Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*TAKE\s+972756\s+\-\s+Implement\s+fallocate\.\s*$/: 20 ]

Total 20 documents matching your query.

1. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author: Eric Sandeen <sandeen@xxxxxxxxxxx>
Date: Mon, 10 Dec 2007 11:50:44 -0600
http://oss.sgi.com/cgi-bin/cvsweb.cgi/xfs-linux/> linux-2.6/xfs_iops.c.diff?r1=text&tr1=1.268&r2=text&tr2=1.267&f=h Is this ever going to go upstream...? -eric
/archives/xfs/2007-12/msg00059.html (8,178 bytes)

2. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author: Eric Sandeen <sandeen@xxxxxxxxxxx>
Date: Mon, 10 Dec 2007 11:50:44 -0600
http://oss.sgi.com/cgi-bin/cvsweb.cgi/xfs-linux/> linux-2.6/xfs_iops.c.diff?r1=text&tr1=1.268&r2=text&tr2=1.267&f=h Is this ever going to go upstream...? -eric
/archives/xfs/2007-12/msg00291.html (8,178 bytes)

3. TAKE 972756 - Implement fallocate. (score: 1)
Author: dgc@xxxxxxx (David Chinner)
Date: Fri, 2 Nov 2007 13:43:14 +1100 (EST)
Implement fallocate. Implement the new generic callout for file preallocation. Atomically change the file size if requested. The following file(s) were checked into: longdrop.melbourne.sgi.com:/isms/
/archives/xfs/2007-11/msg00016.html (8,165 bytes)

4. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author: "Bhagi rathi" <jahnu77@xxxxxxxxx>
Date: Tue, 6 Nov 2007 00:12:52 +0530
David, What happens if offset is not aligned to 4k? Let's say we have a file whose size is not aligned to 4k. It could have blocks beyond the eof which haven't been zero'ed out. fallocate may increas
/archives/xfs/2007-11/msg00040.html (10,608 bytes)

5. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author: David Chinner <dgc@xxxxxxx>
Date: Tue, 6 Nov 2007 11:12:23 +1100
No it won't. They are *preallocated* blocks, which by definition are zero-filled. Preallocated blocks are marked as unwritten on disk, so it is known that they contain zeros, even if they lie beyond
/archives/xfs/2007-11/msg00042.html (8,743 bytes)

6. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author: "Bhagi rathi" <jahnu77@xxxxxxxxx>
Date: Tue, 6 Nov 2007 22:57:03 +0530
File is of size 1k. A 4k block is allocated as file-system block size is Preallocation happened from 1k to 256k. Now, it looks to me that we have un-written extents from 4k to 256k. There is no guara
/archives/xfs/2007-11/msg00053.html (10,603 bytes)

7. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author: Eric Sandeen <sandeen@xxxxxxxxxxx>
Date: Tue, 06 Nov 2007 13:04:05 -0600
You've tested this and found it to be true? -Eric
/archives/xfs/2007-11/msg00056.html (9,220 bytes)

8. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author: David Chinner <dgc@xxxxxxx>
Date: Wed, 7 Nov 2007 07:41:00 +1100
-vp" /mnt/test/fred wrote 1024/1024 bytes at offset 0 1 KiB, 1 ops; 0.0000 sec (42.459 MiB/sec and 43478.2609 ops/sec) /mnt/test/fred: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL FLAGS 0: [0..7]:
/archives/xfs/2007-11/msg00059.html (9,899 bytes)

9. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author: Nathan Scott <nscott@xxxxxxxxxx>
Date: Wed, 07 Nov 2007 09:38:53 +1100
That guarantee does exist - when the initial 1K block write is done, the end of the block is zeroed (by the kernel write path). This is always done (guaranteed) and is required independently to unwri
/archives/xfs/2007-11/msg00061.html (9,303 bytes)

10. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author: "Bhagi rathi" <jahnu77@xxxxxxxxx>
Date: Wed, 7 Nov 2007 11:12:28 +0530
Since size log change and data I/O are not binded, it is always possible that size can reach to the disk before I/O reaching to the disk. Also, the other problem is because of speculative allocation.
/archives/xfs/2007-11/msg00065.html (11,307 bytes)

11. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author: nscott@xxxxxxxxxx
Date: Wed, 7 Nov 2007 20:35:21 +1100 (EST)
Not clear what that has to do with whether partial blocks are zeroed or not? Can you give a specific series of steps that would demonstrate a problem? (preferably with a test case) Again, I think a
/archives/xfs/2007-11/msg00067.html (10,353 bytes)

12. TAKE 972756 - Implement fallocate. (score: 1)
Author:
Date: Fri, 2 Nov 2007 13:43:14 +1100 (EST)
Implement fallocate. Implement the new generic callout for file preallocation. Atomically change the file size if requested. The following file(s) were checked into: longdrop.melbourne.sgi.com:/isms/
/archives/xfs/2007-11/msg00332.html (8,165 bytes)

13. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author:
Date: Tue, 6 Nov 2007 00:12:52 +0530
David, What happens if offset is not aligned to 4k? Let's say we have a file whose size is not aligned to 4k. It could have blocks beyond the eof which haven't been zero'ed out. fallocate may increas
/archives/xfs/2007-11/msg00356.html (10,608 bytes)

14. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author:
Date: Tue, 6 Nov 2007 11:12:23 +1100
No it won't. They are *preallocated* blocks, which by definition are zero-filled. Preallocated blocks are marked as unwritten on disk, so it is known that they contain zeros, even if they lie beyond
/archives/xfs/2007-11/msg00358.html (8,743 bytes)

15. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author:
Date: Tue, 6 Nov 2007 22:57:03 +0530
File is of size 1k. A 4k block is allocated as file-system block size is Preallocation happened from 1k to 256k. Now, it looks to me that we have un-written extents from 4k to 256k. There is no guara
/archives/xfs/2007-11/msg00369.html (10,603 bytes)

16. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author:
Date: Tue, 06 Nov 2007 13:04:05 -0600
You've tested this and found it to be true? -Eric
/archives/xfs/2007-11/msg00372.html (9,220 bytes)

17. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author:
Date: Wed, 7 Nov 2007 07:41:00 +1100
-vp" /mnt/test/fred wrote 1024/1024 bytes at offset 0 1 KiB, 1 ops; 0.0000 sec (42.459 MiB/sec and 43478.2609 ops/sec) /mnt/test/fred: EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL FLAGS 0: [0..7]:
/archives/xfs/2007-11/msg00375.html (9,899 bytes)

18. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author:
Date: Wed, 07 Nov 2007 09:38:53 +1100
That guarantee does exist - when the initial 1K block write is done, the end of the block is zeroed (by the kernel write path). This is always done (guaranteed) and is required independently to unwri
/archives/xfs/2007-11/msg00377.html (9,303 bytes)

19. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author:
Date: Wed, 7 Nov 2007 11:12:28 +0530
Since size log change and data I/O are not binded, it is always possible that size can reach to the disk before I/O reaching to the disk. Also, the other problem is because of speculative allocation.
/archives/xfs/2007-11/msg00381.html (11,307 bytes)

20. Re: TAKE 972756 - Implement fallocate. (score: 1)
Author:
Date: Wed, 7 Nov 2007 20:35:21 +1100 (EST)
Not clear what that has to do with whether partial blocks are zeroed or not? Can you give a specific series of steps that would demonstrate a problem? (preferably with a test case) Again, I think a
/archives/xfs/2007-11/msg00383.html (10,353 bytes)

Current List: 1 - 20
Page: [1]
This search system is powered by Namazu