On Fri, 17 Feb 2006, Bryce Harrington wrote: > On Fri, Feb 17, 2006 at 11:03:43AM +0000, Mel Gorman wrote: > > On Tue, 14 Feb 2006, Bryce Harrington wrote: > > > On Fri, Jan 20, 2006 at 11:54:15AM +0000, Mel Gorman wrote: > > > > This is a rebase of the list-based anti-fragmentation approach to act as > > > ... > > > > > > Hi Mel, > > > > > > By chance do you have a web or ftp site where these patches are posted? > > > > > > > I didn't, but I do now. > > > > list-based anti-fragmentation > > o http://www.csn.ul.ie/~mel/projects/patches/brokenout/mbuddy/v22 > > o Full patch is called full-mbuddy-v22.diff > > zone-based anti-fragmentation > > o http://www.csn.ul.ie/~mel/projects/patches/brokenout/zbuddy/v5 > > o Full patch is called zbuddy-v5-full.diff > > Great, thanks! > Thank you for picking them up. > > > Also, would you find cross compile testing of your patches to be of > > > interest? > > > > > > > I would. While I currently have access to the machines needed to > > cross-compile, I do not have any automated mechanism setup for > > anti-fragmentation yet so I only test ppc64 and x86. Greater coverage > > would be ideal. > > Okay, great. We have an automated cross compile system here at osdl > called PLM, that will now watch for new patches at the mbuddy and zbuddy > URL's. Great. They will always be in a vN directory where N is the number of release. > The compile results are all posted on the web as soon as they > run, but I will also try to always review them and identify > "interesting" results for you (e.g., new warnings or errors beyond what > the base kernels would have). > That would be very handy. I generally try and catch all of these things before I release, but something will eventually slip through. > > > (I've been running cross-compile tests for the NFSv4 developers for the > > > past year and would be happy to do the same for memory hotplug if it > > > would be of interest.) > > > > > > > I'd appreciate it. However, to be clear, the patches I am working on are > > for anti-fragmentation which will be of benefit to memory hotplug and for > > huge tlb. For the memory hotplug patches and the -mhp tree, Dave Hansen is > > the man to talk to. > > Yup, actually we've been pulling Dave's patches for a while. But since > we've already got the tools set up and automated, they can handle some > more work. ;-) > Suits me just fine. > Also, if you know of any regression or performance tests that you'd find > useful to have run automatically for anti-fragmentation (or other > memory-related aspects), I could work on setting those up to run on x86, > and later x86_64 and ia64. > The tests I always run are posted with each patch. On VMRegress, they correspond to bench-kbuild, bench-aim9, bench-stresshighalloc, bench-hugetlbcap and more recently bench-hotremovecap. However, I'm interested in any performance figures or reports you are willing to generate on as many platforms as possible. -- Mel Gorman Part-time Phd Student Linux Technology Center University of Limerick IBM Dublin Software Lab
