Re: [mmotm][experimental][PATCH] coalescing charge

[KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>]

On Fri, 4 Sep 2009 15:40:50 +0900
Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> wrote:

> On Fri, 4 Sep 2009 14:26:54 +0900, KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> wrote:
> > On Fri, 4 Sep 2009 14:21:43 +0900
> > KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> wrote:
> > 
> > > On Fri, 4 Sep 2009 14:11:57 +0900
> > > Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> wrote:
> > > 
> > > > > > > Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
> > > > > > It looks basically good. I'll do some tests with all patches applied.
> > > > > > 
> > > > > thanks.
> > > > > 
> > > > it seems that these patches make rmdir stall again...
> > > > This batched charge patch seems not to be the (only) suspect, though.
> > > > 
> > > Ouch, no probelm with the latest mmotm ? I think this charge-uncharge-offload
> > > patch set doesn't use css_set()/get()...
> > > Hm, softlimit related parts ?
> > > 
> hmm, these patches(including softlimit cleanup) seems not to be guilt.
> Current(I'm using mmotm-2009-08-27-16-51) mmotm seems to be broken about memcg's rmdir.
> 
> I must admit I've not tested mmotm for several months because I have been working
> on stabilizing mainline for a long time...
> 
> > Ah, one more question. What memory.usage_in_bytes shows in that case ?
> > If not zero, charge/uncharge coalescing is guilty.
> > 
> usage_in_bytes is 0.
> I've confirmed by crash command that the mem_cgroup has extra ref counts.
> 
> I'll dig more..
> 
Ok, then, I and you see different problem...
Hmm..css refcnt leak. I'll dig, too. I hope we can catch it before sneaking
into mainline.

Thanks,
-Kame

> 
> Thanks,
> Daisuke Nishimura.
> 

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>