Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[PATCH\s+2\/9\]\:\s+Reduce\s+Log\s+I\/O\s+latency\s*$/: 40 ]

Total 40 documents matching your query.

1. [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Thu, 22 Nov 2007 11:33:39 +1100
Reduce log I/O latency To ensure that log I/O is issued as the highest priority I/O, set the I/O priority of the log I/O to the highest possible. This will ensure that log I/O is not held up behind b
/archives/xfs/2007-11/msg00209.html (11,040 bytes)

2. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Thu, 22 Nov 2007 01:49:25 +0100
Won't that possible disturb other RT priority users that do not need log IO (e.g. working on preallocated files)? Seems a little dangerous. I suspect you want a "higher than bulk but lower than RT" p
/archives/xfs/2007-11/msg00218.html (9,584 bytes)

3. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Thu, 22 Nov 2007 12:12:14 +1100
In all the cases that I know of where ppl are using what could be considered real-time I/O (e.g. media environments where they do real-time ingest and playout from the same filesystem) the real-time
/archives/xfs/2007-11/msg00220.html (10,410 bytes)

4. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Wed, 21 Nov 2007 20:57:27 -0600
I've seen PVRs that would be upset by this. They put media on one filesystem and database/apps/swap/etc. on another, but have everything on a single spindle. Stalling a media filesystem read for a wr
/archives/xfs/2007-11/msg00221.html (11,127 bytes)

5. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Thu, 22 Nov 2007 14:41:06 +1100
Sounds like the PVR is badly designed to me. If a write can cause a read to miss a playback deadline, then you haven't built enough buffering into your playback application. Cheers, Dave. -- Dave Chi
/archives/xfs/2007-11/msg00222.html (10,933 bytes)

6. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Thu, 22 Nov 2007 14:28:43 +1100
FWIW from a "real time" database POV this seems to make sense to me... in fact, we probably rely on filesystem metadata way too much (historically it's just "worked".... although we do seem to get is
/archives/xfs/2007-11/msg00223.html (11,151 bytes)

7. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Thu, 22 Nov 2007 01:25:49 -0600
Normally it's not a problem. But your proposed change can push a working system into a non-working system by making non-critical I/O on an unrelated filesystem have higher priority than the thing tha
/archives/xfs/2007-11/msg00224.html (12,504 bytes)

8. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Thu, 22 Nov 2007 21:31:59 +1100
This has nothing to do with this patch - it's a problem with sharing a single resource in a RT system between two non-deterministic constructs. e.g. I can put two ext3 filesystems on the one spindle,
/archives/xfs/2007-11/msg00225.html (15,389 bytes)

9. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Thu, 22 Nov 2007 13:06:11 +0100
For that case you really would need priority inheritance: any metadata IO on behalf or blocking a process needs to use the process' block IO priority. David's change just fixes a limited set of case
/archives/xfs/2007-11/msg00226.html (10,136 bytes)

10. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Fri, 23 Nov 2007 00:15:39 +1100
How do you do that when the processes are blocking on semaphores, mutexes or rw-semaphores in the fileysystem three layers removed from the I/O in progress? e.g. a low priority process transaction is
/archives/xfs/2007-11/msg00227.html (11,334 bytes)

11. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Thu, 22 Nov 2007 12:10:29 -0600
Sure. And it's up to the RT system designer not to do something stupid like that. The problem is that your patch potentially promotes a non-RT I/O activity to an RT one without regard to the rest of
/archives/xfs/2007-11/msg00229.html (16,169 bytes)

12. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Fri, 23 Nov 2007 09:29:09 +1100
So this: http://marc.info/?l=linux-kernel&m=119247074517414&w=2 shouldn't be allowed, either? (rt kjournald for ext3) Ok. I'll point anyone that complains at you, Matt ;) See my reply to Andi. No, no
/archives/xfs/2007-11/msg00230.html (12,627 bytes)

13. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Fri, 23 Nov 2007 10:09:22 +1100
Actually, I might change it to use the highest non-rt priority, which would solve the latency issues in the normal cases and still leave the RT rope dangling for those that want to use it. Is that an
/archives/xfs/2007-11/msg00231.html (11,432 bytes)

14. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Thu, 22 Nov 2007 18:20:31 -0600
No, I think not. If a user wants to manually promote kjournald, that's fine. I did. And I'll admit it's pretty thorny and I certainly don't know enough about XFS internals to comment further. I was a
/archives/xfs/2007-11/msg00232.html (13,169 bytes)

15. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Thu, 22 Nov 2007 18:21:41 -0600
Yes, that's perfectly fine. -- Mathematics is the supreme nostalgia of our time.
/archives/xfs/2007-11/msg00233.html (11,643 bytes)

16. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Fri, 23 Nov 2007 03:53:17 +0100
[...] I didn't say it was easy (or rather explicitely said it would be tricky). Probably it would be possible to fold it somehow into rt mutexes PI, but it's not easy and semaphores would need to be
/archives/xfs/2007-11/msg00237.html (11,052 bytes)

17. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Fri, 23 Nov 2007 15:03:29 +1100
The point is that it's not actually a thread-based problem - the priority can't be inherited via the traditional mutex-like manner. There is no connection between a thread and an I/o it has already i
/archives/xfs/2007-11/msg00239.html (11,629 bytes)

18. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Fri, 23 Nov 2007 13:01:15 +0100
It could be handled in theory similar to standard CPU priority inheritance -- \ keep track of IO priority of all threads you block and boost your IO priority always to that level. But it would be pro
/archives/xfs/2007-11/msg00243.html (12,116 bytes)

19. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Sat, 24 Nov 2007 12:43:33 -0600
Well I think what Dave is saying is that we can't find the related process. The submitter process may have even exited before the flush happens.. You'd instead have to keep track of (the max of) all
/archives/xfs/2007-11/msg00255.html (12,856 bytes)

20. Re: [PATCH 2/9]: Reduce Log I/O latency (score: 1)
Author:
Date: Mon, 26 Nov 2007 13:11:46 +1100
Index: 2.6.x-xfs-new/fs/xfs/xfs_log.c == -- 2.6.x-xfs-new.orig/fs/xfs/xfs_log.c 2007-11-22 10:47:21.945395328 +1100 +++ 2.6.x-xfs-new/fs/xfs/xfs_log.c 2007-11-22 10:53:11.556186722 +1100 @@ -1443,6 +
/archives/xfs/2007-11/msg00268.html (9,487 bytes)


This search system is powered by Namazu