Hello,
kernel test robot noticed a -19.4% regression of filebench.sum_operations/s on:
commit: 7c1ac89480e8d5d34d38a868642216c8f05ee602 ("cifs: Enable large folio support")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
testcase: filebench
test machine: 128 threads 2 sockets Intel(R) Xeon(R) Platinum 8358 CPU @ 2.60GHz (Ice Lake) with 128G memory
parameters:
disk: 1HDD
fs: ext4
fs2: cifs
test: fivestreamread.f
cpufreq_governor: performance
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <oliver.sang@xxxxxxxxx>
| Closes: https://lore.kernel.org/oe-lkp/202405291057.64718f4-oliver.sang@xxxxxxxxx
Details are as below:
-------------------------------------------------------------------------------------------------->
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20240529/202405291057.64718f4-oliver.sang@xxxxxxxxx
=========================================================================================
compiler/cpufreq_governor/disk/fs2/fs/kconfig/rootfs/tbox_group/test/testcase:
gcc-13/performance/1HDD/cifs/ext4/x86_64-rhel-8.3/debian-12-x86_64-20240206.cgz/lkp-icl-2sp6/fivestreamread.f/filebench
commit:
b593634424 ("cifs: Remove some code that's no longer used, part 3")
7c1ac89480 ("cifs: Enable large folio support")
b593634424d4ff13 7c1ac89480e8d5d34d38a868642
---------------- ---------------------------
%stddev %change %stddev
\ | \
1.56 ± 7% +44.3% 2.25 ± 2% iostat.cpu.system
2597 ± 30% -82.6% 451.00 ± 16% perf-c2c.DRAM.local
1.53 ± 7% +0.7 2.23 ± 2% mpstat.cpu.all.sys%
9.73 ± 98% +481.0% 56.53 ± 5% mpstat.max_utilization_pct
2712692 ± 17% -57.3% 1158294 ± 15% numa-numastat.node0.local_node
2790157 ± 16% -55.9% 1230718 ± 14% numa-numastat.node0.numa_hit
2789418 ± 16% -55.9% 1230047 ± 14% numa-vmstat.node0.numa_hit
2711951 ± 17% -57.3% 1157623 ± 15% numa-vmstat.node0.numa_local
28475 ± 29% +207.2% 87478 ± 14% sched_debug.cfs_rq:/.avg_vruntime.avg
28475 ± 29% +207.2% 87478 ± 14% sched_debug.cfs_rq:/.min_vruntime.avg
3.17 ± 4% +18.9% 3.77 ± 6% vmstat.procs.r
10197 +7.6% 10973 vmstat.system.in
701646 ± 6% +46.9% 1030651 ± 6% meminfo.AnonPages
937851 ± 5% +36.5% 1280516 ± 4% meminfo.Committed_AS
722721 ± 6% +45.5% 1051746 ± 5% meminfo.Inactive(anon)
5888 +11.2% 6550 ± 2% meminfo.PageTables
36277 ± 6% -19.4% 29230 ± 4% filebench.sum_bytes_mb/s
2178950 ± 6% -19.4% 1755646 ± 4% filebench.sum_operations
36313 ± 6% -19.4% 29258 ± 4% filebench.sum_operations/s
36313 ± 6% -19.4% 29258 ± 4% filebench.sum_reads/s
0.14 ± 6% +24.0% 0.17 ± 4% filebench.sum_time_ms/op
175413 ± 6% +46.9% 257668 ± 6% proc-vmstat.nr_anon_pages
180693 ± 6% +45.5% 262957 ± 5% proc-vmstat.nr_inactive_anon
1472 +11.2% 1637 ± 2% proc-vmstat.nr_page_table_pages
63627 -4.2% 60945 proc-vmstat.nr_slab_reclaimable
1079 ± 7% +19.7% 1292 ± 11% proc-vmstat.nr_writeback
180693 ± 6% +45.5% 262957 ± 5% proc-vmstat.nr_zone_inactive_anon
5942 ±157% +1351.7% 86270 ± 28% proc-vmstat.numa_hint_faults
3304 ±175% +1389.9% 49230 ± 36% proc-vmstat.numa_hint_faults_local
4601423 -47.1% 2432956 proc-vmstat.numa_hit
4467440 -48.5% 2300320 proc-vmstat.numa_local
49222 ± 40% +193.4% 144420 ± 27% proc-vmstat.numa_pte_updates
623992 ± 5% +42.5% 889010 ± 6% proc-vmstat.pgfault
5825920 -21.1% 4596157 proc-vmstat.pgfree
30735 ± 8% +80.3% 55418 ± 28% proc-vmstat.pgreuse
38.97 +257.2% 139.21 ± 4% perf-stat.i.MPKI
2.87 +0.3 3.19 perf-stat.i.branch-miss-rate%
5231053 -5.6% 4936215 perf-stat.i.branch-misses
11.93 ± 2% +5.7 17.63 ± 3% perf-stat.i.cache-miss-rate%
1.199e+08 ± 4% +28.5% 1.541e+08 ± 6% perf-stat.i.cache-misses
4.493e+08 ± 5% -18.5% 3.663e+08 ± 4% perf-stat.i.cache-references
3.27 ± 3% +115.6% 7.05 ± 2% perf-stat.i.cpi
7.142e+09 ± 6% +41.5% 1.01e+10 ± 2% perf-stat.i.cpu-cycles
0.42 -12.0% 0.37 perf-stat.i.ipc
3060 ± 5% +52.6% 4668 ± 7% perf-stat.i.minor-faults
3060 ± 5% +52.6% 4668 ± 7% perf-stat.i.page-faults
74.09 ± 6% +28.8% 95.45 ± 8% perf-stat.overall.MPKI
26.72 ± 2% +15.3 42.06 ± 3% perf-stat.overall.cache-miss-rate%
4.39 ± 3% +41.9% 6.24 perf-stat.overall.cpi
0.23 ± 3% -29.6% 0.16 perf-stat.overall.ipc
5215140 -5.6% 4921709 perf-stat.ps.branch-misses
1.198e+08 ± 4% +28.6% 1.541e+08 ± 6% perf-stat.ps.cache-misses
4.488e+08 ± 5% -18.4% 3.66e+08 ± 4% perf-stat.ps.cache-references
7.131e+09 ± 6% +41.3% 1.008e+10 ± 2% perf-stat.ps.cpu-cycles
3031 ± 5% +52.4% 4620 ± 7% perf-stat.ps.minor-faults
3031 ± 5% +52.4% 4620 ± 7% perf-stat.ps.page-faults
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.
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
