* [LKP] [net] 11ef7a8996d: +27.3% netperf.Throughput_Mbps [not found] <53d1f50b.CEZoGFBjN5Kgc+zm%fengguang.wu@intel.com> @ 2014-07-25 6:31 ` Aaron Lu 2014-07-25 6:37 ` Tom Herbert 0 siblings, 1 reply; 6+ messages in thread From: Aaron Lu @ 2014-07-25 6:31 UTC (permalink / raw) To: Tom Herbert; +Cc: David S. Miller, LKML, lkp [-- Attachment #1: Type: text/plain, Size: 3660 bytes --] FYI, we noticed the below changes on commit 11ef7a8996d5d433c9cd75d80651297eccbf6d42 ("net: Performance fix for process_backlog") test case: lkp-t410/netperf/300s-200%-10K-SCTP_STREAM_MANY 68b7107b62983f2 11ef7a8996d5d433c9cd75d80 --------------- ------------------------- 1023 ~ 3% +27.3% 1302 ~ 0% TOTAL netperf.Throughput_Mbps 0.72 ~10% -91.4% 0.06 ~23% TOTAL turbostat.%c3 13385 ~12% -92.6% 987 ~12% TOTAL cpuidle.C6-NHM.usage 22745 ~10% -95.5% 1016 ~40% TOTAL cpuidle.C3-NHM.usage 42675736 ~12% -84.6% 6571705 ~19% TOTAL cpuidle.C6-NHM.time 88342 ~11% -82.1% 15811 ~ 9% TOTAL softirqs.SCHED 19148006 ~12% -95.7% 821873 ~27% TOTAL cpuidle.C3-NHM.time 439.94 ~10% -77.5% 99.05 ~ 5% TOTAL uptime.idle 1.35 ~ 6% -65.8% 0.46 ~24% TOTAL turbostat.%c6 4 ~23% +114.3% 9 ~ 0% TOTAL vmstat.procs.r 1680 ~ 3% +40.4% 2359 ~ 3% TOTAL proc-vmstat.nr_alloc_batch 447921 ~ 4% +36.2% 610047 ~ 0% TOTAL softirqs.TIMER 9.09 ~ 9% +27.6% 11.60 ~ 8% TOTAL perf-profile.cpu-cycles.memcpy.sctp_outq_flush.sctp_outq_uncork.sctp_cmd_interpreter.sctp_do_sm 2350916 ~ 4% +35.4% 3184088 ~ 0% TOTAL proc-vmstat.pgalloc_dma 7.82 ~ 9% +24.1% 9.71 ~ 4% TOTAL perf-profile.cpu-cycles.copy_user_generic_string.sctp_user_addto_chunk.sctp_datamsg_from_user.sctp_sendmsg.inet_sendmsg 38837537 ~ 3% +27.1% 49358639 ~ 0% TOTAL proc-vmstat.numa_local 38837537 ~ 3% +27.1% 49358639 ~ 0% TOTAL proc-vmstat.numa_hit 50216 ~ 1% +17.0% 58745 ~ 6% TOTAL softirqs.RCU 1.41 ~ 4% +11.6% 1.58 ~ 1% TOTAL perf-profile.cpu-cycles.get_page_from_freelist.__alloc_pages_nodemask.alloc_kmem_pages_node.kmalloc_large_node.__kmalloc_node_track_caller 48539 ~ 1% -25.5% 36171 ~ 1% TOTAL vmstat.system.cs 75.64 ~ 4% +30.6% 98.82 ~ 0% TOTAL turbostat.%c0 3949 ~ 2% +13.4% 4478 ~ 0% TOTAL vmstat.system.in Legend: ~XX% - stddev percent [+-]XX% - change percent vmstat.system.cs 52000 ++------------------------------------------------------------------+ 50000 ++ * .* *. ** *. * *. | | .* + *.** *. : **.* .* .**.**. * + + *.* * + : * .**. *. .** 48000 ** * * * * * * * .* * * * ** | 46000 ++ * | | | 44000 ++ | 42000 ++ | 40000 ++ | | | 38000 +O O O | 36000 O+ O O O O OO OO OO O O O O O OO O OO O | | O O O O O O O | 34000 ++ O O O O | 32000 ++------------------------------------------------------------------+ [*] bisect-good sample [O] bisect-bad sample Disclaimer: Results have been estimated based on internal Intel analysis and are provided for informational purposes only. Any difference in system hardware or software design or configuration may affect actual performance. Thanks, Aaron [-- Attachment #2: reproduce --] [-- Type: text/plain, Size: 711 bytes --] echo performance > /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu1/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu2/cpufreq/scaling_governor echo performance > /sys/devices/system/cpu/cpu3/cpufreq/scaling_governor netserver netperf -t SCTP_STREAM_MANY -c -C -l 300 -- -m 10K netperf -t SCTP_STREAM_MANY -c -C -l 300 -- -m 10K netperf -t SCTP_STREAM_MANY -c -C -l 300 -- -m 10K netperf -t SCTP_STREAM_MANY -c -C -l 300 -- -m 10K netperf -t SCTP_STREAM_MANY -c -C -l 300 -- -m 10K netperf -t SCTP_STREAM_MANY -c -C -l 300 -- -m 10K netperf -t SCTP_STREAM_MANY -c -C -l 300 -- -m 10K netperf -t SCTP_STREAM_MANY -c -C -l 300 -- -m 10K ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [LKP] [net] 11ef7a8996d: +27.3% netperf.Throughput_Mbps 2014-07-25 6:31 ` [LKP] [net] 11ef7a8996d: +27.3% netperf.Throughput_Mbps Aaron Lu @ 2014-07-25 6:37 ` Tom Herbert 2014-07-25 6:44 ` Aaron Lu 2014-07-25 6:48 ` David Miller 0 siblings, 2 replies; 6+ messages in thread From: Tom Herbert @ 2014-07-25 6:37 UTC (permalink / raw) To: Aaron Lu; +Cc: David S. Miller, LKML, lkp Are you pointing out a regressions in this? On Thu, Jul 24, 2014 at 11:31 PM, Aaron Lu <aaron.lu@intel.com> wrote: > FYI, we noticed the below changes on > > commit 11ef7a8996d5d433c9cd75d80651297eccbf6d42 ("net: Performance fix for process_backlog") > > test case: lkp-t410/netperf/300s-200%-10K-SCTP_STREAM_MANY > > 68b7107b62983f2 11ef7a8996d5d433c9cd75d80 > --------------- ------------------------- > 1023 ~ 3% +27.3% 1302 ~ 0% TOTAL netperf.Throughput_Mbps > 0.72 ~10% -91.4% 0.06 ~23% TOTAL turbostat.%c3 > 13385 ~12% -92.6% 987 ~12% TOTAL cpuidle.C6-NHM.usage > 22745 ~10% -95.5% 1016 ~40% TOTAL cpuidle.C3-NHM.usage > 42675736 ~12% -84.6% 6571705 ~19% TOTAL cpuidle.C6-NHM.time > 88342 ~11% -82.1% 15811 ~ 9% TOTAL softirqs.SCHED > 19148006 ~12% -95.7% 821873 ~27% TOTAL cpuidle.C3-NHM.time > 439.94 ~10% -77.5% 99.05 ~ 5% TOTAL uptime.idle > 1.35 ~ 6% -65.8% 0.46 ~24% TOTAL turbostat.%c6 > 4 ~23% +114.3% 9 ~ 0% TOTAL vmstat.procs.r > 1680 ~ 3% +40.4% 2359 ~ 3% TOTAL proc-vmstat.nr_alloc_batch > 447921 ~ 4% +36.2% 610047 ~ 0% TOTAL softirqs.TIMER > 9.09 ~ 9% +27.6% 11.60 ~ 8% TOTAL perf-profile.cpu-cycles.memcpy.sctp_outq_flush.sctp_outq_uncork.sctp_cmd_interpreter.sctp_do_sm > 2350916 ~ 4% +35.4% 3184088 ~ 0% TOTAL proc-vmstat.pgalloc_dma > 7.82 ~ 9% +24.1% 9.71 ~ 4% TOTAL perf-profile.cpu-cycles.copy_user_generic_string.sctp_user_addto_chunk.sctp_datamsg_from_user.sctp_sendmsg.inet_sendmsg > 38837537 ~ 3% +27.1% 49358639 ~ 0% TOTAL proc-vmstat.numa_local > 38837537 ~ 3% +27.1% 49358639 ~ 0% TOTAL proc-vmstat.numa_hit > 50216 ~ 1% +17.0% 58745 ~ 6% TOTAL softirqs.RCU > 1.41 ~ 4% +11.6% 1.58 ~ 1% TOTAL perf-profile.cpu-cycles.get_page_from_freelist.__alloc_pages_nodemask.alloc_kmem_pages_node.kmalloc_large_node.__kmalloc_node_track_caller > 48539 ~ 1% -25.5% 36171 ~ 1% TOTAL vmstat.system.cs > 75.64 ~ 4% +30.6% 98.82 ~ 0% TOTAL turbostat.%c0 > 3949 ~ 2% +13.4% 4478 ~ 0% TOTAL vmstat.system.in > > Legend: > ~XX% - stddev percent > [+-]XX% - change percent > > > vmstat.system.cs > > 52000 ++------------------------------------------------------------------+ > 50000 ++ * .* *. ** *. * *. | > | .* + *.** *. : **.* .* .**.**. * + + *.* * + : * .**. *. .** > 48000 ** * * * * * * * .* * * * ** | > 46000 ++ * | > | | > 44000 ++ | > 42000 ++ | > 40000 ++ | > | | > 38000 +O O O | > 36000 O+ O O O O OO OO OO O O O O O OO O OO O | > | O O O O O O O | > 34000 ++ O O O O | > 32000 ++------------------------------------------------------------------+ > > > [*] bisect-good sample > [O] bisect-bad sample > > > Disclaimer: > Results have been estimated based on internal Intel analysis and are provided > for informational purposes only. Any difference in system hardware or software > design or configuration may affect actual performance. > > Thanks, > Aaron ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [LKP] [net] 11ef7a8996d: +27.3% netperf.Throughput_Mbps 2014-07-25 6:37 ` Tom Herbert @ 2014-07-25 6:44 ` Aaron Lu 2014-07-25 6:48 ` David Miller 1 sibling, 0 replies; 6+ messages in thread From: Aaron Lu @ 2014-07-25 6:44 UTC (permalink / raw) To: Tom Herbert; +Cc: David S. Miller, LKML, lkp On 07/25/2014 02:37 PM, Tom Herbert wrote: > Are you pointing out a regressions in this? No, the report is an indication your commit makes the Throughput_Mbps of the netperf benchamrk increased 27.3%, a good thing I think. Thanks, Aaron > > On Thu, Jul 24, 2014 at 11:31 PM, Aaron Lu <aaron.lu@intel.com> wrote: >> FYI, we noticed the below changes on >> >> commit 11ef7a8996d5d433c9cd75d80651297eccbf6d42 ("net: Performance fix for process_backlog") >> >> test case: lkp-t410/netperf/300s-200%-10K-SCTP_STREAM_MANY >> >> 68b7107b62983f2 11ef7a8996d5d433c9cd75d80 >> --------------- ------------------------- >> 1023 ~ 3% +27.3% 1302 ~ 0% TOTAL netperf.Throughput_Mbps >> 0.72 ~10% -91.4% 0.06 ~23% TOTAL turbostat.%c3 >> 13385 ~12% -92.6% 987 ~12% TOTAL cpuidle.C6-NHM.usage >> 22745 ~10% -95.5% 1016 ~40% TOTAL cpuidle.C3-NHM.usage >> 42675736 ~12% -84.6% 6571705 ~19% TOTAL cpuidle.C6-NHM.time >> 88342 ~11% -82.1% 15811 ~ 9% TOTAL softirqs.SCHED >> 19148006 ~12% -95.7% 821873 ~27% TOTAL cpuidle.C3-NHM.time >> 439.94 ~10% -77.5% 99.05 ~ 5% TOTAL uptime.idle >> 1.35 ~ 6% -65.8% 0.46 ~24% TOTAL turbostat.%c6 >> 4 ~23% +114.3% 9 ~ 0% TOTAL vmstat.procs.r >> 1680 ~ 3% +40.4% 2359 ~ 3% TOTAL proc-vmstat.nr_alloc_batch >> 447921 ~ 4% +36.2% 610047 ~ 0% TOTAL softirqs.TIMER >> 9.09 ~ 9% +27.6% 11.60 ~ 8% TOTAL perf-profile.cpu-cycles.memcpy.sctp_outq_flush.sctp_outq_uncork.sctp_cmd_interpreter.sctp_do_sm >> 2350916 ~ 4% +35.4% 3184088 ~ 0% TOTAL proc-vmstat.pgalloc_dma >> 7.82 ~ 9% +24.1% 9.71 ~ 4% TOTAL perf-profile.cpu-cycles.copy_user_generic_string.sctp_user_addto_chunk.sctp_datamsg_from_user.sctp_sendmsg.inet_sendmsg >> 38837537 ~ 3% +27.1% 49358639 ~ 0% TOTAL proc-vmstat.numa_local >> 38837537 ~ 3% +27.1% 49358639 ~ 0% TOTAL proc-vmstat.numa_hit >> 50216 ~ 1% +17.0% 58745 ~ 6% TOTAL softirqs.RCU >> 1.41 ~ 4% +11.6% 1.58 ~ 1% TOTAL perf-profile.cpu-cycles.get_page_from_freelist.__alloc_pages_nodemask.alloc_kmem_pages_node.kmalloc_large_node.__kmalloc_node_track_caller >> 48539 ~ 1% -25.5% 36171 ~ 1% TOTAL vmstat.system.cs >> 75.64 ~ 4% +30.6% 98.82 ~ 0% TOTAL turbostat.%c0 >> 3949 ~ 2% +13.4% 4478 ~ 0% TOTAL vmstat.system.in >> >> Legend: >> ~XX% - stddev percent >> [+-]XX% - change percent >> >> >> vmstat.system.cs >> >> 52000 ++------------------------------------------------------------------+ >> 50000 ++ * .* *. ** *. * *. | >> | .* + *.** *. : **.* .* .**.**. * + + *.* * + : * .**. *. .** >> 48000 ** * * * * * * * .* * * * ** | >> 46000 ++ * | >> | | >> 44000 ++ | >> 42000 ++ | >> 40000 ++ | >> | | >> 38000 +O O O | >> 36000 O+ O O O O OO OO OO O O O O O OO O OO O | >> | O O O O O O O | >> 34000 ++ O O O O | >> 32000 ++------------------------------------------------------------------+ >> >> >> [*] bisect-good sample >> [O] bisect-bad sample >> >> >> Disclaimer: >> Results have been estimated based on internal Intel analysis and are provided >> for informational purposes only. Any difference in system hardware or software >> design or configuration may affect actual performance. >> >> Thanks, >> Aaron ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [LKP] [net] 11ef7a8996d: +27.3% netperf.Throughput_Mbps 2014-07-25 6:37 ` Tom Herbert 2014-07-25 6:44 ` Aaron Lu @ 2014-07-25 6:48 ` David Miller 2014-07-25 6:49 ` Aaron Lu 1 sibling, 1 reply; 6+ messages in thread From: David Miller @ 2014-07-25 6:48 UTC (permalink / raw) To: therbert; +Cc: aaron.lu, linux-kernel, lkp From: Tom Herbert <therbert@google.com> Date: Thu, 24 Jul 2014 23:37:07 -0700 > Are you pointing out a regressions in this? I think he's letting you know that performance has improved, in fact :) ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [LKP] [net] 11ef7a8996d: +27.3% netperf.Throughput_Mbps 2014-07-25 6:48 ` David Miller @ 2014-07-25 6:49 ` Aaron Lu 2014-07-25 7:16 ` Tom Herbert 0 siblings, 1 reply; 6+ messages in thread From: Aaron Lu @ 2014-07-25 6:49 UTC (permalink / raw) To: David Miller, therbert; +Cc: linux-kernel, lkp On 07/25/2014 02:48 PM, David Miller wrote: > From: Tom Herbert <therbert@google.com> > Date: Thu, 24 Jul 2014 23:37:07 -0700 > >> Are you pointing out a regressions in this? > > I think he's letting you know that performance has improved, in fact :) Yes, exactly :-) -Aaron ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [LKP] [net] 11ef7a8996d: +27.3% netperf.Throughput_Mbps 2014-07-25 6:49 ` Aaron Lu @ 2014-07-25 7:16 ` Tom Herbert 0 siblings, 0 replies; 6+ messages in thread From: Tom Herbert @ 2014-07-25 7:16 UTC (permalink / raw) To: Aaron Lu; +Cc: David Miller, LKML, lkp On Thu, Jul 24, 2014 at 11:49 PM, Aaron Lu <aaron.lu@intel.com> wrote: > On 07/25/2014 02:48 PM, David Miller wrote: >> From: Tom Herbert <therbert@google.com> >> Date: Thu, 24 Jul 2014 23:37:07 -0700 >> >>> Are you pointing out a regressions in this? >> >> I think he's letting you know that performance has improved, in fact :) > > Yes, exactly :-) > Very nice, thanks for posting the results! > -Aaron > ^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2014-07-25 7:16 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
[not found] <53d1f50b.CEZoGFBjN5Kgc+zm%fengguang.wu@intel.com>
2014-07-25 6:31 ` [LKP] [net] 11ef7a8996d: +27.3% netperf.Throughput_Mbps Aaron Lu
2014-07-25 6:37 ` Tom Herbert
2014-07-25 6:44 ` Aaron Lu
2014-07-25 6:48 ` David Miller
2014-07-25 6:49 ` Aaron Lu
2014-07-25 7:16 ` Tom Herbert
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox