Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*Review\:\s+fix\s+mapping\s+invalidation\s+callouts\s*$/: 30 ]

Total 30 documents matching your query.

1. Review: fix mapping invalidation callouts (score: 1)
Author: David Chinner <dgc@xxxxxxx>
Date: Mon, 8 Jan 2007 15:03:09 +1100
With the recent cancel_dirty_page() changes, a warning was added if we cancel a dirty page that is still mapped into the page tables. This happens in XFS from fs_tosspages() and fs_flushinval_pages()
/archives/xfs/2007-01/msg00010.html (10,205 bytes)

2. Re: Review: fix mapping invalidation callouts (score: 1)
Author: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Date: Mon, 8 Jan 2007 09:09:16 +0000
Generally looks good. But I feel a little cautios about changes in this area, so we should throw all possible test loads at this before commiting it.
/archives/xfs/2007-01/msg00013.html (9,585 bytes)

3. Re: Review: fix mapping invalidation callouts (score: 1)
Author:
Date: Tue, 9 Jan 2007 10:04:29 +1100
Yup - fsx is one test that I really want to hit with this. The guy that reported the initial problem has replied saying this patch fixes the warnings (good start ;), but I'll hold off pushing it for
/archives/xfs/2007-01/msg00032.html (10,549 bytes)

4. Re: Review: fix mapping invalidation callouts (score: 1)
Author:
Date: Tue, 09 Jan 2007 11:57:38 +0000
David Chinner wrote: On Mon, Jan 08, 2007 at 09:09:16AM +0000, Christoph Hellwig wrote: On Mon, Jan 08, 2007 at 03:03:09PM +1100, David Chinner wrote: With the recent cancel_dirty_page() changes, a w
/archives/xfs/2007-01/msg00048.html (11,444 bytes)

5. Re: Review: fix mapping invalidation callouts (score: 1)
Author:
Date: Wed, 10 Jan 2007 11:10:28 +1100
By definition fs_flush_pages() only flushes pages. If you need to flush and invalidate pages, you use fs_flushinval_pages(). Passing B_INVAL to fs_flush_pages() is broken code. good ;) Cheers, Dave.
/archives/xfs/2007-01/msg00049.html (9,433 bytes)

6. Re: Review: fix mapping invalidation callouts (score: 1)
Author:
Date: Wed, 10 Jan 2007 17:23:44 +1100
I don't think this is right. Assuming 4k page size, first = 2k, last = 6k will result in invalidating page indexes 1 and 2 i.e. offset 4k -> 12k. In fact, we want to invalidate pages 0 and 1. IOWs, I
/archives/xfs/2007-01/msg00055.html (10,885 bytes)

7. Re: Review: fix mapping invalidation callouts (score: 1)
Author:
Date: Wed, 10 Jan 2007 08:39:33 +0000
David Chinner wrote: On Mon, Jan 08, 2007 at 03:03:09PM +1100, David Chinner wrote: With the recent cancel_dirty_page() changes, a warning was added if we cancel a dirty page that is still mapped int
/archives/xfs/2007-01/msg00056.html (11,566 bytes)

8. Re: Review: fix mapping invalidation callouts (score: 1)
Author:
Date: Thu, 11 Jan 2007 17:49:58 +1100
Yeah, you'd think so. The first xfsqa run I do -after- checking it in (been running for 24 hours) I get a stack dump with the warning in cancel_dirty_page(), so clearly this isn't right either. I'm n
/archives/xfs/2007-01/msg00069.html (12,222 bytes)

9. Re: Review: fix mapping invalidation callouts (score: 1)
Author:
Date: Thu, 11 Jan 2007 19:00:32 +1100
Of course, I just realised that this is 2.6.19 that I'm testing on (fmeh) and so the code is different - cancel-dirty_page() doesn't exist in this tree, and the warning is coming from invalidate_inod
/archives/xfs/2007-01/msg00070.html (10,624 bytes)

10. Re: Review: fix mapping invalidation callouts (score: 1)
Author:
Date: Thu, 11 Jan 2007 19:01:37 +1100
Ack. Lets get Donald to pull 2.6.20-rc into 2.6.x-xfs, or do we need to wait until you have this fixed? David -- David Chatterton XFS Engineering Manager SGI Australia
/archives/xfs/2007-01/msg00071.html (13,065 bytes)

11. Review: fix mapping invalidation callouts (score: 1)
Author:
Date: Mon, 8 Jan 2007 15:03:09 +1100
With the recent cancel_dirty_page() changes, a warning was added if we cancel a dirty page that is still mapped into the page tables. This happens in XFS from fs_tosspages() and fs_flushinval_pages()
/archives/xfs/2007-01/msg00250.html (10,205 bytes)

12. Re: Review: fix mapping invalidation callouts (score: 1)
Author:
Date: Mon, 8 Jan 2007 09:09:16 +0000
Generally looks good. But I feel a little cautios about changes in this area, so we should throw all possible test loads at this before commiting it.
/archives/xfs/2007-01/msg00253.html (9,585 bytes)

13. Re: Review: fix mapping invalidation callouts (score: 1)
Author: >
Date: Tue, 9 Jan 2007 10:04:29 +1100
Yup - fsx is one test that I really want to hit with this. The guy that reported the initial problem has replied saying this patch fixes the warnings (good start ;), but I'll hold off pushing it for
/archives/xfs/2007-01/msg00272.html (10,549 bytes)

14. Re: Review: fix mapping invalidation callouts (score: 1)
Author: >
Date: Tue, 09 Jan 2007 11:57:38 +0000
David Chinner wrote: On Mon, Jan 08, 2007 at 09:09:16AM +0000, Christoph Hellwig wrote: On Mon, Jan 08, 2007 at 03:03:09PM +1100, David Chinner wrote: With the recent cancel_dirty_page() changes, a w
/archives/xfs/2007-01/msg00288.html (11,444 bytes)

15. Re: Review: fix mapping invalidation callouts (score: 1)
Author: >
Date: Wed, 10 Jan 2007 11:10:28 +1100
By definition fs_flush_pages() only flushes pages. If you need to flush and invalidate pages, you use fs_flushinval_pages(). Passing B_INVAL to fs_flush_pages() is broken code. good ;) Cheers, Dave.
/archives/xfs/2007-01/msg00289.html (9,433 bytes)

16. Re: Review: fix mapping invalidation callouts (score: 1)
Author: )
Date: Wed, 10 Jan 2007 17:23:44 +1100
I don't think this is right. Assuming 4k page size, first = 2k, last = 6k will result in invalidating page indexes 1 and 2 i.e. offset 4k -> 12k. In fact, we want to invalidate pages 0 and 1. IOWs, I
/archives/xfs/2007-01/msg00295.html (10,885 bytes)

17. Re: Review: fix mapping invalidation callouts (score: 1)
Author: >
Date: Wed, 10 Jan 2007 08:39:33 +0000
David Chinner wrote: On Mon, Jan 08, 2007 at 03:03:09PM +1100, David Chinner wrote: With the recent cancel_dirty_page() changes, a warning was added if we cancel a dirty page that is still mapped int
/archives/xfs/2007-01/msg00296.html (11,566 bytes)

18. Re: Review: fix mapping invalidation callouts (score: 1)
Author: )
Date: Thu, 11 Jan 2007 17:49:58 +1100
Yeah, you'd think so. The first xfsqa run I do -after- checking it in (been running for 24 hours) I get a stack dump with the warning in cancel_dirty_page(), so clearly this isn't right either. I'm n
/archives/xfs/2007-01/msg00309.html (12,222 bytes)

19. Re: Review: fix mapping invalidation callouts (score: 1)
Author: >
Date: Thu, 11 Jan 2007 19:00:32 +1100
Of course, I just realised that this is 2.6.19 that I'm testing on (fmeh) and so the code is different - cancel-dirty_page() doesn't exist in this tree, and the warning is coming from invalidate_inod
/archives/xfs/2007-01/msg00310.html (10,624 bytes)

20. Re: Review: fix mapping invalidation callouts (score: 1)
Author: >
Date: Thu, 11 Jan 2007 19:01:37 +1100
Ack. Lets get Donald to pull 2.6.20-rc into 2.6.x-xfs, or do we need to wait until you have this fixed? David -- David Chatterton XFS Engineering Manager SGI Australia
/archives/xfs/2007-01/msg00311.html (13,065 bytes)


This search system is powered by Namazu