Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*stress\s+test\s+on\s+ppc\s*$/: 54 ]

Total 54 documents matching your query.

1. stress test on ppc (score: 1)
Author: Thomas Graichen <news-innominate.list.sgi.xfs@xxxxxxxxxxxxx>
Date: 9 Nov 2000 14:33:04 GMT
heres the output of a stress test run on a ppc machine ... i've set this one up here at work now and had to fiddle a bit with it due to the bad integration of the latest ppc code into the main kernel
/archives/xfs/2000-11/msg00047.html (17,038 bytes)

2. Re: stress test on ppc (score: 1)
Author: "Nathan Scott" <nathans@xxxxxxxxxxxxxxxxxxxxxxxx>
Date: Fri, 10 Nov 2000 11:03:05 -0400
hi Thomas, from a look at stress/common.rc i'd say your SCRATCH_DEV is either failing the "_is_block_dev" call (which isn't very clean - i'll checkin a new version in a second) or your SCRATCH_DEV is
/archives/xfs/2000-11/msg00051.html (9,349 bytes)

3. Re: stress test on ppc (score: 1)
Author: "Marcelo E. Magallon" <marcelo.magallon@xxxxxxxxxxx>
Date: Fri, 10 Nov 2000 09:41:51 +0100
This is the bash related bug I reported a while ago (I do remember seeing it commited to the CVS tree) Index: cmd/xfs/stress/002 == RCS file: /cvs/linux-2.4-xfs/cmd/xfs/stress/002,v retrieving revis
/archives/xfs/2000-11/msg00058.html (9,978 bytes)

4. Re: stress test on ppc (score: 1)
Author: "Nathan Scott" <nathans@xxxxxxxxxxxxxxxxxxxxxxxx>
Date: Sat, 11 Nov 2000 00:06:31 -0400
ah - I think I see whats happened - there's two -ne tests like this & last time I only fixed one ... hopefully its fixed now (as of two minutes ago). thanks. -- Nathan
/archives/xfs/2000-11/msg00063.html (9,449 bytes)

5. Re: stress test on ppc (score: 1)
Author: Thomas Graichen <thomas.graichen@xxxxxxxxxxxxxx>
Date: Fri, 10 Nov 2000 21:28:08 +0100
no it's a different one - so it must be the first - will try your new stuff on monday will do this on monday too - i'm at home right now t p.s.: also this machine is now running XFS / and is still up
/archives/xfs/2000-11/msg00070.html (10,278 bytes)

6. Re: stress test on ppc (score: 1)
Author: Thomas Graichen <news-innominate.list.sgi.xfs@xxxxxxxxxxxxx>
Date: 13 Nov 2000 08:11:57 GMT
ok - reran the tests with your fixes - the current results (with all the failed .out and .out.bad files) can be found at http://innominate.org/~graichen/projects/xfs/ppc/ppc.13-11-2000.tgz let my kno
/archives/xfs/2000-11/msg00079.html (11,244 bytes)

7. Re: stress test on ppc (score: 1)
Author: "Nathan Scott" <nathans@xxxxxxxxxxxxxxxxxxxxxxxx>
Date: Tue, 14 Nov 2000 10:59:49 -0400
hi Thomas, ok, some progress - looks like the scratch device problem is resolved and test 002 is fixed - great! 004 - this looks like a 32 bit number overflow in the xfs_db "freesp" command, i'll nee
/archives/xfs/2000-11/msg00082.html (11,308 bytes)

8. Re: stress test on ppc (score: 1)
Author: tes@xxxxxxxxxxxxxxxxxxxxxxx (Timothy Shimmin)
Date: Tue, 14 Nov 2000 13:55:46 +1100 (EDT)
Looks like a reoccurrence. The dump/restore is not reading the inventory. I'll use numeric gid instead (fixed in checkin). --Tim
/archives/xfs/2000-11/msg00084.html (9,934 bytes)

9. Re: stress test on ppc (score: 1)
Author: Thomas Graichen <news-innominate.list.sgi.xfs@xxxxxxxxxxxxx>
Date: 15 Nov 2000 09:37:03 GMT
will try that the current results (with fresh kernel and fresh cmd) are at http://innominate.org/~graichen/procjects/xfs/ppc.15-11-2000.tgz but they are at a rough view not really different - by mayb
/archives/xfs/2000-11/msg00098.html (13,233 bytes)

10. Re: stress test on ppc (score: 1)
Author: "Nathan Scott" <nathans@xxxxxxxxxxxxxxxxxxxxxxxx>
Date: Wed, 22 Nov 2000 12:44:25 -0400
hi Thomas, going through this one again - this doesn't look like a bug in xfs_db after all (the xfs_db output in the .bad file looks correct). (cmd/xfs/stress/004 on ppc produced...) QA output create
/archives/xfs/2000-11/msg00158.html (11,584 bytes)

11. Re: stress test on ppc (score: 1)
Author: Thomas Graichen <news-innominate.list.sgi.xfs@xxxxxxxxxxxxx>
Date: 24 Nov 2000 13:21:27 GMT
ok - here it is - sorry for the delay - i was a few days away: df gave: blocks=3136128 used=11488 avail=3124640 blocksize from xfs_db is '524288' xfs_db for /dev/hda9 from to extents blocks pct 1 1 4
/archives/xfs/2000-11/msg00170.html (13,328 bytes)

12. Re: stress test on ppc (score: 1)
Author: "Nathan Scott" <nathans@xxxxxxxxxxxxxxxxxxxxxxxx>
Date: Sun, 26 Nov 2000 13:36:46 -0400
hi Thomas, that's the problem right there (the blocksize). I don't understand how one could get a blocksize like that since the test runs mkfs.xfs on the scratch device and so should always have a bl
/archives/xfs/2000-11/msg00187.html (11,602 bytes)

13. Re: stress test on ppc (score: 1)
Author: Thomas Graichen <news-innominate.list.sgi.xfs@xxxxxxxxxxxxx>
Date: 27 Nov 2000 08:27:55 GMT
ah - i have an idea here: i'm currently using the ide driver from the ppc linux tree - where i had to add the case BLKSETSIZE: to ide_ioctl in ide.c - maybe i have missed something there - but from t
/archives/xfs/2000-11/msg00193.html (14,126 bytes)

14. Re: stress test on ppc (score: 1)
Author: "Nathan Scott" <nathans@xxxxxxxxxxxxxxxxxxxxxxxx>
Date: Tue, 28 Nov 2000 10:48:43 -0400
no, thats not it. the (filesystem) blocksize comes from mkfs.xfs and is written into all of the superblocks using the value which mkfs calculates. By default (which is the case, in test 004) this is
/archives/xfs/2000-11/msg00198.html (16,162 bytes)

15. Re: stress test on ppc (score: 1)
Author: Thomas Graichen <news-innominate.list.sgi.xfs@xxxxxxxxxxxxx>
Date: 28 Nov 2000 10:37:55 GMT
hm - but mkfs.xfs is using the correct one: ... naming =version 2 bsize=4096 log =internal log bsize=4096 blocks=1200 ... so you assume that either xfs_db gets it wrong or it is stored somehow wrong
/archives/xfs/2000-11/msg00203.html (16,787 bytes)

16. Re: stress test on ppc (score: 1)
Author: "Nathan Scott" <nathans@xxxxxxxxxxxxxxxxxxxxxxxx>
Date: Wed, 29 Nov 2000 09:40:41 -0400
you snipped the interesting bit there - a couple of lines up from "naming" ("data = bsize=????"). ;-) i'm not sure where its going wrong - test 004 does a mkfs, mount, a series of writes, umount, mo
/archives/xfs/2000-11/msg00206.html (12,228 bytes)

17. Re: stress test on ppc (score: 1)
Author: Thomas Graichen <news-innominate.list.sgi.xfs@xxxxxxxxxxxxx>
Date: 29 Nov 2000 09:21:42 GMT
looks like it happens pretty early ppc:/usr/src/xfs/cmd/xfs/mkfs # ./mkfs.xfs -f /dev/hda9 meta-data=/dev/hda9 isize=256 agcount=8, agsize=49152 blks data = bsize=4096 blocks=393216, imaxpct=25 = sun
/archives/xfs/2000-11/msg00208.html (12,467 bytes)

18. Re: stress test on ppc (score: 1)
Author: "Nathan Scott" <nathans@xxxxxxxxxxxxxxxxxxxxxxxx>
Date: Thu, 30 Nov 2000 10:40:48 -0400
hi Thomas, ok, so the problem is in either mkfs or xfs_db. after mkfs, run: 0000000 X F S B \0 \0 020 \0 0000012 you should see exactly that (the second 4 are the blocksize). if you do, its an xfs_db
/archives/xfs/2000-11/msg00213.html (12,213 bytes)

19. Re: stress test on ppc (score: 1)
Author: Thomas Graichen <news-innominate.list.sgi.xfs@xxxxxxxxxxxxx>
Date: 30 Nov 2000 09:01:12 GMT
ppc:~ # od -c -N 8 /dev/hda9 0000000 X F S B \0 \0 020 \0 0000010 ppc:~ # so it looks like xfs_db no problem ppc:~ # xfs_db -r -c sb -c p /dev/hda9 magicnum = 0x58465342 blocksize = 524288 dblocks =
/archives/xfs/2000-11/msg00217.html (13,908 bytes)

20. Re: stress test on ppc (score: 1)
Author: Russell Cattelan <cattelan@xxxxxxxxxxx>
Date: Thu, 30 Nov 2000 10:22:22 -0600
Ok this doesn't look good. Several fields looked bad already. Notably the rootino should be 128 Was this output taken directly after a mkfs or after a mount? We need to narrow down our problems. Firs
/archives/xfs/2000-11/msg00227.html (15,405 bytes)


This search system is powered by Namazu