Re: fadvise DONTNEED implementation (or lack thereof)

2010-11-15 Thread Ben Gamari
On Mon, 15 Nov 2010 16:28:32 +0900 (JST), KOSAKI Motohiro kosaki.motoh...@jp.fujitsu.com wrote: Who can make rsync like io pattern test suite? a code change is easy. but to comfirm justification is more harder work. I'm afraid I don't have time to work up any code. I would be happy to try the

Re: fadvise DONTNEED implementation (or lack thereof)

2010-11-14 Thread Brian K. White
On 11/14/2010 12:20 AM, Ben Gamari wrote: On Sun, 14 Nov 2010 14:09:29 +0900 (JST), KOSAKI Motohirokosaki.motoh...@jp.fujitsu.com wrote: Because we have an alternative solution already. please try memcgroup :) Alright, fair enough. It still seems like there are many cases where fadvise

Re: fadvise DONTNEED implementation (or lack thereof)

2010-11-09 Thread Ben Gamari
On Tue, 9 Nov 2010 16:28:02 +0900 (JST), KOSAKI Motohiro kosaki.motoh...@jp.fujitsu.com wrote: So, I don't think application developers will use fadvise() aggressively because we don't have a cross platform agreement of a fadvice behavior. I strongly disagree. For a long time I have been

fadvise DONTNEED implementation (or lack thereof)

2010-11-03 Thread Ben Gamari
I've recently been trying to track down the root cause of my server's persistent issue of thrashing horribly after being left inactive. It seems that the issue is likely my nightly backup schedule (using rsync) which traverses my entire 50GB home directory. I was surprised to find that rsync does