> Dan, I hope you will release these as a patchset against 2.6.22 when > it's out or 2.6.21. I find I have a lot more confidence in results, good > or bad, when comparing something I have run in production with just one > patchset added. There are enough other changes in an -rc to confuse the > issue, and I don't run them in production (at least not usually). > There has since been a some style cleanups and the raid5 refactor, but you can go grab the 2.6.21-iop1 patch series from SourceForge if you want to try these changes out. Use the attached series file instead of the one in the tarball. You can also wait for 2.6.22-iop1, which should be the final version of md-accel queued for the merge window. https://sourceforge.net/project/downloading.php?group_id=115074&filename =patches-2.6.21-iop1.tar.gz&47542009 > -- > bill davidsen <[email protected]> > CTO TMR Associates, Inc > Doing interesting things with small computers since 1979 Thank you for testing, Dan
Attachment:
series
Description: series
- References:
- Re: [md-accel PATCH 00/19] md raid acceleration and the async_tx api
- From: Bill Davidsen <[email protected]>
- Re: [md-accel PATCH 00/19] md raid acceleration and the async_tx api
- Prev by Date: Re: [PATCH] trim memory not covered by WB MTRRs
- Next by Date: Re: Please release a stable kernel Linux 3.0
- Previous by thread: Re: [md-accel PATCH 00/19] md raid acceleration and the async_tx api
- Next by thread: [patch 0/3] MAP_NOZERO - VM_NOZERO/MAP_NOZERO early summer madness
- Index(es):