- 28 May, 2013 40 commits
-
-
David Ahern authored
Number of samples needs to be greater 1 to have a variance. Fixes nan% in perf-kvm-live output. Signed-off-by:
David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Runzhen Wang <runzhen@linux.vnet.ibm.com> Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1369527896-3650-9-git-send-email-dsahern@gmail.comSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
David Ahern authored
Save previous pointer and free on failure. Signed-off-by:
-
David Ahern authored
message is currently shown as: Error: You may not have permission to collect %sstats. Consider tweaking /proc/sys/kernel/perf_event_paranoid: Note the %sstats. With patch this becomes: Error: You may not have permission to collect stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid: Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Its 'multiple', not 'mutliple', noticed while preparing a talk for Linuxtag'13. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.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> Link: http://lkml.kernel.org/n/tip-dzy9nl1ku7a5umddvdic4ibl@git.kernel.orgSigned-off-by:
-
Jiri Olsa authored
The current logic is to attach pair to the leader hist_entry. Arguments of hist_entry__add_pair function were placed the other way round.. driving me crazy. I.e. list_add_tail expects (new_node, head). Signed-off-by:
Jiri Olsa <jolsa@redhat.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1355404152-16523-3-git-send-email-jolsa@redhat.comSigned-off-by:
-
Jiri Olsa authored
There's missing change for hists__precompute to iterate either entries_collapsed or entries_in tree. The change was initiated for hists_compute_resort function in commit: 66f97ed3 perf diff: Use internal rb tree for compute resort but was missing for hists__precompute function changes. Signed-off-by:
-
Namhyung Kim authored
Now an user can set a default value of --percent-limit option into the perfconfig file. $ cat ~/.perfconfig [report] percent-limit = 0.1 Signed-off-by:
Namhyung Kim <namhyung@kernel.org> Acked-by:
Pekka Enberg <penberg@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1368497347-9628-9-git-send-email-namhyung@kernel.orgSigned-off-by:
-
Namhyung Kim authored
The --percent-limit option is for not showing small overhead entries in the output. Signed-off-by:
-
Namhyung Kim authored
The --percent-limit option is for not showing small overhead entries in the output. Maybe we want to set a certain default value like 0.1. Signed-off-by:
-
Namhyung Kim authored
The 'perf report'command is single-threaded, so no need to grab a lock. Although the fast path of pthread_mutex_[un]lock() is very fast, there's a ~3% gain by eliminating it when we have huge sample data. $ perf record -a -F 100000 -o perf.data.bench -- perf bench sched all $ perf record -e cycles:upp -o perf.data.before -- \ > perf report -i perf.data.bench --stdio > /dev/null ... apply this patch ... $ perf record -e cycles:upp -o perf.data.after -- \ > perf report -i perf.data.bench --stdio > /dev/null $ perf diff perf.data.{before,after} | grep pthread +0.02% libpthread-2.15.so [.] _pthread_cleanup_push_defer +0.02% libpthread-2.15.so [.] _pthread_cleanup_pop_restore 0.05% -0.05% perf [.] pthread_mutex_unlock@plt 0.05% -0.05% perf [.] pthread_mutex_lock@plt 1.01% -1.01% libpthread-2.15.so [.] pthread_mutex_lock 1.68% -1.68% libpthread-2.15.so [.] __pthread_mutex_unlock_usercnt 0.05% -0.05% libpthread-2.15.so [.] pthread_mutex_unlock Signed-off-by: -
Namhyung Kim authored
It's a preparation patch to eliminate unneeded locking in the perf report path. Signed-off-by:
-
Namhyung Kim authored
Those _threaded() functions are needed to make hist tree handling thread-safe, but AFAICS the only thing it does is forcing it to use the intermediate 'collapsed' tree. This can be acheived by setting sort__need_collapse to 1 in cmd_top() so no need to keep those _threaded() variants. Signed-off-by:
-
Namhyung Kim authored
If there's no sample, kernel and exact percent output at the header looked like "-nan%". Tested-by:
-
Namhyung Kim authored
The -E/--entries option controls how many lines to be printed on stdio output but it doesn't work as it should be: If -E option is specified, print that many lines regardless of current window size, if not automatically adjust number of lines printed to fit into the window size. Reported-by:
Minchan Kim <minchan@kernel.org> Tested-by:
-
David Ahern authored
Perf data files cannot be processed until the header is updated which is done via an on_exit handler. If perf is killed due to a SIGTERM it does not run the on_exit hooks leaving the perf.data file in a random state which perf-report will happily spin on trying to read. As noted by Mike an easy reproducer is: perf record -a -g & sleep 1; killall perf Fix by catching SIGTERM like it does SIGINT. Also need to remove the kill which was added via commit f7b7c26e. Acked-by:
Stephane Eranian <eranian@google.com> Signed-off-by:
-
Andi Kleen authored
Need to check for /dev/zero. Most likely more strings are missing too. Signed-off-by:
Andi Kleen <ak@linux.intel.com> Link: http://lkml.kernel.org/r/1366848182-30449-1-git-send-email-andi@firstfloor.orgSigned-off-by:
-
Sukadev Bhattiprolu authored
When building on powerpc, we get compile errors in bp_signal.c and bp_signal_overflow.c due to __u64 and '%llx'. Powerpc, needs __SANE_USERSPACE_TYPES__ to be defined so we pick up <asm-generic/int-ll64.h> and define __u64 as unsigned long long. Signed-off-by:
Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20130426173320.GA7029@us.ibm.comSigned-off-by:
-
Jiri Olsa authored
Unmatched spaces/tabs Makefile indentation could make the Makefile fails. While the tabed line could be considered sometimes as follow up for rule command, the mixed space tab meses up with makefile if conditions. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
The TUI hist browser had a similar variable has_symbols for the same purpose. Let's get rid of the duplication. Signed-off-by:
-
Namhyung Kim authored
perf top had a similar variable sort_has_symbols for the same purpose. Signed-off-by:
-
Namhyung Kim authored
The sort__has_sym variable is set only if a symbol-related sort key was added. Since branch stack and memory sort dimensions are separated, it doesn't need to be checked from common dimension. Signed-off-by:
-
Namhyung Kim authored
It's in common sort dimension so it'd be more natural to place it with other common column index. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
It is analysis, not analisys. Reported-by:
William Cohen <wcohen@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-s7476m0irq0naxkzd9iekbr3@git.kernel.orgSigned-off-by:
-
Namhyung Kim authored
The same code was duplicate to places, factor them out to common sort__setup_elide(). Signed-off-by:
-
Namhyung Kim authored
Since they're used only for perf mem, separate out them to a different dimension so that normal user cannot access them by any chance. For global/local weights, I'm not entirely sure to place them into the memory dimension. But it's the only user at this time. Signed-off-by:
-
Namhyung Kim authored
Let's remove duplicate code. Suggested-by:
-
Namhyung Kim authored
It's used for determining current sort mode which can be one of NORMAL, BRANCH and new MEMORY. Signed-off-by:
-
Namhyung Kim authored
When -v option is given, the symbol sort key prints its address also but it wasn't properly aligned since hists__calc_col_len() misses the additional part. Also it missed 2 spaces for 0x prefix when printing. $ perf report --stdio -v -s sym # Samples: 133 of event 'cycles' # Event count (approx.): 50536717 # # Overhead Symbol # ........ .............................. # 12.20% 0xffffffff81384c50 v [k] intel_idle 7.62% 0xffffffff8170976a v [k] ftrace_caller 7.02% 0x2d986d B [.] 0x00000000002d986d Signed-off-by: -
Namhyung Kim authored
The mem info is shared between matched entries so one should be freed. Signed-off-by:
-
Namhyung Kim authored
The branch info was allocated for the whole stack and passed matching hist entry for each level during processing samples. Thus when a hist entry tries to free its branch info like in hists__collapse_insert_entry it'll face following error. *** glibc detected *** perf: munmap_chunk(): invalid pointer: 0x00000000014e9d20 *** ======= Backtrace: ========= /lib64/libc.so.6[0x387d47ae16] perf[0x4923bd] perf(cmd_report+0xd68)[0x432a08] perf[0x41a663] perf(main+0x58f)[0x419eaf] /lib64/libc.so.6(__libc_start_main+0xf5)[0x387d421735] perf[0x419f95] Fix it by allocating and copying branch info for each new hist entry. Signed-off-by:
-
Sukadev Bhattiprolu authored
One of the reasons 'perf test' is failing on Power appears to be due to a bug in isupper(). isupper(c) and islower(c) should be checking 'c' against the mask 0x20. Instead they are checking sane_ctype[c] which causes isupper() to be true for lower case letters. Signed-off-by:
-
Li Zefan authored
The old softlockup detector has been replaced with new lockup detector long ago. Signed-off-by:
Li Zefan <lizefan@huawei.com> Acked-by:
Don Zickus <dzickus@redhat.com> Link: http://lkml.kernel.org/r/51959687.9090305@huawei.comSigned-off-by:
Ingo Molnar <mingo@kernel.org>
-
Li Zefan authored
Signed-off-by:
-
Li Zefan authored
In old kernels, it's allowed to set softlockup_thresh to -1 or 0 to disable softlockup detection. However watchdog_thresh only uses 0 to disable detection, and setting it to -1 just froze my box and nothing I can do but reboot. Signed-off-by:
-
Peter Zijlstra authored
Josh reported that his QEMU is a bad hardware emulator and trips a WARN in the AMD PMU init code. He requested the WARN be turned into a pr_err() or similar. While there, rework the code a little. Reported-by:
Josh Boyer <jwboyer@redhat.com> Acked-by:
Robert Richter <rric@kernel.org> Acked-by:
Jacob Shin <jacob.shin@amd.com> Cc: Stephane Eranian <eranian@google.com> Signed-off-by:
Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20130521110537.GG26912@twins.programming.kicks-ass.netSigned-off-by:
-
Stephane Eranian authored
This patch moves commit 7cc23cd6 to the generic code: perf/x86/intel/lbr: Demand proper privileges for PERF_SAMPLE_BRANCH_KERNEL The check is now implemented in generic code instead of x86 specific code. That way we do not have to repeat the test in each arch supporting branch sampling. Signed-off-by:
-
Dan Carpenter authored
We're trying to use 64 bit masks but the shifts wrap so we can't use the high 32 bits. I've fixed this by changing several types to unsigned long long. This is a static checker fix. The one change which is clearly needed is "mask = 0xff << (idx * 8);" where the author obviously intended to use all 64 bits. The other changes are mostly to silence my static checker. Signed-off-by:
Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by:
Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20130518183452.GA14587@elgon.mountainSigned-off-by:
-
Stephane Eranian authored
This patch adds /sys/device/xxx/perf_event_mux_interval_ms to ajust the multiplexing interval per PMU. The unit is milliseconds. Value has to be >= 1. In the 4th version, we renamed the sysfs file to be more consistent with the other /proc/sys/kernel entries for perf_events. In the 5th version, we handle the reprogramming of the hrtimer using hrtimer_forward_now(). That way, we sync up to new timer value quickly (suggested by Jiri Olsa). Signed-off-by:
-
Stephane Eranian authored
The current scheme of using the timer tick was fine for per-thread events. However, it was causing bias issues in system-wide mode (including for uncore PMUs). Event groups would not get their fair share of runtime on the PMU. With tickless kernels, if a core is idle there is no timer tick, and thus no event rotation (multiplexing). However, there are events (especially uncore events) which do count even though cores are asleep. This patch changes the timer source for multiplexing. It introduces a per-PMU per-cpu hrtimer. The advantage is that even when a core goes idle, it will come back to service the hrtimer, thus multiplexing on system-wide events works much better. The per-PMU implementation (suggested by PeterZ) enables adjusting the multiplexing interval per PMU. The preferred interval is stashed into the struct pmu. If not set, it will be forced to the default interval value. In order to minimize the impact of the hrtimer, it is turned on and off on demand. When the PMU on a CPU is overcommited, the hrtimer is activated. It is stopped when the PMU is not overcommitted. In order for this to work properly, we had to change the order of initialization in start_kernel() such that hrtimer_init() is run before perf_event_init(). The default interval in milliseconds is set to a timer tick just like with the old code. We will provide a sysctl to tune this in another patch. Signed-off-by:
-
Jiri Olsa authored
The hw breakpoint pmu 'add' function is missing the period_left update needed for SW events. The perf HW breakpoint events use the SW events framework to process the overflow, so it needs to be properly initialized in the PMU 'add' method. Signed-off-by:
-
