Bug 2064055
| Summary: | VMware LSO - degradation in RBD Snapshot creation time in 4.10 vs 4.9 | ||
|---|---|---|---|
| Product: | [Red Hat Storage] Red Hat OpenShift Data Foundation | Reporter: | Yuli Persky <ypersky> |
| Component: | csi-driver | Assignee: | Rakshith <rar> |
| Status: | CLOSED NOTABUG | QA Contact: | Elad <ebenahar> |
| Severity: | medium | Docs Contact: | |
| Priority: | unspecified | ||
| Version: | 4.10 | CC: | alayani, idryomov, jopinto, kramdoss, madam, mmuench, muagarwa, ocs-bugs, odf-bz-bot, ypadia |
| Target Milestone: | --- | Keywords: | Automation, Performance, Regression |
| Target Release: | --- | ||
| Hardware: | Unspecified | ||
| OS: | Unspecified | ||
| Whiteboard: | |||
| Fixed In Version: | Doc Type: | If docs needed, set a value | |
| Doc Text: | Story Points: | --- | |
| Clone Of: | Environment: | ||
| Last Closed: | 2022-04-28 04:43:58 UTC | Type: | Bug |
| Regression: | --- | Mount Type: | --- |
| Documentation: | --- | CRM: | |
| Verified Versions: | Category: | --- | |
| oVirt Team: | --- | RHEL 7.3 requirements from Atomic Host: | |
| Cloudforms Team: | --- | Target Upstream Version: | |
| Embargoed: | |||
|
Description
Yuli Persky
2022-03-14 23:30:18 UTC
Not a 4.10 blocker based on the analysis done so far, keeping it open as it still awaits some answers. Relevant Jenkins job for a reproduction of the current BZ : https://ocs4-jenkins-csb-odf-qe.apps.ocp-c1.prod.psi.redhat.com/job/qe-deploy-ocs-cluster/11817/ Since the prev job failed with system issue ( not a bug in the system or test) - I've retriggered the job : https://ocs4-jenkins-csb-odf-qe.apps.ocp-c1.prod.psi.redhat.com/job/qe-deploy-ocs-cluster/11919/ will update on the results. The last test execution failed due to leftovers problem on the cluster. Another test run was triggered on the newsly deployed cluster : https://ocs4-jenkins-csb-odf-qe.apps.ocp-c1.prod.psi.redhat.com/job/qe-deploy-ocs-cluster/12114/ Will update on the results. https://ocs4-jenkins-csb-odf-qe.apps.ocp-c1.prod.psi.redhat.com/job/qe-deploy-ocs-cluster/12115/console - the updated run A bug was deiscovered in the test. The test was fixed, and run on 4.10.0-221 and the measurements were taken. The summary of the results is: RBD Snapshot Creation times ( one big file with size of 60% of the initial pvc) in 4.9 are: 1GB snapshot: 0.501 sec 10GB snapshot: 0.466 sec 100GB snapshot: 0.798 sec RBD Snapshot Creation times 4.10 ( build 4.10.0-156) are: 1GB snapshot: 1.875 sec 10GB snapshot: 1.893 sec 100GB snapshot: 1.806 sec RBD Snapshot Creation times 4.10 ( build 4.10.0-221) are: 1GB snapshot: 0.5 sec 10GB snapshot: 0.74 sec 100GB snapshot: 0.5 sec The must gather logs are available here: rhsqe-repo.lab.eng.blr.redhat.com:/var/www/html/OCS/ocs-qe-bugs/bz-2064055/logs-20220427-224105/ As we see - the results of 4.10.0. build 221 are much better than results of 4.10.0 build 156. Actually they are about the same, except 10GB snapshot creation time (in 4.9 it is 0.466 sec and in 4.10.0-221 it is 0.74 sec). However, the 100GB snapshot creation time is quite good. At this point I do not see a need to fix anything at this area. Looks like the changes in 4.10 between build 156 and build 221 caused improvement in the performance. Great. In this case, we can close the bug. thanks, Yuli. |