Hide Forgot
Description of problem: iothread values' logic not quite clear Version-Release number of selected component (if applicable): kernel-3.10.0-508.el7.x86_64 libcgroup-0.41-11.el7.x86_64 How reproducible: 100% Steps to Reproduce: 1. # pwd /sys/fs/cgroup/cpu,cpuacct/machine.slice/machine-qemu\x2d1\x2dvirtlabtestcopy.scope 2. # ll | egrep "vcpu|iothread|emulator" drwxr-xr-x. 2 root root 0 Sep 20 13:40 emulator drwxr-xr-x. 2 root root 0 Sep 20 13:51 iothread1 drwxr-xr-x. 2 root root 0 Sep 20 13:40 vcpu0 drwxr-xr-x. 2 root root 0 Sep 20 13:40 vcpu1 drwxr-xr-x. 2 root root 0 Sep 20 13:40 vcpu2 drwxr-xr-x. 2 root root 0 Sep 20 13:40 vcpu3 3. current cpu related values as follow: # cat cpu.shares 1024 # cat cpu.cfs_quota_us 2500 # cat cpu.cfs_period_us 100000 # cat vcpu*/cpu.cfs_quota_us 1000 1000 1000 1000 # cat vcpu*/cpu.cfs_period_us 100000 100000 100000 100000 # cat emulator*/cpu.cfs_quota_us -1 # cat emulator*/cpu.cfs_period_us 100000 # cat iothread1/cpu.cfs_quota_us 1300 # cat iothread1/cpu.cfs_period_us 100000 4. try to set iothread1/cpu.cfs_period_us to 51998, it's failed # echo 51998 > iothread1/cpu.cfs_period_us -bash: echo: write error: Invalid argument 5. try to set iothread1/cpu.cfs_period_us to 51999, it's successful # echo 51999 > iothread1/cpu.cfs_period_us # cat iothread1/cpu.cfs_period_us 51999 Actual results: as step 4, echo 51998 > iothread1/cpu.cfs_period_us Expected results: why set 51998 failed but set 51999 successful? the logic is not quite clear. Additional info: This is from bug 1356937
Red Hat Enterprise Linux version 7 entered the Maintenance Support 1 phase in August 2019. In this phase only qualified Critical and Important Security errata advisories (RHSAs) and Urgent Priority Bug Fix errata advisories (RHBAs) may be released as they become available. Other errata advisories may be delivered as appropriate. This bug has been reviewed by Engineering representative and does not meet the inclusion criteria for Maintenance Support 1 phase. For more information about Red Hat Enterprise Linux Lifecycle, please see https://access.redhat.com/support/policy/updates/errata#Maintenance_Support_1_Phase. Feel free to re-open this for Red Hat Enterprise Linux 8 if you still see issue there.