Em Tue, Jan 05, 2021 at 08:55:27AM -0500, Liang, Kan escreveu:
>
>
> On 12/19/2020 3:56 PM, Arnaldo Carvalho de Melo wrote:
> > Em Wed, Dec 16, 2020 at 10:58:01AM -0800, kan.li...@linux.intel.com
> > escreveu:
> > > From: Kan Liang
> > >
> &g
Em Wed, Dec 30, 2020 at 02:28:52PM +0100, Jiri Olsa escreveu:
> On Wed, Dec 30, 2020 at 02:28:02PM +0100, Jiri Olsa wrote:
> > On Wed, Dec 30, 2020 at 10:03:37AM +0100, Jiri Olsa wrote:
> > > On Tue, Dec 29, 2020 at 11:28:35PM +, Qais Yousef wrote:
> > > > Hi Jiri
> > > >
> > > > On 12/29/20
Em Tue, Dec 29, 2020 at 04:23:47PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Tue, Dec 29, 2020 at 04:18:48PM -0300, Arnaldo Carvalho de Melo escreveu:
> > Em Tue, Dec 29, 2020 at 07:11:12PM +, Song Liu escreveu:
> > > > On Dec 29, 2020, at 10:48 AM, Arn
Em Tue, Dec 29, 2020 at 04:18:48PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Tue, Dec 29, 2020 at 07:11:12PM +, Song Liu escreveu:
> > > On Dec 29, 2020, at 10:48 AM, Arnaldo Carvalho de Melo
> > > wrote:
> > > I'll check this one to get a patch that
Em Tue, Dec 29, 2020 at 07:11:12PM +, Song Liu escreveu:
>
>
> > On Dec 29, 2020, at 10:48 AM, Arnaldo Carvalho de Melo
> > wrote:
> >
> > Em Tue, Dec 29, 2020 at 06:42:18PM +, Song Liu escreveu:
> >>
> >>
> >>> On Dec
Em Tue, Dec 29, 2020 at 06:42:18PM +, Song Liu escreveu:
>
>
> > On Dec 29, 2020, at 7:15 AM, Arnaldo Carvalho de Melo
> > wrote:
> >
> > Em Mon, Dec 28, 2020 at 11:43:25PM +, Song Liu escreveu:
> >>
> >>
> >>> On Dec 2
Em Tue, Dec 29, 2020 at 05:14:12PM +, Song Liu escreveu:
> > On Dec 29, 2020, at 3:48 AM, Arnaldo Carvalho de Melo
> > wrote:
> > Em Tue, Dec 29, 2020 at 04:01:41PM +0900, Namhyung Kim escreveu:
> >> On Tue, Dec 29, 2020 at 2:41 AM Song Liu wrote:
> >&
Em Mon, Dec 28, 2020 at 11:43:25PM +, Song Liu escreveu:
>
>
> > On Dec 28, 2020, at 12:11 PM, Arnaldo Carvalho de Melo
> > wrote:
> >
> > Em Mon, Dec 28, 2020 at 09:40:53AM -0800, Song Liu escreveu:
> >> Introduce perf-stat -b option, whi
Em Wed, Dec 16, 2020 at 06:05:56PM +0900, Namhyung Kim escreveu:
> Currently it parses the /proc file everytime it opens a file in the
> cgroupfs. Save the last result to avoid it (assuming it won't be
> changed between the accesses).
Which is the most likely case, but can't we use something
Em Tue, Dec 29, 2020 at 04:01:41PM +0900, Namhyung Kim escreveu:
> On Tue, Dec 29, 2020 at 2:41 AM Song Liu wrote:
> > BPF programs are useful in perf to profile BPF programs. BPF skeleton is
> I'm having difficulties understanding the first sentence - looks like a
> recursion. :) So do you
Em Mon, Dec 28, 2020 at 09:40:53AM -0800, Song Liu escreveu:
> Introduce perf-stat -b option, which counts events for BPF programs, like:
>
> [root@localhost ~]# ~/perf stat -e ref-cycles,cycles -b 254 -I 1000
> 1.487903822115,200 ref-cycles
> 1.487903822
lar expression;
> * Added Masami's Ack tag for patch 03.
>
> [1] https://lore.kernel.org/patchwork/cover/1356212/
>
This one made it into 5.11
> Arnaldo Carvalho de Melo (1):
> perf probe: Fix memory leak in synthesize_sdt_probe_command()
These were now merged in perf/cor
Em Mon, Dec 14, 2020 at 11:54:57AM +0100, Jiri Olsa escreveu:
> Adding --buildid-mmap option to enable build id in mmap2 events.
> It will only work if there's kernel support for that and it disables
> build id cache (implies --no-buildid).
>
> It's also possible to enable it permanently via
Em Mon, Dec 14, 2020 at 11:54:45AM +0100, Jiri Olsa escreveu:
> Adding support to carry build id data in mmap2 event.
>
> The build id data replaces maj/min/ino/ino_generation
> fields, which are also used to identify map's binary,
> so it's ok to replace them with build id data:
>
> union {
>
through the source to "remember" that was e.g. 4000.
Thanks, applied.
- Arnaldo
> Signed-off-by: Hans-Peter Nilsson
> Cc: Peter Zijlstra
> Cc: Ingo Molnar
> Cc: Arnaldo Carvalho de Melo
> Cc: Mark Rutland
> Cc: Alexander Shishkin
> Cc: Jiri Olsa
> Cc: Na
Em Tue, Dec 15, 2020 at 12:55:03PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Mon, Dec 14, 2020 at 11:54:48AM +0100, Jiri Olsa escreveu:
> > Adding support to decompress file before reading build id.
> >
> > Adding filename__read_build_id and change its current
> >
, msr-index and
powerpc and s390 syscall tables.
Signed-off-by: Arnaldo Carvalho de Melo
Test results in the signed tag at:
https://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git/tag/?h=perf-tools-2020-12-24
Arnaldo
Em Wed, Dec 23, 2020 at 02:39:04PM +0800, Leo Yan escreveu:
> Arm64 ELF section '.note.stapsdt' uses string format "-4@[sp, NUM]" if
> the probe is to access data in stack, e.g. below is an example for
> dumping Arm64 ELF file and shows the argument format:
>
> Arguments: -4@[sp, 12] -4@[sp, 8]
Em Thu, Dec 24, 2020 at 08:54:04PM +0800, Jin Yao escreveu:
> Uncore becomes die-scope on Xeon Cascade Lake-AP and perf has supported
> --per-die aggregation yet.
>
> One issue is found in check_per_pkg() for uncore events running on
> AP system. On cascade Lake-AP, we have:
>
> S0-D0
> S0-D1
>
Em Thu, Dec 24, 2020 at 08:24:06PM +0800, Tian Tao escreveu:
> since commit c93e4aeed1be
> ("Makefile.extrawarn: remove -Wnested-externs warning")
> has removed this check, so it's not needed here.
But the above commit is for the kernel, scripts/Makefile.extrawarn isn't
included in tools/perf/
Em Wed, Dec 23, 2020 at 11:17:47PM +0100, Jiri Olsa escreveu:
> On Fri, Dec 04, 2020 at 11:48:36AM +, John Garry wrote:
> > On 03/12/2020 15:39, Jiri Olsa wrote:
> >
> > +
> >
> > > On Thu, Nov 26, 2020 at 04:13:16PM +0200, James Clark wrote:
> > > > Changes since v5:
> > > >* Fix test
Em Wed, Dec 23, 2020 at 08:54:59PM +0530, Naveen N. Rao escreveu:
> Arnaldo Carvalho de Melo wrote:
> > Em Fri, Dec 18, 2020 at 08:08:56PM +0530, Naveen N. Rao escreveu:
> > > Hi Arnaldo,
> > >
> > > Arnaldo Carvalho de Melo wrote:
> > > > E
Em Sat, Dec 19, 2020 at 05:56:39PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Wed, Dec 16, 2020 at 10:58:01AM -0800, kan.li...@linux.intel.com escreveu:
> > From: Kan Liang
> >
> > Add option --data-page-size in "perf mem" to record/report data page
> >
Em Tue, Dec 22, 2020 at 09:11:31AM +0800, Jin Yao escreveu:
> The event default list includes the most common events which are widely
> used by users. But with -e option, the current perf only counts the events
> assigned by -e option. Users may want to collect some extra events with
> the default
Em Fri, Dec 18, 2020 at 08:08:56PM +0530, Naveen N. Rao escreveu:
> Hi Arnaldo,
>
> Arnaldo Carvalho de Melo wrote:
> > Em Fri, Dec 18, 2020 at 08:26:59AM -0300, Arnaldo Carvalho de Melo escreveu:
> > > Em Fri, Dec 18, 2020 at 03:59:23PM +0800, Tiezhu Yang escreve
in --for-each-cgroup.
pipe mode:
- Allow to use stdio functions for pipe mode.
- Support 'perf report's' --header-only for pipe mode.
- Support pipe mode display in 'perf evlist'.
Documentation:
- Update information about CAP_PERFMON.
Signed-off-by: Arnaldo Carvalho de Melo
Test
Em Wed, Dec 16, 2020 at 10:58:01AM -0800, kan.li...@linux.intel.com escreveu:
> From: Kan Liang
>
> Add option --data-page-size in "perf mem" to record/report data page
> size.
>
> Here are some examples.
> perf mem --phys-data --data-page-size report -D
So I stopped at this cset, it isn't
Em Fri, Dec 18, 2020 at 08:26:59AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Fri, Dec 18, 2020 at 03:59:23PM +0800, Tiezhu Yang escreveu:
> > This silences the following tools/perf/ build warning:
> > Warning: Kernel ABI header at
> > 'tools/perf/arch/powerpc/entry
Em Fri, Dec 18, 2020 at 03:59:24PM +0800, Tiezhu Yang escreveu:
> This silences the following tools/perf/ build warning:
> Warning: Kernel ABI header at
> 'tools/perf/arch/s390/entry/syscalls/syscall.tbl' differs from latest version
> at 'arch/s390/kernel/syscalls/syscall.tbl'
>
> Just make
Em Fri, Dec 18, 2020 at 03:59:23PM +0800, Tiezhu Yang escreveu:
> This silences the following tools/perf/ build warning:
> Warning: Kernel ABI header at
> 'tools/perf/arch/powerpc/entry/syscalls/syscall.tbl' differs from latest
> version at 'arch/powerpc/kernel/syscalls/syscall.tbl'
Hi Ravi,
Em Mon, Dec 07, 2020 at 03:25:07PM -0500, Liang, Kan escreveu:
>
>
> On 12/7/2020 12:07 PM, Arnaldo Carvalho de Melo wrote:
> > Em Mon, Nov 30, 2020 at 09:27:53AM -0800, kan.li...@linux.intel.com
> > escreveu:
> > > From: Kan Liang
> &
Em Wed, Dec 16, 2020 at 11:30:47AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Wed, Dec 16, 2020 at 07:14:02PM +0800, Jiaxun Yang escreveu:
> >
> >
> > 在 2020/12/16 下午6:05, Tiezhu Yang 写道:
> > > Hi,
> > >
> > > In the current upstream
Em Wed, Dec 16, 2020 at 07:14:02PM +0800, Jiaxun Yang escreveu:
>
>
> 在 2020/12/16 下午6:05, Tiezhu Yang 写道:
> > Hi,
> >
> > In the current upstream mainline kernel, perf record --call-graph dwarf
> > is not supported for architecture mips64. I find the following related
> > patches about this
Em Wed, Dec 16, 2020 at 11:41:10AM +, John Garry escreveu:
> On 10/12/2020 19:57, John Garry wrote:
> > Obviously I never tested building for one of test architectures which
> > does not use PMU events - sorry!
> Just wondering if you have had any more problems here? Shall I send a formal
>
Em Wed, Dec 16, 2020 at 09:16:40AM +0900, Masami Hiramatsu escreveu:
> On Thu, 26 Nov 2020 14:26:03 -0300
Arnaldo Carvalho de Melo wrote:
> > Em Thu, Nov 26, 2020 at 09:21:25AM +0900, Masami Hiramatsu escreveu:
> > > On Wed, 25 Nov 2020 14:27:55 -0300 Arnaldo Carvalho de
Em Tue, Dec 15, 2020 at 05:18:38PM +0100, Jiri Olsa escreveu:
> On Tue, Dec 15, 2020 at 01:03:32PM -0300, Arnaldo Carvalho de Melo wrote:
> > I see it, but why not use the more natural ' ' space to separate the
> > command from its arguments? Just like in a bash command line, say
Em Tue, Dec 15, 2020 at 04:59:11PM +0100, Jiri Olsa escreveu:
> On Tue, Dec 15, 2020 at 12:23:43PM -0300, Arnaldo Carvalho de Melo wrote:
> > Em Thu, Dec 10, 2020 at 09:43:30PM +0100, Jiri Olsa escreveu:
> > > Adding new control events to display all evlist events.
> >
Em Sat, Dec 12, 2020 at 11:43:55AM +0100, Jiri Olsa escreveu:
> Allow perf daemon to send SIGUSR2 to all running sessions:
>
> # perf daemon
> [1:364758] perf record -m 10M -e cycles -o /opt/perfdata/1/perf.data
> --overwrite --switch-output -a
> [2:364759] perf record -m 10M -e sched:* -o
Em Tue, Dec 15, 2020 at 04:24:20PM +0100, Jiri Olsa escreveu:
> On Tue, Dec 15, 2020 at 12:14:13PM -0300, Arnaldo Carvalho de Melo wrote:
> > Em Thu, Dec 10, 2020 at 09:43:29PM +0100, Jiri Olsa escreveu:
> > > Adding new control events to enable/disable specific event.
> >
Em Mon, Dec 14, 2020 at 11:54:48AM +0100, Jiri Olsa escreveu:
> Adding support to decompress file before reading build id.
>
> Adding filename__read_build_id and change its current
> versions to read_build_id.
>
> Shutting down stderr output of perf list in the shell test:
> 82: Check open
Em Mon, Dec 14, 2020 at 11:54:55AM +0100, Jiri Olsa escreveu:
> Adding --debuginfod option to specify debuginfod url and
> support to do that through config file as well.
>
> Use following in ~/.perfconfig file:
>
> [buildid-cache]
> debuginfod=http://192.168.122.174:8002
I was going to try
Em Mon, Dec 14, 2020 at 11:54:45AM +0100, Jiri Olsa escreveu:
> Adding support to carry build id data in mmap2 event.
>
> The build id data replaces maj/min/ino/ino_generation
> fields, which are also used to identify map's binary,
> so it's ok to replace them with build id data:
>
> union {
>
Em Mon, Dec 14, 2020 at 11:54:43AM +0100, Jiri Olsa escreveu:
> Moving stack_map_get_build_id into lib with
> declaration in linux/buildid.h header:
>
> int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id);
>
> This function returns build id for given struct vm_area_struct.
Em Sat, Dec 12, 2020 at 11:43:56AM +0100, Jiri Olsa escreveu:
> Allow 'perf daemon' to stop daemon process:
>
> # perf daemon --stop
> perf daemon is exciting
It looks exciting, yes, a nice functionality! ;-)
- Arnaldo
> Signed-off-by: Jiri Olsa
> ---
>
Em Sat, Dec 12, 2020 at 11:43:57AM +0100, Jiri Olsa escreveu:
> Add 'lock' file under daemon base and flock it, so only one
> perf daemon can run on top of it.
>
> # perf daemon --config ./config.daemon
> # perf daemon --config ./config.daemon
> failed: another perf daemon (pid 369675) owns
Em Sat, Dec 12, 2020 at 11:43:58AM +0100, Jiri Olsa escreveu:
> Setup control fifos for session and add --control
> option to session arguments.
You're stating what this does, not why this is useful, can you add a
paragraph to that effect?
- Arnaldo
> Use can list control fifos with:
>
>#
Em Sat, Dec 12, 2020 at 11:43:54AM +0100, Jiri Olsa escreveu:
> Adding daemon command that allows to run record sessions
> on background. Each session represents one perf record
> process and is configured in config file.
>
> Example:
>
> # cat config.daemon
> [daemon]
> base=/opt/perfdata
Em Sat, Dec 12, 2020 at 11:43:53AM +0100, Jiri Olsa escreveu:
> Add interface to load config set from custom file
> by using perf_config_set__new_file function.
>
> It will be used in perf daemon command to process
> custom config file.
The naming may be misleading, as this is not _setting_ the
Em Sat, Dec 12, 2020 at 11:43:51AM +0100, Jiri Olsa escreveu:
> Allow to set debug output file via new debug_set_file function.
>
> It's called during perf startup in perf_debug_setup to set stderr
> file as default and any perf command can set it later to different
> file.
>
> It will be used
Em Sat, Dec 12, 2020 at 11:43:52AM +0100, Jiri Olsa escreveu:
> Allow to display time in perf debug output via new
> debug_set_display_time function.
>
> It will be used in perf daemon command to get verbose
> output into log file.
>
> The debug time format is:
>
> [2020-12-03
Em Tue, Dec 15, 2020 at 10:49:59PM +0900, Namhyung Kim escreveu:
> Hello,
>
> On Tue, Dec 15, 2020 at 10:35 AM Tiezhu Yang wrote:
> >
> > DWARF register mappings have not been defined for some architectures,
> > at least for mips, so we can print an error message and then return
> > directly
Em Thu, Dec 10, 2020 at 09:43:30PM +0100, Jiri Olsa escreveu:
> Adding new control events to display all evlist events.
>
> The interface string for control file is 'evlist' and
> 'evlist-verbose'.
Can't we pass args to such commands?
Then its just one event, i.e. "evlist", and -v can be passed
Em Thu, Dec 10, 2020 at 09:43:28PM +0100, Jiri Olsa escreveu:
> Adding interface to enable/disable single event in the
> evlist based on its name. It will be used later in new
> control enable/disable interface.
>
> Keeping the evlist::enabled true when one or more events
> are enabled so the
Em Thu, Dec 10, 2020 at 09:43:29PM +0100, Jiri Olsa escreveu:
> Adding new control events to enable/disable specific event.
> The interface string for control file are:
>
> 'enable-'
> 'disable-'
Wwy do we have "enable-" as the "tag" for this?
Also is it possible to use "enable sched:*" and
Em Mon, Dec 14, 2020 at 07:04:30PM -0800, Andi Kleen escreveu:
> > My first thought was: Why not have a 'perf iiostat' subcommand?
> Same would apply to a lot of options in perf stat.
> I guess you could add some aliases to "perf" that give shortcuts
> for common perf stat command lines.
Em Tue, Dec 15, 2020 at 09:35:31AM +0800, Tiezhu Yang escreveu:
> DWARF register mappings have not been defined for some architectures,
> at least for mips, so we can print an error message and then return
> directly when use '--call-graph dwarf'.
>
> E.g. without this patch:
Thanks, applied.
Em Mon, Dec 14, 2020 at 08:56:55PM +0800, Tiezhu Yang escreveu:
> DWARF register mappings have not been defined for some architectures,
> at least for mips, so we can print an error message and then return
> directly when use '--call-graph dwarf'.
>
> E.g. without this patch:
>
> [root@linux
Em Thu, Dec 10, 2020 at 12:03:35PM +0300, Alexander Antonov escreveu:
> Mode is intended to provide four I/O performance metrics in MB per each
> IIO stack:
> - Inbound Read: I/O devices below IIO stack read from the host memory
> - Inbound Write: I/O devices below IIO stack write to the host
Em Mon, Dec 14, 2020 at 12:00:35AM +0100, Jiri Olsa escreveu:
> On Thu, Dec 10, 2020 at 03:13:02PM +0900, Namhyung Kim wrote:
> > Likewise, perf evlist command should print event attributes by reading
> > PERF_RECORD_HEADER_ATTR records.
> >
> > Before:
> > $ perf record -o- true | ./perf
Em Mon, Dec 14, 2020 at 12:00:19AM +0100, Jiri Olsa escreveu:
> On Thu, Dec 10, 2020 at 03:13:01PM +0900, Namhyung Kim wrote:
> > The --header-only checks file header and prints the feature data. But
> > as pipe mode doesn't have it in the header it prints almost nothing.
> > Change it to process
Em Thu, Dec 10, 2020 at 09:20:42PM +0300, Alexei Budankov escreveu:
>
> On 10.12.2020 21:06, Jiri Olsa wrote:
> > On Thu, Dec 10, 2020 at 05:24:30PM +0100, Jiri Olsa wrote:
> >> On Mon, Dec 07, 2020 at 08:02:20PM +0300, Alexei Budankov wrote:
> >>> Hi,
> >>>
> >>> On 06.12.2020 20:05, Jiri Olsa
Em Thu, Dec 10, 2020 at 05:44:51PM +, John Garry escreveu:
>
> > > > > > > + evsel_name = cmd_data +
> > > > > > > sizeof(EVLIST_CTL_CMD_ENABLE_EVSEL_TAG) - 1;
> > >
> > > > > > It makes sense to check that evsel_name still points
> > > > > > into cmd_data buffer
Em Thu, Dec 10, 2020 at 02:19:03PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Thu, Dec 10, 2020 at 02:15:03PM -0300, Arnaldo Carvalho de Melo escreveu:
> > Em Thu, Dec 10, 2020 at 05:24:30PM +0100, Jiri Olsa escreveu:
> > > On Mon, Dec 07, 2020 at 08:02:20PM +0300, Ale
Em Thu, Dec 10, 2020 at 02:15:03PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Thu, Dec 10, 2020 at 05:24:30PM +0100, Jiri Olsa escreveu:
> > On Mon, Dec 07, 2020 at 08:02:20PM +0300, Alexei Budankov wrote:
> > > On 06.12.2020 20:05, Jiri Olsa wrote:
> > >
Em Thu, Dec 10, 2020 at 05:24:30PM +0100, Jiri Olsa escreveu:
> On Mon, Dec 07, 2020 at 08:02:20PM +0300, Alexei Budankov wrote:
> > Hi,
> >
> > On 06.12.2020 20:05, Jiri Olsa wrote:
> > > Adding new control events to enable/disable specific event.
> > > The interface string for control file are:
Em Sat, Dec 05, 2020 at 09:12:56AM +0900, Masami Hiramatsu escreveu:
> On Fri, 04 Dec 2020 15:04:03 -
> "tip-bot2 for Masami Hiramatsu" wrote:
>
> > The following commit has been merged into the x86/urgent branch of tip:
> >
> > Commit-ID: 9dc23f960adb9ce410ef835b32a2398fdb09c828
> >
Em Sun, Dec 06, 2020 at 10:02:50AM +0100, Borislav Petkov escreveu:
> ( drop stable@ )
>
> On Sun, Dec 06, 2020 at 12:53:25PM +0900, Masami Hiramatsu wrote:
> > On Sat, 5 Dec 2020 11:17:04 +0100
> > Borislav Petkov wrote:
> >
> > > On Sat, Dec 05, 2020 at 09:12:56AM +0900, Masami Hiramatsu
Em Tue, Dec 08, 2020 at 10:32:33PM +0530, Ravi Bangoria escreveu:
> On 12/8/20 8:13 PM, Thomas Richter wrote:
> > On 12/7/20 5:35 PM, Arnaldo Carvalho de Melo wrote:
> > > Em Tue, Nov 24, 2020 at 03:04:53PM +0530, Ravi Bangoria escreveu:
> > > > On 11/1
Em Tue, Dec 08, 2020 at 03:43:17PM +0100, Thomas Richter escreveu:
> On 12/7/20 5:35 PM, Arnaldo Carvalho de Melo wrote:
> > Em Tue, Nov 24, 2020 at 03:04:53PM +0530, Ravi Bangoria escreveu:
> >>
> >>
> >> On 11/19/20 7:20 PM, Kajol Jain wrote:
> >>&
Em Tue, Dec 08, 2020 at 10:16:44AM -0800, Song Liu escreveu:
> This set introduces perf-stat -b option to count events for BPF programs.
> This is similar to bpftool-prog-profile. But perf-stat makes it much more
> flexible.
>
> Changes v2 => v3:
> 1. Small fixes in Makefile.perf and
Em Fri, Dec 04, 2020 at 07:10:14PM +0800, John Garry escreveu:
> Currently printing metricgroups for core- or uncore-based events matched
> by CPUID is supported.
>
> Extend this for system events.
>
> Signed-off-by: John Garry
> Acked-by: Kajol Jain
> ---
> tools/perf/util/metricgroup.c | 64
Em Fri, Dec 04, 2020 at 07:10:12PM +0800, John Garry escreveu:
> Support for metric expressions using aliases which cover multiple PMUs is
> broken. Consider the following test metric expression:
>
> "MetricExpr": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE *
> UNC_CBO_XSNP_RESPONSE.MISS_EVICTION"
>
>
ours, next time please test
this and provide a similar error message.
- Arnaldo
commit 2044fec7fcc6070b09f9b6a67922b0b9e4295dba
Author: Arnaldo Carvalho de Melo
Date: Mon Dec 7 14:04:05 2020 -0300
perf evsel: Emit warning about kernel not supporting the data page size
sample_type bit
Em Mon, Nov 30, 2020 at 09:27:52AM -0800, kan.li...@linux.intel.com escreveu:
> From: Kan Liang
>
> To get the changes in:
>
>commit 8d97e71811aa ("perf/core: Add PERF_SAMPLE_DATA_PAGE_SIZE")
>commit 995f088efebe ("perf/core: Add support for
> PERF_SAMPLE_CODE_PAGE_SIZE")
>
> This
Em Fri, Nov 27, 2020 at 03:45:40PM +0800, Zheng Zengkai escreveu:
> Ping...
Thanks, applied.
- Arnaldo
> > On Fri, Jul 03, 2020 at 05:33:44PM +0800, Zheng Zengkai wrote:
> > > when using perf record option '-I' or '--user-regs='
> > > along with argument '?' to list available register names,
>
Em Tue, Nov 24, 2020 at 03:04:53PM +0530, Ravi Bangoria escreveu:
>
>
> On 11/19/20 7:20 PM, Kajol Jain wrote:
> > Commit ed21d6d7c48e6e ("perf tests: Add test for PE binary format support")
> > adds a WINDOWS EXE file named tests/pe-file.exe, which is
> > examined by the test case 'PE file
Em Sun, Dec 06, 2020 at 06:05:19PM +0100, Jiri Olsa escreveu:
> Adding new control event to display all evlist events.
>
> The interface string for control file is 'list'. When
> received, perf will scan and print current evlist into
> perf record terminal.
>
> Example session:
>
> terminal
Em Fri, Dec 04, 2020 at 12:08:36AM +0100, Jiri Olsa escreveu:
> We're missing -lcap in test-all.bin target, so in case it's
> the only library missing (if more are missing test-all.bin
> fails anyway), we will falsely claim that we detected it and
> fail build, like:
Thanks, applied.
- Arnaldo
If I use:
module_param_named(bpf.sig_enforce, sig_enforce, bool_enable_only, 0644);
It explodes and if I do as before:
module_param(sig_enforce, sig_enforce, bool_enable_only, 0644);
Then it ends up as 'syscall.sig_enforce'.
The closest I got so far was:
commit
Em Tue, Dec 01, 2020 at 10:25:17AM -0300, Arnaldo Carvalho de Melo escreveu:
> Hi Masami,
> Any idea why listing the source code doesn't work while simply
> adding the probe works?
> [root@seventh ~]# perf probe -L verify_pkcs7_signature
> Specified source line is not f
Hi Masami,
Any idea why listing the source code doesn't work while simply
adding the probe works?
[root@seventh ~]# perf probe verify_pkcs7_signature
Added new event:
probe:verify_pkcs7_signature (on verify_pkcs7_signature)
You can now use it in all perf tools, such as:
perf
801163749305260 0xc70 [0x40]: PERF_RECORD_SAMPLE(IP, 0x2):
> > 51956/51956: 0xaa6571f0 period: 145785 addr: 0
> >... user regs: mask 0x30 ABI 64-bit
> > x40x006c
> >.... x50x00100101
> > ... thread: ls:51956
>
Em Thu, Nov 19, 2020 at 08:48:57AM -0800, Ian Rogers escreveu:
> On Thu, Nov 19, 2020 at 7:25 AM Kajol Jain wrote:
> > Result in power9 platform after this patch:
> > [command]# ./perf test 10
> > 10: PMU events :
> > 10.1: PMU event table
Em Fri, Nov 27, 2020 at 01:14:04PM +0900, Namhyung Kim escreveu:
> It calculates IPC from the cycles and instruction counts and compares
> it with the shadow stat for both global aggregation (default) and no
> aggregation mode.
>
> $ perf stat -a -A -e cycles,instructions sleep 1
>
>
when not asked to in 'perf record'.
- Use proper CPU for shadow stats in 'perf stat'.
- Update copy of libbpf's hashmap.c, silencing tools/perf build warning.
- Fix return value in 'perf diff'.
Signed-off-by: Arnaldo Carvalho de Melo
https://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git
Em Fri, Nov 27, 2020 at 02:48:55PM +0900, Masami Hiramatsu escreveu:
> Since some gcc generates a broken DWARF which lacks DW_AT_declaration
> attribute from the subprogram DIE of function prototype.
> (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=97060)
>
> So, in addition to the
Em Fri, Nov 27, 2020 at 01:14:03PM +0900, Namhyung Kim escreveu:
> Currently perf stat shows some metrics (like IPC) for defined events.
> But when no aggregation mode is used (-A option), it shows incorrect
> values since it used a value from a different cpu.
>
> Before:
>
> $ perf stat -aA
Em Fri, Nov 27, 2020 at 04:45:57PM +0100, Jiri Olsa escreveu:
> On Fri, Nov 27, 2020 at 02:43:56PM +0900, Namhyung Kim wrote:
> > It didn't check the tool->cgroup_events bit which is set when
> > the --all-cgroups option is given. Without it, samples will not have
> > cgroup info so no reason to
Em Fri, Nov 27, 2020 at 02:22:02PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Fri, Nov 27, 2020 at 10:35:37PM +0900, Namhyung Kim escreveu:
> > On Tue, Nov 24, 2020 at 7:37 PM Zhen Lei wrote:
> > > An appropriate return value should be set on the failed path.
> > &
Em Fri, Nov 27, 2020 at 10:35:37PM +0900, Namhyung Kim escreveu:
> Hello,
>
> On Tue, Nov 24, 2020 at 7:37 PM Zhen Lei wrote:
> >
> > An appropriate return value should be set on the failed path.
> >
> > Reported-by: Hulk Robot
> > Signed-off-by: Zhen Lei
>
> Acked-by: Namhyung Kim
Thanks,
Em Thu, Nov 26, 2020 at 06:00:23PM +0100, Jiri Olsa escreveu:
> Adding support to specify perf data file as -a option file
> argument,
>
> If the file is detected to be perf data file, it is processed
> and all dso objects with sample hit are stored to the build
> id cache.
Would be interesting
Em Thu, Nov 26, 2020 at 06:00:22PM +0100, Jiri Olsa escreveu:
> Adding build_id_cache__add function as core function
> that adds file into build id database. It will be
> set from another callers in following changes.
Thanks, applied.
- Arnaldo
> Acked-by: Ian Rogers
> Signed-off-by: Jiri
Em Thu, Nov 26, 2020 at 06:00:20PM +0100, Jiri Olsa escreveu:
> Adding __perf_session__cache_build_ids function as an
> interface for caching sessions build ids with callback
> function and its data pointer.
Thanks, applied.
- Arnaldo
> Signed-off-by: Jiri Olsa
> ---
>
Em Thu, Nov 26, 2020 at 06:00:19PM +0100, Jiri Olsa escreveu:
> Using machine__for_each_dso in perf_session__cache_build_ids,
> so we can reuse perf_session__cache_build_ids with different
> callback in following changes.
Thanks, applied.
- Arnaldo
> Signed-off-by: Jiri Olsa
> ---
>
Em Thu, Nov 26, 2020 at 06:00:21PM +0100, Jiri Olsa escreveu:
> Adding is_perf_data function that returns true if
> the given path is perf data file. It will be used
> in following patches.
Thanks, applied.
- Arnaldo
> Acked-by: Ian Rogers
> Signed-off-by: Jiri Olsa
> ---
>
Em Thu, Nov 26, 2020 at 06:00:13PM +0100, Jiri Olsa escreveu:
> Currently we don't check on kernel's vmlinux the same way as
> we do for normal binaries, but we either look for kallsyms
> file in build id database or check on known vmlinux locations
> (plus some other optional paths).
>
> This
Em Thu, Nov 26, 2020 at 06:00:12PM +0100, Jiri Olsa escreveu:
> Using struct extra_kernel_map in machine__process_kernel_mmap_event,
> to pass mmap details. This way we can used single function for all 3
> mmap versions.
Thanks, applied.
- Arnaldo
> Acked-by: Ian Rogers
> Signed-off-by: Jiri
Em Thu, Nov 26, 2020 at 06:00:10PM +0100, Jiri Olsa escreveu:
> Adding support to decompress file before reading build id.
>
> Adding filename__read_build_id and change its current
> versions to read_build_id.
>
> Shutting down stderr output of perf list in the shell test:
> 82: Check open
Em Thu, Nov 26, 2020 at 06:00:11PM +0100, Jiri Olsa escreveu:
> When adding new build id link we fail if the link is already
> there. Adding check for existing link and output debug message
> that the build id is already linked.
Thanks, applied.
- Arnaldo
> Signed-off-by: Jiri Olsa
> ---
>
Em Thu, Nov 26, 2020 at 06:00:09PM +0100, Jiri Olsa escreveu:
> Factor filename__decompress from decompress_kmodule function.
> It can decompress files with compressions supported in perf -
> xz and gz, the support needs to be compiled in.
>
> It will to be used in following changes to get build
301 - 400 of 34296 matches
Mail list logo