Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*Speed\s+up\s+xfsdump\s+\?\s*$/>

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*Speed\s+up\s+xfsdump\s+\?\s*$/: 28 ]

Total 28 documents matching your query.

1. Speed up xfsdump ? (score: 1): Author: Nicolas Kowalski <Nicolas.Kowalski@xxxxxxx>; Date: Mon, 12 Sep 2005 18:43:39 +0200; I am testing the backup of a new SCSI-attached RAID5 SATA array on a SDLT320 tape drive, using xfsdump 2.2.27. I noticed that xfsdump is "much" slower than tar of cpio, and I would like to know if I; /archives/xfs/2005-09/msg00073.html (8,810 bytes)
2. Re: Speed up xfsdump ? (score: 1): Author: Lonni J Friedman <netllama@xxxxxxxxxxxxx>; Date: Mon, 12 Sep 2005 10:56:45 -0500 (EST); more RAM? -- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Lonni J Friedman netllama@xxxxxxxxxxxxx LlamaLand http://netllama.linux-sxs.org; /archives/xfs/2005-09/msg00075.html (8,804 bytes)
3. Re: Speed up xfsdump ? (score: 1): Author: Nicolas Kowalski <Nicolas.Kowalski@xxxxxxx>; Date: Mon, 12 Sep 2005 19:04:05 +0200; I should have mentionned it: the server has 512MB of RAM, and during the tests, no relevant swap was used, so I guess it's not the problem... -- Nicolas; /archives/xfs/2005-09/msg00076.html (8,877 bytes)
4. Re: Speed up xfsdump ? (score: 1): Author: Bill Kendall <wkendall@xxxxxxx>; Date: Mon, 12 Sep 2005 12:27:05 -0500; I am testing the backup of a new SCSI-attached RAID5 SATA array on a SDLT320 tape drive, using xfsdump 2.2.27. I noticed that xfsdump is "much" slower than tar of cpio, and I would like to know if I; /archives/xfs/2005-09/msg00077.html (11,270 bytes)
5. Re: Speed up xfsdump ? (score: 1): Author: "Bryan J. Smith" <b.j.smith@xxxxxxxx>; Date: Mon, 12 Sep 2005 10:39:56 -0700 (PDT); Hmmm, are you trying to use "dd" as a buffering program? I think there are far better programs to do such. Heck, what do you get if you just use "-f /dev/nst0" directory by xfsdump? I don't think you; /archives/xfs/2005-09/msg00078.html (9,473 bytes)
6. Re: Speed up xfsdump ? (score: 1): Author: "Bryan J. Smith" <b.j.smith@xxxxxxxx>; Date: Mon, 12 Sep 2005 10:42:23 -0700 (PDT); Agreed. Play with the blocking/buffering options of xfsdump itself. Again (I know, I'm repeating myself), there is no reason to use an external buffering program to a local tape device. Only if you a; /archives/xfs/2005-09/msg00080.html (9,587 bytes)
7. Re: Speed up xfsdump ? (score: 1): Author: Tim Shimmin <tes@xxxxxxx>; Date: Tue, 13 Sep 2005 12:38:53 +1000; My 2 cents FWIW. The -d 8192 means that the media files are around 8192Mb i.e. they are big and should be less of them. Each media file is a contained unit and repeats a header with directories and i; /archives/xfs/2005-09/msg00084.html (11,264 bytes)
8. Re: Speed up xfsdump ? (score: 1): Author: Nicolas Kowalski <Nicolas.Kowalski@xxxxxxx>; Date: Tue, 13 Sep 2005 10:44:54 +0200; Using this exact command line (plus '-p 300' to see the status) does not improve the speed. At the end, xfsdump shows me: xfsdump: dump size (non-dir files) : 28364433152 bytes xfsdump: dump complete; /archives/xfs/2005-09/msg00085.html (8,756 bytes)
9. Re: Speed up xfsdump ? (score: 1): Author: Nicolas Kowalski <Nicolas.Kowalski@xxxxxxx>; Date: Tue, 13 Sep 2005 13:07:06 +0200; [...] Using your tips, I also tested with this: xfsdump -J -f /dev/nst0 -S -p 300 -b 262144 /raid At the end, I have: xfsdump: dump size (non-dir files) : 28364432208 bytes xfsdump: dump complete: 46; /archives/xfs/2005-09/msg00086.html (9,704 bytes)
10. Re: Speed up xfsdump ? (score: 1): Author: Bill Kendall <wkendall@xxxxxxx>; Date: Tue, 13 Sep 2005 08:25:32 -0500; Nicolas Kowalski wrote: On Tue, 13 Sep 2005, Tim Shimmin wrote: On Mon, Sep 12, 2005 at 10:42:23AM -0700, Bryan J. Smith wrote: Bill Kendall <wkendall@xxxxxxx> wrote: Try the dump this way and see if; /archives/xfs/2005-09/msg00087.html (11,142 bytes)
11. Re: Speed up xfsdump ? (score: 1): Author: Nicolas Kowalski <Nicolas.Kowalski@xxxxxxx>; Date: Tue, 13 Sep 2005 17:42:30 +0200; I guess it's not related to the interaction between xfsdump and the tape drive: in my initial tests, I used dd to write on the tape. Here is the result you asked for: It gives me: xfsdump: dump size; /archives/xfs/2005-09/msg00088.html (10,237 bytes)
12. Re: Speed up xfsdump ? (score: 1): Author: dean gaudet <dean-list-linux-xfs@xxxxxxxxxx>; Date: Tue, 13 Sep 2005 09:35:57 -0700 (PDT); if the xfs filesystem was created "live" and had files added/deleted along the way it's likely to be more fragmented than a freshly created ext3 filesystem which had a bunch of files copied to it rig; /archives/xfs/2005-09/msg00089.html (9,892 bytes)
13. Re: Speed up xfsdump ? (score: 1): Author: Nicolas Kowalski <Nicolas.Kowalski@xxxxxxx>; Date: Tue, 13 Sep 2005 18:48:02 +0200; That's what I do: all my tests with xfsdump are done on a newly created/populated filesystem, so that fragmentation does not "corrupt" my results. -- Nicolas; /archives/xfs/2005-09/msg00090.html (10,006 bytes)
14. Re: Speed up xfsdump ? (score: 1): Author: Andi Kleen <ak@xxxxxxx>; Date: 14 Sep 2005 09:06:32 +0200; I remember looking at the code some time ago. It shouldn't be that hard to port to pthreads shouldn't it? Any specific reason that hasn't been done yet? -Andi; /archives/xfs/2005-09/msg00091.html (9,114 bytes)
15. Speed up xfsdump ? (score: 1): Author: Nicolas Kowalski <Nicolas.Kowalski@xxxxxxx>; Date: Mon, 12 Sep 2005 18:43:39 +0200; I am testing the backup of a new SCSI-attached RAID5 SATA array on a SDLT320 tape drive, using xfsdump 2.2.27. I noticed that xfsdump is "much" slower than tar of cpio, and I would like to know if I; /archives/xfs/2005-09/msg00288.html (8,810 bytes)
16. Re: Speed up xfsdump ? (score: 1): Author: Lonni J Friedman <netllama@xxxxxxxxxxxxx>; Date: Mon, 12 Sep 2005 10:56:45 -0500 (EST); more RAM? -- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Lonni J Friedman netllama@xxxxxxxxxxxxx LlamaLand http://netllama.linux-sxs.org; /archives/xfs/2005-09/msg00290.html (8,804 bytes)
17. Re: Speed up xfsdump ? (score: 1): Author: Nicolas Kowalski <Nicolas.Kowalski@xxxxxxx>; Date: Mon, 12 Sep 2005 19:04:05 +0200; I should have mentionned it: the server has 512MB of RAM, and during the tests, no relevant swap was used, so I guess it's not the problem... -- Nicolas; /archives/xfs/2005-09/msg00291.html (8,877 bytes)
18. Re: Speed up xfsdump ? (score: 1): Author: Bill Kendall <wkendall@xxxxxxx>; Date: Mon, 12 Sep 2005 12:27:05 -0500; I am testing the backup of a new SCSI-attached RAID5 SATA array on a SDLT320 tape drive, using xfsdump 2.2.27. I noticed that xfsdump is "much" slower than tar of cpio, and I would like to know if I; /archives/xfs/2005-09/msg00292.html (11,270 bytes)
19. Re: Speed up xfsdump ? (score: 1): Author: "Bryan J. Smith" <b.j.smith@xxxxxxxx>; Date: Mon, 12 Sep 2005 10:39:56 -0700 (PDT); Hmmm, are you trying to use "dd" as a buffering program? I think there are far better programs to do such. Heck, what do you get if you just use "-f /dev/nst0" directory by xfsdump? I don't think you; /archives/xfs/2005-09/msg00293.html (9,473 bytes)
20. Re: Speed up xfsdump ? (score: 1): Author: "Bryan J. Smith" <b.j.smith@xxxxxxxx>; Date: Mon, 12 Sep 2005 10:42:23 -0700 (PDT); Agreed. Play with the blocking/buffering options of xfsdump itself. Again (I know, I'm repeating myself), there is no reason to use an external buffering program to a local tape device. Only if you a; /archives/xfs/2005-09/msg00295.html (9,587 bytes)

Current List: 1 - 20
Page: [1] [2]