[<prev] [next>] [day] [month] [year] [list]
Message-ID: <1434076329.18774.61.camel@intel.com>
Date: Fri, 12 Jun 2015 10:32:09 +0800
From: Huang Ying <ying.huang@...el.com>
To: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
Cc: LKML <linux-kernel@...r.kernel.org>, LKP ML <lkp@...org>,
Huang Ying <ying.huang@...el.com>
Subject: [lkp] [rcu] cd73ca21cd2: No primary result change, +47.6%
aim7.time.involuntary_context_switches
FYI, we noticed the below changes on
git://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git master
commit cd73ca21cd2bb3711b8d80ba74c90d37ef15fe4d ("rcu: Force wakeup of rcu_gp_kthread at grace-period end")
testcase/path_params/tbox_group: aim7/performance-100-fork_test/lkp-a03
3382adbc1bb8c80e cd73ca21cd2bb3711b8d80ba74
---------------- --------------------------
%stddev %change %stddev
\ | \
205760 ± 2% +47.6% 303763 ± 1% aim7.time.involuntary_context_switches
215 ± 1% +24.7% 268 ± 22% sched_debug.cfs_rq[2]:/.load
205760 ± 2% +47.6% 303763 ± 1% time.involuntary_context_switches
366314 ± 1% +32.8% 486545 ± 3% softirqs.RCU
1493 ± 2% +17.1% 1749 ± 2% slabinfo.kmalloc-128.num_objs
1374 ± 1% +20.5% 1656 ± 2% slabinfo.kmalloc-128.active_objs
4511 ± 0% +7.5% 4850 ± 0% vmstat.system.in
7806 ± 0% +5.9% 8264 ± 1% vmstat.system.cs
335 ± 13% +30.2% 436 ± 12% latency_stats.avg.call_rwsem_down_write_failed.copy_process.do_fork.SyS_clone.system_call_fastpath
1266 ± 1% +18.6% 1501 ± 0% latency_stats.avg.do_wait.SyS_wait4.system_call_fastpath
188 ± 18% +27.9% 241 ± 19% latency_stats.avg.sync_inodes_sb.sync_inodes_one_sb.iterate_supers.sys_sync.system_call_fastpath
955 ± 9% -29.6% 672 ± 17% latency_stats.avg.call_rwsem_down_write_failed.anon_vma_clone.anon_vma_fork.copy_process.do_fork.SyS_clone.system_call_fastpath
211 ± 3% -11.1% 188 ± 4% latency_stats.avg.pipe_wait.pipe_read.__vfs_read.vfs_read.SyS_read.system_call_fastpath
1109 ± 8% -24.0% 842 ± 18% latency_stats.avg.call_rwsem_down_write_failed.anon_vma_fork.copy_process.do_fork.SyS_clone.system_call_fastpath
3 ± 0% -33.3% 2 ± 0% latency_stats.hits.rpc_wait_bit_killable.__rpc_execute.rpc_execute.rpc_run_task.nfs4_call_sync_sequence.[nfsv4]._nfs4_proc_getattr.[nfsv4].nfs4_proc_getattr.[nfsv4].__nfs_revalidate_inode.nfs_getattr.vfs_getattr_nosec.vfs_getattr.vfs_fstat
3 ± 0% -33.3% 2 ± 0% latency_stats.hits.wait_on_page_bit.filemap_fdatawait_range.filemap_fdatawait.filemap_write_and_wait.nfs_wb_all.nfs_getattr.vfs_getattr_nosec.vfs_getattr.vfs_fstat.SYSC_newfstat.SyS_newfstat.system_call_fastpath
1853 ± 1% +8.4% 2009 ± 2% latency_stats.hits.do_wait.SyS_wait4.system_call_fastpath
59 ± 11% +14.6% 68 ± 2% latency_stats.hits.call_rwsem_down_write_failed.cgroup_post_fork.copy_process.do_fork.SyS_clone.system_call_fastpath
28538 ± 10% -18.5% 23253 ± 5% latency_stats.max.call_rwsem_down_write_failed.anon_vma_clone.anon_vma_fork.copy_process.do_fork.SyS_clone.system_call_fastpath
32316 ± 17% -17.6% 26627 ± 6% latency_stats.max.call_rwsem_down_write_failed.anon_vma_fork.copy_process.do_fork.SyS_clone.system_call_fastpath
2347345 ± 2% +28.6% 3019561 ± 3% latency_stats.sum.do_wait.SyS_wait4.system_call_fastpath
3596 ± 10% +20.5% 4333 ± 6% latency_stats.sum.wait_on_page_bit_killable.__lock_page_or_retry.filemap_fault.__do_fault.handle_pte_fault.handle_mm_fault.__do_page_fault.do_page_fault.page_fault
1335990 ± 12% +49.7% 2000350 ± 12% latency_stats.sum.call_rwsem_down_write_failed.copy_process.do_fork.SyS_clone.system_call_fastpath
13375861 ± 15% -29.6% 9420979 ± 27% latency_stats.sum.call_rwsem_down_write_failed.anon_vma_clone.anon_vma_fork.copy_process.do_fork.SyS_clone.system_call_fastpath
1291678 ± 4% -10.6% 1155232 ± 3% latency_stats.sum.pipe_wait.pipe_read.__vfs_read.vfs_read.SyS_read.system_call_fastpath
567 ± 18% +27.8% 725 ± 19% latency_stats.sum.sync_inodes_sb.sync_inodes_one_sb.iterate_supers.sys_sync.system_call_fastpath
1343 ± 5% -29.4% 948 ± 5% latency_stats.sum.wait_on_page_bit.filemap_fdatawait_range.filemap_fdatawait.filemap_write_and_wait.nfs_wb_all.nfs_getattr.vfs_getattr_nosec.vfs_getattr.vfs_fstat.SYSC_newfstat.SyS_newfstat.system_call_fastpath
lkp-a03: Atom
Memory: 8G
softirqs.RCU
520000 ++-----------------------------------------------------------------+
| O |
500000 O+ O O O O O O |
480000 ++ O O O O O O O O O O O |
| O O O O |
460000 ++ |
440000 ++ |
| |
420000 ++ |
400000 ++ |
| *.. |
380000 ++ .. *.. .*.. |
360000 ++ .*.. .*.. .*..*..*.*..*.* *.*..*.*.. .. * *.*.. .*..*
*..* * * *.* * |
340000 ++-----------------------------------------------------------------+
aim7.time.involuntary_context_switches
320000 ++-----------------------------------------------------------------+
| O O O O O O O O O |
300000 O+ O O O O O O O O O O |
| O O |
280000 ++ O |
| |
260000 ++ |
| |
240000 ++ |
| |
220000 ++ |
| .*.*.. .*..*..*. .*.*..*.. .*.. .*..*. .*..*.*.. .*..*. |
200000 *+ *.*..* *. * * *. * *..*
| |
180000 ++-----------------------------------------------------------------+
time.involuntary_context_switches
320000 ++-----------------------------------------------------------------+
| O O O O O O O O O |
300000 O+ O O O O O O O O O O |
| O O |
280000 ++ O |
| |
260000 ++ |
| |
240000 ++ |
| |
220000 ++ |
| .*.*.. .*..*..*. .*.*..*.. .*.. .*..*. .*..*.*.. .*..*. |
200000 *+ *.*..* *. * * *. * *..*
| |
180000 ++-----------------------------------------------------------------+
vmstat.system.in
4900 ++---------------------------O---------------------------------------+
O O O O O O O O O O O O O |
4850 ++ O O O O O O O O O |
4800 ++ |
| |
4750 ++ |
4700 ++ |
| |
4650 ++ |
4600 ++ |
| |
4550 ++ .*..*.. .*.. |
4500 *+.*. .*. .*..*.*.. .*.*..*..*.*..*.*..*..* *.*. *. .*
| *..*. *. *. *. |
4450 ++-------------------------------------------------------------------+
[*] bisect-good sample
[O] bisect-bad sample
To reproduce:
apt-get install ruby
git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
cd lkp-tests
bin/setup-local job.yaml # the job file attached in this email
bin/run-local job.yaml
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,
Ying Huang
-------------------------------------
lkp@...ists.intel.com
https://eclists.intel.com/sympa/info/lkp
Unsubscribe by sending email to sympa@...ists.intel.com with subject "Unsubscribe lkp"
View attachment "job.yaml" of type "text/plain" (3054 bytes)
View attachment "reproduce" of type "text/plain" (293 bytes)
Powered by blists - more mailing lists