Messages in this thread | | | Date | Fri, 1 May 2015 19:48:20 +0200 (CEST) | From | Julia Lawall <> | Subject | RE: [HPDD-discuss] [PATCH 2/11] Staging: lustre: fld: Use kzalloc and kfree |
| |
On Fri, 1 May 2015, Simmons, James A. wrote:
> >From: Julia Lawall <Julia.Lawall@lip6.fr> > > > >Replace OBD_ALLOC, OBD_ALLOC_WAIT, OBD_ALLOC_PTR, and OBD_ALLOC_PTR_WAIT by > >kalloc/kcalloc, and OBD_FREE and OBD_FREE_PTR by kfree. > > Nak: James Simmons <jsimmons@infradead.org> > > A simple replace will not work. The OBD_ALLOC and OBD_FREE functions allocate memory > anywhere from one page to 4MB in size. You can't use kmalloc for the 4MB allocations. > Currently lustre uses a 4 page water mark to determine if we allocate using vmalloc. Even > using kmalloc for 4 pages has shown high failure rates on some systems. It gets even more > messy with 64K page systems like ppc64 boxes. Now I'm not suggesting to port the larger > allocations to vmalloc either since issues have been founded with using vmalloc. For example > when using large stripe count files the MDS rpc generated crosses the 4 page line and vmalloc > is used. Using vmalloc caused a global spinlock to be taken which causes meta data operations > to serialized on the MDS servers.
It's not the LARGE functions that do the switching? For example OBD_ALLOC ends up at __OBD_MALLOC_VERBOSE, which as far as I can see calls kmalloc (with __GFP_ZERO, and hance the use of kzalloc).
julia
| |