- 04 Dec, 2013 12 commits
-
-
Adrian Hunter authored
When built without libelf, perf tools was failing to initialize a file descriptor, but nevertheless closing it. That sometimes resulted in the output being truncated because the stdout file descriptor got closed. Signed-off-by:
Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.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 <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1386166981-30197-1-git-send-email-adrian.hunter@intel.comSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Dongsheng Yang authored
As we have changed the default behavior of 'perf kvm' to --guest enabled, the parts of the man page that covers the 'record' subcommand are outdated. This patch updates it to show the correct output with --host/--guest/neither/both of them. Signed-off-by:
Dongsheng Yang <yangds.fnst@cn.fujitsu.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/3a3a9c1e05acb5a274d1d8369db5a4c6467d6276.1386197481.git.yangds.fnst@cn.fujitsu.comSigned-off-by:
-
Dongsheng Yang authored
As option --host and --guest request no input for it, there should not be a '=' after them in the man page sources. And --output expects a filename as the input, so there should be a '=' after it. This patch removes the needless '=' after --guest and --host, and adds a '=' after --output in perf-kvm.txt. Signed-off-by:
-
Dongsheng Yang authored
As the buildid is read from /sys/kernel/notes, then if we use perf kvm buildid-list with a perf data file captured by perf kvm record with --guestkallsyms and --guestmodules, there is no result in output. This patch add a explanation about it and add a limit of using perf kvm buildid-list. Signed-off-by:
-
Dongsheng Yang authored
Check for cpu_map__dummy_new() or cpu_map__new() to be called in perf_evlist__create_maps() is more complicated. This patch moves the checking work into target.h, combining two conditions and making perf_evlist__create_maps() more readable. Signed-off-by:
-
Dongsheng Yang authored
In machine__get_kernel_start_addr, the code, which is using machine->root_dir to build filename, works for both host and guests initialized from guestmount, as root_dir is set to "" for the host machine in the machine__init() function. So this patch remove the branch for machine__is_host. Signed-off-by:
-
Jiri Olsa authored
We use -fstack-protector-all option to enable stack protecting for all available functions. There's no reason for enabling -Wstack-protector to get warning for unprotected functions. Removing stackprotector feature check which was used to enable the -Wstack-protector option. Signed-off-by:
Jiri Olsa <jolsa@redhat.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.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> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1386076182-14484-2-git-send-email-jolsa@redhat.comSigned-off-by:
-
Adrian Hunter authored
Looking up an ip's source file name and line number does not succeed always. Current logic disables the lookup for a dso entirely on any failure. Change it so that disabling never happens if there has ever been a successful lookup for that dso but disable if the first 123 lookups fail. Signed-off-by:
-
Adrian Hunter authored
Currently, lookup of an ip's source file name and line number is done using the dso file name. Instead retain the file name used to lookup the dso's symbols and use that. Signed-off-by:
-
Adrian Hunter authored
Closng and re-opening for every lookup when using libbfd to lookup source file name and line number is very very slow. Instead keep the reference on struct dso. Signed-off-by:
-
Adrian Hunter authored
The asprintf library function is equivalent to malloc plus snprintf so use it because it is simpler. 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/tools improvements and fixes from Arnaldo Carvalho de Melo: * Honour -m option in 'trace', the tool was offering the option to set the mmap size, but wasn't using it when doing the actual mmap on the events file descriptors, fix from Jiri Olsa. * Correct the message in feature-libnuma checking, swowing the right devel package names for various distros, from Dongsheng Yang. * Polish 'readn' function and introduce its counterpart, 'writen', from Jiri Olsa. * Start moving timechart state from global variables to a 'perf_tool' derived 'timechart' struct. Signed-off-by:
Ingo Molnar <mingo@kernel.org>
-
- 02 Dec, 2013 12 commits
-
-
Jiri Olsa authored
Currently trace command supports '-m' option, but does not honours its value and keeps the default. Changing the perf_evlist__mmap function call to use the '-m' configured value. Signed-off-by:
David Ahern <dsahern@gmail.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.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/1385657842-8914-1-git-send-email-jolsa@redhat.comSigned-off-by:
-
Jiri Olsa authored
We're missing test-stackprotector-all.c in test-all check, adding it. Signed-off-by:
-
Dongsheng Yang authored
The package required for numa is named numactl-devel in Fedora or RHEL, and libnuma-devel in OpenSuSE, and libnuma-dev in Ubuntu. This patch corrects the package name in warning message in feature-libnuma checking. Signed-off-by:
Peter Hurley <peter@hurleysoftware.com> Cc: Peter Hurley <peter@hurleysoftware.com> Link: http://lkml.kernel.org/r/1385998008-6851-1-git-send-email-yangds.fnst@cn.fujitsu.comSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Removing another global variable. Cc: Adrian Hunter <adrian.hunter@intel.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@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stanislav Fomichev <stfomichev@yandex-team.ru> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-14rpuci11l2s0o01yta87kxe@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Removing another global variable. Cc: Adrian Hunter <adrian.hunter@intel.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@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stanislav Fomichev <stfomichev@yandex-team.ru> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-2akef3p9caau56itf5mugd2b@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Removing another global variable. This one tho would be better done by using the machine infrastructure, searching for the 'struct thread' with a pid, then using thread->priv, etc. TODO list material for now. Cc: Adrian Hunter <adrian.hunter@intel.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@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stanislav Fomichev <stfomichev@yandex-team.ru> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-yyfpudgjvr6mev4bue9u72a2@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
To avoid having all those global variables and to use the interface to event processing that is based on passing a 'perf_tool' struct that should be embedded in a per tool specific struct passed to all the sample processing callbacks. There are some more globals to move, next patches will do it. Cc: Adrian Hunter <adrian.hunter@intel.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@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stanislav Fomichev <stfomichev@yandex-team.ru> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-0iah65pq796ezbk5u1lzwy1k@git.kernel.orgSigned-off-by:
-
Jiri Olsa authored
Adding perf_data_file__write interface to centralize output to files. The function prototype is: ssize_t perf_data_file__write(struct perf_data_file *file, void *buf, size_t size); Returns number of bytes written or -1 in case of error. NOTE: Also indenting 'struct perf_data_file' members, no functional change done. Signed-off-by: -
Jiri Olsa authored
Adding 'writen' function as a synchronous wrapper for write syscall with following prototype: ssize_t writen(int fd, void *buf, size_t n) Returns the number of bytes written on success or -1 in case of err. Signed-off-by:
-
Jiri Olsa authored
Added a 'left' variable to make the flow clearer, and added a debug check for the return value - returning 'n' is more obvious. Added small comment for readn. Signed-off-by:
-
Jiri Olsa authored
Changing readn function return type to ssize_t because read returns ssize_t not int. Changing callers holding variable types as well. Signed-off-by:
-
Jiri Olsa authored
Unifying current 2 data output functions do_write_output and write_output into single one perf_record__write. Signed-off-by:
-
- 30 Nov, 2013 1 commit
-
-
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: * Make per-cpu mmaps the default in 'perf record', from Adrian Hunter. * Default -t/--thread 'perf record' option to no inheritance, from Adrian Hunter. * Make 'perf top -g' refer to callchains, for consistency with other tools, from David Ahern. * Skip ignored symbols while printing callchain, from David Ahern. * Print callchains and symbols if they exist in 'perf script', from David Ahern. * Remove thread summary coloring in 'perf trace', from Pekka Enberg. * zsh completion support, from Ramkumar Ramachandra. * 'perf timechart' improvements, including backtrace support, from Stanislav Fomichev. * Fix using kcore files stored in the buildid cache when doing report/annotate in non-live sessions, from Adrian Hunter * Minor 'timechart' cleanups. * Fix tags/TAGS targets rebuilding, from Jiri Olsa. * Add options to show comm, fork, exit and mmap PERF_RECORD_ events in 'perf script', from Namhyung Kim. Signed-off-by:
-
- 27 Nov, 2013 15 commits
-
-
Jiri Olsa authored
Once the tags/TAGS file is generated it's never rebuilt until it's removed by hand. The reason is that the Makefile does not treat tags/TAGS as targets but as files and thus won't rebuilt them once they are in place. Adding PHONY tags/TAGS targets into Makefile. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
The 'event' parameter _is_ used. Cc: Adrian Hunter <adrian.hunter@intel.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@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stanislav Fomichev <stfomichev@yandex-team.ru> Cc: Stephane Eranian <eranian@google.com> echo Link: http://lkml.kernel.org/n/tip-`ranpwd -l 24`@git.kernel.org Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Cc: Adrian Hunter <adrian.hunter@intel.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@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stanislav Fomichev <stfomichev@yandex-team.ru> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-jomi6mjv5zi9vsn4vmih5xps@git.kernel.orgSigned-off-by:
-
Stanislav Fomichev authored
Since b000c806 "tracing: Remove the extra 4 bytes of padding in events" removed padding bytes, perf timechart got out of sync with the kernel's trace_entry structure. Convert perf timechart to use dynamic fields offsets (via perf_evsel__intval) not relying on a hardcoded copy of fields layout from the kernel. Signed-off-by:
Stanislav Fomichev <stfomichev@yandex-team.ru> Acked-by:
Namhyung Kim <namhyung@kernel.org> Cc: Chia-I Wu <olvaffe@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/20131127104459.GB3309@stfomichev-desktopSigned-off-by:
-
Adrian Hunter authored
The logic was not looking in the buildid cache for kcore if the host kernel buildid did not match the recorded kernel buildid. This affects the non-live case i.e. the kernel has changed and we are looking at a special copy of kcore that we placed in the buildid cache (using "perf buildid-cache -v -k /proc/kcore") when the data was recorded. After this fix kernel symbols get resolved/annotated correctly. Signed-off-by:
-
Namhyung Kim authored
If --show-mmap-events option is given, also print internal MMAP and MMAP2 events. It would be helpful for debugging. $ perf script --show-mmap-events ... sleep 9486 [009] 3350640.335531: PERF_RECORD_MMAP 9486/9486: [0x400000(0x6000) @ 0]: x /usr/bin/sleep sleep 9486 [009] 3350640.335542: PERF_RECORD_MMAP 9486/9486: [0x3153a00000(0x223000) @ 0]: x /usr/lib64/ld-2.17.so sleep 9486 [009] 3350640.335553: PERF_RECORD_MMAP 9486/9486: [0x7fff8b5fe000(0x2000) @ 0x7fff8b5fe000]: x [vdso] sleep 9486 [009] 3350640.335643: PERF_RECORD_MMAP 9486/9486: [0x3153e00000(0x3c0000) @ 0]: x /usr/lib64/libc-2.17.so Signed-off-by:Frederic Weisbecker <fweisbec@gmail.com> Reviewed-by:
-
Namhyung Kim authored
If --show-task-events option is given, also print internal COMM, FORK and EXIT events. It would be helpful for debugging. $ perf script --show-task-events ... swapper 0 [009] 3350640.335261: sched:sched_switch: prev_comm=swapper/9 sleep 9486 [009] 3350640.335509: PERF_RECORD_COMM: sleep:9486 sleep 9486 [009] 3350640.335806: sched:sched_stat_runtime: comm=sleep pid=9486 firefox 2635 [003] 3350641.275896: PERF_RECORD_FORK(2635:9487):(2635:2635) firefox 2635 [003] 3350641.275896: sched:sched_process_fork: comm=firefox pid=2635 sleep 9486 [009] 3350641.336009: PERF_RECORD_EXIT(9486:9486):(9486:9486) Signed-off-by: -
David Ahern authored
The intent of perf-script is to dump the events and information in the file. H/W, S/W and raw events all dump callchains if they are present; might as well make that the default for tracepoints too. v2: Only add options for sym, dso and ip if callchains are present Signed-off-by:
-
David Ahern authored
Used in upcoming patches (perf sched timehist command). Signed-off-by:
-
David Ahern authored
Signed-off-by:
-
David Ahern authored
Allows list of idle symbols to be leveraged by other commands, such as the upcoming timehist command. Signed-off-by:
-
David Ahern authored
Allows a command to have a symbol_filter controlled by the user to skip certain functions in a backtrace. One example is to allow the user to reduce repeating patterns like: do_select core_sys_select sys_select to just sys_select when dumping callchains, consuming less real estate on the screen while still conveying the essential message - the process is in a select call. This option is leveraged by the upcoming timehist command. Signed-off-by: -
Stanislav Fomichev authored
Add -g flag to `perf timechart record` which saves callchain info in the perf.data. When generating SVG, add backtrace information to the figure details, so now it's possible to see which code path woke up the task and why some task went to sleep. Signed-off-by:
-
Stanislav Fomichev authored
If we don't want either power or task events we may use -T or -P with the `perf timechart record` command to filter out events while recording to keep perf.data small. Signed-off-by:
-
Stanislav Fomichev authored
Add titles to figures so we can run SVG interactively in Firefox and check event details in the tooltips. This also aids exploring SVG with Inkscape because when user clicks on one part of logical figure, all parts are selected. It's also possible to read titles with Inkscape in the object details. Signed-off-by:
-
