Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*Xfs\s+delaylog\s+hanged\s+up\s*$/>

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*Xfs\s+delaylog\s+hanged\s+up\s*$/: 21 ]

Total 21 documents matching your query.

1. Xfs delaylog hanged up (score: 1): Author: Spelic <spelic@xxxxxxxxxxxxx>; Date: Mon, 22 Nov 2010 20:27:14 +0100; Hi there EXCELLENT speed improvement with delaylog! My congratulations. Now there's a problem: it hanged on me (not sure it was because of delaylog, but anyway...) I am on 2.6.37rc2 16 disk MD raid-5; /archives/xfs/2010-11/msg00332.html (38,909 bytes)
2. Re: Xfs delaylog hanged up (score: 1): Author: Dave Chinner <david@xxxxxxxxxxxxx>; Date: Tue, 23 Nov 2010 10:29:29 +1100; What is the storage hardware and the MD raid5 configuration? FYI, relatime, attr2, logbufs=8 and noquota are default values that you don't need to specify. Thanks for the test case - I'll try to repr; /archives/xfs/2010-11/msg00337.html (12,308 bytes)
3. Re: Xfs delaylog hanged up (score: 1): Author: Spelic <spelic@xxxxxxxxxxxxx>; Date: Tue, 23 Nov 2010 12:17:41 +0100; On 11/23/2010 12:29 AM, Dave Chinner wrote: 16 disk MD raid-5 What is the storage hardware and the MD raid5 configuration? Tyan motherboard with 5400 chipset dual Xeon E5420 16 disks on this one: 05:; /archives/xfs/2010-11/msg00341.html (11,001 bytes)
4. Re: Xfs delaylog hanged up (score: 1): Author: Spelic <spelic@xxxxxxxxxxxxx>; Date: Tue, 23 Nov 2010 14:28:09 +0100; I forgot one setting: md/stripe_cache_size was set to 32768 I forgot to check stripe_cache_active during the hang... but I don't think it was an MD bug Regards; /archives/xfs/2010-11/msg00346.html (8,030 bytes)
5. Re: Xfs delaylog hanged up (score: 1): Author: Dave Chinner <david@xxxxxxxxxxxxx>; Date: Wed, 24 Nov 2010 07:46:09 +1100; Hmmmm. We get plenty of reports about problems with 3ware RAID controllers, many of which are RAID controller problems. Can you make sure you are running the latest firmware on the controller? Nothin; /archives/xfs/2010-11/msg00353.html (10,060 bytes)
6. Re: Xfs delaylog hanged up (score: 1): Author: Stan Hoeppner <stan@xxxxxxxxxxxxxxxxx>; Date: Tue, 23 Nov 2010 16:14:16 -0600; Dave Chinner put forth on 11/23/2010 2:46 PM: Somewhat off topic, but how are you generating 10,000 IOPS by carving a 16TB LUN/volume from 12 x 2TB SATA disk spindles? Such drives aren't even capable; /archives/xfs/2010-11/msg00356.html (8,728 bytes)
7. Re: Xfs delaylog hanged up (score: 1): Author: Emmanuel Florac <eflorac@xxxxxxxxxxxxxx>; Date: Tue, 23 Nov 2010 23:48:11 +0100; Le Wed, 24 Nov 2010 07:46:09 +1100 vous écriviez: So Spelic, you're using the 3Ware as a SATA controller, but not a RAID controller? This is quite unexpected, though going with md instead provides be; /archives/xfs/2010-11/msg00357.html (8,863 bytes)
8. Re: Xfs delaylog hanged up (score: 1): Author: Dave Chinner <david@xxxxxxxxxxxxx>; Date: Wed, 24 Nov 2010 11:20:23 +1100; 512MB of BBWC backing the disks. The BBWC does a much better job of reordering out-of-order writes than the Linux elevators because 512MB is a much bigger window than a couple of thousand 4k IOs. Hen; /archives/xfs/2010-11/msg00358.html (9,463 bytes)
9. Re: Xfs delaylog hanged up (score: 1): Author: Spelic <spelic@xxxxxxxxxxxxx>; Date: Wed, 24 Nov 2010 01:36:37 +0100; On 11/23/2010 11:48 PM, Emmanuel Florac wrote: So Spelic, you're using the 3Ware as a SATA controller, but not a RAID controller? This is quite unexpected, though going with md instead provides bette; /archives/xfs/2010-11/msg00359.html (9,725 bytes)
10. Re: Xfs delaylog hanged up (score: 1): Author: Spelic <spelic@xxxxxxxxxxxxx>; Date: Wed, 24 Nov 2010 01:58:25 +0100; On 11/23/2010 09:46 PM, Dave Chinner wrote: Hmmmm. We get plenty of reports about problems with 3ware RAID controllers, many of which are RAID controller problems. Can you make sure you are running t; /archives/xfs/2010-11/msg00361.html (10,791 bytes)
11. Re: Xfs delaylog hanged up (score: 1): Author: Stan Hoeppner <stan@xxxxxxxxxxxxxxxxx>; Date: Tue, 23 Nov 2010 19:40:45 -0600; Spelic put forth on 11/23/2010 6:36 PM: If there is no advantage then why buy an $800+ real hardware RAID card and then deploy it as a vanilla SAS/SATA HBA with software RAID? What a waste of a decen; /archives/xfs/2010-11/msg00363.html (10,121 bytes)
12. Re: Xfs delaylog hanged up (score: 1): Author: Richard Scobie <r.scobie@xxxxxxxxxxxx>; Date: Wed, 24 Nov 2010 17:03:45 +1300; and > it's easier to align filesystem to stripes. Also my time is better Slightly off topic, but your previously mentioned xfs_info shows sunit and swidth values of zero, so your filesystem is not al; /archives/xfs/2010-11/msg00367.html (8,254 bytes)
13. Re: Xfs delaylog hanged up (score: 1): Author: Dave Chinner <david@xxxxxxxxxxxxx>; Date: Wed, 24 Nov 2010 16:44:22 +1100; But if that is the cause, then it would indicate an MD problem rather than an XFS problem. Testing on a similar but slightly different configuration helps isolate where the problem may lie. As it is,; /archives/xfs/2010-11/msg00370.html (10,773 bytes)
14. Re: Xfs delaylog hanged up (score: 1): Author: Michael Monnerie <michael.monnerie@xxxxxxxxxxxxxxxxxxx>; Date: Wed, 24 Nov 2010 07:18:19 +0100; Better broken drive detection (hw raid controllers are more picky than linux), server CPU offload, out-of-band notification of problems, and broken disks don't lead to a non-bootable system - what if; /archives/xfs/2010-11/msg00371.html (9,434 bytes)
15. Re: Xfs delaylog hanged up (score: 1): Author: Emmanuel Florac <eflorac@xxxxxxxxxxxxxx>; Date: Wed, 24 Nov 2010 08:44:43 +0100; Le Wed, 24 Nov 2010 01:36:37 +0100 vous écriviez: More predictable performance under heavy load (nfs kernel server, typically). BTW the 3Ware is not a very good sata controller; I've found that it is; /archives/xfs/2010-11/msg00373.html (9,818 bytes)
16. Re: Xfs delaylog hanged up (score: 1): Author: Spelic <spelic@xxxxxxxxxxxxx>; Date: Wed, 24 Nov 2010 14:12:32 +0100; 512MB of BBWC backing the disks. The BBWC does a much better job of reordering out-of-order writes than the Linux elevators because 512MB is a much bigger window than a couple of thousand 4k IOs. Hmm; /archives/xfs/2010-11/msg00377.html (11,010 bytes)
17. Re: Xfs delaylog hanged up (score: 1): Author: Dave Chinner <david@xxxxxxxxxxxxx>; Date: Thu, 25 Nov 2010 08:50:04 +1100; Actually, it's a SAS RAID controller: 03:00.0 RAID bus controller: LSI Logic / Symbios Logic MegaRAID SAS 1078 (rev 04) With each disk exported as a RAID0 lun because the raid controller does not do; /archives/xfs/2010-11/msg00382.html (12,223 bytes)
18. Re: Xfs delaylog hanged up (score: 1): Author: Spelic <spelic@xxxxxxxxxxxxx>; Date: Wed, 24 Nov 2010 23:52:43 +0100; I tried to reproduce it today but unfortunately I wasn't able to, not even on the same hardware. The first time it happened so soon after starting such parallel-kernel-unpack benchmark (at the second; /archives/xfs/2010-11/msg00383.html (8,679 bytes)
19. Re: Xfs delaylog hanged up (score: 1): Author: Spelic <spelic@xxxxxxxxxxxxx>; Date: Fri, 26 Nov 2010 00:34:13 +0100; On 11/23/2010 09:46 PM, Dave Chinner wrote: ... I note that the load is generating close to 10,000 iops on my test system, so it may very well be triggering load related problems in your raid control; /archives/xfs/2010-11/msg00404.html (10,226 bytes)
20. Re: Xfs delaylog hanged up (score: 1): Author: Dave Chinner <david@xxxxxxxxxxxxx>; Date: Fri, 26 Nov 2010 15:20:59 +1100; http://marc.info/?l=linux-fsdevel&m=129013629728687&w=2 It peaked at over 10,000 iops, lowest rate was ~4000iops and the average would have been around 7000iops. 33 seconds, with it being limited by; /archives/xfs/2010-11/msg00406.html (10,795 bytes)

Current List: 1 - 20
Page: [1] [2]