[linus:master] [bpf] f18b03faba: stress-ng.seccomp.ops_per_sec -2.0% regression
From: kernel test robot
Date: Thu Nov 23 2023 - 19:41:26 EST
Hello,
kernel test robot noticed a -2.0% regression of stress-ng.seccomp.ops_per_sec on:
commit: f18b03fabaa9b7c80e80b72a621f481f0d706ae0 ("bpf: Implement BPF exceptions")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
testcase: stress-ng
test machine: 36 threads 1 sockets Intel(R) Core(TM) i9-10980XE CPU @ 3.00GHz (Cascade Lake) with 128G memory
parameters:
nr_threads: 1
disk: 1HDD
testtime: 60s
fs: ext4
class: os
test: seccomp
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/202311231458.61e2502f-oliver.sang@xxxxxxxxx
Details are as below:
-------------------------------------------------------------------------------------------------->
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20231123/202311231458.61e2502f-oliver.sang@xxxxxxxxx
=========================================================================================
class/compiler/cpufreq_governor/disk/fs/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime:
os/gcc-12/performance/1HDD/ext4/x86_64-rhel-8.3/1/debian-11.1-x86_64-20220510.cgz/lkp-csl-d02/seccomp/stress-ng/60s
commit:
335d1c5b54 ("bpf: Implement support for adding hidden subprogs")
f18b03faba ("bpf: Implement BPF exceptions")
335d1c5b545284d7 f18b03fabaa9b7c80e80b72a621
---------------- ---------------------------
%stddev %change %stddev
\ | \
13890 ± 7% -9.4% 12579 ± 3% turbostat.POLL
0.01 ± 13% +48.4% 0.01 ± 16% perf-sched.sch_delay.avg.ms.syslog_print.do_syslog.kmsg_read.vfs_read
0.01 ± 11% +70.3% 0.01 ± 16% perf-sched.sch_delay.max.ms.syslog_print.do_syslog.kmsg_read.vfs_read
0.78 ± 23% -0.2 0.55 ± 11% mpstat.cpu.all.irq%
0.05 ± 17% -0.0 0.03 ± 12% mpstat.cpu.all.soft%
2.39 ± 8% +0.3 2.65 ± 2% mpstat.cpu.all.sys%
27256 -2.0% 26712 stress-ng.seccomp.ops
454.26 -2.0% 445.19 stress-ng.seccomp.ops_per_sec
54565 -1.9% 53516 stress-ng.time.voluntary_context_switches
7.07 ± 4% -1.7 5.36 ± 11% perf-profile.calltrace.cycles-pp.emit_mov_imm32.do_jit.bpf_int_jit_compile.bpf_prog_select_runtime.bpf_prepare_filter
6.01 ± 5% -1.4 4.64 ± 10% perf-profile.children.cycles-pp.emit_mov_imm32
0.21 ± 15% -0.0 0.16 ± 15% perf-profile.children.cycles-pp.mod_objcg_state
4.91 ± 5% -1.0 3.90 ± 10% perf-profile.self.cycles-pp.emit_mov_imm32
3921440 -2.3% 3831836 proc-vmstat.numa_hit
3921405 -2.3% 3829327 proc-vmstat.numa_local
19214848 -2.1% 18810333 proc-vmstat.pgalloc_normal
19165012 -2.1% 18760451 proc-vmstat.pgfree
116766 ± 8% -6.0% 109716 proc-vmstat.pgreuse
25902 -2.0% 25381 proc-vmstat.thp_fault_alloc
1.73 ± 59% -1.3 0.48 ± 41% perf-stat.i.branch-miss-rate%
23564234 ± 2% -5.6% 22236469 perf-stat.i.cache-references
331079 ± 18% -27.3% 240834 ± 9% perf-stat.i.dTLB-load-misses
0.07 ± 45% -0.0 0.03 ± 26% perf-stat.i.dTLB-store-miss-rate%
53.82 ± 4% -4.7 49.17 perf-stat.i.iTLB-load-miss-rate%
679766 ± 6% +11.1% 755158 perf-stat.i.iTLB-loads
9620 ± 7% +13.6% 10932 ± 2% perf-stat.i.instructions-per-iTLB-miss
2454 ± 2% +4.3% 2560 perf-stat.overall.cycles-between-cache-misses
0.03 ± 6% -0.0 0.03 ± 2% perf-stat.overall.dTLB-store-miss-rate%
52.10 -2.3 49.76 perf-stat.overall.iTLB-load-miss-rate%
9654 ± 3% +6.5% 10286 perf-stat.overall.instructions-per-iTLB-miss
23233597 ± 2% -5.8% 21887967 perf-stat.ps.cache-references
326645 ± 18% -27.4% 237090 ± 9% perf-stat.ps.dTLB-load-misses
669939 ± 6% +10.9% 743269 perf-stat.ps.iTLB-loads
4.987e+11 -3.2% 4.829e+11 perf-stat.total.instructions
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