- 26 Aug, 2013 3 commits
-
-
David Ahern authored
Occassionally events (e.g., context-switch, sched tracepoints) are losing the conversion of sample data associated with a thread. For example: $ perf record -e sched:sched_switch -c 1 -a -- sleep 5 $ perf script <selected events shown> ls 30482 [000] 1379727.583037: sched:sched_switch: prev_comm=ls prev_pid=30482 ... ls 30482 [000] 1379727.586339: sched:sched_switch: prev_comm=ls prev_pid=30482 ... :30482 30482 [000] 1379727.589462: sched:sched_switch: prev_comm=ls prev_pid=30482 ... The last line lost the conversion from tid to comm. If you look at the events (perf script -D) you see why - a SAMPLE event is generated after the EXIT: 0 1379727589449774 0x1540b0 [0x38]: PERF_RECORD_EXIT(30482:30482):(30482:30482) 0 1379727589462497 0x1540e8 [0x80]: PERF_RECORD_SAMPLE(IP, 1): 30482/30482: 0xffffffff816416f1 period: 1 addr: 0 ... thread: :30482:30482 When perf processes the EXIT event the thread is moved to the dead_threads list. When the SAMPLE event is processed no thread exists for the pid so a new one is created by machine__findnew_thread. This patch address the problem by delaying the move to the dead_threads list until the tid is re-used (per Adrian's suggestion). With this patch we get the previous example shows: ls 30482 [000] 1379727.583037: sched:sched_switch: prev_comm=ls prev_pid=30482 ... ls 30482 [000] 1379727.586339: sched:sched_switch: prev_comm=ls prev_pid=30482 ... ls 30482 [000] 1379727.589462: sched:sched_switch: prev_comm=ls prev_pid=30482 ... and 0 1379727589449774 0x1540b0 [0x38]: PERF_RECORD_EXIT(30482:30482):(30482:30482) 0 1379727589462497 0x1540e8 [0x80]: PERF_RECORD_SAMPLE(IP, 1): 30482/30482: 0xffffffff816416f1 period: 1 addr: 0 ... thread: ls:30482 v4: per Arnaldo's request add dead flag to thread struct and set when task exits v3: re-do from a time based check to a delayed move to dead_threads list v2: Rebased to latest perf/core branch. Changed time comparison to use a macro which explicitly shows the time basis Signed-off-by:David Ahern <dsahern@gmail.com> Acked-by:
Adrian Hunter <adrian.hunter@intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1376491767-84171-1-git-send-email-dsahern@gmail.comSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
David Ahern authored
Common arguments like thread id, CPU list, mmap pages, etc should be consistent across perf commands. v3: Updated man page v2: rebased to latest core branch Signed-off-by:
-
Arnaldo Carvalho de Melo authored
To output all 'trace' output to a filename, just like 'strace -ofile' Cc: Adrian Hunter <adrian.hunter@intel.com> 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-6q1homkwoayhmoq64y5vhel6@git.kernel.orgSigned-off-by:
-
- 16 Aug, 2013 10 commits
-
-
Adrian Hunter authored
It is useful to see the arguments to perf_event_open and whether the perf events ring buffer was mmapped per-cpu or per-thread. That information will now be displayed when verbose is 2 i.e option -vv. Signed-off-by:
Namhyung Kim <namhyung@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> 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/r/1376484517-5339-3-git-send-email-adrian.hunter@intel.com [ fixup trivial conflict with fcb14f7 ] Signed-off-by:
-
Adrian Hunter authored
The python/perf.so python binding links a subset of objects. Re-implement 'verbose' and 'eprintf' so they (and consequently 'pr_debug') can be used in objects linked into pythin/perf.so. Note 'eprintf' must be re-implemented because the full version links the browser ui. Signed-off-by:
-
Andi Kleen authored
perf stat -a needs 10 open file descriptors per logical CPU perf stat -a -dddd needs 20 open fds for each. This implies that stat -a doesn't work on any system with the default ulimit -n 1024 which has more than ~100 CPUs and stat -a -dddd doesn't work on anything with more than 46 CPUs. Longer term there needs to be probably some way to lower the file descriptor requirements. This would need some changes in the kernel/user interface. But short term this patch just tries to increase the file descriptor limit in perf itself, when it runs into a EMFILE. It first sets it to the hard limit, and then tries to increase the hard limit. On Fedora systems the default seems to be soft limit 1024 and hard limit 4*1024. So even non root can support 409 or 186 CPUs respectively. root can go far higher. Signed-off-by:
Andi Kleen <ak@linux.intel.com> Link: http://lkml.kernel.org/r/1375670486-15480-1-git-send-email-andi@firstfloor.orgSigned-off-by:
-
David Ahern authored
4a4d371a missed builtin-kvm in the cleanup to remove the force option to cmd_record. Signed-off-by:
-
Peter Zijlstra authored
We should not be calling calc_timer_values() for events that do not actually have an mmap()'ed userpage. Signed-off-by:
Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20130802191630.GT27162@twins.programming.kicks-ass.netSigned-off-by:
Ingo Molnar <mingo@kernel.org>
-
Frederic Weisbecker authored
Freq events may not always be affine to a particular CPU. As such, account_event_cpu() may crash if we account per cpu a freq event that has event->cpu == -1. To solve this, lets account freq events globally. In practice this doesn't change much the picture because perf tools create per-task perf events with one event per CPU by default. Profiling a single CPU is usually a corner case so there is no much point in optimizing things that way. Reported-by:
Jiri Olsa <jolsa@redhat.com> Suggested-by:
Frederic Weisbecker <fweisbec@gmail.com> Tested-by:
-
Frederic Weisbecker authored
When we fail to allocate the callchain buffers, we roll back the refcount we did and return from get_callchain_buffers(). However we take the refcount and allocate under the callchain lock but the rollback is done outside the lock. As a result, while we roll back, some concurrent callchain user may call get_callchain_buffers(), see the non-zero refcount and give up because the buffers are NULL without itself retrying the allocation. The consequences aren't that bad but that behaviour looks weird enough and it's better to give their chances to the following callchain users where we failed. Reported-by:
-
Yan, Zheng authored
This patch adds support for the SNB-EP PCU uncore PMU extra_sel_bit (bit 21) which is missing from the documentation in Table-2.75 of Intel Xeon Processor E5-2600 Product Family Uncore Performance Monitoring Guide. It is referred to later in Table-2.81. Without this selection bit explicitly enabled by the kernel, some events such as COREx_TRANSITION_CYCLES do not count correctly. Signed-off-by:
Yan, Zheng <zheng.z.yan@intel.com> Reviewed-by:
Stephane Eranian <eranian@google.com> Signed-off-by:
-
Yan, Zheng authored
The QPI uncore boxes have two pairs of MATCH/MASK registers that user to filter packet traffic serviced by QPI link layer. These registers are in auxiliary PCI devices. This patch adds the auxiliary PCI devices to snbep_uncore_pci_ids and adds field definitions for the MATCH/MASK registers. Signed-off-by:
-
Yan, Zheng authored
The QPI uncore boxes have two pairs of MATCH/MASK registers that user to filter packet traffic serviced by QPI link layer. These registers are in auxiliary PCI devices. This patch changes the meaning of (struct pci_device_id)->driver_data. The first 8 bits are device index of the same uncore type, the second 8 bytes are uncore type index. Auxiliary PCI device's type is defined as UNCORE_EXTRA_PCI_DEV(0xff) Signed-off-by:
-
- 15 Aug, 2013 3 commits
-
-
Ingo Molnar authored
Merge branch 'tip/perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace into perf/core Pull perf optimizations from Steve Rostedt. Signed-off-by:
-
Ingo Molnar authored
Merge Linux 3.11-rc5, to sync up with the latest upstream fixes since -rc1. Signed-off-by: -
Ingo Molnar authored
Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: * Allow specifying syscalls in 'perf trace', a la strace. * Simplify symbol filtering by doing it at machine class level, from Adrian Hunter. * Add option to 'perf kvm' to print only events that exceed a specified time duration, from David Ahern. * 'perf sched' improvements, including removing some tracepoints that provide the same information as the PERF_RECORD_{FORK,EXIT} events. * Improve stack trace printing, from David Ahern. * Update documentation with live command, from David Ahern * Fix 'perf test' compile failure on do_sort_something, from David Ahern. * Improve robustness of topology parsing code, from Stephane Eranian. Signed-off-by:
-
- 14 Aug, 2013 6 commits
-
-
Arnaldo Carvalho de Melo authored
Similar to -e in strace, i.e. a comma separated list of syscall names to trace. 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-5zku7q5wug3103k1dzn3yy63@git.kernel.orgSigned-off-by:
-
Stephane Eranian authored
This patch improves the robustness of the build_cpu_topo() routine by allowing either the CPU parsing or the thread parsing to fail and yet get perf to produce some topology data which could be useful for the analysis. Without this patch, if the cpu parsing fails, the thread parsing is not attempted vice-versa. Signed-off-by:
-
David Ahern authored
Commit b55ae0a9 added code-reading.c which fails to compile on Fedora 16 with compiler version: $ gcc --version gcc (GCC) 4.6.3 20120306 (Red Hat 4.6.3-2) Failure message is: tests/code-reading.c: In function ‘do_sort_something’: tests/code-reading.c:305:13: error: stack protector not protecting local variables: variable length buffer [-Werror=stack-protector] cc1: all warnings being treated as errors make: *** [/tmp/junk/tests/code-reading.o] Error 1 make: *** Waiting for unfinished jobs.... v2: as Adrian noticed changed sizeof to ARRAY_SIZE Signed-off-by:
-
Oleg Nesterov authored
perf_trace_buf_prepare() + perf_trace_buf_submit(task => NULL) make no sense if hlist_empty(head). Change perf_trace_##call() to check ->perf_events beforehand and do nothing if it is empty. This removes the overhead for tasks without events associated with them. For example, "perf record -e sched:sched_switch -p1" attaches the counter(s) to the single task, but every task in system will do perf_trace_buf_prepare/submit() just to realize that it was not attached to this event. However, we can only do this if __task == NULL, so we also add the __builtin_constant_p(__task) check. With this patch "perf bench sched pipe" shows approximately 4% improvement when "perf record -p1" runs in parallel, many thanks to Steven for the testing. Link: http://lkml.kernel.org/r/20130806160847.GA2746@redhat.comTested-by:
Oleg Nesterov <oleg@redhat.com> Signed-off-by:
Steven Rostedt <rostedt@goodmis.org>
-
Oleg Nesterov authored
The next patch tries to avoid the costly perf_trace_buf_* calls when possible but there is a problem. We can only do this if __task == NULL, perf_tp_event(task != NULL) has the additional code for this case. Unfortunately, TP_perf_assign/__perf_xxx which changes the default values of __count/__task variables for perf_trace_buf_submit() is called "too late", after we already did perf_trace_buf_prepare(), and the optimization above can't work. So this patch simply embeds __perf_xxx() into TP_ARGS(), this way DECLARE_EVENT_CLASS() can use the result of assignments hidden in "args" right after ftrace_get_offsets_##call() which is mostly trivial. This allows us to have the fast-path "__task != NULL" check at the start, see the next patch. Link: http://lkml.kernel.org/r/20130806160844.GA2739@redhat.comTested-by:
-
Oleg Nesterov authored
To simplify the review of the next patches: 1. We are going to reimplent __perf_task/counter and embedd them into TP_ARGS(). expand TRACE_EVENT(sched_stat_runtime) into DECLARE_EVENT_CLASS() + DEFINE_EVENT(), this way they can use different TP_ARGS's. 2. Change perf_trace_##call() macro to do perf_fetch_caller_regs() right before perf_trace_buf_prepare(). This way it evaluates TP_ARGS() asap, the next patch explores this fact. Note: after 87f44bbc perf_trace_buf_prepare() doesn't need "struct pt_regs *regs", perhaps it makes sense to remove this argument. And perhaps we can teach perf_trace_buf_submit() to accept regs == NULL and do fetch_caller_regs(CALLER_ADDR1) in this case. 3. Cosmetic, but the typecast from "void*" buys nothing. It just adds the noise, remove it. Link: http://lkml.kernel.org/r/20130806160841.GA2736@redhat.comAcked-by:
-
- 12 Aug, 2013 18 commits
-
-
Adrian Hunter authored
Now that the symbol filter is recorded on the machine there is no need to pass it to thread__find_addr_map(). So remove it. Signed-off-by:
-
Adrian Hunter authored
Now that the symbol filter is recorded on the machine there is no need to pass it to thread__find_addr_location(). So remove it. Signed-off-by:
-
Adrian Hunter authored
Now that the symbol filter is recorded on the machine there is no need to pass it to perf_event__preprocess_sample(). So remove it. Signed-off-by:
-
Adrian Hunter authored
Take into use the machines symbol filter member. Signed-off-by:
-
Adrian Hunter authored
Member 'annotate_init' of struct perf_mem is unused. Remove it. Signed-off-by:
-
Adrian Hunter authored
Take into use the machines' symbol filter member. Signed-off-by:
-
Adrian Hunter authored
Take into use the machines symbol filter member. Signed-off-by:
-
Adrian Hunter authored
The symbol filter needs to be applied machine-wide, so add it to struct machine. Currently tools pass the symbol filter as a parameter to various map-related functions. However a need to load a map can occur anywhere in the code, at which point the filter is needed. Signed-off-by:
-
David Ahern authored
Any event can have RAW data attribute set. The intent of the function is to determine if the session has tracepoints, so check for the type of each event explicitly. Signed-off-by:
-
David Ahern authored
Option is used by upcoming timehist command. Signed-off-by:
-
David Ahern authored
Option is used by upcoming timehist command. Signed-off-by:
-
David Ahern authored
Make print options based on flags. Simplifies addition of more print options which is the subject of upcoming patches. Signed-off-by:
-
David Ahern authored
The PERF_RECORD_FORK event is already collected as part of the use of cmd_record and those events are analyzed as part of the libperf machinery. Using the fork tracepoint as well just duplicates the event load. Signed-off-by:
-
David Ahern authored
Event is not needed nor analyzed. Since perf-sched leverages perf-record to capture the sched data, we already capture task events like EXIT. Signed-off-by:
-
David Ahern authored
Not used in the function, so no sense in doing the lookup here. Thread look up will be done in the timehist command, and no sense in doing it twice. Signed-off-by:
-
David Ahern authored
Destroy argument is not necessary. If session is not returned to caller, then clean it up. Signed-off-by:
-
David Ahern authored
Update perf-kvm documentation with new live subcommand. Add -p/--pid option for perf-kvm-stat-report as well. Signed-off-by:
Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.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/1375926999-75129-2-git-send-email-dsahern@gmail.comSigned-off-by:
-
David Ahern authored
This is useful to spot high latency blips. It is normal for HLT reasons to have long exit times, so strip those from the duration check. v2: changed threshold to duration per acme's request Signed-off-by:
-
