stdio
 Kernel address maps (/proc/{kallsyms,modules}) were restricted,
 check /proc/sys/kernel/kptr_restrict before running 'perf record'.

 If some relocation was applied (e.g. kexec) symbols may be misresolved.

 Samples in kernel modules can't be resolved as well.

 # Events: 13  cycles
 #
 # Overhead  Command      Shared Object                 Symbol
 # ........  .......  .................  .....................
 #
    20.24%    sleep  [kernel.kallsyms]  [k] page_fault
    20.04%    sleep  [kernel.kallsyms]  [k] filemap_fault
    19.78%    sleep  [kernel.kallsyms]  [k] __lru_cache_add
    19.69%    sleep  ld-2.12.so         [.] memcpy
    14.71%    sleep  [kernel.kallsyms]  [k] dput
     4.70%    sleep  [kernel.kallsyms]  [k] flush_signal_handlers
     0.73%    sleep  [kernel.kallsyms]  [k] perf_event_comm
     0.11%    sleep  [kernel.kallsyms]  [k] native_write_msr_safe

 #
 # (For a higher level overview, try: perf report --sort comm,dso)
 #
 [acme@emilia ~]$

This is because it found a suitable vmlinux (build-id checked) in
/lib/modules/2.6.39-rc7+/build/vmlinux (use -v in perf report to see the long
file name).

If we remove that file from the vmlinux path:

 [root@emilia ~]# mv /lib/modules/2.6.39-rc7+/build/vmlinux \
		     /lib/modules/2.6.39-rc7+/build/vmlinux.OFF
 [acme@emilia ~]$ perf report --stdio
 [kernel.kallsyms] with build id 57298cdbe0131f6871667ec0eaab4804dcf6f562
 not found, continuing without symbols

 Kernel address maps (/proc/{kallsyms,modules}) were restricted, check
 /proc/sys/kernel/kptr_restrict before running 'perf record'.

 As no suitable kallsyms nor vmlinux was found, kernel samples can't be
 resolved.

 Samples in kernel modules can't be resolved as well.

 # Events: 13  cycles
 #
 # Overhead  Command      Shared Object  Symbol
 # ........  .......  .................  ......
 #
    80.31%    sleep  [kernel.kallsyms]  [k] 0xffffffff8103425a
    19.69%    sleep  ld-2.12.so         [.] memcpy

 #
 # (For a higher level overview, try: perf report --sort comm,dso)
 #
 [acme@emilia ~]$
Reported-by: NStephane Eranian <eranian@google.com>
Suggested-by: NDavid Miller <davem@davemloft.net>
Cc: Dave Jones <davej@redhat.com>
Cc: David Miller <davem@davemloft.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Kees Cook <kees.cook@canonical.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Link: http://lkml.kernel.org/n/tip-mt512joaxxbhhp1odop04yit@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      ec80fde7
  27. 15 5月, 2011 1 次提交
    • A
      perf evlist: Fix per thread mmap setup · aece948f
      由 Arnaldo Carvalho de Melo 提交于 
      The PERF_EVENT_IOC_SET_OUTPUT ioctl was returning -EINVAL when using
--pid when monitoring multithreaded apps, as we can only share a ring
buffer for events on the same thread if not doing per cpu.

Fix it by using per thread ring buffers.

Tested with:

[root@felicio ~]# tuna -t 26131 -CP | nl
  1                      thread       ctxt_switches
  2    pid SCHED_ rtpri affinity voluntary nonvoluntary             cmd
  3 26131   OTHER     0      0,1  10814276      2397830 chromium-browse
  4  642    OTHER     0      0,1     14688            0 chromium-browse
  5  26148  OTHER     0      0,1    713602       115479 chromium-browse
  6  26149  OTHER     0      0,1    801958         2262 chromium-browse
  7  26150  OTHER     0      0,1   1271128          248 chromium-browse
  8  26151  OTHER     0      0,1         3            0 chromium-browse
  9  27049  OTHER     0      0,1     36796            9 chromium-browse
 10  618    OTHER     0      0,1     14711            0 chromium-browse
 11  661    OTHER     0      0,1     14593            0 chromium-browse
 12  29048  OTHER     0      0,1     28125            0 chromium-browse
 13  26143  OTHER     0      0,1   2202789          781 chromium-browse
[root@felicio ~]#

So 11 threads under pid 26131, then:

[root@felicio ~]# perf record -F 50000 --pid 26131

[root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl
  1 7fa4a2538000-7fa4a25b9000 rwxs 00000000 00:09 4064 anon_inode:[perf_event]
  2 7fa4a25b9000-7fa4a263a000 rwxs 00000000 00:09 4064 anon_inode:[perf_event]
  3 7fa4a263a000-7fa4a26bb000 rwxs 00000000 00:09 4064 anon_inode:[perf_event]
  4 7fa4a26bb000-7fa4a273c000 rwxs 00000000 00:09 4064 anon_inode:[perf_event]
  5 7fa4a273c000-7fa4a27bd000 rwxs 00000000 00:09 4064 anon_inode:[perf_event]
  6 7fa4a27bd000-7fa4a283e000 rwxs 00000000 00:09 4064 anon_inode:[perf_event]
  7 7fa4a283e000-7fa4a28bf000 rwxs 00000000 00:09 4064 anon_inode:[perf_event]
  8 7fa4a28bf000-7fa4a2940000 rwxs 00000000 00:09 4064 anon_inode:[perf_event]
  9 7fa4a2940000-7fa4a29c1000 rwxs 00000000 00:09 4064 anon_inode:[perf_event]
 10 7fa4a29c1000-7fa4a2a42000 rwxs 00000000 00:09 4064 anon_inode:[perf_event]
 11 7fa4a2a42000-7fa4a2ac3000 rwxs 00000000 00:09 4064 anon_inode:[perf_event]
[root@felicio ~]#

11 mmaps, one per thread since we didn't specify any CPU list, so we need one
mmap per thread and:

[root@felicio ~]# perf record -F 50000 --pid 26131
^M
^C[ perf record: Woken up 79 times to write data ]
[ perf record: Captured and wrote 20.614 MB perf.data (~900639 samples) ]

[root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl
     1	 371310 26131
     2	  96516 26148
     3	  95694 26149
     4	  95203 26150
     5	   7291 26143
     6	     87 27049
     7	     76 661
     8	     60 29048
     9	     47 618
    10	     43 642
[root@felicio ~]#

Ok, one of the threads, 26151 was quiescent, so no samples there, but all the
others are there.

Then, if I specify one CPU:

[root@felicio ~]# perf record -F 50000 --pid 26131 --cpu 1
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.680 MB perf.data (~29730 samples) ]

[root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl
     1	   8444 26131
     2	   2584 26149
     3	   2518 26148
     4	   2324 26150
     5	    123 26143
     6	      9 661
     7	      9 29048
[root@felicio ~]#

This machine has two cores, so fewer threads appeared on the radar, and:

[root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl
 1 7f484b922000-7f484b9a3000 rwxs 00000000 00:09 4064 anon_inode:[perf_event]
[root@felicio ~]#

Just one mmap, as now we can use just one per-cpu buffer instead of the
per-thread needed in the previous case.

For global profiling:

[root@felicio ~]# perf record -F 50000 -a
^C[ perf record: Woken up 26 times to write data ]
[ perf record: Captured and wrote 7.128 MB perf.data (~311412 samples) ]

[root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl
     1	7fb49b435000-7fb49b4b6000 rwxs 00000000 00:09 4064                       anon_inode:[perf_event]
     2	7fb49b4b6000-7fb49b537000 rwxs 00000000 00:09 4064                       anon_inode:[perf_event]
[root@felicio ~]#

It uses per-cpu buffers.

For just one thread:

[root@felicio ~]# perf record -F 50000 --tid 26148
^C[ perf record: Woken up 2 times to write data ]
[ perf record: Captured and wrote 0.330 MB perf.data (~14426 samples) ]

[root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl
     1	   9969 26148
[root@felicio ~]#

[root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl
     1	7f286a51b000-7f286a59c000 rwxs 00000000 00:09 4064                       anon_inode:[perf_event]
[root@felicio ~]#
Tested-by: NDavid Ahern <dsahern@gmail.com>
Tested-by: NLin Ming <ming.m.lin@intel.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Link: http://lkml.kernel.org/r/20110426204401.GB1746@ghostprotocols.netSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      aece948f
  29. 15 4月, 2011 1 次提交
  31. 31 3月, 2011 1 次提交
    • F
      perf: mmap 512 kiB by default · 800cd25c
      由 Frederic Weisbecker 提交于 
      The default setting of perf record is to mmap 128 pages if the user
did not override with -m.

However the page size may vary accross different architecture
settings, giving different default size between each.

Moreover the kernel side still has a default max number of mlocked
pages of 512 kiB + 1 page for unprivileged users. 128 + 1 pages
with page size > 4096 overlaps this threshold.

Thus, better adapt to this limitation and set the default number of
pages to fit those 512 kiB + 1 page.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
LKML-Reference: <1301535324-9735-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
      800cd25c
  33. 30 3月, 2011 2 次提交
    • D
      perf tools: Emit clearer message for sys_perf_event_open ENOENT return · ca6a4258
      由 David Ahern 提交于 
      Resend of patch sent back in January 2011 in light of recent confusion around
unsupported events for a given platform.

Improve sys_perf_event_open ENOENT return handling in top and record, just
like 5a3446bc does for stat.

Retry of Arnaldo's patch using ui_warning instead of die which allows the
fallback from hardware cycles to software clock.

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
LKML-Reference: <1301080271-20945-1-git-send-email-daahern@cisco.com>
Signed-off-by: NDavid Ahern <daahern@cisco.com>
[ committer note: Some adjustments to make it apply to newer codebase ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      ca6a4258
    • A
      perf tools: Fixup exit path when not able to open events · c286c419
      由 Arnaldo Carvalho de Melo 提交于 
      We have to deal with the TUI mode in perf top, so that we don't end up
with a garbled screen when, say, a non root user on a machine with a
paranoid setting (the default) tries to use 'perf top'.

Introduce a ui__warning_paranoid() routine shared by top and record that
tells the user the valid values for /proc/sys/kernel/perf_event_paranoid.

Cc: David Ahern <daahern@cisco.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      c286c419
  35. 10 3月, 2011 1 次提交
    • A
      perf session: Use evlist/evsel for managing perf.data attributes · a91e5431
      由 Arnaldo Carvalho de Melo 提交于 
      So that we can reuse things like the id to attr lookup routine
(perf_evlist__id2evsel) that uses a hash table instead of the linear
lookup done in the older perf_header_attr routines, etc.

Also to make evsels/evlist more pervasive an API, simplyfing using the
emerging perf lib.

cc: Arun Sharma <arun@sharma-home.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      a91e5431
  37. 02 3月, 2011 1 次提交
    • F
      perf: Set filters before mmaping events · 0a102479
      由 Frederic Weisbecker 提交于 
      We currently set the filters after we mmap the events, this is a
race that let undesired events record themselves in the buffer before
we had the time to set the filters.

So set the filters before they can be recorded. That also librarizes
the filters setting so that filtering can be done more easily
from other tools than perf record later.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
      0a102479
  39. 17 2月, 2011 1 次提交
    • A
      perf record: Delay setting the header writing atexit call · 712a4b60
      由 Arnaldo Carvalho de Melo 提交于 
      While testing the --filter option I noticed that we were writing lots of
unneeded stuff to the perf.data header when the filter ioctl fails, so
move the atexit(atexit_header) call to after we create the counters
successfully.

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      712a4b60
  41. 16 2月, 2011 1 次提交
    • S
      perf tool: Add cgroup support · 023695d9
      由 Stephane Eranian 提交于 
      This patch adds the ability to filter monitoring based on container groups
(cgroups) for both perf stat and perf record. It is possible to monitor
multiple cgroup in parallel. There is one cgroup per event. The cgroups to
monitor are passed via a new -G option followed by a comma separated list of
cgroup names.

The cgroup filesystem has to be mounted. Given a cgroup name, the perf tool
finds the corresponding directory in the cgroup filesystem and opens it. It
then passes that file descriptor to the kernel.

Example:

$ perf stat -B -a -e cycles:u,cycles:u,cycles:u -G test1,,test2 -- sleep 1
 Performance counter stats for 'sleep 1':

      2,368,667,414  cycles                   test1
      2,369,661,459  cycles
      <not counted>  cycles                   test2

        1.001856890  seconds time elapsed
Signed-off-by: NStephane Eranian <eranian@google.com>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d590290.825bdf0a.7d0a.4890@mx.google.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
      023695d9
  43. 10 2月, 2011 1 次提交
    • A
      perf tools: Fix thread_map event synthesizing in top and record · 401b8e13
      由 Arnaldo Carvalho de Melo 提交于 
      Jeff Moyer reported these messages:

  Warning:  ... trying to fall back to cpu-clock-ticks

couldn't open /proc/-1/status
couldn't open /proc/-1/maps
[ls output]
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.008 MB perf.data (~363 samples) ]

That lead me and David Ahern to see that something was fishy on the thread
synthesizing routines, at least for the case where the workload is started
from 'perf record', as -1 is the default for target_tid in 'perf record --tid'
parameter, so somehow we were trying to synthesize the PERF_RECORD_MMAP and
PERF_RECORD_COMM events for the thread -1, a bug.

So I investigated this and noticed that when we introduced support for
recording a process and its threads using --pid some bugs were introduced and
that the way to fix it was to instead of passing the target_tid to the event
synthesizing routines we should better pass the thread_map that has the list of
threads for a --pid or just the single thread for a --tid.

Checked in the following ways:

On a 8-way machine run cyclictest:

[root@emilia ~]# perf record cyclictest -a -t -n -p99 -i100 -d50
policy: fifo: loadavg: 0.00 0.13 0.31 2/139 28798

T: 0 (28791) P:99 I:100 C:  25072 Min:      4 Act:    5 Avg:    6 Max:     122
T: 1 (28792) P:98 I:150 C:  16715 Min:      4 Act:    6 Avg:    5 Max:      27
T: 2 (28793) P:97 I:200 C:  12534 Min:      4 Act:    5 Avg:    4 Max:       8
T: 3 (28794) P:96 I:250 C:  10028 Min:      4 Act:    5 Avg:    5 Max:      96
T: 4 (28795) P:95 I:300 C:   8357 Min:      5 Act:    6 Avg:    5 Max:      12
T: 5 (28796) P:94 I:350 C:   7163 Min:      5 Act:    6 Avg:    5 Max:      12
T: 6 (28797) P:93 I:400 C:   6267 Min:      4 Act:    5 Avg:    5 Max:       9
T: 7 (28798) P:92 I:450 C:   5571 Min:      4 Act:    5 Avg:    5 Max:       9
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.108 MB perf.data (~4719 samples) ]

[root@emilia ~]#

This will create one extra thread per CPU:

[root@emilia ~]# tuna -t cyclictest -CP
                      thread       ctxt_switches
    pid SCHED_ rtpri affinity voluntary nonvoluntary             cmd
 28825   OTHER     0     0xff      2169          671      cyclictest
  28832   FIFO    93        6     52338            1      cyclictest
  28833   FIFO    92        7     46524            1      cyclictest
  28826   FIFO    99        0    209360            1      cyclictest
  28827   FIFO    98        1    139577            1      cyclictest
  28828   FIFO    97        2    104686            0      cyclictest
  28829   FIFO    96        3     83751            1      cyclictest
  28830   FIFO    95        4     69794            1      cyclictest
  28831   FIFO    94        5     59825            1      cyclictest
[root@emilia ~]#

So we should expect only samples for the above 9 threads when using the
--dump-raw-trace|-D perf report switch to look at the column with the tid:

[root@emilia ~]# perf report -D | grep RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort | uniq -c
    629 28825
    110 28826
    491 28827
    308 28828
    198 28829
    621 28830
    225 28831
    203 28832
     89 28833
[root@emilia ~]#

So for workloads started by 'perf record' seems to work, now for existing workloads,
just run cyclictest first, without 'perf record':

[root@emilia ~]# tuna -t cyclictest -CP
                      thread       ctxt_switches
    pid SCHED_ rtpri affinity voluntary nonvoluntary             cmd
 28859   OTHER     0     0xff       594          200      cyclictest
  28864   FIFO    95        4     16587            1      cyclictest
  28865   FIFO    94        5     14219            1      cyclictest
  28866   FIFO    93        6     12443            0      cyclictest
  28867   FIFO    92        7     11062            1      cyclictest
  28860   FIFO    99        0     49779            1      cyclictest
  28861   FIFO    98        1     33190            1      cyclictest
  28862   FIFO    97        2     24895            1      cyclictest
  28863   FIFO    96        3     19918            1      cyclictest
[root@emilia ~]#

and then later did:

[root@emilia ~]# perf record --pid 28859 sleep 3
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.027 MB perf.data (~1195 samples) ]
[root@emilia ~]#

To collect 3 seconds worth of samples for pid 28859 and its children:

[root@emilia ~]# perf report -D | grep RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort | uniq -c
     15 28859
     33 28860
     19 28861
     13 28862
     13 28863
     10 28864
     11 28865
      9 28866
    255 28867
[root@emilia ~]#

Works, last thing is to check if looking at just one of those threads also works:

[root@emilia ~]# perf record --tid 28866 sleep 3
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.006 MB perf.data (~242 samples) ]
[root@emilia ~]# perf report -D | grep RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort | uniq -c
      3 28866
[root@emilia ~]#

Works too.
Reported-by: NJeff Moyer <jmoyer@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      401b8e13
  45. 31 1月, 2011 1 次提交
    • A
      perf evlist: Store pointer to the cpu and thread maps · 7e2ed097
      由 Arnaldo Carvalho de Melo 提交于 
      So that we don't have to pass it around to the several methods that
needs it, simplifying usage.

There is one case where we don't have the thread/cpu map in advance,
which is in the parsing routines used by top, stat, record, that we have
to wait till all options are parsed to know if a cpu or thread list was
passed to then create those maps.

For that case consolidate the cpu and thread map creation via
perf_evlist__create_maps() out of the code in top and record, while also
providing a perf_evlist__set_maps() for cases where multiple evlists
share maps or for when maps that represent CPU sockets, for instance,
get crafted out of topology information or subsets of threads in a
particular application are to be monitored, providing more granularity
in specifying which cpus and threads to monitor.

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      7e2ed097
  47. 30 1月, 2011 3 次提交
  49. 24 1月, 2011 2 次提交
    • A
      perf threads: Move thread_map to separate file · fd78260b
      由 Arnaldo Carvalho de Melo 提交于 
      To untangle it from struct thread handling, that is tied to symbols, etc.

Right now in the python bindings I'm working on I need just a subset of
the util/ files, untangling it allows me to do that.

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      fd78260b
    • F
      perf record: auto detect when stdout is a pipe · d7065adb
      由 Franck Bui-Huu 提交于 
      This patch gives the ability to 'perf record' to detect when its stdout
has been redirected to a pipe. There's now no more need to add '-o -'
switch in this case.

However '-o <path>' option has always precedence, that is if specified
and stdout has been connected via a pipe then the output will go into
the specified output.

LKML-Reference: <m3ipxo966i.fsf@gmail.com>
Signed-off-by: NFranck Bui-Huu <fbuihuu@gmail.com>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      d7065adb
  51. 23 1月, 2011 1 次提交
    • A
      perf record: Use perf_evlist__mmap · 0a27d7f9
      由 Arnaldo Carvalho de Melo 提交于 
      There is more stuff that can go to the perf_ev{sel,list} layer, like
detecting if sample_id_all is available, etc, but lets try using this in
'perf test' first.

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      0a27d7f9