Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*deep\s+chmod\|chown\s+\-R\s+begin\s+to\s+start\s+OOMkiller\s*$/: 59 ]

Total 59 documents matching your query.

1. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: Peter Broadwell <peter@xxxxxxxx>
Date: Fri, 12 May 2006 12:36:21 -0700
I seem to be having the same problem as CHIKAMA Masaki was having in December namely "chown -R" running very slowly when hitting lots of files (~17 million in my case). My machine doesn't have the sa
/archives/xfs/2006-05/msg00012.html (27,650 bytes)

2. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: Anders Saaby <as@xxxxxxxxxxxx>
Date: Mon, 15 May 2006 11:59:34 +0200
Do you have high CPU usage when running the chown? - Or just processes hanging i D-state? -- Med venlig hilsen - Best regards - Meilleures salutations Anders Saaby Systems Engineer -- Cohaesio A/S -
/archives/xfs/2006-05/msg00016.html (31,400 bytes)

3. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: David Chinner <dgc@xxxxxxx>
Date: Mon, 15 May 2006 23:29:36 +1000
The problem is different because there's no OOM killer being invoked, right? All you see is a slowdown? How much CPU time is the chmod consuming? Well, doing a chmod on a single file requires an inod
/archives/xfs/2006-05/msg00019.html (10,656 bytes)

4. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: Peter Broadwell <peter@xxxxxxxx>
Date: Mon, 15 May 2006 14:57:59 -0700
Thanks first off for your reply as well. It was your old postings that inspired me to even ask my question... You're right that their is no OOMKiller on my system, so the problem is perhaps unrelate
/archives/xfs/2006-05/msg00020.html (12,501 bytes)

5. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: Peter Broadwell <peter@xxxxxxxx>
Date: Mon, 15 May 2006 14:30:54 -0700
First, thanks for the reply. Yes, high CPU load, around 6-7 on a dual AMD Opteron system but much of it may be caused by other things running. Is there some tool that can isolate the load vs. D-stat
/archives/xfs/2006-05/msg00021.html (29,849 bytes)

6. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: Peter Broadwell <peter@xxxxxxxx>
Date: Mon, 15 May 2006 20:12:06 -0700
David Chinner wrote: On Mon, May 15, 2006 at 02:30:54PM -0700, Peter Broadwell wrote: My chown did finally finish, some 63 hrs later for about 75 chowns/sec. This is running on system with 4 SATA 720
/archives/xfs/2006-05/msg00022.html (12,364 bytes)

7. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: David Chinner <dgc@xxxxxxx>
Date: Tue, 16 May 2006 15:09:43 +1000
If you wanted to change every inode in the filesystem, then yes, it could be done this way (e.g. an inode cluster at a time). And the difference in I/Os would be more like an order of magnitude. Howe
/archives/xfs/2006-05/msg00023.html (10,522 bytes)

8. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: Peter Broadwell <peter@xxxxxxxx>
Date: Fri, 12 May 2006 12:36:21 -0700
I seem to be having the same problem as CHIKAMA Masaki was having in December namely "chown -R" running very slowly when hitting lots of files (~17 million in my case). My machine doesn't have the sa
/archives/xfs/2006-05/msg00112.html (27,650 bytes)

9. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: Anders Saaby <as@xxxxxxxxxxxx>
Date: Mon, 15 May 2006 11:59:34 +0200
Do you have high CPU usage when running the chown? - Or just processes hanging i D-state? -- Med venlig hilsen - Best regards - Meilleures salutations Anders Saaby Systems Engineer -- Cohaesio A/S -
/archives/xfs/2006-05/msg00116.html (31,400 bytes)

10. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: David Chinner <dgc@xxxxxxx>
Date: Mon, 15 May 2006 23:29:36 +1000
The problem is different because there's no OOM killer being invoked, right? All you see is a slowdown? How much CPU time is the chmod consuming? Well, doing a chmod on a single file requires an inod
/archives/xfs/2006-05/msg00119.html (10,656 bytes)

11. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: Peter Broadwell <peter@xxxxxxxx>
Date: Mon, 15 May 2006 14:57:59 -0700
Thanks first off for your reply as well. It was your old postings that inspired me to even ask my question... You're right that their is no OOMKiller on my system, so the problem is perhaps unrelate
/archives/xfs/2006-05/msg00120.html (12,501 bytes)

12. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: Peter Broadwell <peter@xxxxxxxx>
Date: Mon, 15 May 2006 14:30:54 -0700
First, thanks for the reply. Yes, high CPU load, around 6-7 on a dual AMD Opteron system but much of it may be caused by other things running. Is there some tool that can isolate the load vs. D-stat
/archives/xfs/2006-05/msg00121.html (29,849 bytes)

13. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: Peter Broadwell <peter@xxxxxxxx>
Date: Mon, 15 May 2006 20:12:06 -0700
David Chinner wrote: On Mon, May 15, 2006 at 02:30:54PM -0700, Peter Broadwell wrote: My chown did finally finish, some 63 hrs later for about 75 chowns/sec. This is running on system with 4 SATA 720
/archives/xfs/2006-05/msg00122.html (12,364 bytes)

14. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: David Chinner <dgc@xxxxxxx>
Date: Tue, 16 May 2006 15:09:43 +1000
If you wanted to change every inode in the filesystem, then yes, it could be done this way (e.g. an inode cluster at a time). And the difference in I/Os would be more like an order of magnitude. Howe
/archives/xfs/2006-05/msg00123.html (10,522 bytes)

15. deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: CHIKAMA masaki <masaki-c@xxxxxxxxxx>
Date: Wed, 7 Dec 2005 18:35:31 +0900
Hello all. I have trouble about a storange behavior on xfs fileststem. When I did "chmod -R 755 ." on deep directory, the system became slow down and began to start OOMkiller after a while. At that t
/archives/xfs/2005-12/msg00028.html (8,408 bytes)

16. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: David Chinner <dgc@xxxxxxx>
Date: Thu, 8 Dec 2005 18:08:41 +1100
How many files in the directory structure and how deep is it? What is the machine you are running this test on (CPU, ram, etc). Can you send the output of /proc/meminfo, /proc/slabinfo and the OOM ki
/archives/xfs/2005-12/msg00037.html (9,971 bytes)

17. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: CHIKAMA masaki <masaki-c@xxxxxxxxxx>
Date: Fri, 9 Dec 2005 10:41:48 +0900
The directory structure is like this. A/B/C/D/E/F.jpg A: from "1" to "14" B: from "0" to "16" C: "00" D: from "0" to "6" E: from "0" to "255" F: from "0" to "255" The number of files should be aroun
/archives/xfs/2005-12/msg00040.html (13,865 bytes)

18. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: David Chinner <dgc@xxxxxxx>
Date: Mon, 12 Dec 2005 12:46:33 +1100
Lots of files. Large filesystem, comparitively little RAM to speak of. Looks to me like you haven't got enough memory to hold all the active log items when chmod -R runs and so you run out of memory
/archives/xfs/2005-12/msg00051.html (10,579 bytes)

19. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: Chris Wedgwood <cw@xxxxxxxx>
Date: Sun, 11 Dec 2005 18:34:42 -0800
It's it ia32 there will still be a limit of 900MB or so for slab anyhow. They then want to consider a 64-bit kernel if the CPU supports it.
/archives/xfs/2005-12/msg00053.html (9,692 bytes)

20. Re: deep chmod|chown -R begin to start OOMkiller (score: 1)
Author: Andi Kleen <ak@xxxxxxx>
Date: 12 Dec 2005 00:57:12 -0700
It is nasty that XFS can get into this state though. Would it make sense to limit the in memory log based on available memory? With such a limit it would still work, but slower, right? -Andi
/archives/xfs/2005-12/msg00054.html (9,958 bytes)


This search system is powered by Namazu