If you fix the issue, kindly add following tagĬompiler/cpufreq_governor/disk/fs/kconfig/rootfs/tbox_group/testcase: This can be helpful for further investigation. Since there are both improvements and regressions in various microīenchmarks, we are sending this report to provide some data and hope | testcase: change | phoronix-test-suite: phoronix-test-suite.mb_s 20.4% improvement | | test machine | 128 threads 2 sockets Intel(R) Xeon(R) Platinum 8358 CPU 2.60GHz (Ice Lake) with 128G memory | | testcase: change | phoronix-test-suite: .mb_s 25.7% improvement | | | option_a=input.i3d 129 Cells Per Direction |
| testcase: change | phoronix-test-suite: conds 3.6% regression | | test parameters | cpufreq_governor=performance | | test machine | 96 threads 2 sockets Intel(R) Xeon(R) Gold 6252 CPU 2.10GHz (Cascade Lake) with 512G memory | | testcase: change | phoronix-test-suite: _s 21.4% improvement | In addition to that, the commit also has impact on the following tests:
#Flow free bridges sampler 8x8 level 15 portable#
Test-description: Blogbench is a portable filesystem benchmark that tries to reproduce the load of a real-world busy file server. Test machine: 88 threads 2 sockets Intel(R) Xeon(R) Gold 6238M CPU 2.10GHz (Cascade Lake) with 128G memory
Kernel test robot noticed a -10.9% regression of blogbench.read_score on:Ĭommit: adfcf4231b8cbc2d9c1e7bfaa965b907e60639eb ("x86: don't use REP_GOOD or ERMS for user memory copies") 17:39 ` Linus Torvalds 0 siblings, 1 reply 5+ messages in threadįrom: kernel test robot 8:09 UTC ( / raw)Ĭc: oe-lkp, lkp, linux-kernel, ying.huang, feng.tang, fengwei.yin Adfcf4231b: blogbench.read_score -10.9% regression public inbox for help / color / mirror / Atom feed * adfcf4231b: blogbench.read_score -10.9% regression 8:09 kernel test robot
0 kommentar(er)
