Messages in this thread | | | From | Ben Gamari <> | Subject | Re: [PATCH 2/3] Reclaim invalidated page ASAP | Date | Tue, 30 Nov 2010 09:11:01 -0500 |
| |
On Tue, 30 Nov 2010 09:18:22 +0000, Mel Gorman <mel@csn.ul.ie> wrote: > I would agree except as said elsewhere, it's a chicken and egg problem. > We don't have a real world test because fadvise is not useful in its > current iteration. I'm hoping that there will be a test comparing > > rsync on vanilla kernel > rsync on patched kernel > rsync+patch on vanilla kernel > rsync+patch on patched kernel > > Are the results of such a test likely to happen? > Yes, absolutely, although I'm sorry it has taken so long. Between thanksgiving and the impending end of the semester things have been a bit hectic. Nevertheless, I just finished putting together a script to record some metics from /proc/vmstat and /proc/[pid]/statm, so at this point I'm ready to finally take some data. Any suggestions for particular patterns to look for in the numbers or other metrics to record are welcome. Cheers,
- Ben
| |