Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*TAKE\s+\-\s+turn\s+on\s+delayed\s+allocation\s*$/: 14 ]

Total 14 documents matching your query.

1. Re: TAKE - turn on delayed allocation (score: 1)
Author: Russell Cattelan <cattelan@xxxxxxxxxxx>
Date: Wed, 10 May 2000 14:39:56 -0500
The corruption problem occurs with PAGEBUF_META off as well as on. Please don't through more variables in the mix just yet. http://oss.sgi.com/cgi-bin/cvsweb.cgi/linux-2.4-xfs/> linux/fs/page_buf.c.d
/archives/xfs/2000-05/msg00107.html (8,399 bytes)

2. Re: TAKE - turn on delayed allocation (score: 1)
Author: Rajagopal Ananthanarayanan <ananth@xxxxxxx>
Date: Wed, 10 May 2000 12:52:38 -0700
Well, it may not have to do with PAGEBUF_META. The corruption does seem to go away with delay_alloc ON. I'd like to get as much exposure with delay allocation: it's been in there for 3 weeks now ...
/archives/xfs/2000-05/msg00108.html (8,733 bytes)

3. Re: TAKE - turn on delayed allocation (score: 1)
Author: Russell Cattelan <cattelan@xxxxxxxxxxx>
Date: Wed, 10 May 2000 15:05:07 -0500
Can you verify that? I'm looking at the pagebuf_file_write path ... delayed alloc short circutes a lot code.... maks me wonder it the problem isn't someplace within the code that is then truned off.
/archives/xfs/2000-05/msg00109.html (9,540 bytes)

4. Re: TAKE - turn on delayed allocation (score: 1)
Author: Rajagopal Ananthanarayanan <ananth@xxxxxxx>
Date: Wed, 10 May 2000 13:15:41 -0700
I know one thing for sure: withe delay_alloc ON and PAGEBUF_META off I've never seen corruption. With a 3/30/2000 snap shot (before the days of delalloc): (a) Corruption with PAGEBUF_META ON (b) NO c
/archives/xfs/2000-05/msg00110.html (9,928 bytes)

5. Re: TAKE - turn on delayed allocation (score: 1)
Author: Rajagopal Ananthanarayanan <ananth@xxxxxxx>
Date: Wed, 10 May 2000 13:32:29 -0700
Another symptom I've seen with PAGEBUF_META turned on is that sometimes the machine freezes hard ... can't into kdb either when this happens. I've not seen any hard hangs with PAGEBUF_META off. -- Ra
/archives/xfs/2000-05/msg00111.html (8,324 bytes)

6. Re: TAKE - turn on delayed allocation (score: 1)
Author: Russell Cattelan <cattelan@xxxxxxxxxxx>
Date: Wed, 10 May 2000 15:51:29 -0500
It probably changes the timing enough. Page buf meta data had leakage problems at that time, which would cause other forms of corruption, hard to say what was causing what at that point. Corruption d
/archives/xfs/2000-05/msg00113.html (11,409 bytes)

7. TAKE - Turn ON delayed allocation (score: 1)
Author: Ananth Ananthanarayanan <ananth@xxxxxxxxxxxxxxxxxx>
Date: Thu, 25 May 2000 12:48:57 -0700
More stuff runs now without "VM killing process" problem. I've tried: bonnie, aim, dbench, doio and kernel compilation, all of which didn't show any problems. There are a couple of water-marks which
/archives/xfs/2000-05/msg00199.html (8,114 bytes)

8. Re: TAKE - turn on delayed allocation (score: 1)
Author: Russell Cattelan <cattelan@xxxxxxxxxxx>
Date: Wed, 10 May 2000 14:39:56 -0500
The corruption problem occurs with PAGEBUF_META off as well as on. Please don't through more variables in the mix just yet. http://oss.sgi.com/cgi-bin/cvsweb.cgi/linux-2.4-xfs/> linux/fs/page_buf.c.d
/archives/xfs/2000-05/msg00379.html (8,399 bytes)

9. Re: TAKE - turn on delayed allocation (score: 1)
Author: Rajagopal Ananthanarayanan <ananth@xxxxxxx>
Date: Wed, 10 May 2000 12:52:38 -0700
Well, it may not have to do with PAGEBUF_META. The corruption does seem to go away with delay_alloc ON. I'd like to get as much exposure with delay allocation: it's been in there for 3 weeks now ...
/archives/xfs/2000-05/msg00380.html (8,733 bytes)

10. Re: TAKE - turn on delayed allocation (score: 1)
Author: Russell Cattelan <cattelan@xxxxxxxxxxx>
Date: Wed, 10 May 2000 15:05:07 -0500
Can you verify that? I'm looking at the pagebuf_file_write path ... delayed alloc short circutes a lot code.... maks me wonder it the problem isn't someplace within the code that is then truned off.
/archives/xfs/2000-05/msg00381.html (9,540 bytes)

11. Re: TAKE - turn on delayed allocation (score: 1)
Author: Rajagopal Ananthanarayanan <ananth@xxxxxxx>
Date: Wed, 10 May 2000 13:15:41 -0700
I know one thing for sure: withe delay_alloc ON and PAGEBUF_META off I've never seen corruption. With a 3/30/2000 snap shot (before the days of delalloc): (a) Corruption with PAGEBUF_META ON (b) NO c
/archives/xfs/2000-05/msg00382.html (9,928 bytes)

12. Re: TAKE - turn on delayed allocation (score: 1)
Author: Rajagopal Ananthanarayanan <ananth@xxxxxxx>
Date: Wed, 10 May 2000 13:32:29 -0700
Another symptom I've seen with PAGEBUF_META turned on is that sometimes the machine freezes hard ... can't into kdb either when this happens. I've not seen any hard hangs with PAGEBUF_META off. -- Ra
/archives/xfs/2000-05/msg00383.html (8,324 bytes)

13. Re: TAKE - turn on delayed allocation (score: 1)
Author: Russell Cattelan <cattelan@xxxxxxxxxxx>
Date: Wed, 10 May 2000 15:51:29 -0500
It probably changes the timing enough. Page buf meta data had leakage problems at that time, which would cause other forms of corruption, hard to say what was causing what at that point. Corruption d
/archives/xfs/2000-05/msg00385.html (11,409 bytes)

14. TAKE - Turn ON delayed allocation (score: 1)
Author: Ananth Ananthanarayanan <ananth@xxxxxxxxxxxxxxxxxx>
Date: Thu, 25 May 2000 12:48:57 -0700
More stuff runs now without "VM killing process" problem. I've tried: bonnie, aim, dbench, doio and kernel compilation, all of which didn't show any problems. There are a couple of water-marks which
/archives/xfs/2000-05/msg00471.html (8,114 bytes)


This search system is powered by Namazu