Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*Review\:\s+Reduce\s+in\-core\s+superblock\s+lock\s+contention\s+near\s+ENOSPC\s*$/: 22 ]

Total 22 documents matching your query.

1. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: Lachlan McIlroy <lachlan@xxxxxxx>
Date: Fri, 01 Dec 2006 19:22:18 +0000
David Chinner wrote: On Thu, Nov 30, 2006 at 06:03:40PM +0000, Lachlan McIlroy wrote: Dave, Could you have changed the SB_LOCK from a spinlock to a blocking mutex and have achieved a similar effect?
/archives/xfs/2006-12/msg00003.html (15,372 bytes)

2. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: Lachlan McIlroy <lachlan@xxxxxxx>
Date: Fri, 01 Dec 2006 20:12:17 +0000
David Chinner wrote: On Fri, Dec 01, 2006 at 09:38:11AM +1100, David Chinner wrote: On Thu, Nov 30, 2006 at 06:03:40PM +0000, Lachlan McIlroy wrote: These changes wouldn't apply cleanly to tot (3 hun
/archives/xfs/2006-12/msg00004.html (11,908 bytes)

3. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: David Chinner <dgc@xxxxxxx>
Date: Mon, 4 Dec 2006 10:49:28 +1100
Well, the reason I didn't go down this path in the first place was that typically only one type of counter would need rebalancing at a time (e.g. free blocks or free inodes, but not both at the same
/archives/xfs/2006-12/msg00010.html (10,666 bytes)

4. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: Klaus Strebel <klaus.strebel@xxxxxxx>
Date: Tue, 05 Dec 2006 12:46:46 +0100
David Chinner wrote: On Fri, Dec 01, 2006 at 07:22:18PM +0000, Lachlan McIlroy wrote: David Chinner wrote: On Thu, Nov 30, 2006 at 06:03:40PM +0000, Lachlan McIlroy wrote: I think the slow path code
/archives/xfs/2006-12/msg00018.html (12,046 bytes)

5. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: David Chinner <dgc@xxxxxxx>
Date: Wed, 6 Dec 2006 08:55:04 +1100
Sorry - my bad. The code did not change for UP, so I didn't think to test it. The patch below abstracts the icsb_mutex so that it doesn't get directly referenced by code outside the per-cpu counter c
/archives/xfs/2006-12/msg00022.html (14,500 bytes)

6. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: Lachlan McIlroy <lachlan@xxxxxxx>
Date: Wed, 06 Dec 2006 08:43:47 +0000
David Chinner wrote: On Tue, Dec 05, 2006 at 12:46:46PM +0100, Klaus Strebel wrote: Hi guys, just updated my CVS copy from oss.sgi.com ( the linux-2.6-xfs ) and tried to compile ... but your patch fa
/archives/xfs/2006-12/msg00027.html (10,902 bytes)

7. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: David Chinner <dgc@xxxxxxx>
Date: Fri, 8 Dec 2006 16:16:29 +1100
No. I didn't abstract the mutex_init and mutex_destroy calls because they are in the init/destroy functions for the icsb subsystem and those functions are #define'd out when HAVE_PERCPU_SB is not def
/archives/xfs/2006-12/msg00062.html (11,052 bytes)

8. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: xx>
Date: Fri, 01 Dec 2006 19:22:18 +0000
/archives/xfs/2006-12/msg00218.html (15,372 bytes)

9. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: xx>
Date: Fri, 01 Dec 2006 20:12:17 +0000
/archives/xfs/2006-12/msg00219.html (11,908 bytes)

10. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: xx>
Date: Mon, 4 Dec 2006 10:49:28 +1100
/archives/xfs/2006-12/msg00225.html (10,666 bytes)

11. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: xx>
Date: Tue, 05 Dec 2006 12:46:46 +0100
/archives/xfs/2006-12/msg00233.html (12,046 bytes)

12. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: xx>
Date: Wed, 6 Dec 2006 08:55:04 +1100
/archives/xfs/2006-12/msg00237.html (14,500 bytes)

13. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: xx>
Date: Wed, 06 Dec 2006 08:43:47 +0000
/archives/xfs/2006-12/msg00242.html (10,902 bytes)

14. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: xx>
Date: Fri, 8 Dec 2006 16:16:29 +1100
/archives/xfs/2006-12/msg00277.html (11,052 bytes)

15. Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: David Chinner <dgc@xxxxxxx>
Date: Thu, 23 Nov 2006 15:41:22 +1100
The existing per-cpu superblock counter code still uses the existing superblock spin lock when we approach ENOSPC for global synchronisation. On larger machines than this code was originally tested o
/archives/xfs/2006-11/msg00138.html (27,188 bytes)

16. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: >
Date: Thu, 30 Nov 2006 18:03:40 +0000
Could you have changed the SB_LOCK from a spinlock to a blocking mutex and have achieved a similar effect? Has this change had much testing on a large machine? These changes wouldn't apply cleanly t
/archives/xfs/2006-11/msg00198.html (11,535 bytes)

17. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: >
Date: Fri, 1 Dec 2006 09:38:11 +1100
Sort of - it would still be inefficient and wouldn't help solve the underlying causes of contention. Also, everything else that uses the SB_LOCK would now have a sleep point where there wasn't one pr
/archives/xfs/2006-11/msg00201.html (12,783 bytes)

18. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: >
Date: Fri, 1 Dec 2006 11:41:12 +1100
I see the problem - the next patch I am going to send out for review which is earlier in my series.... The growfs fix changes the delta parameter to xfs_icsb_modify_counters() from int to int64_t, an
/archives/xfs/2006-11/msg00204.html (26,452 bytes)

19. Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: >
Date: Thu, 23 Nov 2006 15:41:22 +1100
The existing per-cpu superblock counter code still uses the existing superblock spin lock when we approach ENOSPC for global synchronisation. On larger machines than this code was originally tested o
/archives/xfs/2006-11/msg00346.html (27,188 bytes)

20. Re: Review: Reduce in-core superblock lock contention near ENOSPC (score: 1)
Author: xx>
Date: Thu, 30 Nov 2006 18:03:40 +0000
Could you have changed the SB_LOCK from a spinlock to a blocking mutex and have achieved a similar effect? Has this change had much testing on a large machine? These changes wouldn't apply cleanly t
/archives/xfs/2006-11/msg00406.html (11,535 bytes)


This search system is powered by Namazu