Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*performance\s+over\s+multiple\s+disks\s*$/: 23 ]

Total 23 documents matching your query.

1. re: performance over multiple disks (score: 1)
Author: Chris Tooley <ctooley@xxxxxxxx>
Date: 01 Nov 2002 09:41:05 -0600
Chalk it up to stupidity or just wanting to learn, but I don't understand the prime number rationale. I'm sure there is a perfectly legitimate reason, but I certainly don't know what it is. Could som
/archives/xfs/2002-11/msg00007.html (9,796 bytes)

2. : Question about kernel update (score: 1)
Author: Chris Tooley <ctooley@xxxxxxxx>
Date: 01 Nov 2002 09:41:05 -0600
ho
/archives/xfs/2002-11/msg00460.html (9,796 bytes)

3. linux-2.5 tree changes? (score: 1)
Author: ndeen <sandeen@xxxxxxx>
Date: Thu, 31 Oct 2002 10:49:47 -0700 (MST)
ch has started locking up when I run my backup script. The script creates a LVM snapshot for each of 3 LVs in turn and then uses xfsdump to back them up. After the lockup, no
/archives/xfs/2002-10/msg00761.html (7,878 bytes)

4. emove VPURGE (score: 1)
Author: h <james@xxxxxxxxxxxxx>
Date: Thu, 31 Oct 2002 10:16:42 -0800
're in kdb... but if you're in X, you're stuck there. Blindly typing "go<enter>" may get you going again. I put a fix in recently that prevents XFS from generating a transac
/archives/xfs/2002-10/msg00762.html (8,154 bytes)

5. cmds (score: 1)
Author: ndeen <sandeen@xxxxxxx>
Date: Thu, 31 Oct 2002 20:42:33 +0100
stored on disk. Would it be read faster
/archives/xfs/2002-10/msg00765.html (10,176 bytes)

6. s (score: 1)
Author: xfs@xxxxxxxxxxxxxxxxxxx
Date: Thu, 31 Oct 2002 11:47:03 -0800
kernel does indeed allow my backup to run. It is obvious that you guys have made a number of improvements in XFS/LVS integration in the last several months. I'm looking forwa
/archives/xfs/2002-10/msg00766.html (8,550 bytes)

7. (score: 1)
Author: ksimach@xxxxxxxxxxxxxx>
Date: Thu, 31 Oct 2002 21:13:32 +0100
single disk the read-time will be that of a single seek + file_size/transfer_rate (approxemately). If the file is spread over multiple disks the transfer-time will be reduc
/archives/xfs/2002-10/msg00768.html (9,969 bytes)

8. sks (score: 1)
Author: ksimach@xxxxxxxxxxxxxx>
Date: Thu, 31 Oct 2002 12:28:41 -0800
will have slower writes obv
/archives/xfs/2002-10/msg00770.html (8,787 bytes)

9. disks (score: 1)
Author: ksimach@xxxxxxxxxxxxxx>
Date: Thu, 31 Oct 2002 17:30:58 -0500
o be smart about MD devices and align things as a result of this. I'm not sure how well it works in practice though, I can test a little later... --cw P.S. You've got bogus 8-bit cruf
/archives/xfs/2002-10/msg00773.html (9,292 bytes)

10. l (score: 1)
Author: sandeen@xxxxxxx>
Date: Thu, 31 Oct 2002 10:49:47 -0700 (MST)
was done, since you h
/archives/xfs/2002-10/msg01540.html (7,878 bytes)

11. lurking compile error (score: 1)
Author: ndeen@xxxxxxx>
Date: Thu, 31 Oct 2002 10:16:42 -0800
st changed the way CVS is exported, perhaps there is a problem. We'll look into it today. Eric, That message was supposed to be sent last night, but
/archives/xfs/2002-10/msg01541.html (8,154 bytes)

12. Re: linux-2.5 tree changes? (score: 1)
Author: xxxxxxxxxxxxxxx>
Date: Thu, 31 Oct 2002 20:42:33 +0100
the lockup, no
/archives/xfs/2002-10/msg01544.html (10,176 bytes)

13. x-2.5 tree changes? (score: 1)
Author: xxxxx>
Date: Thu, 31 Oct 2002 11:47:03 -0800
ting a transac
/archives/xfs/2002-10/msg01545.html (8,550 bytes)

14. Lockup with LVM snapshot (score: 1)
Author: xxxxxx>
Date: Thu, 31 Oct 2002 21:13:32 +0100
be read faster
/archives/xfs/2002-10/msg01547.html (9,969 bytes)

15. performance over multiple disks (score: 1)
Author: xxxxxxx
Date: Thu, 31 Oct 2002 12:28:41 -0800
wa
/archives/xfs/2002-10/msg01549.html (8,787 bytes)

16. : re[2]: Lockup with LVM snapshot (score: 1)
Author: xxxxxx>
Date: Thu, 31 Oct 2002 17:30:58 -0500
writes obv
/archives/xfs/2002-10/msg01552.html (9,292 bytes)

17. performance over multiple disks (score: 1)
Author: James Rich <james@xxxxxxxxxxxxx>
Date: Thu, 31 Oct 2002 10:49:47 -0700 (MST)
On another mailing list a debate arose about performance over a single disk vs. multiple disks. It goes something like this: Suppose you have a 6 megabyte file stored on disk. Would it be read faster
/archives/xfs/2002-10/msg02319.html (7,878 bytes)

18. Re: performance over multiple disks (score: 1)
Author: Chris Wedgwood <cw@xxxxxxxx>
Date: Thu, 31 Oct 2002 10:16:42 -0800
It depends.... but usually data over multiple disks reads faster, sometimes n-times the speed of a single disk (but not always). --cw
/archives/xfs/2002-10/msg02320.html (8,250 bytes)

19. Re: performance over multiple disks (score: 1)
Author: Ragnar Kj°rstad <xfs@xxxxxxxxxxxxxxxxxxx>
Date: Thu, 31 Oct 2002 20:42:33 +0100
If the file is stored on a single disk the read-time will be that of a single seek + file_size/transfer_rate (approxemately). If the file is spread over multiple disks the transfer-time will be reduc
/archives/xfs/2002-10/msg02323.html (10,313 bytes)

20. Re: performance over multiple disks (score: 1)
Author: Chris Wedgwood <cw@xxxxxxxx>
Date: Thu, 31 Oct 2002 11:47:03 -0800
More disks -> more heads -> lower average seek time. If you experiment with this, you'll find eads over multiple disks and stripping is almost *always* faster. RAID4/RAID5 will have slower writes obv
/archives/xfs/2002-10/msg02324.html (8,656 bytes)


This search system is powered by Namazu