Bug 1401580
| Summary: | [z-stream clone - 3.6.10] Numa sampling causes very high load on the hypervisor. | ||
|---|---|---|---|
| Product: | Red Hat Enterprise Virtualization Manager | Reporter: | rhev-integ |
| Component: | vdsm | Assignee: | Martin Polednik <mpoledni> |
| Status: | CLOSED ERRATA | QA Contact: | Artyom <alukiano> |
| Severity: | high | Docs Contact: | |
| Priority: | high | ||
| Version: | 3.6.9 | CC: | bazulay, dfediuck, gklein, guchen, lsurette, mavital, melewis, mgoldboi, michal.skrivanek, mkalinin, srevivo, ycui, ykaul |
| Target Milestone: | ovirt-3.6.10 | Keywords: | Performance, Triaged, ZStream |
| Target Release: | --- | ||
| Hardware: | Unspecified | ||
| OS: | Unspecified | ||
| Whiteboard: | |||
| Fixed In Version: | Doc Type: | If docs needed, set a value | |
| Doc Text: |
Previously, NUMA sampling could cause an unnecessarily high load on complex hosts. Now, the sampling interval has been reduced to 10 minutes to reduce the load on hosts. This is frequent enough as NUMA topology rarely changes.
|
Story Points: | --- |
| Clone Of: | 1396910 | Environment: | |
| Last Closed: | 2017-01-17 18:07:25 UTC | Type: | --- |
| Regression: | --- | Mount Type: | --- |
| Documentation: | --- | CRM: | |
| Verified Versions: | Category: | --- | |
| oVirt Team: | Virt | RHEL 7.3 requirements from Atomic Host: | |
| Cloudforms Team: | --- | Target Upstream Version: | |
| Embargoed: | |||
| Bug Depends On: | 1396910 | ||
| Bug Blocks: | |||
|
Description
rhev-integ
2016-12-05 15:39:01 UTC
MOM has nothing to do with NUMA. Moving to VDSM. There also were some big changes to monitoring in 4.0 so this might be just a matter of backporting. However, there is also the (fixed for at least 4.0 and up) bug about high load because of disk IO tune queries: https://bugzilla.redhat.com/show_bug.cgi?id=1366556 (Originally by Martin Sivak) MOM has nothing to do with NUMA. Moving to VDSM. There also were some big changes to monitoring in 4.0 so this might be just a matter of backporting. However, there is also the (fixed for at least 4.0 and up) bug about high load because of disk IO tune queries: https://bugzilla.redhat.com/show_bug.cgi?id=1366556 (Originally by Martin Sivak) *** Bug 1398953 has been marked as a duplicate of this bug. *** (Originally by Martin Sivak) msivak can we consider removing *VM* numa stats totally? it is for reporting only. 2nd option is to relax the interval, but I prefer that if we don't needed, just remove it (Originally by Roy Golan) msivak can we consider removing *VM* numa stats totally? it is for reporting only. 2nd option is to relax the interval, but I prefer that if we don't needed, just remove it (Originally by Roy Golan) It seems it is already removed in 4.1 engine. But we need to instruct VDSM to limit the collection frequency (and possibly remove the code) too. (Originally by Martin Sivak) the code was dropped in 4.1 in bug 1148039 and it is unused in 3.6/4.0 as well, to minimize changes we can just increase the poll interval from 15s to 1h (Originally by michal.skrivanek) I meant 600s, that was actually tested in real setup already. (Originally by michal.skrivanek) Package vdsm-4.16.36-1.el6ev.x86_64 does not include the patch. The right version for 3.6.10 is 4.16.37, please retest Verified on vdsm-4.17.37-1.el7ev.noarch, vdsm has correct NUMA sampling interval. Since the problem described in this bug report should be resolved in a recent advisory, it has been closed with a resolution of ERRATA. For information on the advisory, and where to find the updated files, follow the link below. If the solution does not work for you, open a new bug report. https://rhn.redhat.com/errata/RHBA-2017-0109.html |