Re: [PATCH v2] f2fs: avoid stucking GC due to atomic write

2018-05-04 Thread Jaegeuk Kim
On 05/02, Chao Yu wrote: > On 2018/4/28 10:34, Jaegeuk Kim wrote: > > On 04/27, Chao Yu wrote: > >> On 2018/4/26 23:54, Jaegeuk Kim wrote: > >>> On 04/24, Chao Yu wrote: > f2fs doesn't allow abuse on atomic write class interface, so except > limiting in-mem pages' total memory usage capac

Re: [PATCH v2] f2fs: avoid stucking GC due to atomic write

2018-05-01 Thread Chao Yu
On 2018/4/28 10:34, Jaegeuk Kim wrote: > On 04/27, Chao Yu wrote: >> On 2018/4/26 23:54, Jaegeuk Kim wrote: >>> On 04/24, Chao Yu wrote: f2fs doesn't allow abuse on atomic write class interface, so except limiting in-mem pages' total memory usage capacity, we need to limit atomic-wri

Re: [PATCH v2] f2fs: avoid stucking GC due to atomic write

2018-04-27 Thread Jaegeuk Kim
On 04/27, Chao Yu wrote: > On 2018/4/26 23:54, Jaegeuk Kim wrote: > > On 04/24, Chao Yu wrote: > >> f2fs doesn't allow abuse on atomic write class interface, so except > >> limiting in-mem pages' total memory usage capacity, we need to limit > >> atomic-write usage as well when filesystem is seriou

Re: [PATCH v2] f2fs: avoid stucking GC due to atomic write

2018-04-26 Thread Chao Yu
On 2018/4/26 23:54, Jaegeuk Kim wrote: > On 04/24, Chao Yu wrote: >> f2fs doesn't allow abuse on atomic write class interface, so except >> limiting in-mem pages' total memory usage capacity, we need to limit >> atomic-write usage as well when filesystem is seriously fragmented, >> otherwise we may

Re: [PATCH v2] f2fs: avoid stucking GC due to atomic write

2018-04-26 Thread Jaegeuk Kim
On 04/24, Chao Yu wrote: > f2fs doesn't allow abuse on atomic write class interface, so except > limiting in-mem pages' total memory usage capacity, we need to limit > atomic-write usage as well when filesystem is seriously fragmented, > otherwise we may run into infinite loop during foreground GC

[PATCH v2] f2fs: avoid stucking GC due to atomic write

2018-04-23 Thread Chao Yu
f2fs doesn't allow abuse on atomic write class interface, so except limiting in-mem pages' total memory usage capacity, we need to limit atomic-write usage as well when filesystem is seriously fragmented, otherwise we may run into infinite loop during foreground GC because target blocks in victim s