Dear Xiubo, I managed to collect logs and uploaded them to: ceph-post-file: 3d4d1419-a11e-4937-b0b1-bd99234d4e57 By the way, if you run the test with the conda.tgz at the link location, be careful: it contains a .bashrc file to activate the conda environment. Un-tar it only in a dedicated location. Unfortunately, this is default with a conda installation. I will remove this file from the archive tomorrow. Well, I hope the logs contain what you are looking for. I enabled dmesg debug logs for both, the kclient and nfsd. However, nfsd seems not to log anything, I see only ceph messages. I interrupted the tar command as soon as the error showed up for a number of times. There is indeed a change in log messages at the end, indicating an issue with ceph client caps under high load. It looks as if instead of waiting for an MDS response the kclient completes a request prematurely with insufficient caps. I really hope it is possible to fix that. I will keep the files on the system in case you need FS info for specific inodes. Thanks and best regards, ================= Frank Schilder AIT Risø Campus Bygning 109, rum S14 ________________________________________ From: Frank Schilder <frans@xxxxxx> Sent: Monday, March 27, 2023 5:22 PM To: Xiubo Li; Gregory Farnum Cc: ceph-users@xxxxxxx Subject: Re: Re: ln: failed to create hard link 'file name': Read-only file system > Sorry for late. No worries. > The ceph qa teuthology test cases have already one similar test, which > will untar a kernel tarball, but never seen this yet. > > I will try this again tomorrow without the NFS client. Great. In case you would like to use the archive I sent you a link for, please keep it confidential. It contains files not for publication. I will collect the log information you asked for. Best regards, ================= Frank Schilder AIT Risø Campus Bygning 109, rum S14 _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |