From: Atsushi Kumagai <kumagai-atsushi@xxxxxxxxxxxxxxxxx> Subject: Re: makedumpfile memory usage grows with system memory size Date: Wed, 16 May 2012 17:02:30 +0900 > On Mon, 14 May 2012 14:44:28 +0900 (JST) > HATAYAMA Daisuke <d.hatayama at jp.fujitsu.com> wrote: >> Anyway, I think it better to add _mapcount information to VMCOREINFO >> on upstream as soon as possible. > > I think it's better way to use _mapcount. > But we don't certainly decide to use _mapcount and even if we decide to use it, > we still have problems to use it. > For example, the upstream kernel(v3.4-rc7) has _mapcount in union, we need > a information to judge whether the found data is _mapcount or not. > So, more investigation is needed and I think it's too early to send the request > to upstream kernel. A quick look into the other part of the union---inuse, objects, froze---to which _mapcount belongs, they appears to be used in SLUB allocator. The page with PG_slab appears to use the other part to _mapcount. This means that to decide whether to use _mapcount, it's necessary to first investigate how SLUB allocator works. > > I plan to finish working to reduce memory consumption by the end of June, > and I will continue to discuss performance issues. > Therefore, the request will be delayed until July or August. > I'll wait for your patch on memory consumption and feedback to it. I'll also look into possibility of filtering free memory in constant space on recent kernels. Thanks. HATAYAMA, Daisuke
