[Lustre-discuss] Force read-only ost mount
Is there a way to manually mount an ost read-only? I tried 'mount -t lustre -o ro ost_device mountpoint', but got a mount.lustre: mount /dev/data1recov/ost1 at /mnt/os1brecov failed: Transport endpoint is not connected I know if lustre detects a serious enough problem, ldiskfs error say, it will remount the ost read-only, but I would like to manually force this. A raid logical volume on an oss has some problems and I'm trying to transfer one of two osts to another oss (I believe this is possible by umounting lustre from all servers/clients, executing a 'tunefs.lustre --writeconf' on all lustre servers and the related devices, and remounting --- with the copied ost replacing the problematic one). In order to minimize downtime, I would like to work with a static ost image -- so I can transfer a faithful copy back, after I repair the raid problem. I did deactivate the ost device on the mds, but I'm worried about changes to files that live on the ost (I wasn't planning on creating another image). Thanks, Zach ___ Lustre-discuss mailing list Lustre-discuss@lists.lustre.org http://lists.lustre.org/mailman/listinfo/lustre-discuss
Re: [Lustre-discuss] Force read-only ost mount
On 2011-06-29, at 10:37 AM, Zachary Beebleson wrote: Is there a way to manually mount an ost read-only? I tried 'mount -t lustre -o ro ost_device mountpoint', but got a mount.lustre: mount /dev/data1recov/ost1 at /mnt/os1brecov failed: Transport endpoint is not connected I know if lustre detects a serious enough problem, ldiskfs error say, it will remount the ost read-only, but I would like to manually force this. There was a patch in bugzilla related to this, but it likely needs to be updated. Some of the mount-time code tries to write to the filesystem, and that needs to be disabled. A raid logical volume on an oss has some problems and I'm trying to transfer one of two osts to another oss (I believe this is possible by umounting lustre from all servers/clients, executing a 'tunefs.lustre --writeconf' on all lustre servers and the related devices, and remounting --- with the copied ost replacing the problematic one). In order to minimize downtime, I would like to work with a static ost image -- so I can transfer a faithful copy back, after I repair the raid problem. I did deactivate the ost device on the mds, but I'm worried about changes to files that live on the ost (I wasn't planning on creating another image). Cheers, Andreas -- Andreas Dilger Principal Engineer Whamcloud, Inc. ___ Lustre-discuss mailing list Lustre-discuss@lists.lustre.org http://lists.lustre.org/mailman/listinfo/lustre-discuss
[Lustre-discuss] New wc-discuss Lustre Mailing List
Hi, I'd like to announce the creation of a new mailing list for discussing Lustre releases from Whamcloud. We will also continue to monitor and participate on the existing lustre.org mailing lists, but we consider it prudent to host a separate list from lustre.org due to uncertainty regarding the long-term plans for lustre.org. Subscription information and archives are available at: https://groups.google.com/a/whamcloud.com/group/wc-discuss/ Cheers, Andreas -- Andreas Dilger Principal Engineer Whamcloud, Inc. ___ Lustre-discuss mailing list Lustre-discuss@lists.lustre.org http://lists.lustre.org/mailman/listinfo/lustre-discuss
[Lustre-discuss] speed differences in lustre/infiniband ipoib native ib
hey folks, we're struggling mightily to get ubuntu clients working in native IB mode against centos lustre/IB servers. since we've never had a working native IB client, we have no basis in our assumption that the speed increase should be tremendous thus justify our struggle. what has your experience been? ___ Lustre-discuss mailing list Lustre-discuss@lists.lustre.org http://lists.lustre.org/mailman/listinfo/lustre-discuss
Re: [Lustre-discuss] speed differences in lustre/infiniband ipoib native ib
we're struggling mightily to get ubuntu clients working in native IB mode against centos lustre/IB servers. since we've never had a working native IB client, we have no basis in our assumption that the speed increase should be tremendous thus justify our struggle. It really depends on a ton of factors that are impractical to list here. I guess I would summarize it as significant, most of the time. I wouldn't call it tremendous, compared to just using TCP/IP over the iboib interface. But seriously, though ... struggling mightily? Once we got the Lustre IB module loaded, everything Just Worked. If you want to give some details on what's going wrong here we might be able to help you. (If by some random chance your problem is you can't get the Lustre IB module loaded because of symbol version issues, then you should check the archives because that has been discussed plenty of times). --Ken ___ Lustre-discuss mailing list Lustre-discuss@lists.lustre.org http://lists.lustre.org/mailman/listinfo/lustre-discuss