Re: perf tools: remove option --tail-synthesize ?
> On Nov 21, 2018, at 5:50 PM, Wangnan (F) wrote: > > > > On 2018/11/21 21:11, Arnaldo Carvalho de Melo wrote: >> Em Wed, Nov 21, 2018 at 07:45:28AM +, Song Liu escreveu: >>> Hi, >>> >>> I found perf-record --tail-synthesize without --overwrite breaks symbols >>> for perf-script, perf-report, etc. For example: >>> >>> [root@]# ~/perf record -ag --tail-synthesize -- sleep 1 >>> [ perf record: Woken up 1 times to write data ] >>> [ perf record: Captured and wrote 1.129 MB perf.data (3531 samples) ] >>> [root@]# ~/perf script | head >>> swapper 0 [000] 1250675.051971: 1 cycles:ppp: >>>81009e15 [unknown] ([unknown]) >>>81196b19 [unknown] ([unknown]) >>>81196579 [unknown] ([unknown]) >>>81110ca7 [unknown] ([unknown]) >>>81a01f4a [unknown] ([unknown]) >>>81a017bf [unknown] ([unknown]) >>>8180e17a [unknown] ([unknown]) >>> >>> perf-record with --overwrite does NOT have this issue. >>> >>> After digging into this, I found this issue is introduced by commit >>> a73e24d240bc136619d382b1268f34d75c9d25ce. >>> >>> Reverting this commit does fix this issue. However, on a second thought, >>> I feel it is probably better just drop --tail-synthesize, as it doesn't >>> make much sense without --overwrite. All we need is to do tail_synthesize >>> when --overwrite is set. >>> > > Some cases we use --overwrite without --tail-synthesize. How about setting > --tail-synthesize when selecting --overwrite by default, throw a warning > when --overwrite is not set and leave a --no-tail-synthesize option? > --overwrite implies --tail-synthesize. So with --overwrite, it is always tail-synthesize. Do we really need --overwrite and --no-tail-synthesize? If not, we can probably just drop --tail-synthesize (or mark it as deprecated)? Thanks, Song
Re: perf tools: remove option --tail-synthesize ?
> On Nov 21, 2018, at 5:50 PM, Wangnan (F) wrote: > > > > On 2018/11/21 21:11, Arnaldo Carvalho de Melo wrote: >> Em Wed, Nov 21, 2018 at 07:45:28AM +, Song Liu escreveu: >>> Hi, >>> >>> I found perf-record --tail-synthesize without --overwrite breaks symbols >>> for perf-script, perf-report, etc. For example: >>> >>> [root@]# ~/perf record -ag --tail-synthesize -- sleep 1 >>> [ perf record: Woken up 1 times to write data ] >>> [ perf record: Captured and wrote 1.129 MB perf.data (3531 samples) ] >>> [root@]# ~/perf script | head >>> swapper 0 [000] 1250675.051971: 1 cycles:ppp: >>>81009e15 [unknown] ([unknown]) >>>81196b19 [unknown] ([unknown]) >>>81196579 [unknown] ([unknown]) >>>81110ca7 [unknown] ([unknown]) >>>81a01f4a [unknown] ([unknown]) >>>81a017bf [unknown] ([unknown]) >>>8180e17a [unknown] ([unknown]) >>> >>> perf-record with --overwrite does NOT have this issue. >>> >>> After digging into this, I found this issue is introduced by commit >>> a73e24d240bc136619d382b1268f34d75c9d25ce. >>> >>> Reverting this commit does fix this issue. However, on a second thought, >>> I feel it is probably better just drop --tail-synthesize, as it doesn't >>> make much sense without --overwrite. All we need is to do tail_synthesize >>> when --overwrite is set. >>> > > Some cases we use --overwrite without --tail-synthesize. How about setting > --tail-synthesize when selecting --overwrite by default, throw a warning > when --overwrite is not set and leave a --no-tail-synthesize option? > --overwrite implies --tail-synthesize. So with --overwrite, it is always tail-synthesize. Do we really need --overwrite and --no-tail-synthesize? If not, we can probably just drop --tail-synthesize (or mark it as deprecated)? Thanks, Song
Re: perf tools: remove option --tail-synthesize ?
On Thu, Nov 22, 2018 at 09:50:15AM +0800, Wangnan (F) wrote: > > > On 2018/11/21 21:11, Arnaldo Carvalho de Melo wrote: > > Em Wed, Nov 21, 2018 at 07:45:28AM +, Song Liu escreveu: > >> Hi, > >> > >> I found perf-record --tail-synthesize without --overwrite breaks symbols > >> for perf-script, perf-report, etc. For example: > >> > >> [root@]# ~/perf record -ag --tail-synthesize -- sleep 1 > >> [ perf record: Woken up 1 times to write data ] > >> [ perf record: Captured and wrote 1.129 MB perf.data (3531 samples) ] > >> [root@]# ~/perf script | head > >> swapper 0 [000] 1250675.051971: 1 cycles:ppp: > >> 81009e15 [unknown] ([unknown]) > >> 81196b19 [unknown] ([unknown]) > >> 81196579 [unknown] ([unknown]) > >> 81110ca7 [unknown] ([unknown]) > >> 81a01f4a [unknown] ([unknown]) > >> 81a017bf [unknown] ([unknown]) > >> 8180e17a [unknown] ([unknown]) > >> > >> perf-record with --overwrite does NOT have this issue. > >> > >> After digging into this, I found this issue is introduced by commit > >> a73e24d240bc136619d382b1268f34d75c9d25ce. > >> > >> Reverting this commit does fix this issue. However, on a second thought, > >> I feel it is probably better just drop --tail-synthesize, as it doesn't > >> make much sense without --overwrite. All we need is to do tail_synthesize > >> when --overwrite is set. > >> > > Some cases we use --overwrite without --tail-synthesize. How about setting > --tail-synthesize when selecting --overwrite by default, throw a warning > when --overwrite is not set and leave a --no-tail-synthesize option? sounds good to me thanks, jirka
Re: perf tools: remove option --tail-synthesize ?
On Thu, Nov 22, 2018 at 09:50:15AM +0800, Wangnan (F) wrote: > > > On 2018/11/21 21:11, Arnaldo Carvalho de Melo wrote: > > Em Wed, Nov 21, 2018 at 07:45:28AM +, Song Liu escreveu: > >> Hi, > >> > >> I found perf-record --tail-synthesize without --overwrite breaks symbols > >> for perf-script, perf-report, etc. For example: > >> > >> [root@]# ~/perf record -ag --tail-synthesize -- sleep 1 > >> [ perf record: Woken up 1 times to write data ] > >> [ perf record: Captured and wrote 1.129 MB perf.data (3531 samples) ] > >> [root@]# ~/perf script | head > >> swapper 0 [000] 1250675.051971: 1 cycles:ppp: > >> 81009e15 [unknown] ([unknown]) > >> 81196b19 [unknown] ([unknown]) > >> 81196579 [unknown] ([unknown]) > >> 81110ca7 [unknown] ([unknown]) > >> 81a01f4a [unknown] ([unknown]) > >> 81a017bf [unknown] ([unknown]) > >> 8180e17a [unknown] ([unknown]) > >> > >> perf-record with --overwrite does NOT have this issue. > >> > >> After digging into this, I found this issue is introduced by commit > >> a73e24d240bc136619d382b1268f34d75c9d25ce. > >> > >> Reverting this commit does fix this issue. However, on a second thought, > >> I feel it is probably better just drop --tail-synthesize, as it doesn't > >> make much sense without --overwrite. All we need is to do tail_synthesize > >> when --overwrite is set. > >> > > Some cases we use --overwrite without --tail-synthesize. How about setting > --tail-synthesize when selecting --overwrite by default, throw a warning > when --overwrite is not set and leave a --no-tail-synthesize option? sounds good to me thanks, jirka
Re: perf tools: remove option --tail-synthesize ?
On 2018/11/21 21:11, Arnaldo Carvalho de Melo wrote: > Em Wed, Nov 21, 2018 at 07:45:28AM +, Song Liu escreveu: >> Hi, >> >> I found perf-record --tail-synthesize without --overwrite breaks symbols >> for perf-script, perf-report, etc. For example: >> >> [root@]# ~/perf record -ag --tail-synthesize -- sleep 1 >> [ perf record: Woken up 1 times to write data ] >> [ perf record: Captured and wrote 1.129 MB perf.data (3531 samples) ] >> [root@]# ~/perf script | head >> swapper 0 [000] 1250675.051971: 1 cycles:ppp: >> 81009e15 [unknown] ([unknown]) >> 81196b19 [unknown] ([unknown]) >> 81196579 [unknown] ([unknown]) >> 81110ca7 [unknown] ([unknown]) >> 81a01f4a [unknown] ([unknown]) >> 81a017bf [unknown] ([unknown]) >> 8180e17a [unknown] ([unknown]) >> >> perf-record with --overwrite does NOT have this issue. >> >> After digging into this, I found this issue is introduced by commit >> a73e24d240bc136619d382b1268f34d75c9d25ce. >> >> Reverting this commit does fix this issue. However, on a second thought, >> I feel it is probably better just drop --tail-synthesize, as it doesn't >> make much sense without --overwrite. All we need is to do tail_synthesize >> when --overwrite is set. >> Some cases we use --overwrite without --tail-synthesize. How about setting --tail-synthesize when selecting --overwrite by default, throw a warning when --overwrite is not set and leave a --no-tail-synthesize option? Thank you. >> Thoughts? > > Wang, wdyt? > > - Arnaldo >
Re: perf tools: remove option --tail-synthesize ?
On 2018/11/21 21:11, Arnaldo Carvalho de Melo wrote: > Em Wed, Nov 21, 2018 at 07:45:28AM +, Song Liu escreveu: >> Hi, >> >> I found perf-record --tail-synthesize without --overwrite breaks symbols >> for perf-script, perf-report, etc. For example: >> >> [root@]# ~/perf record -ag --tail-synthesize -- sleep 1 >> [ perf record: Woken up 1 times to write data ] >> [ perf record: Captured and wrote 1.129 MB perf.data (3531 samples) ] >> [root@]# ~/perf script | head >> swapper 0 [000] 1250675.051971: 1 cycles:ppp: >> 81009e15 [unknown] ([unknown]) >> 81196b19 [unknown] ([unknown]) >> 81196579 [unknown] ([unknown]) >> 81110ca7 [unknown] ([unknown]) >> 81a01f4a [unknown] ([unknown]) >> 81a017bf [unknown] ([unknown]) >> 8180e17a [unknown] ([unknown]) >> >> perf-record with --overwrite does NOT have this issue. >> >> After digging into this, I found this issue is introduced by commit >> a73e24d240bc136619d382b1268f34d75c9d25ce. >> >> Reverting this commit does fix this issue. However, on a second thought, >> I feel it is probably better just drop --tail-synthesize, as it doesn't >> make much sense without --overwrite. All we need is to do tail_synthesize >> when --overwrite is set. >> Some cases we use --overwrite without --tail-synthesize. How about setting --tail-synthesize when selecting --overwrite by default, throw a warning when --overwrite is not set and leave a --no-tail-synthesize option? Thank you. >> Thoughts? > > Wang, wdyt? > > - Arnaldo >
Re: perf tools: remove option --tail-synthesize ?
> On Nov 21, 2018, at 2:47 AM, Jiri Olsa wrote: > > On Wed, Nov 21, 2018 at 07:45:28AM +, Song Liu wrote: >> Hi, >> >> I found perf-record --tail-synthesize without --overwrite breaks symbols >> for perf-script, perf-report, etc. For example: >> >> [root@]# ~/perf record -ag --tail-synthesize -- sleep 1 >> [ perf record: Woken up 1 times to write data ] >> [ perf record: Captured and wrote 1.129 MB perf.data (3531 samples) ] >> [root@]# ~/perf script | head >> swapper 0 [000] 1250675.051971: 1 cycles:ppp: >>81009e15 [unknown] ([unknown]) >>81196b19 [unknown] ([unknown]) >>81196579 [unknown] ([unknown]) >>81110ca7 [unknown] ([unknown]) >>81a01f4a [unknown] ([unknown]) >>81a017bf [unknown] ([unknown]) >>8180e17a [unknown] ([unknown]) >> >> perf-record with --overwrite does NOT have this issue. > > actualy I think that now it works properly, if you turn on > task and mmap events, you'll see the samples get resolved > right after aux events are processed: > > [root@krava perf]# ./perf script --show-info --show-task-events > --show-mmap-events > ... > swapper 0 [007] 620566.187355: 64821 cycles:ppp: > ab0b4d7c [unknown] ([unknown]) > aba01b1f [unknown] ([unknown]) > ab75d567 [unknown] ([unknown]) > ab0e1f56 [unknown] ([unknown]) > ab0e216f [unknown] ([unknown]) > ab050dc7 [unknown] ([unknown]) > abd5 [unknown] ([unknown]) > > swapper 0 [000] 0.00: PERF_RECORD_MMAP -1/0: > [0xab00(0x152c8000) @ 0xab00]: x > [kernel.kallsyms]_text > swapper 0 [000] 0.00: PERF_RECORD_MMAP -1/0: > [0xc02c8000(0x4000) @ 0]: x > /lib/modules/4.18.17-200.fc28.x86_64/kernel/drivers/thermal/int340x_thermal/int3403_thermal.ko.xz > swapper 0 [000] 0.00: PERF_RECORD_MMAP -1/0: > [0xc02cd000(0x4000) @ 0]: x > /lib/modules/4.18.17-200.fc28.x86_64/kernel/drivers/thermal/intel_pch_thermal.ko.xz > ... > ext4-rsv-conver 0 [000] 0.00: PERF_RECORD_COMM: > ext4-rsv-conver:989/989 > perf 20063 [005] 620566.187438:1056712 cycles:ppp: > ab1f605d filemap_map_pages+0x9d > (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) > ab23aaa8 __handle_mm_fault+0x1018 > (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) > ab23ae7a handle_mm_fault+0xda > (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) > ab06ac90 __do_page_fault+0x240 > (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) > ab06af62 do_page_fault+0x32 > (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) > aba010ee page_fault+0x1e > (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) > ... > > if you record with --overwrite and --tail-synthesize the aux events > will go to the top of the perf.data, so all's good > >> >> After digging into this, I found this issue is introduced by commit >> a73e24d240bc136619d382b1268f34d75c9d25ce. > > right, we got rid of that, because it will store the 'current/live' > server mmaps for report/script, which is not what you want Agreed. >> Reverting this commit does fix this issue. However, on a second thought, >> I feel it is probably better just drop --tail-synthesize, as it doesn't >> make much sense without --overwrite. All we need is to do tail_synthesize >> when --overwrite is set. >> >> Thoughts? > > maybe we should make --tail-synthesize non optionable for --overwrite, > and get rid of that option completely.. Wang, any idea? > > but definitelly not allow that for non overwrite > --overwrite forces tail-synthesize already: if (record.opts.overwrite) record.opts.tail_synthesize = true; So I guess all we need is to remove --tail-synthesize. If we all agree with this direction, I can draft patch for it. Thanks, Song
Re: perf tools: remove option --tail-synthesize ?
> On Nov 21, 2018, at 2:47 AM, Jiri Olsa wrote: > > On Wed, Nov 21, 2018 at 07:45:28AM +, Song Liu wrote: >> Hi, >> >> I found perf-record --tail-synthesize without --overwrite breaks symbols >> for perf-script, perf-report, etc. For example: >> >> [root@]# ~/perf record -ag --tail-synthesize -- sleep 1 >> [ perf record: Woken up 1 times to write data ] >> [ perf record: Captured and wrote 1.129 MB perf.data (3531 samples) ] >> [root@]# ~/perf script | head >> swapper 0 [000] 1250675.051971: 1 cycles:ppp: >>81009e15 [unknown] ([unknown]) >>81196b19 [unknown] ([unknown]) >>81196579 [unknown] ([unknown]) >>81110ca7 [unknown] ([unknown]) >>81a01f4a [unknown] ([unknown]) >>81a017bf [unknown] ([unknown]) >>8180e17a [unknown] ([unknown]) >> >> perf-record with --overwrite does NOT have this issue. > > actualy I think that now it works properly, if you turn on > task and mmap events, you'll see the samples get resolved > right after aux events are processed: > > [root@krava perf]# ./perf script --show-info --show-task-events > --show-mmap-events > ... > swapper 0 [007] 620566.187355: 64821 cycles:ppp: > ab0b4d7c [unknown] ([unknown]) > aba01b1f [unknown] ([unknown]) > ab75d567 [unknown] ([unknown]) > ab0e1f56 [unknown] ([unknown]) > ab0e216f [unknown] ([unknown]) > ab050dc7 [unknown] ([unknown]) > abd5 [unknown] ([unknown]) > > swapper 0 [000] 0.00: PERF_RECORD_MMAP -1/0: > [0xab00(0x152c8000) @ 0xab00]: x > [kernel.kallsyms]_text > swapper 0 [000] 0.00: PERF_RECORD_MMAP -1/0: > [0xc02c8000(0x4000) @ 0]: x > /lib/modules/4.18.17-200.fc28.x86_64/kernel/drivers/thermal/int340x_thermal/int3403_thermal.ko.xz > swapper 0 [000] 0.00: PERF_RECORD_MMAP -1/0: > [0xc02cd000(0x4000) @ 0]: x > /lib/modules/4.18.17-200.fc28.x86_64/kernel/drivers/thermal/intel_pch_thermal.ko.xz > ... > ext4-rsv-conver 0 [000] 0.00: PERF_RECORD_COMM: > ext4-rsv-conver:989/989 > perf 20063 [005] 620566.187438:1056712 cycles:ppp: > ab1f605d filemap_map_pages+0x9d > (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) > ab23aaa8 __handle_mm_fault+0x1018 > (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) > ab23ae7a handle_mm_fault+0xda > (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) > ab06ac90 __do_page_fault+0x240 > (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) > ab06af62 do_page_fault+0x32 > (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) > aba010ee page_fault+0x1e > (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) > ... > > if you record with --overwrite and --tail-synthesize the aux events > will go to the top of the perf.data, so all's good > >> >> After digging into this, I found this issue is introduced by commit >> a73e24d240bc136619d382b1268f34d75c9d25ce. > > right, we got rid of that, because it will store the 'current/live' > server mmaps for report/script, which is not what you want Agreed. >> Reverting this commit does fix this issue. However, on a second thought, >> I feel it is probably better just drop --tail-synthesize, as it doesn't >> make much sense without --overwrite. All we need is to do tail_synthesize >> when --overwrite is set. >> >> Thoughts? > > maybe we should make --tail-synthesize non optionable for --overwrite, > and get rid of that option completely.. Wang, any idea? > > but definitelly not allow that for non overwrite > --overwrite forces tail-synthesize already: if (record.opts.overwrite) record.opts.tail_synthesize = true; So I guess all we need is to remove --tail-synthesize. If we all agree with this direction, I can draft patch for it. Thanks, Song
Re: perf tools: remove option --tail-synthesize ?
Em Wed, Nov 21, 2018 at 07:45:28AM +, Song Liu escreveu: > Hi, > > I found perf-record --tail-synthesize without --overwrite breaks symbols > for perf-script, perf-report, etc. For example: > > [root@]# ~/perf record -ag --tail-synthesize -- sleep 1 > [ perf record: Woken up 1 times to write data ] > [ perf record: Captured and wrote 1.129 MB perf.data (3531 samples) ] > [root@]# ~/perf script | head > swapper 0 [000] 1250675.051971: 1 cycles:ppp: > 81009e15 [unknown] ([unknown]) > 81196b19 [unknown] ([unknown]) > 81196579 [unknown] ([unknown]) > 81110ca7 [unknown] ([unknown]) > 81a01f4a [unknown] ([unknown]) > 81a017bf [unknown] ([unknown]) > 8180e17a [unknown] ([unknown]) > > perf-record with --overwrite does NOT have this issue. > > After digging into this, I found this issue is introduced by commit > a73e24d240bc136619d382b1268f34d75c9d25ce. > > Reverting this commit does fix this issue. However, on a second thought, > I feel it is probably better just drop --tail-synthesize, as it doesn't > make much sense without --overwrite. All we need is to do tail_synthesize > when --overwrite is set. > > Thoughts? Wang, wdyt? - Arnaldo
Re: perf tools: remove option --tail-synthesize ?
Em Wed, Nov 21, 2018 at 07:45:28AM +, Song Liu escreveu: > Hi, > > I found perf-record --tail-synthesize without --overwrite breaks symbols > for perf-script, perf-report, etc. For example: > > [root@]# ~/perf record -ag --tail-synthesize -- sleep 1 > [ perf record: Woken up 1 times to write data ] > [ perf record: Captured and wrote 1.129 MB perf.data (3531 samples) ] > [root@]# ~/perf script | head > swapper 0 [000] 1250675.051971: 1 cycles:ppp: > 81009e15 [unknown] ([unknown]) > 81196b19 [unknown] ([unknown]) > 81196579 [unknown] ([unknown]) > 81110ca7 [unknown] ([unknown]) > 81a01f4a [unknown] ([unknown]) > 81a017bf [unknown] ([unknown]) > 8180e17a [unknown] ([unknown]) > > perf-record with --overwrite does NOT have this issue. > > After digging into this, I found this issue is introduced by commit > a73e24d240bc136619d382b1268f34d75c9d25ce. > > Reverting this commit does fix this issue. However, on a second thought, > I feel it is probably better just drop --tail-synthesize, as it doesn't > make much sense without --overwrite. All we need is to do tail_synthesize > when --overwrite is set. > > Thoughts? Wang, wdyt? - Arnaldo
Re: perf tools: remove option --tail-synthesize ?
On Wed, Nov 21, 2018 at 07:45:28AM +, Song Liu wrote: > Hi, > > I found perf-record --tail-synthesize without --overwrite breaks symbols > for perf-script, perf-report, etc. For example: > > [root@]# ~/perf record -ag --tail-synthesize -- sleep 1 > [ perf record: Woken up 1 times to write data ] > [ perf record: Captured and wrote 1.129 MB perf.data (3531 samples) ] > [root@]# ~/perf script | head > swapper 0 [000] 1250675.051971: 1 cycles:ppp: > 81009e15 [unknown] ([unknown]) > 81196b19 [unknown] ([unknown]) > 81196579 [unknown] ([unknown]) > 81110ca7 [unknown] ([unknown]) > 81a01f4a [unknown] ([unknown]) > 81a017bf [unknown] ([unknown]) > 8180e17a [unknown] ([unknown]) > > perf-record with --overwrite does NOT have this issue. actualy I think that now it works properly, if you turn on task and mmap events, you'll see the samples get resolved right after aux events are processed: [root@krava perf]# ./perf script --show-info --show-task-events --show-mmap-events ... swapper 0 [007] 620566.187355: 64821 cycles:ppp: ab0b4d7c [unknown] ([unknown]) aba01b1f [unknown] ([unknown]) ab75d567 [unknown] ([unknown]) ab0e1f56 [unknown] ([unknown]) ab0e216f [unknown] ([unknown]) ab050dc7 [unknown] ([unknown]) abd5 [unknown] ([unknown]) swapper 0 [000] 0.00: PERF_RECORD_MMAP -1/0: [0xab00(0x152c8000) @ 0xab00]: x [kernel.kallsyms]_text swapper 0 [000] 0.00: PERF_RECORD_MMAP -1/0: [0xc02c8000(0x4000) @ 0]: x /lib/modules/4.18.17-200.fc28.x86_64/kernel/drivers/thermal/int340x_thermal/int3403_thermal.ko.xz swapper 0 [000] 0.00: PERF_RECORD_MMAP -1/0: [0xc02cd000(0x4000) @ 0]: x /lib/modules/4.18.17-200.fc28.x86_64/kernel/drivers/thermal/intel_pch_thermal.ko.xz ... ext4-rsv-conver 0 [000] 0.00: PERF_RECORD_COMM: ext4-rsv-conver:989/989 perf 20063 [005] 620566.187438:1056712 cycles:ppp: ab1f605d filemap_map_pages+0x9d (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) ab23aaa8 __handle_mm_fault+0x1018 (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) ab23ae7a handle_mm_fault+0xda (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) ab06ac90 __do_page_fault+0x240 (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) ab06af62 do_page_fault+0x32 (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) aba010ee page_fault+0x1e (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) ... if you record with --overwrite and --tail-synthesize the aux events will go to the top of the perf.data, so all's good > > After digging into this, I found this issue is introduced by commit > a73e24d240bc136619d382b1268f34d75c9d25ce. right, we got rid of that, because it will store the 'current/live' server mmaps for report/script, which is not what you want > Reverting this commit does fix this issue. However, on a second thought, > I feel it is probably better just drop --tail-synthesize, as it doesn't > make much sense without --overwrite. All we need is to do tail_synthesize > when --overwrite is set. > > Thoughts? maybe we should make --tail-synthesize non optionable for --overwrite, and get rid of that option completely.. Wang, any idea? but definitelly not allow that for non overwrite thanks, jirka
Re: perf tools: remove option --tail-synthesize ?
On Wed, Nov 21, 2018 at 07:45:28AM +, Song Liu wrote: > Hi, > > I found perf-record --tail-synthesize without --overwrite breaks symbols > for perf-script, perf-report, etc. For example: > > [root@]# ~/perf record -ag --tail-synthesize -- sleep 1 > [ perf record: Woken up 1 times to write data ] > [ perf record: Captured and wrote 1.129 MB perf.data (3531 samples) ] > [root@]# ~/perf script | head > swapper 0 [000] 1250675.051971: 1 cycles:ppp: > 81009e15 [unknown] ([unknown]) > 81196b19 [unknown] ([unknown]) > 81196579 [unknown] ([unknown]) > 81110ca7 [unknown] ([unknown]) > 81a01f4a [unknown] ([unknown]) > 81a017bf [unknown] ([unknown]) > 8180e17a [unknown] ([unknown]) > > perf-record with --overwrite does NOT have this issue. actualy I think that now it works properly, if you turn on task and mmap events, you'll see the samples get resolved right after aux events are processed: [root@krava perf]# ./perf script --show-info --show-task-events --show-mmap-events ... swapper 0 [007] 620566.187355: 64821 cycles:ppp: ab0b4d7c [unknown] ([unknown]) aba01b1f [unknown] ([unknown]) ab75d567 [unknown] ([unknown]) ab0e1f56 [unknown] ([unknown]) ab0e216f [unknown] ([unknown]) ab050dc7 [unknown] ([unknown]) abd5 [unknown] ([unknown]) swapper 0 [000] 0.00: PERF_RECORD_MMAP -1/0: [0xab00(0x152c8000) @ 0xab00]: x [kernel.kallsyms]_text swapper 0 [000] 0.00: PERF_RECORD_MMAP -1/0: [0xc02c8000(0x4000) @ 0]: x /lib/modules/4.18.17-200.fc28.x86_64/kernel/drivers/thermal/int340x_thermal/int3403_thermal.ko.xz swapper 0 [000] 0.00: PERF_RECORD_MMAP -1/0: [0xc02cd000(0x4000) @ 0]: x /lib/modules/4.18.17-200.fc28.x86_64/kernel/drivers/thermal/intel_pch_thermal.ko.xz ... ext4-rsv-conver 0 [000] 0.00: PERF_RECORD_COMM: ext4-rsv-conver:989/989 perf 20063 [005] 620566.187438:1056712 cycles:ppp: ab1f605d filemap_map_pages+0x9d (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) ab23aaa8 __handle_mm_fault+0x1018 (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) ab23ae7a handle_mm_fault+0xda (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) ab06ac90 __do_page_fault+0x240 (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) ab06af62 do_page_fault+0x32 (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) aba010ee page_fault+0x1e (/usr/lib/debug/lib/modules/4.18.17-200.fc28.x86_64/vmlinux) ... if you record with --overwrite and --tail-synthesize the aux events will go to the top of the perf.data, so all's good > > After digging into this, I found this issue is introduced by commit > a73e24d240bc136619d382b1268f34d75c9d25ce. right, we got rid of that, because it will store the 'current/live' server mmaps for report/script, which is not what you want > Reverting this commit does fix this issue. However, on a second thought, > I feel it is probably better just drop --tail-synthesize, as it doesn't > make much sense without --overwrite. All we need is to do tail_synthesize > when --overwrite is set. > > Thoughts? maybe we should make --tail-synthesize non optionable for --overwrite, and get rid of that option completely.. Wang, any idea? but definitelly not allow that for non overwrite thanks, jirka
