Bug 15411

Summary: New version stress-ng, most result of cpu-method test is lower than old version stress-ng
Product: [QA/Testing] Package Testing (ptest) Reporter: robert1030tw <pptsung>
Component: ptestAssignee: Unassigned <unassigned>
Status: RESOLVED INVALID QA Contact:
Severity: major    
Priority: Undecided CC: randy.macleod
Version: 4.3.3   
Target Milestone: ---   
Hardware: x86   
OS: x86_64   
Whiteboard:
OS type for building Yocto: --- Type of Regression: ---
Verified: Documentation change: No (bug/feature does not impact docs)
Attachments:
Description Flags
stress-ng0.16.05_kernel6.1.30_yocto4.3.3_atom3508
none
stress-ng0.13.12_kernel6.1.30_yocto4.3.3_atom3508 none

Description robert1030tw 2024-02-23 02:00:42 UTC
Created attachment 5016 [details]
stress-ng0.16.05_kernel6.1.30_yocto4.3.3_atom3508

Build Configuration:
BB_VERSION           = "2.6.0"
BUILD_SYS            = "x86_64-linux"
NATIVELSBSTRING      = "universal"
TARGET_SYS           = "x86_64-poky-linux"
MACHINE              = "genericx86-64"
DISTRO               = "poky"
DISTRO_VERSION       = "4.3.3"
TUNE_FEATURES        = "m64 core2"
TARGET_FPU           = ""
meta
meta-poky
meta-yocto-bsp       = "nanbield:d3b27346c3a4a7ef7ec517e9d339d22bda74349d"
meta-intel           = "nanbield:8d633bd01e20e31c0dae58cf3cd41eddb2f712c7"

Stress-ng version of Yocto-4.3.3
Default version: 0.16.05
Manual compare version: 0.13.12

Test PC arch info:
CPU: Intel Atom C3508
Memory size: 32G
Memory speed: 1866

Stress-ng test cpu performance command:
for m in cdouble crc16 fft int32float int64float \
ipv4checksum matrixprod parity queens sqrt union; do echo -e $m; \
stress-ng --cpu 0 --cpu-method $m  --metrics-brief -t 60; done

Test result:
Most CPU test result in stress-ng 0.16.05 is lower than stress-ng 0.13.12 at the same CPU and Test PC

cpu_stress_result_stress-ng0.16.05_kernel6.1.30_yocto4.3.3_atom3508.txt
cpu_stress_result_stress-ng0.13.12_kernel6.1.30_yocto4.3.3_atom3508.txt
Comment 1 robert1030tw 2024-02-23 02:01:26 UTC
Created attachment 5017 [details]
stress-ng0.13.12_kernel6.1.30_yocto4.3.3_atom3508

stress-ng0.13.12_kernel6.1.30_yocto4.3.3_atom3508
Comment 2 Randy MacLeod 2024-02-29 15:37:43 UTC
Unless this is something to do with the compiler or other toolchain components, which does not appear to be the case, please work with the upstream stress-ng developers.
Maybe you could just revert the stress-ng and test that change to confirm that it's just the stress-ng upgrade that affects the performance.