Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*XFS\s+corruption\s+with\s+failover\s*$/: 20 ]

Total 20 documents matching your query.

1. XFS corruption with failover (score: 1)
Author: John Quigley <jquigley@xxxxxxxxxxxx>
Date: Thu, 13 Aug 2009 15:17:22 -0500
Folks: We're deploying XFS in a configuration where the file system is being exported with NFS. XFS is being mounted on Linux, with default options; an iSCSI volume is the formatted media. We're work
/archives/xfs/2009-08/msg00120.html (7,954 bytes)

2. Re: XFS corruption with failover (score: 1)
Author: Emmanuel Florac <eflorac@xxxxxxxxxxxxxx>
Date: Thu, 13 Aug 2009 23:17:39 +0200
Le Thu, 13 Aug 2009 15:17:22 -0500 vous écriviez: By killing abruptly the primary server while doing IO, you're probably pushing the envelope... You may have a somewhat better luck with a cluster fs,
/archives/xfs/2009-08/msg00121.html (8,124 bytes)

3. Re: XFS corruption with failover (score: 1)
Author: Felix Blyakher <felixb@xxxxxxx>
Date: Thu, 13 Aug 2009 16:44:05 -0500
Folks: We're deploying XFS in a configuration where the file system is being exported with NFS. XFS is being mounted on Linux, with default options; an iSCSI volume is the formatted media. We're wor
/archives/xfs/2009-08/msg00122.html (9,834 bytes)

4. Re: XFS corruption with failover (score: 1)
Author: Felix Blyakher <felixb@xxxxxxx>
Date: Thu, 13 Aug 2009 17:42:56 -0500
Le Thu, 13 Aug 2009 15:17:22 -0500 vous écriviez: Any advice or insight into what we're doing wrong would be very much appreciated. My apologies in advance for the somewhat off-topic question. By ki
/archives/xfs/2009-08/msg00125.html (10,638 bytes)

5. Re: XFS corruption with failover (score: 1)
Author: Eric Sandeen <sandeen@xxxxxxxxxxx>
Date: Thu, 13 Aug 2009 19:31:12 -0500
Are you sure? if (ohead->oh_clientid != XFS_TRANSACTION && ohead->oh_clientid != XFS_LOG) { xlog_warn( "XFS: xlog_recover_process_data: bad clientid"); ASSERT(0); return (XFS_ERROR(EIO)); } so it doe
/archives/xfs/2009-08/msg00129.html (10,919 bytes)

6. Re: XFS corruption with failover (score: 1)
Author: Lachlan McIlroy <lmcilroy@xxxxxxxxxx>
Date: Thu, 13 Aug 2009 20:38:39 -0400 (EDT)
If that fails too can you run xfs_logprint on /dev/sde and post any errors it reports?
/archives/xfs/2009-08/msg00130.html (12,145 bytes)

7. Re: XFS corruption with failover (score: 1)
Author: John Quigley <jquigley@xxxxxxxxxxxx>
Date: Thu, 13 Aug 2009 19:50:38 -0500
Emmanuel Florac wrote: By killing abruptly the primary server while doing IO, you're probably pushing the envelope... You may have a somewhat better luck with a cluster fs, OCFS2 works very well for
/archives/xfs/2009-08/msg00131.html (10,421 bytes)

8. Re: XFS corruption with failover (score: 1)
Author: John Quigley <jquigley@xxxxxxxxxxxx>
Date: Thu, 13 Aug 2009 19:52:26 -0500
And that was my understanding, based on all I've read about the design and intended usage. XFS has been remarkably resilient in the face of various poor operating conditions, and this is the only env
/archives/xfs/2009-08/msg00132.html (9,224 bytes)

9. Re: XFS corruption with failover (score: 1)
Author: John Quigley <jquigley@xxxxxxxxxxxx>
Date: Thu, 13 Aug 2009 19:56:09 -0500
Interesting suggestion; I don't recall having seen any indication of IO errors, but I'm testing again this evening, and will report back on what I find with dd. That's not a good time to run xfs_repa
/archives/xfs/2009-08/msg00133.html (9,923 bytes)

10. Re: XFS corruption with failover (score: 1)
Author: Lachlan McIlroy <lmcilroy@xxxxxxxxxx>
Date: Thu, 13 Aug 2009 20:58:01 -0400 (EDT)
Should barriers be enabled in XFS then?
/archives/xfs/2009-08/msg00135.html (11,601 bytes)

11. Re: XFS corruption with failover (score: 1)
Author: John Quigley <jquigley@xxxxxxxxxxxx>
Date: Thu, 13 Aug 2009 20:06:18 -0500
if (ohead->oh_clientid != XFS_TRANSACTION && ohead->oh_clientid != XFS_LOG) { xlog_warn( "XFS: xlog_recover_process_data: bad clientid"); ASSERT(0); return (XFS_ERROR(EIO)); } so it does say EIO but
/archives/xfs/2009-08/msg00136.html (10,694 bytes)

12. Re: XFS corruption with failover (score: 1)
Author: John Quigley <jquigley@xxxxxxxxxxxx>
Date: Thu, 13 Aug 2009 20:14:01 -0500
I'll definitely do so, thanks. - John Quigley
/archives/xfs/2009-08/msg00138.html (8,841 bytes)

13. Re: XFS corruption with failover (score: 1)
Author: Eric Sandeen <sandeen@xxxxxxxxxxx>
Date: Thu, 13 Aug 2009 20:35:22 -0500
Could try it but I bet the iscsi target doesn't claim to support them... -eric
/archives/xfs/2009-08/msg00140.html (12,096 bytes)

14. Re: XFS corruption with failover (score: 1)
Author: John Quigley <jquigley@xxxxxxxxxxxx>
Date: Thu, 13 Aug 2009 20:44:35 -0500
Could try it but I bet the iscsi target doesn't claim to support them... The target implementation, being new, is fairly naive and does not support this (or have any caching facilities, for that matt
/archives/xfs/2009-08/msg00141.html (9,169 bytes)

15. Re: XFS corruption with failover (score: 1)
Author: Lachlan McIlroy <lmcilroy@xxxxxxxxxx>
Date: Thu, 13 Aug 2009 21:43:27 -0400 (EDT)
You're probably right. Is it possible for a transaction record to span two log buffers and only one made it to disk so the rest of the transction record appears corrupt?
/archives/xfs/2009-08/msg00142.html (12,331 bytes)

16. Re: XFS corruption with failover (score: 1)
Author: Felix Blyakher <felixb@xxxxxxx>
Date: Fri, 14 Aug 2009 08:21:57 -0500
This is an IO error. Is the block device (/dev/sde) accessible from the server #2 OK? Can you dd from that device? Are you sure? No, I'm not. Replied first without looking at the code ^) if (ohead->
/archives/xfs/2009-08/msg00146.html (10,486 bytes)

17. Re: XFS corruption with failover (score: 1)
Author: John Quigley <jquigley@xxxxxxxxxxxx>
Date: Mon, 17 Aug 2009 13:04:57 -0500
My apologies for the delayed response; output of logprint can be downloaded as a ~4MB bzip: http://www.jquigley.com/files/tmp/xfs-failover-logprint.bz2 Thanks very much for your consideration. - John
/archives/xfs/2009-08/msg00174.html (8,805 bytes)

18. Re: XFS corruption with failover (score: 1)
Author: Lachlan McIlroy <lmcilroy@xxxxxxxxxx>
Date: Tue, 18 Aug 2009 22:18:12 -0400 (EDT)
xfs_logprint doesn't find any problems with this log but that doesn't mean the kernel doesn't - they use different implementations to read the log. I noticed that the active part of the log wraps aro
/archives/xfs/2009-08/msg00186.html (9,914 bytes)

19. Re: XFS corruption with failover (score: 1)
Author: John Quigley <jquigley@xxxxxxxxxxxx>
Date: Wed, 19 Aug 2009 10:46:54 -0500
Lachlan McIlroy wrote: xfs_logprint doesn't find any problems with this log but that doesn't mean the kernel doesn't - they use different implementations to read the log. I noticed that the active pa
/archives/xfs/2009-08/msg00191.html (9,253 bytes)

20. Re: XFS corruption with failover (score: 1)
Author: Lachlan McIlroy <lmcilroy@xxxxxxxxxx>
Date: Fri, 21 Aug 2009 03:11:15 -0400 (EDT)
Hang on, I made a mistake there. The xfs_logprint transactional view of the log didn't find any errors but dumping the contents of the log shows a different story. $ xfs_logprint -f xfs-failover-logp
/archives/xfs/2009-08/msg00230.html (15,503 bytes)


This search system is powered by Namazu