Greeting, There is no primary kpi change in this test, below is the data collected through multiple monitors running background just for your information. commit: f519a3f1c6b7a990e5aed37a8f853c6ecfdee945 ("sched/core: Fix find_idlest_group() for fork") https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master in testcase: ebizzy on test machine: 160 threads Intel(R) Xeon(R) CPU E7-8890 v4 @ 2.20GHz with 512G memory with following parameters: nr_threads: 200% iterations: 100x duration: 10s cpufreq_governor: performance test-description: ebizzy is designed to generate a workload resembling common web application server workloads. test-url: http://ebizzy.sourceforge.net/ Details are as below: --------------------------------------------------------------------------------------------------> To reproduce: git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git cd lkp-tests bin/lkp install job.yaml # job file is attached in this email bin/lkp run job.yaml testcase/path_params/tbox_group/run: ebizzy/200%-100x-10s-performance/lkp-bdw-ex2 6643aab30f88e292 f519a3f1c6b7a990e5aed37a8f ---------------- -------------------------- 2704 ± 4% 15% 3120 ± 3% ebizzy.throughput.per_thread.min 7900 -5% 7539 ebizzy.throughput.per_thread.max 114170 ±173% -4e+04 69344 ±100% latency_stats.avg.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_do_access.nfs_permission.__inode_permission.inode_permission 232398 ±106% -2e+05 228 ± 11% latency_stats.avg.wait_on_page_bit.__filemap_fdatawait_range.filemap_fdatawait_range.filemap_write_and_wait_range.nfs_file_fsync.vfs_fsync_range.vfs_fsync.nfs4_file_flush.[nfsv4].filp_close.do_dup2.SyS_dup2.entry_SYSCALL_64_fastpath 744886 ±139% -3e+05 447909 ± 68% latency_stats.avg.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_fstatat 953762 ± 98% -3e+05 615947 ± 27% latency_stats.avg.max 232398 ±106% -2e+05 228 ± 11% latency_stats.max.wait_on_page_bit.__filemap_fdatawait_range.filemap_fdatawait_range.filemap_write_and_wait_range.nfs_file_fsync.vfs_fsync_range.vfs_fsync.nfs4_file_flush.[nfsv4].filp_close.do_dup2.SyS_dup2.entry_SYSCALL_64_fastpath 744886 ±139% -3e+05 447909 ± 68% latency_stats.max.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_fstatat 232398 ±106% -2e+05 228 ± 11% latency_stats.sum.wait_on_page_bit.__filemap_fdatawait_range.filemap_fdatawait_range.filemap_write_and_wait_range.nfs_file_fsync.vfs_fsync_range.vfs_fsync.nfs4_file_flush.[nfsv4].filp_close.do_dup2.SyS_dup2.entry_SYSCALL_64_fastpath 744886 ±139% -3e+05 447909 ± 68% latency_stats.sum.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_fstatat 1027542 ±173% -4e+05 624100 ±100% latency_stats.sum.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_do_access.nfs_permission.__inode_permission.inode_permission 14.80 ± 8% 46% 21.67 ± 5% perf-stat.node-store-miss-rate% 84.97 6% 90.44 perf-stat.node-load-miss-rate% 0.01 0.01 perf-stat.dTLB-store-miss-rate% 1.611e+09 1.583e+09 perf-stat.dTLB-store-misses 0.01 0.01 perf-stat.ipc 3.209e+12 3.124e+12 perf-stat.instructions 7.003e+11 -4% 6.72e+11 perf-stat.branch-instructions 3.396e+08 ± 4% -5% 3.217e+08 perf-stat.node-store-misses 9215 ± 6% -17% 7676 ± 12% perf-stat.instructions-per-iTLB-miss 4.153e+09 ± 10% -27% 3.048e+09 ± 5% perf-stat.cache-misses 0.02 ± 10% -27% 0.01 ± 6% perf-stat.cache-miss-rate% 1.615e+08 ± 12% -40% 96874183 ± 22% perf-stat.node-loads 1.979e+09 ± 14% -41% 1.169e+09 ± 9% perf-stat.node-stores :4 25% 1:4 kmsg.DHCP/BOOTP:Reply_not_for_us_on_eth#,op[#]xid[#] ebizzy.throughput.per_thread.min 3500 ++-------------------------------------------------------------------+ | O O O O O O O O O O 3000 O+ O O O O O O O .O...O | | .* * .*..*...*..*... .*...*. *..| 2500 *+ : : *...*..*...*..*...*. *. * | : : : : | 2000 ++ : : : : | | : : : : | 1500 ++ : : : : | | : : : : | 1000 ++ : : : : | | : : : : | 500 ++ : : : : | | : : | 0 ++-----*------*--O---------------------------------------------------+ [*] 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, Xiaolong