- 08 May, 2015 1 commit
-
-
Peter Zijlstra authored
Stephane asked about PERF_COUNT_SW_CPU_MIGRATIONS and I realized it was borken: > The problem is that the task isn't actually scheduled while its being > migrated (obviously), and if its not scheduled, the counters aren't > scheduled either, so there's no observing of the fact. > > A further problem with migrations is that many migrations happen from > softirq context, which is nested inside the 'random' task context of > whoemever happens to run at that time, similarly for the wakeup > migrations triggered from (soft)irq context. All those end up being > accounted in the task that's currently running, eg. your 'ls'. The below cures this by marking a task as migrated and accounting it on the subsequent sched_in(). Signed-off-by:
Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by:
Ingo Molnar <mingo@kernel.org>
-
- 06 May, 2015 1 commit
-
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo-3' 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: User visible changes: - Improve --filter support for 'perf probe', allowing using its arguments on other commands, as --add, --del, etc (Masami Hiramatsu) - Show warning when running 'perf kmem stat' on a unsuitable perf.data file, i.e. one with events that are not the ones required for the stat variant used (Namhyung Kim). Infrastructure changes: - Auxtrace support patches, paving the way to support Intel PT and BTS (Adrian Hunter) - hists browser (top, report) refactorings (Namhyung Kim) Signed-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by:
-
- 05 May, 2015 22 commits
-
-
Namhyung Kim authored
The has_children and unfolded fields don't belong to the struct map_symbol since they're used by the TUI only. Move those fields out of map_symbol since the struct is also used by other places. This will also help to compact the sizeof struct hist_entry. Signed-off-by:
Namhyung Kim <namhyung@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1429687101-4360-11-git-send-email-namhyung@kernel.org Link: http://lkml.kernel.org/r/1430837746-5439-1-git-send-email-namhyung@kernel.orgSigned-off-by:
-
Namhyung Kim authored
Now LEFT key press action can just use do_zoom_dso/thread() code to get out of the current filter. Signed-off-by:
Jiri Olsa <jolsa@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1429838133-14001-2-git-send-email-namhyung@kernel.orgSigned-off-by:
-
Namhyung Kim authored
The pstack_peek() is to get the topmost entry without removing it. Signed-off-by:
-
Namhyung Kim authored
Currently perf_evsel__hists_browse() function spins on a huge loop and handles many key actions. Since it's hard to read and modify, let's split it out into small helper functions. The add_XXX_opt() functions are to register popup menu item on the selected entry. When it adds an item, it also saves related data into struct popup_action and returns 1 so that it can increase the number of items (nr_options). With this change, we can simplify the code just to call selected callback function without considering various conditions. A callback function named do_XXX is called with saved data when the item is selected by user. No functional change intended. Signed-off-by:
Jiri Olsa <jolsa@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1429687101-4360-9-git-send-email-namhyung@kernel.orgSigned-off-by:
-
Namhyung Kim authored
Currently perf_evsel__hists_browse() function spins on a huge loop and handles many key actions. Since it's hard to read and modify, let's split it out into small helper functions. This patch introduces do_XXX() functions which corresponds to each goto label. This way we can call such functions both from key press actions and popup menu actions. No functional change intended. Signed-off-by:
-
Namhyung Kim authored
The perf_session_env is to save system informantion at the recording time to be refered in the hist browser. So it'd be better to keep in the struct hist_browser. This is a preparation to later change. Signed-off-by:
-
Namhyung Kim authored
The struct pstack is to save currently applied thread and/or dso filters in the browser. So it'd be better to keep in the struct hist_browser. This is a preparation to later change. Suggested-by:
Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by:
-
Namhyung Kim authored
The struct hist_browser_timer is to carry perf-top related info throughout the hist browser code. So it'd be better to keep in the struct hist_browser. This is a preparation to later change. Suggested-by:
-
Namhyung Kim authored
The options array saves strings for each popup menu item. The number of items can be vary according to the currently selected item. So it can leak some memory if it's exited from a small item. Fix it by freeing all items when loop terminates. Signed-off-by:
-
Namhyung Kim authored
The init_have_children is used to init callchain info only for TUI. So it'd be better to move it to the TUI-specific unnamed union member. Signed-off-by:
-
Namhyung Kim authored
Since perf diff only supports stdio output, TUI fields are only accessed from perf report (or perf top). So add a new unnamed union and move struct hist_entry_tui and those TUI-specific fields. Signed-off-by:
-
Namhyung Kim authored
Sometimes one can mistakenly run 'perf kmem stat' without running 'perf kmem record' before or with a different configuration like recording --slab and stat --page. Show a warning message like the one below to inform the user: # perf kmem stat --page --caller No page allocation events found. Have you run 'perf kmem record --page'? Signed-off-by:
Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/1430837572-31395-1-git-send-email-namhyung@kernel.orgSigned-off-by:
-
Masami Hiramatsu authored
To simplify the 'perf probe' command code, consolidate some similar functions and use command short-name for command classification, instead of separate booleans. Signed-off-by:
Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20150505152257.18790.41548.stgit@localhost.localdomainSigned-off-by:
-
Masami Hiramatsu authored
Since params.filter will be released in cleanup_params, we don't need to clear it in each command. Signed-off-by:
-
Masami Hiramatsu authored
This allows the user to pass the filter pattern directly to the --funcs option as below: ---- # ./perf probe -F *kmalloc __kmalloc devm_kmalloc mempool_kmalloc sg_kmalloc sock_kmalloc ---- We previously needed to use the --filter option for that. Signed-off-by:
-
Masami Hiramatsu authored
This makes perf-probe --del option to accept filter rules not only simple glob pattern. This simplifies the code and improve the flexibility. E.g. if we remove 2 different pattern events, we need 2 -d options. ---- # ./perf probe -d vfs\* -d malloc Removed event: probe_libc:malloc Removed event: probe:vfs_read ---- This allows you to joint the 2 patterns with '|'. ---- # ./perf probe -d 'vfs*|malloc' Removed event: probe:vfs_read Removed event: probe_libc:malloc ---- Signed-off-by: -
Adrian Hunter authored
Add a new option and support for Instruction Tracing Snapshot Mode. When the new option is selected, no AUX area tracing data is captured until a signal (SIGUSR2) is received. Signed-off-by:
Adrian Hunter <adrian.hunter@intel.com> Acked-by:
-
Adrian Hunter authored
Add support for making snapshots of AUX area tracing data. Signed-off-by:
-
Adrian Hunter authored
Add support for the PERF_RECORD_ITRACE_START event type. This event can be used to determine the pid and tid that are running when Instruction Tracing starts. Generally that information would come from a sched_switch event but, at the start, no sched_switch events may yet have been recorded. Signed-off-by:
-
Adrian Hunter authored
Add support for the PERF_RECORD_AUX event type. PERF_RECORD_AUX is a new kernel event that records when new data lands in the AUX buffer. Currently it is assumed that AUX data follows the same ring buffer conventions used by the perf events buffer, and consequently the AUX event is not processed during recording. It is processed during session processing so that the information in the 'flags' member is made available. The format of PERF_RECORD_AUX is outlined in the linux/perf_events.h header file. The 'flags' are also enumerated. Intel PT and Intel BTS use the flag named PERF_AUX_FLAG_TRUNCATED to determine if data has been lost because the buffer became full as perf was not able to empty it fast enough. Signed-off-by:
-
Adrian Hunter authored
Add AUX area tracing option 'x' to synthesize events for transactions. This will be used by Intel PT to synthesize an event record for each TSX start, commit or abort. Signed-off-by:
-
Adrian Hunter authored
Add build option NO_AUXTRACE to exclude compiling support for AUX area tracing. Support for both recording and processing is excluded and by implication any future additions such as Intel PT and Intel BTS will also not be compiled in with this option. Signed-off-by:
-
- 04 May, 2015 16 commits
-
-
Adrian Hunter authored
We need to include all buildids when a perf.data file contains AUX area tracing data because we do not decode the trace for that purpose because it would take too long. Signed-off-by:
-
Adrian Hunter authored
Add an index of AUX area tracing events within a perf.data file. perf record uses a special user event PERF_RECORD_FINISHED_ROUND to enable sorting of events in chunks instead of having to sort all events altogether. AUX area tracing events contain data that can span back to the very beginning of the recording period. i.e. they do not obey the rules of PERF_RECORD_FINISHED_ROUND. By adding an index, AUX area tracing events can be found in advance and the PERF_RECORD_FINISHED_ROUND approach works as usual. The index is recorded with the auxtrace feature in the perf.data file. A session reads the index but does not process it. An AUX area decoder can queue all the AUX area data in advance using auxtrace_queues__process_index() or otherwise process the index in some custom manner. Signed-off-by:
-
Adrian Hunter authored
Unwittingly the itrace options for perf report ended up below the Overhead Calculation section. Move it back with the other options. Signed-off-by:
-
Namhyung Kim authored
Currently perf kmem command will select --slab if neither --slab nor --page is given for backward compatibility. Add kmem.default config option to select the default value ('page' or 'slab'). # cat ~/.perfconfig [kmem] default = page # perf kmem stat SUMMARY (page allocator) ======================== Total allocation requests : 1,518 [ 6,096 KB ] Total free requests : 1,431 [ 5,748 KB ] Total alloc+freed requests : 1,330 [ 5,344 KB ] Total alloc-only requests : 188 [ 752 KB ] Total free-only requests : 101 [ 404 KB ] Total allocation failures : 0 [ 0 KB ] ... Signed-off-by: -
Namhyung Kim authored
Save libtraceevent output and print it in the header. # perf kmem stat --page --caller # # GFP flags # --------- # 00000010: NI: GFP_NOIO # 000000d0: K: GFP_KERNEL # 00000200: NWR: GFP_NOWARN # 000084d0: K|R|Z: GFP_KERNEL|GFP_REPEAT|GFP_ZERO # 000200d2: HU: GFP_HIGHUSER # 000200da: HUM: GFP_HIGHUSER_MOVABLE # 000280da: HUM|Z: GFP_HIGHUSER_MOVABLE|GFP_ZERO # 002084d0: K|R|Z|NT: GFP_KERNEL|GFP_REPEAT|GFP_ZERO|GFP_NOTRACK # 0102005a: NF|HW|M: GFP_NOFS|GFP_HARDWALL|GFP_MOVABLE --------------------------------------------------------------------------------------------------------- Total alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------------------- 60 | 15 | 0 | UNMOVABL | K|R|Z|NT | pte_alloc_one 40 | 10 | 0 | MOVABLE | HUM|Z | handle_mm_fault 24 | 6 | 0 | MOVABLE | HUM | do_wp_page 24 | 6 | 0 | UNMOVABL | K | __pollwait ... Requested-by:Joonsoo Kim <js1304@gmail.com> Suggested-by:
Minchan Kim <minchan@kernel.org> Signed-off-by:
-
Namhyung Kim authored
Currently 'perf kmem stat --page' shows total (page) allocation stat by default, but sometimes one might want to see live (total alloc-only) requests/pages only. The new --live option does this by subtracting freed allocation from the stat. E.g.: # perf kmem stat --page SUMMARY (page allocator) ======================== Total allocation requests : 988,858 [ 4,045,368 KB ] Total free requests : 886,484 [ 3,624,996 KB ] Total alloc+freed requests : 885,969 [ 3,622,628 KB ] Total alloc-only requests : 102,889 [ 422,740 KB ] Total free-only requests : 515 [ 2,368 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 172,173 3,083 806,686 . . 1 284 . . . . 2 6,124 58 . . . 3 114 335 . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . 1 . . 10 . . . . . # perf kmem stat --page --live SUMMARY (page allocator) ======================== Total allocation requests : 988,858 [ 4,045,368 KB ] Total free requests : 886,484 [ 3,624,996 KB ] Total alloc+freed requests : 885,969 [ 3,622,628 KB ] Total alloc-only requests : 102,889 [ 422,740 KB ] Total free-only requests : 515 [ 2,368 KB ] Total allocation failures : 0 [ 0 KB ] Order Unmovable Reclaimable Movable Reserved CMA/Isolated ----- ------------ ------------ ------------ ------------ ------------ 0 2,214 3,025 97,156 . . 1 59 . . . . 2 19 58 . . . 3 23 335 . . . 4 . . . . . 5 . . . . . 6 . . . . . 7 . . . . . 8 . . . . . 9 . . . . . 10 . . . . . # Signed-off-by: -
Namhyung Kim authored
Add new sort keys for page: page, order, migtype, gfp - existing 'bytes', 'hit' and 'callsite' sort keys also work for page. Note that -s/--sort option should be preceded by either of --slab or --page option to determine where the sort keys applies. Now it properly groups and sorts allocation stats - so same page/caller with different order/migtype/gfp will be printed on a different line. # perf kmem stat --page --caller -l 10 -s order,hit ----------------------------------------------------------------------------- Total alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite ----------------------------------------------------------------------------- 64 | 4 | 2 | RECLAIM | 00285250 | new_slab 50,144 | 12,536 | 0 | MOVABLE | 0102005a | __page_cache_alloc 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 40 | 10 | 0 | MOVABLE | 000280da | handle_mm_fault 28 | 7 | 0 | UNMOVABL | 000000d0 | __pollwait 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 8 | 2 | 0 | UNMOVABL | 000084d0 | __pud_alloc ... | ... | ... | ... | ... | ... ----------------------------------------------------------------------------- Signed-off-by: -
Namhyung Kim authored
It is 'perf kmem' support caller statistics for page. Unlike slab case, the tracepoints in page allocator don't provide callsite info. So it records with callchain and extracts callsite info. Note that the callchain contains several memory allocation functions which has no meaning for users. So skip those functions to get proper callsites. I used following regex pattern to skip the allocator functions: ^_?_?(alloc|get_free|get_zeroed)_pages? This gave me a following list of functions: # perf kmem record --page sleep 3 # perf kmem stat --page -v ... alloc func: __get_free_pages alloc func: get_zeroed_page alloc func: alloc_pages_exact alloc func: __alloc_pages_direct_compact alloc func: __alloc_pages_nodemask alloc func: alloc_page_interleave alloc func: alloc_pages_current alloc func: alloc_pages_vma alloc func: alloc_page_buffers alloc func: alloc_pages_exact_nid ... The output looks mostly same as --alloc (I also added callsite column to that) but groups entries by callsite. Currently, the order, migrate type and GFP flag info is for the last allocation and not guaranteed to be same for all allocations from the callsite. --------------------------------------------------------------------------------------------- Total_alloc (KB) | Hits | Order | Mig.type | GFP flags | Callsite --------------------------------------------------------------------------------------------- 1,064 | 266 | 0 | UNMOVABL | 000000d0 | __pollwait 52 | 13 | 0 | UNMOVABL | 002084d0 | pte_alloc_one 44 | 11 | 0 | MOVABLE | 000280da | handle_mm_fault 20 | 5 | 0 | MOVABLE | 000200da | do_cow_fault 20 | 5 | 0 | MOVABLE | 000200da | do_wp_page 16 | 4 | 0 | UNMOVABL | 000084d0 | __pmd_alloc 16 | 4 | 0 | UNMOVABL | 00000200 | __tlb_remove_page 12 | 3 | 0 | UNMOVABL | 000084d0 | __pud_alloc 8 | 2 | 0 | UNMOVABL | 00000010 | bio_copy_user_iov 4 | 1 | 0 | UNMOVABL | 000200d2 | pipe_write 4 | 1 | 0 | MOVABLE | 000280da | do_wp_page 4 | 1 | 0 | UNMOVABL | 002084d0 | pgd_alloc --------------------------------------------------------------------------------------------- Signed-off-by: -
Masami Hiramatsu authored
Currently, perf-probe --list option ignores given event filter. ---- # ./perf probe -l vfs\* probe:vfs_read (on vfs_read@ksrc/linux-3/fs/read_write.c) probe_libc:malloc (on __libc_malloc@malloc/malloc.c in /usr/lib64/libc-2.17.so) ---- This changes --list option to accept the event filter argument as below. ---- # ./perf probe -l vfs\* probe:vfs_read (on vfs_read@ksrc/linux-3/fs/read_write.c) # ./perf probe -l \*libc:\* probe_libc:malloc (on __libc_malloc@malloc/malloc.c in /usr/lib64/libc-2.17.so) ---- Signed-off-by: -
Masami Hiramatsu authored
Accept multiple filter options. Each filters are combined by logical-or. E.g. --filter abc* --filter *def is same as --filter abc*|*def Signed-off-by:
-
Masami Hiramatsu authored
Add strfilter__string to recover rules string from strfilter. This will be good for debugging. Signed-off-by:
-
Masami Hiramatsu authored
Add strfilter__or/and to append additional rules to existing strfilter. Signed-off-by:
-
Naveen N. Rao authored
Currently, perf probe considers patterns including a '.' to be a file. However, this causes problems on powerpc ABIv1 where all functions have a leading '.': $ perf probe -F | grep schedule_timeout_interruptible .schedule_timeout_interruptible $ perf probe .schedule_timeout_interruptible Semantic error :File always requires line number or lazy pattern. Error: Command Parse Error. Fix this: - by checking the probe pattern in more detail, and - skipping leading dot if one exists when creating/deleting events. Signed-off-by:Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Reviewed-by:
Srikar Dronamraju <srikar@linux.vnet.ibm.com> Acked-by:
-
Namhyung Kim authored
The YYLTYPE_IS_TRIVIAL is defined in the Build file, but unlike pmu-bison.c, gcc complained about it for parse-events-bison.c: CC util/parse-events-bison.o In file included from util/parse-events.y:16: util/parse-events-bison.h:101:1: error: "YYLTYPE_IS_TRIVIAL" redefined <command-line>: error: this is the location of the previous definition make[3]: *** [util/parse-events-bison.o] Error 1 Comments from Jiri Olsa: "Reason is the parse error handling that was added just recently: it adds YYLTYPE type (which is not present in pmu-bison.h), so YYLTYPE_IS_TRIVIAL gets redefined, which is ok in F20 that handle the error via '-w' option, but it's not ok for RHEL6 where the '-w' does not work for this kind of error." Signed-off-by: -
Naveen N. Rao authored
Add a debug message to indicate that the build id didn't match. Signed-off-by:
-
Adrian Hunter authored
Add support for decoding an AUX area assuming it contains instruction tracing data. Signed-off-by:
-
