The ec5761e cset introduced the symfs feature with a bug for loading vmlinux
files that ended up causing this failure:
[root@emilia v2.6.38-rc5+]# strace -e trace=open perf top --vmlinux ./vmlinux 2>&1 | tail -3
open("/./vmlinux", O_RDONLY) = -1 ENOENT (No such file or directory)
./vmlinux with build id b9266bf40e98dadb5d43a2f3e95d3c5d4aff46dc not found, continuing without symbols
The ./vmlinux file can't be used
[root@emilia v2.6.38-rc5+]#
Remove the extra slash, just like is done in the DSO__ORIG_DSO handling in
dso__load() and other parts of the ec5761e cset.
Reported-by: Ingo Molnar <mingo@elte.hu>
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: Arnaldo Carvalho de Melo <acme@redhat.com>
Currently numcpus is determined in pid_put_sample which is only
called on sched_switch/sched_wakeup sample processing.
On a machine with a lot cpus I often saw the last cpu missing.
Check for (max) numcpus on every event happening and in the
beginning. -> fixes the issue for me.
Signed-off-by: Thomas Renninger <trenn@suse.de>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: lenb@kernel.org
LKML-Reference: <1298842606-55712-6-git-send-email-trenn@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Follow kernel coding style traditions more closely.
Delete typedef, re-name "per cpu counters" to
simply be counters etc.
This patch changes no functionality.
Suggested-by: Thiago Farina <tfransosi@gmail.com>
Signed-off-by: Len Brown <len.brown@intel.com>
bug could cause false positive on indicating
presence of invarient TSC or APERF support.
Signed-off-by: Thomas Renninger <trenn@suse.de>
Signed-off-by: Len Brown <len.brown@intel.com>
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: Jeff 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: Arnaldo Carvalho de Melo <acme@redhat.com>
Introduced in: c52b12ed, when this sequence:
count[0] = count[1] = count[2] = 0;
Was replaced with:
aggr->val = 0;
Which is equivalent to zeroing just the first entry in the 'count'
array.
Fix it by zeroing the three entries with:
aggr->val = aggr->ena = aggr->run = 0;
Reported-by: Ingo Molnar <mingo@elte.hu>
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: Arnaldo Carvalho de Melo <acme@redhat.com>
The -Wstack-protector and -Wvolatile-register-var warnings, for
instance, are not supported by gcc 3.4.6.
So fix by doing the same check we already do for -fstack-protector-all.
With this and the other patches in this series, perf builds unmodified
on, for instance, RHEL4.
Cc: Eric Dumazet <eric.dumazet@gmail.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: Arnaldo Carvalho de Melo <acme@redhat.com>
[acme@localhost linux]$ make O=~acme/git/build/perf -C tools/perf
make: Entering directory `/home/acme/git/linux/tools/perf'
Makefile:526: No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev
Makefile:582: newt not found, disables TUI support. Please install newt-devel or libnewt-dev
CC /home/acme/git/build/perf/builtin-annotate.o
In file included from builtin-annotate.c:23:
util/parse-events.h:26: warning: declaration of 'evsel_list' shadows a global declaration
util/parse-events.h:12: warning: shadowed declaration is here
make: *** [/home/acme/git/build/perf/builtin-annotate.o] Error 1
make: Leaving directory `/home/acme/git/linux/tools/perf'
[acme@localhost linux]$ gcc --version | head -1
gcc (GCC) 3.4.6 20060404 (Red Hat 3.4.6-11)
[acme@localhost linux]$
Fix it by renaming the parameter to evlist.
Cc: Eric Dumazet <eric.dumazet@gmail.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: Arnaldo Carvalho de Melo <acme@redhat.com>
We need the definiton for __always_inline in bitops.h to fix the build
on distros where it isn't available or compiler.h doesn't get included
indirectly.
One of the fixes needed to build perf on RHEL4 systems, for instance.
Cc: Eric Dumazet <eric.dumazet@gmail.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: Arnaldo Carvalho de Melo <acme@redhat.com>
When some of CPUs are offline:
# cat /sys/devices/system/cpu/online
0,6-31
perf test will fail on #3 testcase:
3: detect open syscall event on all cpus:
--- start ---
perf_evsel__read_on_cpu: expected to intercept 111 calls on cpu 0, got 681
perf_evsel__read_on_cpu: expected to intercept 112 calls on cpu 1, got 117
perf_evsel__read_on_cpu: expected to intercept 113 calls on cpu 2, got 118
perf_evsel__read_on_cpu: expected to intercept 114 calls on cpu 3, got 119
perf_evsel__read_on_cpu: expected to intercept 115 calls on cpu 4, got 120
perf_evsel__read_on_cpu: expected to intercept 116 calls on cpu 5, got 121
perf_evsel__read_on_cpu: expected to intercept 117 calls on cpu 6, got 122
perf_evsel__read_on_cpu: expected to intercept 118 calls on cpu 7, got 123
perf_evsel__read_on_cpu: expected to intercept 119 calls on cpu 8, got 124
perf_evsel__read_on_cpu: expected to intercept 120 calls on cpu 9, got 125
perf_evsel__read_on_cpu: expected to intercept 121 calls on cpu 10, got 126
....
This patch try to use 'cpus->map[cpu]' when setting cpu affinity, and
will check the return code of sched_setaffinity()
LKML-Reference: <20110120114707.GA11781@hpt.nay.redhat.com>
Signed-off-by: Han Pingtian <phan@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
In ARM's Thumb mode the bottom bit of the symbol address is set to mark
the function as Thumb; the instructions are in reality 2 or 4 byte on 2
byte alignments, and when the +1 address is used in annotate it causes
objdump to disassemble invalid instructions.
The patch removes that bottom bit during symbol loading.
Many thinks to Dave Martin for comments on an initial version of the
patch.
(For reference this corresponds to this bug
https://bugs.launchpad.net/linux-linaro/+bug/677547 )
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Dave Martin <dave.martin@linaro.org>
LKML-Reference: <20110121163922.GA31398@davesworkthinkpad>
Signed-off-by: Dr. David Alan Gilbert <david.gilbert@linaro.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
perf tools: Fix tracepoint id to string perf.data header table
perf tools: Fix handling of wildcards in tracepoint event selectors
powerpc: perf: Fix frequency calculation for overflowing counters
It wasn't accounting the ':' when consuming bytes in the the event
selector string, so parse_events() would fail in this test:
if (!(*str == 0 || *str == ',' || isspace(*str)))
return -1;
as *str would be pointing to '*', the last character in the '-e' arg in:
$ perf record -q -a -D -e sched:sched_* | perf script -i - -s perf-script.py
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: Arnaldo Carvalho de Melo <acme@redhat.com>
* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
rcu: avoid pointless blocked-task warnings
rcu: demote SRCU_SYNCHRONIZE_DELAY from kernel-parameter status
rtmutex: Fix comment about why new_owner can be NULL in wake_futex_pi()
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86, olpc: Add missing Kconfig dependencies
x86, mrst: Set correct APB timer IRQ affinity for secondary cpu
x86: tsc: Fix calibration refinement conditionals to avoid divide by zero
x86, ia64, acpi: Clean up x86-ism in drivers/acpi/numa.c
* 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
timekeeping: Make local variables static
time: Rename misnamed minsec argument of clocks_calc_mult_shift()
* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
tracing: Remove syscall_exit_fields
tracing: Only process module tracepoints once
perf record: Add "nodelay" mode, disabled by default
perf sched: Fix list of events, dropping unsupported ':r' modifier
Revert "perf tools: Emit clearer message for sys_perf_event_open ENOENT return"
perf top: Fix annotate segv
perf evsel: Fix order of event list deletion
Sometimes there is a need to use perf in "live-log" mode. The problem
is, for seldom events, actual info output is largely delayed because
perf-record reads sample data in whole pages.
So for such scenarious, add flag for perf-record to go in "nodelay"
mode. To track e.g. what's going on in icmp_rcv while ping is running
Use it with something like this:
(1) $ perf probe -L icmp_rcv | grep -U8 '^ *43\>'
goto error;
}
38 if (!pskb_pull(skb, sizeof(*icmph)))
goto error;
icmph = icmp_hdr(skb);
43 ICMPMSGIN_INC_STATS_BH(net, icmph->type);
/*
* 18 is the highest 'known' ICMP type. Anything else is a mystery
*
* RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently
* discarded.
*/
50 if (icmph->type > NR_ICMP_TYPES)
goto error;
$ perf probe icmp_rcv:43 'type=icmph->type'
(2) $ cat trace-icmp.py
[...]
def trace_begin():
print "in trace_begin"
def trace_end():
print "in trace_end"
def probe__icmp_rcv(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
__probe_ip, type):
print_header(event_name, common_cpu, common_secs, common_nsecs,
common_pid, common_comm)
print "__probe_ip=%u, type=%u\n" % \
(__probe_ip, type),
[...]
(3) $ perf record -a -D -e probe:icmp_rcv -o - | \
perf script -i - -s trace-icmp.py
Thanks to Peter Zijlstra for pointing how to do it.
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>, 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: <20110112140613.GA11698@tugrik.mns.mnsspb.ru>
Signed-off-by: Kirill Smelkov <kirr@mns.spb.ru>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
