[LU-18693] sanity-lnet: nfs: server 10.240.16.204 not responding, timed out

• Type: Bug
• Resolution: Unresolved
• Priority: Major
• Severity: 3
• Assignee: DevOps Triage
• Reporter: Maloo

Description

This issue was created by maloo for Sergey Cheremencev <[e-mail]>

This issue relates to the following test suite run: https://testing.whamcloud.com/test_sets/ad35ccfd-9d51-4822-983f-49b83d52bd79

Test session details:
clients: https://build.whamcloud.com/job/lustre-reviews/110784 - 5.15.0-94-generic
servers: https://build.whamcloud.com/job/lustre-reviews/110784 - 4.18.0-553.16.1.el8_lustre.x86_64

Session failed with status ABORT. sanity-lnet completed successfully. After completion there is a lot of messages like:

[21792.120241] nfs: server 10.240.16.204 not responding, still trying
[21822.838662] nfs: server 10.240.16.204 not responding, timed out
[22003.436593] nfs: server 10.240.16.204 not responding, timed out
...
[27155.664682] nfs: server 10.240.16.204 not responding, timed out

From the MDS:

[25994.958602] Autotest: Test running for 430 minutes (lustre-reviews_review-ldiskfs-ubuntu_110784.43)
[26298.043672] Autotest: Test running for 435 minutes (lustre-reviews_review-ldiskfs-ubuntu_110784.43)
[26402.490385] LustreError: lustre-OST0006-osc-MDT0000: operation ost_connect to node 10.240.22.243@tcp failed: rc = -19
[26402.497237] LustreError: Skipped 3 previous similar messages
[26601.219038] Autotest: Test running for 440 minutes (lustre-reviews_review-ldiskfs-ubuntu_110784.43)
[26904.277762] Autotest: Test running for 445 minutes (lustre-reviews_review-ldiskfs-ubuntu_110784.43)
[26965.747102] Autotest: Timing session out! Timeout has been exceeded but the test framework is still running (lustre-reviews_review-ldiskfs-ubuntu_110784.43)

Issue Links

• is duplicated by: LU-18569 sanity-sec: timeout - clients lost connection to MGS
• is duplicated by: LU-19175 sanity-sec test_68: fails with "timeout occurred after 450 minutes"
• is duplicated by: LU-19341 sanity-sec: random hang (test 72d)
• is related to: LU-19297 sanity-sec test_72b: test_72b returned 1