Messages in this thread | | | Date | Tue, 1 Dec 2015 16:15:42 +0900 | From | Sergey Senozhatsky <> | Subject | Re: [PATCH v3 2/2] zram: try vmalloc() after kmalloc() |
| |
On (12/01/15 15:35), Kyeongdon Kim wrote: [..] > @test #4 > kmalloc(f) > __vmalloc(f) > // cannot find failure both until now > > log message (test #4) : > <4>[ 641.440468][7] KDKIM: zcomp_lz4_create: 24: ret = ffffffc002190000 > <snip> > <4>[ 922.182980][7] KDKIM: zcomp_lz4_create: 24: ret = ffffffc002208000 > <snip> > <4>[ 923.197593][7] KDKIM: zcomp_lz4_create: 24: ret = ffffffc002020000 > <snip> > <4>[ 939.813499][7] KDKIM: zcomp_lz4_create: 24: ret = ffffffc0020a0000
Thanks!
> So,is there another problem if we remove the flag from both sides? >
Technically, '~__GFP_NOMEMALLOC' is what we've been doing for some time (well, always); and, as Minchan noted, zsmalloc does not depend on emergency pools.
I vote for removal of __GFP_NOMEMALLOC from both kmalloc() and __vmalloc().
(user can make ->max_strm big enough to deplete emergency mem; but I tend to ignore it).
Minchan?
-ss
| |