| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <202505160902.c72854e8-lkp@intel.com>
Date: Fri, 16 May 2025 10:39:32 +0800
From: kernel test robot <oliver.sang@...el.com>
To: Charlie Jenkins <charlie@...osinc.com>
CC: <oe-lkp@...ts.linux.dev>, <lkp@...el.com>, <linux-kernel@...r.kernel.org>,
<x86@...nel.org>, Thomas Gleixner <tglx@...utronix.de>, Alexandre Ghiti
<alexghiti@...osinc.com>, <oliver.sang@...el.com>
Subject: [tip:core/entry] [entry] e43b8bb56e:
stress-ng.personality.ops_per_sec 3.2% improvement
Hello,
kernel test robot noticed a 3.2% improvement of stress-ng.personality.ops_per_sec on:
commit: e43b8bb56e537bfc8d9076793091e7679020fc9c ("entry: Inline syscall_exit_to_user_mode()")
https://git.kernel.org/cgit/linux/kernel/git/tip/tip.git core/entry
testcase: stress-ng
config: x86_64-rhel-9.4
compiler: gcc-12
test machine: 64 threads 2 sockets Intel(R) Xeon(R) Gold 6346 CPU @ 3.10GHz (Ice Lake) with 256G memory
parameters:
nr_threads: 100%
testtime: 60s
test: personality
cpufreq_governor: performance
In addition to that, the commit also has significant impact on the following tests:
+------------------+--------------------------------------------------------------------------------+
| testcase: change | stress-ng: stress-ng.context.swapcontext_calls_per_sec 2.1% improvement |
| test machine | 384 threads 2 sockets Intel(R) Xeon(R) 6972P (Granite Rapids) with 128G memory |
| test parameters | cpufreq_governor=performance |
| | nr_threads=100% |
| | test=context |
| | testtime=60s |
+------------------+--------------------------------------------------------------------------------+
Details are as below:
-------------------------------------------------------------------------------------------------->
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20250516/202505160902.c72854e8-lkp@intel.com
=========================================================================================
compiler/cpufreq_governor/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime:
gcc-12/performance/x86_64-rhel-9.4/100%/debian-12-x86_64-20240206.cgz/lkp-icl-2sp7/personality/stress-ng/60s
commit:
7ace1602ab ("LoongArch: entry: Migrate ret_from_fork() to C")
e43b8bb56e ("entry: Inline syscall_exit_to_user_mode()")
7ace1602abf21da5 e43b8bb56e537bfc8d907679309
---------------- ---------------------------
%stddev %change %stddev
\ | \
6.44 ±100% -6.4 0.00 perf-profile.calltrace.cycles-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.personality
6.84 ±100% -6.8 0.00 perf-profile.children.cycles-pp.syscall_exit_to_user_mode
5.76 ±100% -5.8 0.00 perf-profile.self.cycles-pp.syscall_exit_to_user_mode
3.346e+08 +3.2% 3.455e+08 stress-ng.personality.ops
5577357 +3.2% 5758223 stress-ng.personality.ops_per_sec
1278 +1.5% 1297 stress-ng.time.user_time
1.31 +3.5% 1.36 perf-stat.i.cpi
1.48e+11 -3.1% 1.435e+11 perf-stat.i.instructions
0.76 -3.4% 0.74 perf-stat.i.ipc
1.31 +3.5% 1.36 perf-stat.overall.cpi
0.76 -3.4% 0.74 perf-stat.overall.ipc
1.456e+11 -3.1% 1.411e+11 perf-stat.ps.instructions
8.985e+12 -3.6% 8.659e+12 perf-stat.total.instructions
0.97 ±111% -99.9% 0.00 ±141% perf-sched.sch_delay.avg.ms.irqentry_exit_to_user_mode.asm_exc_page_fault.[unknown]
1.55 ± 4% -100.0% 0.00 perf-sched.sch_delay.avg.ms.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
1.30 ±103% -99.9% 0.00 ±141% perf-sched.sch_delay.max.ms.irqentry_exit_to_user_mode.asm_exc_page_fault.[unknown]
5.64 ± 25% -100.0% 0.00 perf-sched.sch_delay.max.ms.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
2.42 ± 37% +49.9% 3.62 ± 4% perf-sched.sch_delay.max.ms.wait_for_partner.fifo_open.do_dentry_open.vfs_open
698.88 ± 15% -40.0% 419.17 ± 20% perf-sched.wait_and_delay.avg.ms.__cond_resched.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
3.61 ± 12% -100.0% 0.00 perf-sched.wait_and_delay.avg.ms.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
3781 ± 7% -100.0% 0.00 perf-sched.wait_and_delay.count.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
504.70 ± 98% -100.0% 0.00 perf-sched.wait_and_delay.max.ms.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
698.87 ± 15% -40.0% 419.16 ± 20% perf-sched.wait_time.avg.ms.__cond_resched.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
2.06 ± 23% -100.0% 0.00 perf-sched.wait_time.avg.ms.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
502.38 ± 98% -100.0% 0.00 perf-sched.wait_time.max.ms.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
***************************************************************************************************
lkp-gnr-2ap2: 384 threads 2 sockets Intel(R) Xeon(R) 6972P (Granite Rapids) with 128G memory
=========================================================================================
compiler/cpufreq_governor/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime:
gcc-12/performance/x86_64-rhel-9.4/100%/debian-12-x86_64-20240206.cgz/lkp-gnr-2ap2/context/stress-ng/60s
commit:
7ace1602ab ("LoongArch: entry: Migrate ret_from_fork() to C")
e43b8bb56e ("entry: Inline syscall_exit_to_user_mode()")
7ace1602abf21da5 e43b8bb56e537bfc8d907679309
---------------- ---------------------------
%stddev %change %stddev
\ | \
49055 ± 2% -4.1% 47032 proc-vmstat.pgreuse
96.00 ± 19% -42.5% 55.17 ± 37% sched_debug.cpu.nr_uninterruptible.max
4.04 ± 70% -4.0 0.00 perf-profile.calltrace.cycles-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.swapcontext
4.25 ± 70% -4.2 0.00 perf-profile.children.cycles-pp.syscall_exit_to_user_mode
3.55 ± 70% -3.6 0.00 perf-profile.self.cycles-pp.syscall_exit_to_user_mode
1.047e+08 +2.1% 1.069e+08 stress-ng.context.ops
1745421 +2.1% 1781401 stress-ng.context.ops_per_sec
4541476 +2.1% 4636071 stress-ng.context.swapcontext_calls_per_sec
9344 -1.6% 9196 stress-ng.time.system_time
13524 +1.1% 13679 stress-ng.time.user_time
0.06 ± 11% -100.0% 0.00 perf-sched.sch_delay.avg.ms.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
10.75 ± 79% -100.0% 0.00 perf-sched.sch_delay.max.ms.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
0.91 ± 97% -100.0% 0.00 perf-sched.wait_and_delay.avg.ms.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
3274 ± 2% -100.0% 0.00 perf-sched.wait_and_delay.count.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
512.24 ± 95% -100.0% 0.00 perf-sched.wait_and_delay.max.ms.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
0.86 ±104% -100.0% 0.00 perf-sched.wait_time.avg.ms.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
505.95 ± 97% -100.0% 0.00 perf-sched.wait_time.max.ms.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
1.173e+11 -3.6% 1.13e+11 perf-stat.i.branch-instructions
1.49 +0.1 1.57 perf-stat.i.branch-miss-rate%
1.727e+09 +2.3% 1.767e+09 perf-stat.i.branch-misses
2.10 +4.2% 2.19 perf-stat.i.cpi
6.241e+11 -3.6% 6.019e+11 perf-stat.i.instructions
0.48 -4.2% 0.46 perf-stat.i.ipc
1.47 +0.1 1.56 perf-stat.overall.branch-miss-rate%
2.11 +4.0% 2.19 perf-stat.overall.cpi
0.47 -3.9% 0.46 perf-stat.overall.ipc
1.154e+11 -3.6% 1.112e+11 perf-stat.ps.branch-instructions
1.698e+09 +2.3% 1.738e+09 perf-stat.ps.branch-misses
6.136e+11 -3.5% 5.919e+11 perf-stat.ps.instructions
3.804e+13 -4.6% 3.628e+13 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
Powered by blists - more mailing lists