Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 24 10月, 2016 1 次提交
  3. 16 7月, 2016 1 次提交
    • W
      perf session: Don't warn about out of order event if write_backward is used · f06149c0
      由 Wang Nan 提交于 
      If write_backward attribute is set, records are written into kernel
ring buffer from end to beginning, but read from beginning to end.
To avoid 'XX out of order events recorded' warning message (timestamps
of records is in reverse order when using write_backward), suppress the
warning message if write_backward is selected by at lease one event.

Result:

Before this patch:
  # perf record -m 1 -e raw_syscalls:sys_exit/overwrite/ \
                     -e raw_syscalls:sys_enter \
                     dd if=/dev/zero of=/dev/null count=300
  300+0 records in
  300+0 records out
  153600 bytes (154 kB) copied, 0.000601617 s, 255 MB/s
  [ perf record: Woken up 5 times to write data ]
  Warning:
  40 out of order events recorded.
  [ perf record: Captured and wrote 0.096 MB perf.data (696 samples) ]

After this patch:
  # perf record -m 1 -e raw_syscalls:sys_exit/overwrite/ \
                     -e raw_syscalls:sys_enter \
                     dd if=/dev/zero of=/dev/null count=300
  300+0 records in
  300+0 records out
  153600 bytes (154 kB) copied, 0.000644873 s, 238 MB/s
  [ perf record: Woken up 5 times to write data ]
  [ perf record: Captured and wrote 0.096 MB perf.data (696 samples) ]
Signed-off-by: NWang Nan <wangnan0@huawei.com>
Acked-by: NJiri Olsa <jolsa@kernel.org>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nilay Vaish <nilayvaish@gmail.com>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1468485287-33422-15-git-send-email-wangnan0@huawei.comSigned-off-by: NHe Kuang <hekuang@huawei.com>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      f06149c0
  5. 23 6月, 2016 1 次提交
  7. 22 6月, 2016 1 次提交
  9. 30 5月, 2016 1 次提交
    • A
      perf tools: Per event max-stack settings · 792d48b4
      由 Arnaldo Carvalho de Melo 提交于 
      The tooling counterpart, now it is possible to do:

  # perf record -e sched:sched_switch/max-stack=10/ -e cycles/call-graph=dwarf,max-stack=4/ -e cpu-cycles/call-graph=dwarf,max-stack=1024/ usleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.052 MB perf.data (5 samples) ]
  # perf evlist -v
  sched:sched_switch: type: 2, size: 112, config: 0x110, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CALLCHAIN|CPU|PERIOD|RAW|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, sample_max_stack: 10
  cycles/call-graph=dwarf,max-stack=4/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 4
  cpu-cycles/call-graph=dwarf,max-stack=1024/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 1024
  # Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events

Using just /max-stack=N/ means /call-graph=fp,max-stack=N/, that should
be further configurable by means of some .perfconfig knob.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Zefan Li <lizefan@huawei.com>
Link: http://lkml.kernel.org/n/tip-kolmn1yo40p7jhswxwrc7rrd@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      792d48b4
  11. 18 4月, 2016 2 次提交
  13. 14 4月, 2016 1 次提交
  15. 13 4月, 2016 1 次提交
  17. 12 4月, 2016 5 次提交
  19. 31 3月, 2016 1 次提交
    • A
      perf tools: Add time conversion event · 46bc29b9
      由 Adrian Hunter 提交于 
      Intel PT uses the time members from the perf_event_mmap_page to convert
between TSC and perf time.

Due to a lack of foresight when Intel PT was implemented, those time
members were recorded in the (implementation dependent) AUXTRACE_INFO
event, the structure of which is generally inaccessible outside of the
Intel PT decoder.  However now the conversion between TSC and perf time
is needed when processing a jitdump file when Intel PT has been used for
tracing.

So add a user event to record the time members.  'perf record' will
synthesize the event if the information is available.  And session
processing will put a copy of the event on the session so that tools
like 'perf inject' can easily access it.
Signed-off-by: NAdrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1457426324-30158-1-git-send-email-adrian.hunter@intel.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      46bc29b9
  21. 23 3月, 2016 1 次提交
  23. 08 3月, 2016 1 次提交
  25. 16 1月, 2016 1 次提交
    • R
      perf kvm record/report: 'unprocessable sample' error while recording/reporting guest data · 3caeaa56
      由 Ravi Bangoria 提交于 
      While recording guest samples in host using perf kvm record, it will
populate unprocessable sample error, though samples will be recorded
properly. While generating report using perf kvm report, no samples will
be processed and same error will populate. We have seen this behaviour
with upstream perf(4.4-rc3) on x86 and ppc64 hardware.

Reason behind this failure is, when it tries to fetch machine from
rb_tree of machines, it fails. As a part of tracing a bug, we figured
out that this code was incorrectly refactored in commit 54245fdc
("perf session: Remove wrappers to machines__find").

This patch will change the functionality such that if it can't fetch
machine in first trial, it will create one node of machine and add that to
rb_tree. So next time when it tries to fetch same machine from rb_tree,
it won't fail. Actually it was the case before refactoring of code in
aforementioned commit.

This patch is generated from acme perf/core branch.

Below I've mention an example that demonstrate the behaviour before and
after applying patch.

Before applying patch:
[Note: One needs to run guest before recording data in host]

  ravi@ravi-bangoria:~$ ./perf kvm record -a
  Warning:
  5903 unprocessable samples recorded.
  Do you have a KVM guest running and not using 'perf kvm'?
  [ perf record: Captured and wrote 1.409 MB perf.data.guest (285 samples) ]

  ravi@ravi-bangoria:~$ ./perf kvm report --stdio
  Warning:
  5903 unprocessable samples recorded.
  Do you have a KVM guest running and not using 'perf kvm'?
  # To display the perf.data header info, please use --header/--header-only options.
  #
  # Total Lost Samples: 0
  #
  # Samples: 285  of event 'cycles'
  # Event count (approx.): 88715406
  #
  # Overhead  Command  Shared Object  Symbol
  # ........  .......  .............  ......
  #

  # (For a higher level overview, try: perf report --sort comm,dso)
  #

After applying patch:

  ravi@ravi-bangoria:~$ ./perf kvm record -a
  [ perf record: Captured and wrote 1.188 MB perf.data.guest (17 samples) ]

  ravi@ravi-bangoria:~$ ./perf kvm report --stdio
  # To display the perf.data header info, please use --header/--header-only options.
  #
  # Total Lost Samples: 0
  #
  # Samples: 17  of event 'cycles'
  # Event count (approx.): 700746
  #
  # Overhead  Command  Shared Object     Symbol
  # ........  .......  ................  ......................
  #
      34.19%  :5758    [unknown]         [g] 0xffffffff818682ab
      22.79%  :5758    [unknown]         [g] 0xffffffff812dc7f8
      22.79%  :5758    [unknown]         [g] 0xffffffff818650d0
      14.83%  :5758    [unknown]         [g] 0xffffffff8161a1b6
       2.49%  :5758    [unknown]         [g] 0xffffffff818692bf
       0.48%  :5758    [unknown]         [g] 0xffffffff81869253
       0.05%  :5758    [unknown]         [g] 0xffffffff81869250
Signed-off-by: NRavi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: stable@vger.kernel.org # v3.19+
Fixes: 54245fdc ("perf session: Remove wrappers to machines__find")
Link: http://lkml.kernel.org/r/1449471302-11283-1-git-send-email-ravi.bangoria@linux.vnet.ibm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      3caeaa56
  27. 18 12月, 2015 8 次提交
  29. 11 12月, 2015 1 次提交
    • M
      perf tools: Make perf_session__register_idle_thread drop the refcount · 9d8b172f
      由 Masami Hiramatsu 提交于 
      Note that since the thread was already inserted to the session
list, it will be released when the session is released.
Also, in perf_session__register_idle_thread() failure path,
the thread should be put before returning.

Refcnt debugger shows that the perf_session__register_idle_thread
gets the returned thread, but the caller (__cmd_top) does not
put the returned idle thread.

  ----
  ==== [0] ====
  Unreclaimed thread@0x24e6240
  Refcount +1 => 0 at
    ./perf(thread__new+0xe5) [0x4c8a75]
    ./perf(machine__findnew_thread+0x9a) [0x4bbdba]
    ./perf(perf_session__register_idle_thread+0x28) [0x4c63c8]
    ./perf(cmd_top+0xd7d) [0x43cf6d]
    ./perf() [0x47ba35]
    ./perf(main+0x617) [0x4225b7]
    /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f06027c5af5]
    ./perf() [0x42272d]
  Refcount +1 => 1 at
    ./perf(thread__get+0x2c) [0x4c8bcc]
    ./perf(machine__findnew_thread+0xee) [0x4bbe0e]
    ./perf(perf_session__register_idle_thread+0x28) [0x4c63c8]
    ./perf(cmd_top+0xd7d) [0x43cf6d]
    ./perf() [0x47ba35]
    ./perf(main+0x617) [0x4225b7]
    /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f06027c5af5]
    ./perf() [0x42272d]
  Refcount +1 => 2 at
    ./perf(thread__get+0x2c) [0x4c8bcc]
    ./perf(machine__findnew_thread+0x112) [0x4bbe32]
    ./perf(perf_session__register_idle_thread+0x28) [0x4c63c8]
    ./perf(cmd_top+0xd7d) [0x43cf6d]
    ./perf() [0x47ba35]
    ./perf(main+0x617) [0x4225b7]
    /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f06027c5af5]
    ./perf() [0x42272d]
  ----
Signed-off-by: NMasami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20151209021122.10245.69707.stgit@localhost.localdomain
[ Drop the refcount in perf_session__register_idle_thread() ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      9d8b172f
  31. 12 11月, 2015 1 次提交
  33. 01 10月, 2015 1 次提交
  35. 29 9月, 2015 2 次提交
  37. 18 9月, 2015 1 次提交
    • M
      perf record: Avoid infinite loop at buildid processing with no samples · 381c02f6
      由 Mark Rutland 提交于 
      If a session contains no events, we can get stuck in an infinite loop in
__perf_session__process_events, with a non-zero file_size and data_offset, but
a zero data_size.

In this case, we can mmap the entirety of the file (consisting of the file and
attribute headers), and fetch_mmaped_event will correctly refuse to read any
(unmapped and non-existent) event headers. This causes
__perf_session__process_events to unmap the file and retry with the exact same
parameters, getting stuck in an infinite loop.

This has been observed to result in an exit-time hang when counting
rare/unschedulable events with perf record, and can be triggered artificially
with the script below:

  ----
  #!/bin/sh
  printf "REPRO: launching perf\n";
  ./perf record -e software/config=9/ sleep 1 &
  PERF_PID=$!;
  sleep 0.002;
  kill -2 $PERF_PID;
  printf "REPRO: waiting for perf (%d) to exit...\n" "$PERF_PID";
  wait $PERF_PID;
  printf "REPRO: perf exited\n";
  ----

To avoid this, have __perf_session__process_events bail out early when
the file has no data (i.e. it has no events).

Commiter note:

I only managed to reproduce this when setting
/proc/sys/kernel/kptr_restrict to '1' and changing the code to
purposefully not process any samples and no synthesized samples, i.e.
kptr_restrict prevents 'record' from synthesizing the kernel mmaps for
vmlinux + modules and since it is a workload started from perf, we don't
synthesize mmap/comm records for existing threads.

Adrian Hunter managed to reproduce it in his environment tho.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Tested-by: NArnaldo Carvalho de Melo <acme@kernel.org>
Tested-by: NAdrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1442423929-12253-1-git-send-email-mark.rutland@arm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      381c02f6
  39. 14 9月, 2015 2 次提交
  41. 04 9月, 2015 1 次提交
  43. 03 9月, 2015 1 次提交
    • K
      perf tools: Store the cpu socket and core ids in the perf.data header · 2bb00d2f
      由 Kan Liang 提交于 
      This patch stores the cpu socket_id and core_id in a perf.data header,
and reads them into the perf_env struct when processing perf.data files.

The changes modifies the CPU_TOPOLOGY section, making sure it is
backward/forward compatible.

The patch checks the section size before reading the core and socket ids.

It never reads data crossing the section boundary.  An old perf binary
without this patch can also correctly read the perf.data from a new perf
with this patch.

Because the new info is added at the end of the cpu_topology section, an
old perf tool ignores the extra data.

Examples:

1. New perf with this patch read perf.data from an old perf without the
   patch:

  $ perf_new report -i perf_old.data --header-only -I
  ......
  # sibling threads : 33
  # sibling threads : 34
  # sibling threads : 35
  # Core ID and Socket ID information is not available
  # node0 meminfo  : total = 32823872 kB, free = 29315548 kB
  # node0 cpu list : 0-17,36-53
  ......

2. Old perf without the patch reads perf.data from a new perf with the
   patch:

  $ perf_old report -i perf_new.data --header-only -I
  ......
  # sibling threads : 33
  # sibling threads : 34
  # sibling threads : 35
  # node0 meminfo  : total = 32823872 kB, free = 29190932 kB
  # node0 cpu list : 0-17,36-53
  ......

3. New perf read new perf.data:

  $ perf_new report -i perf_new.data --header-only -I
  ......
  # sibling threads : 33
  # sibling threads : 34
  # sibling threads : 35
  # CPU 0: Core ID 0, Socket ID 0
  # CPU 1: Core ID 1, Socket ID 0
  ......
  # CPU 61: Core ID 10, Socket ID 1
  # CPU 62: Core ID 11, Socket ID 1
  # CPU 63: Core ID 16, Socket ID 1
  # node0 meminfo  : total = 32823872 kB, free = 29190932 kB
  # node0 cpu list : 0-17,36-53
Signed-off-by: NKan Liang <kan.liang@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/1441115893-22006-2-git-send-email-kan.liang@intel.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      2bb00d2f
  45. 29 8月, 2015 1 次提交
  47. 07 8月, 2015 1 次提交
  49. 29 7月, 2015 1 次提交
    • A
      perf session env: Rename exit method · 4c7de49a
      由 Arnaldo Carvalho de Melo 提交于 
      The semantic associated in tools/perf/ with foo__delete(instance) is to
release all resources referenced by 'instance' members and then release
the memory for 'instance' itself.

The perf_session_env__delete() function isn't doing this, it just does
the first part, but the space used by 'instance' itself isn't freed, as
it is embedded in a larger structure, that will be freed at other stage.

For these cases we se foo__exit(), i.e. the usage is:

 void foo__delete(foo)
 {
         if (foo) {
                 foo__exit(foo);
                 free(foo);
         }
 }

But when we have something like:

 struct bar {
         struct foo foo;
         . . .
 }

Then we can't really call foo__delete(&bar.foo), we must have this
instead:

 void bar__exit(bar)
 {
         foo__exit(&bar.foo);
         /* free other bar-> resources */
 }

 void bar__delete(bar)
 {
         if (bar) {
		bar__exit(bar);
                free(bar);
         }
 }

So just rename perf_session_env__delete() to perf_session_env__exit().

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-djbgpcfo5udqptx3q0flwtmk@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      4c7de49a
  51. 24 7月, 2015 1 次提交