| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Print out the cache-miss percentage as well if the cache refs were
collected, for all the generic cache event types.
Before:
11,103,723,230 dTLB-loads # 622.471 M/sec ( +- 0.30% )
87,065,337 dTLB-load-misses # 4.881 M/sec ( +- 0.90% )
After:
11,353,713,242 dTLB-loads # 626.020 M/sec ( +- 0.35% )
113,393,472 dTLB-load-misses # 1.00% of all dTLB cache hits ( +- 0.49% )
Also ASCII color highlight too high percentages, them when it's executed on the console.
Cc: Peter Zijlstra <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Steven Rostedt <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Print even more detailed statistics if requested via perf stat -d:
-d: detailed events, L1 and LLC data cache
-d -d: more detailed events, dTLB and iTLB events
-d -d -d: very detailed events, adding prefetch events
Full output looks like this now:
Performance counter stats for '/home/mingo/hackbench 10' (5 runs):
1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% )
49,068 context-switches # 0.029 M/sec ( +- 16.66% )
8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% )
17,397 page-faults # 0.010 M/sec ( +- 0.46% )
2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%]
1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%]
743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%]
1,314,416,379 instructions # 0.56 insns per cycle
# 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%]
272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%]
3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%]
449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%]
22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%]
6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%]
1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%]
411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%]
27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%]
464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%]
10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%]
1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%]
117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%]
4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%]
1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%]
0.195622057 seconds time elapsed ( +- 6.84% )
Also clean up the attribute construction code to be appending, and factor
it out into add_default_attributes().
Tweak the coverage percentage printout a bit, so that it's easier to view it
alongside the +- sttddev colum.
Cc: Peter Zijlstra <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Steven Rostedt <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
perf bench needs this to build the kernel's memcpy routine:
In file included from bench/mem-memcpy-x86-64-asm.S:2:0:
bench/../../../arch/x86/lib/memcpy_64.S:7:33: fatal error: asm/alternative-asm.h: No such file or directory
Cc: Peter Zijlstra <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Steven Rostedt <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
This patch fixes an issue with event parsing.
The following commit appears to have broken the
ability to specify a comma separated list of events:
commit ceb53fbf6dbb1df26d38379a262c6981fe73dd36
Author: Ingo Molnar <[email protected]>
Date: Wed Apr 27 04:06:33 2011 +0200
perf stat: Fail more clearly when an invalid modifier is specified
This patch fixes this while preserving the desired effect:
$ perf stat -e instructions:u,instructions:k ls /dev/null /dev/null
Performance counter stats for 'ls /dev/null':
365956 instructions:u # 0.00 insns per cycle
731806 instructions:k # 0.00 insns per cycle
0.001108862 seconds time elapsed
$ perf stat -e task-clock-msecs true
invalid event modifier: '-msecs'
Run 'perf list' for a list of valid events and modifiers
Signed-off-by: Stephane Eranian <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/20110517133619.GA6999@quad
Signed-off-by: Ingo Molnar <[email protected]>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux-2.6 into perf/urgent
|
|
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: David Ahern <[email protected]>
Tested-by: Lin Ming <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Tom Zanussi <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
The perf_evlist__create_maps was discarding the --cpu parameter when a
--pid or --tid was specified, fix that.
Cc: Frederic Weisbecker <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Tom Zanussi <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
|
|
pubname_callback_param::found should be initialized to 0 in
fastpath lookup, the structure is on the stack and
uninitialized otherwise.
Signed-off-by: Lin Ming <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Merge reason: pull in the latest fixes.
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Including "../../annotate.h" once in
tools/perf/util/ui/browsers/annotate.c is enough. No need to do it twice.
Signed-off-by: Jesper Juhl <[email protected]>
Signed-off-by: Jiri Kosina <[email protected]>
|
|
The original Makefile uses "uname -m" to determine ARCH.
This causes problem on x86 when compile perf tool on 32 bit
userspace with a 64 bit kernel.
bench/../../../arch/x86/lib/memcpy_64.S: Assembler messages:
bench/../../../arch/x86/lib/memcpy_64.S:28: Error: bad register name `%rdi'
This is because "uname -m" returns x86_64 and memcpy_64.S is
included in 32 bit build.
Reported-by: Riccardo Magliocchetti <[email protected]>
Signed-off-by: Lin Ming <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Link: http://lkml.kernel.org/r/1304743274.3132.17.camel@localhost
Signed-off-by: Ingo Molnar <[email protected]>
|
|
If RCU priority boosting is to be meaningful, callback invocation must
be boosted in addition to preempted RCU readers. Otherwise, in presence
of CPU real-time threads, the grace period ends, but the callbacks don't
get invoked. If the callbacks don't get invoked, the associated memory
doesn't get freed, so the system is still subject to OOM.
But it is not reasonable to priority-boost RCU_SOFTIRQ, so this commit
moves the callback invocations to a kthread, which can be boosted easily.
Also add comments and properly synchronized all accesses to
rcu_cpu_kthread_task, as suggested by Lai Jiangshan.
Signed-off-by: Paul E. McKenney <[email protected]>
Signed-off-by: Paul E. McKenney <[email protected]>
Reviewed-by: Josh Triplett <[email protected]>
|
|
Similar to perf-record, tell user about unsupported events
that will not be counted if invoked in verbose mode.
e.g.,
$ perf stat -e dTLB-prefetch-misses -v -- sleep 1
dTLB-prefetch-misses event is not supported by the kernel.
dTLB-prefetch-misses: 0 0 0
Performance counter stats for 'sleep 1':
<not counted> dTLB-prefetch-misses
1.001884783 seconds time elapsed
Signed-off-by: David Ahern <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Recent stalled-cycles event names were larger than the 40 chars printout
used by perf list.
Extend that, make it robust for future extensions and also adjust alignments
in face of wider event names.
Cc: Peter Zijlstra <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
David Ahern reported this perf stat failure:
> # /tmp/build-perf/perf stat -- sleep 1
> Error: stalled-cycles-frontend event is not supported.
> Fatal: Not all events could be opened.
>
> This is a Dell R410 with an E5620 processor.
Fail in a softer fashion on unknown/unsupported events.
Reported-by: David Ahern <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Triple digit percentages do not fit otherwise.
Cc: Peter Zijlstra <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Adjust to color thresholds to better match the percentages seen in
real workloads. Both are now a bit more sensitive.
Cc: Peter Zijlstra <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Sample output:
Performance counter stats for './loop_1b':
873.691065 task-clock # 1.000 CPUs utilized
1 context-switches # 0.000 M/sec
1 CPU-migrations # 0.000 M/sec
96 page-faults # 0.000 M/sec
2,012,637,222 cycles # 2.304 GHz (66.58%)
1,001,397,911 stalled-cycles-frontend # 49.76% frontend cycles idle (66.58%)
7,523,398 stalled-cycles-backend # 0.37% backend cycles idle (66.76%)
2,004,551,046 instructions # 1.00 insns per cycle
# 0.50 stalled cycles per insn (66.80%)
1,001,304,992 branches # 1146.063 M/sec (66.76%)
39,453 branch-misses # 0.00% of all branches (66.64%)
0.874046121 seconds time elapsed
Cc: Peter Zijlstra <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Update perf tooling to deal with front-end and back-end stalled cycles events.
Add both the default 'perf stat' output.
Cc: Peter Zijlstra <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Instead of failing on an unknown event, when new perf stat is run on
older kernels:
$ ./perf stat true
Error: open_counter returned with 22 (Invalid argument). /bin/dmesg
may provide additional information.
Fatal: Not all events could be opened.
Just ignore EINVAL and ENOSYS, we'll print the results as not counted:
Performance counter stats for 'true':
0.239483 task-clock # 0.493 CPUs utilized
0 context-switches # 0.000 M/sec
0 CPU-migrations # 0.000 M/sec
86 page-faults # 0.359 M/sec
704,766 cycles # 2.943 GHz
<not counted> stalled-cycles
381,961 instructions # 0.54 insns per cycle
69,626 branches # 290.735 M/sec
4,594 branch-misses # 6.60% of all branches
0.000485883 seconds time elapsed
Cc: Peter Zijlstra <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
--sync will tell perf stat to run sync() before starting a command.
This allows IO-heavy tests to be used with --repeat, without one
iteration impacting the other.
Elapsed time will stabilize for example:
before: 3.971525714 seconds time elapsed ( +- 8.56% )
after: 3.211098537 seconds time elapsed ( +- 1.52% )
So measurements will be more accurate.
Cc: Peter Zijlstra <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Before:
|
| Performance counter stats for '/home/mingo/hackbench 20' (5 runs):
|
| 71,321,607 instructions:u # 0.42 insns per cycle ( +- 0.00% )
| 168,040,009 cycles:u # 0.000 GHz ( +- 0.81% )
|
| 1.468002368 seconds time elapsed ( +- 1.33% )
|
After:
|
| Performance counter stats for '/home/mingo/hackbench 20' (5 runs):
|
| 71,321,607 instructions:u # 0.42 insns per cycle ( +- 0.00% )
| 168,040,009 cycles:u # 0.000 GHz ( +- 0.81% )
|
| 1.468002368 seconds time elapsed ( +- 1.33% )
|
The last column (stddev noise) is properly aligned, vertically.
Cc: Peter Zijlstra <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Add the new -d/--detailed flag, which generates a pretty detailed event list:
Performance counter stats for './hackbench 10' (10 runs):
1514.287888 task-clock # 10.897 CPUs utilized ( +- 3.05% )
39,698 context-switches # 0.026 M/sec ( +- 12.19% )
8,147 CPU-migrations # 0.005 M/sec ( +- 16.55% )
17,918 page-faults # 0.012 M/sec ( +- 0.37% )
2,944,504,050 cycles # 1.944 GHz ( +- 3.89% ) (32.60%)
1,043,971,283 stalled-cycles # 35.45% of all cycles are idle ( +- 5.22% ) (44.48%)
1,655,906,768 instructions # 0.56 insns per cycle
# 0.63 stalled cycles per insn ( +- 1.95% ) (55.09%)
338,832,373 branches # 223.757 M/sec ( +- 1.96% ) (64.47%)
3,892,416 branch-misses # 1.15% of all branches ( +- 5.49% ) (73.12%)
606,410,482 L1-dcache-loads # 400.459 M/sec ( +- 1.29% ) (71.21%)
31,204,395 L1-dcache-load-misses # 5.15% of all L1-dcache hits ( +- 3.04% ) (60.43%)
3,922,751 LLC-loads # 2.590 M/sec ( +- 6.80% ) (46.87%)
5,037,288 LLC-load-misses # 3.327 M/sec ( +- 3.56% ) (13.00%)
0.138966828 seconds time elapsed ( +- 4.11% )
This can be used "at a glance" for narrower analysis.
-d can also be used in addition to other -e events, to further expand an event list.
Acked-by: Peter Zijlstra <[email protected]>
Acked-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Print out this kind of l1-dcache-misses percentage:
Performance counter stats for './bw_tcp localhost':
29,956,262,201 cycles # 3.002 GHz (scaled from 85.14%)
8,255,209,558 stalled-cycles # 27.56% of all cycles are idle (scaled from 86.56%)
1,206,130,308 l1-dcache-misses # 40.49% of all L1-dcache hits (scaled from 86.30%)
2,978,756,779 l1-dcache-refs # 298.512 M/sec (scaled from 70.02%)
8,861,956,159 instructions # 0.30 insns per cycle
# 0.93 stalled cycles per insn (scaled from 84.27%)
1,644,306,068 branches # 164.782 M/sec (scaled from 86.43%)
74,778,443 branch-misses # 4.55% of all branches (scaled from 70.69%)
9978.695711 task-clock # 0.693 CPUs utilized
14.404347983 seconds time elapsed
And color the result depending on the severity of cache-trashing.
Acked-by: Peter Zijlstra <[email protected]>
Acked-by Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Print the missed-branches percentage with different warning level ASCII colors,
as the percentage passes the 5%/10%/20% thresholds.
These thresholds are set to relatively low levels, because on most CPUs even a
moderate percentage of branch-misses already shows up as a slowdown.
Acked-by: Peter Zijlstra <[email protected]>
Acked-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Print the stalled-cycles percentage with different warning level ASCII colors,
as the percentage passes the 25%/50%/75% thresholds.
Acked-by: Peter Zijlstra <[email protected]>
Acked-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Before:
0 CPU-migrations # 0.000 M/sec ( +- -nan% )
After:
0 CPU-migrations # 0.000 M/sec ( +- 0.00% )
Also factor out the noise printing function.
Acked-by: Peter Zijlstra <[email protected]>
Acked-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
The new default output looks like this:
Performance counter stats for './loop_1b_instructions':
236.010686 task-clock # 0.996 CPUs utilized
0 context-switches # 0.000 M/sec
0 CPU-migrations # 0.000 M/sec
99 page-faults # 0.000 M/sec
756,487,646 cycles # 3.205 GHz
354,938,996 stalled-cycles # 46.92% of all cycles are idle
1,001,403,797 instructions # 1.32 insns per cycle
# 0.35 stalled cycles per insn
100,279,773 branches # 424.895 M/sec
12,646 branch-misses # 0.013 % of all branches
0.236902540 seconds time elapsed
We dropped cache-refs and cache-misses and added stalled-cycles - this is a
more generic "how well utilized is the CPU" metric.
If the stalled-cycles ratio is too high then more specific measurements can be
taken to figure out the source of the inefficiency.
Acked-by: Peter Zijlstra <[email protected]>
Acked-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Add stalled cycles accounting and use it to print the "cycles stalled per
instruction" value.
Also change the unit of the cycles output from M/sec to GHz - this is more
intuitive.
Prettify the output to:
Performance counter stats for './loop_1b_instructions':
239.775036 task-clock # 0.997 CPUs utilized
761,903,912 cycles # 3.178 GHz
356,620,620 stalled-cycles # 46.81% of all cycles are idle
1,001,578,351 instructions # 1.31 insns per cycle
# 0.36 stalled cycles per insn
14,782 cache-references # 0.062 M/sec
5,694 cache-misses # 38.520 % of all cache refs
0.240493656 seconds time elapsed
Also adjust the --repeat output to make the percentages align vertically:
Performance counter stats for './loop_1b_instructions' (10 runs):
236.096793 task-clock # 0.997 CPUs utilized ( +- 0.011% )
756,553,086 cycles # 3.204 GHz ( +- 0.002% )
354,942,692 stalled-cycles # 46.92% of all cycles are idle ( +- 0.008% )
1,001,389,700 instructions # 1.32 insns per cycle
# 0.35 stalled cycles per insn ( +- 0.000% )
10,166 cache-references # 0.043 M/sec ( +- 0.742% )
468 cache-misses # 4.608 % of all cache refs ( +- 13.385% )
0.236874136 seconds time elapsed ( +- 0.01% )
Acked-by: Peter Zijlstra <[email protected]>
Acked-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Create update_shadow_stats() which is then used in both read_counter_aggr()
and read_counter().
This not only simplifies the code but also fixes a bug: HW_CACHE_REFERENCES
was not updated in read_counter().
Acked-by: Peter Zijlstra <[email protected]>
Acked-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Right now we display this by default:
0.202204 task-clock-msecs # 0.282 CPUs
0 context-switches # 0.000 M/sec
0 CPU-migrations # 0.000 M/sec
85 page-faults # 0.420 M/sec
The task-clock-msecs event cannot actually be passed back as an
event name, the event name we recognize is 'task-clock'.
So change the output of the cpu-clock and task-clock events
to be idempotent.
( Units should be printed out in the right-side column, if needed. )
Acked-by: Peter Zijlstra <[email protected]>
Acked-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Currently we fail without printing any error message on "perf stat -e task-clock-msecs".
The reason is that the task-clock event is matched and the "-msecs" postfix is assumed
to be an event modifier - but is not recognized.
This patch changes the code to be more informative:
$ perf stat -e task-clock-msecs true
invalid event modifier: '-msecs'
Run 'perf list' for a list of valid events and modifiers
And restructures the return value of parse_event_modifier() to allow
the printing of all variants of invalid event modifiers.
Acked-by: Peter Zijlstra <[email protected]>
Acked-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
We currently fail on something like '-e CPU-migrations', with:
invalid or unsupported event: 'CPU-migrations'
While 'CPU-migrations' is how we actually print out the event
in the default perf stat output:
Performance counter stats for 'true':
0.202204 task-clock-msecs # 0.282 CPUs
0 context-switches # 0.000 M/sec
0 CPU-migrations # 0.000 M/sec
So change the matching to be case-insensitive.
Acked-by: Peter Zijlstra <[email protected]>
Acked-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Before:
113,393,041 cache-references # 83.636 M/sec
7,052,454 cache-misses # 5.202 M/sec
After:
112,589,441 cache-references # 87.925 M/sec
6,556,354 cache-misses # 5.823 %
misses/hits percentages are more expressive than absolute numbers
or rates.
(Also prettify the CPUs printout line to not have a trailing whitespace.)
Acked-by: Peter Zijlstra <[email protected]>
Acked-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Print:
611,527 cycles
400,553 instructions # ( 0.71 instructions per cycle )
77,809 stalled-cycles # ( 12.71% of all cycles )
0.000610987 seconds time elapsed
Acked-by: Peter Zijlstra <[email protected]>
Acked-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
|
|
The new PERF_COUNT_HW_STALLED_CYCLES event tries to approximate
cycles the CPU does nothing useful, because it is stalled on a
cache-miss or some other condition.
Acked-by: Peter Zijlstra <[email protected]>
Acked-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Fast-forwarded to current state of Linus' tree as there are patches to be
applied for files that didn't exist on the old branch.
|
|
Neil Brown pointed out that lock_depth somehow escaped the BKL
removal work. Let's get rid of it now.
Note that the perf scripting utilities still have a bunch of
code for dealing with common_lock_depth in tracepoints; I have
left that in place in case anybody wants to use that code with
older kernels.
Suggested-by: Neil Brown <[email protected]>
Signed-off-by: Jonathan Corbet <[email protected]>
Cc: Arnd Bergmann <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Andrew Morton <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
|
|
Check for required sample attributes using evsel rather than sample_type
in the session header. If the attribute for a default field is not
present for the event type (e.g., new command operating on file from
older kernel) the field is removed from the output list.
Expected event types must exist. For example, if a user specifies
-f trace:time,trace -f sw:time,cpu,sym
the perf.data file must contain both tracepoints and software events
(ie., it is an error if either does not exist in the file).
Attribute checking is done once at the beginning of perf-script rather
than for each sample.
v1 -> v2:
- addressed comments from acme
Cc: Frederic Weisbecker <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: David Ahern <[email protected]>
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Useful for getting stack traces for hardware events not handled by
PERF_TYPE_HARDWARE.
Cc: Frederic Weisbecker <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Tom Zanussi <[email protected]>
Signed-off-by: Arun Sharma <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Signed-off-by: Michael Witten <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
The `try-cc' user-defined function was in tools/perf/feature-tests.mak;
this commit moves it to tools/perf/config/utilities.mak.
Signed-off-by: Michael Witten <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Currently, Python 3 is not supported by perf's code; this
can cause the build to fail for systems that have Python 3
installed as the default python:
python{,-config}
The Correct Solution is to write compatibility code so that
Python 3 works out-of-the-box.
However, users often have an ancillary Python 2 installed:
python2{,-config}
Therefore, a quick fix is to allow the user to specify those
ancillary paths as the python binaries that Makefile should
use, thereby avoiding Python 3 altogether; as an added benefit,
the Python binaries may be installed in non-standard locations
without the need for updating any PATH variable.
This commit adds the ability to set PYTHON and/or PYTHON_CONFIG
either as environment variables or as make variables on the
command line; the paths may be relative, and usually only PYTHON
is necessary in order for PYTHON_CONFIG to be defined implicitly.
Some rudimentary error checking is performed when the user
explicitly specifies a value for any of these variables.
In addition, this commit introduces significantly robust makefile
infrastructure for working with paths and communicating with the
shell; it's currently only used for handling Python, but I hope
it will prove useful in refactoring the makefiles.
Thanks to:
Raghavendra D Prabhu <[email protected]>
for motivating this patch.
Acked-by: Raghavendra D Prabhu <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Michael Witten <[email protected]>
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
There is no need for a subshell or an explicit `export';
as per the POSIX Shell Command Language specification:
http://pubs.opengroup.org/onlinepubs/009695399/utilities/xcu_chap02.html#tag_02_09_01
http://pubs.opengroup.org/onlinepubs/009695399/utilities/xcu_chap02.html#tag_02_10_02
It is only necessary to include the environment variable
assignment just before the command to be run.
Also, it is better to use single-quotes, because GNU make
might expand `$(BASIC_CFLAGS)' into something that the shell
could interpret within double-quotes.
Acked-by: Raghavendra D Prabhu <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Michael Witten <[email protected]>
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
One more installment on an area that is mostly dormant.
Suggested-by: Thomas Gleixner <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Tom Zanussi <[email protected]>
LKML-Reference: <new-submission>
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Merge reason: we'll be queueing up dependent changes.
Signed-off-by: Ingo Molnar <[email protected]>
|
|
perf stat doesn't mmap and its perfectly fine for it to use task-bound
counters with inheritance.
So set the attr.inherit on the caller and leave the syscall itself to
validate it.
When the mmap fails perf_evlist__mmap will just emit a warning if this
is the failure reason.
Reported-by: Peter Zijlstra <[email protected]>
Acked-by: Peter Zijlstra <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Tom Zanussi <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
In hists browser, press hotkey 'a' to annotate current symbol.
Now it causes segment fault if 'a' is pressed on a null symbol.
Here are 2 small bugs:
- In perf_evsel__hists_browse, the condition check after 'a' is pressed
is not correct, we should check ->sym instead of ->map.
- In symbol__tui_annotate we must check whether sym is NULL or not
before getting annotation structure.
This patch fixes above 2 small bugs.
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Lin Ming <[email protected]>
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
|
|
Signed-off-by: Justin P. Mattock <[email protected]>
Signed-off-by: Jiri Kosina <[email protected]>
|