From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gioh Kim Subject: Re: [PATCH] [RFC] CMA: clear buffer-head lru before page migration Date: Tue, 08 Jul 2014 13:44:04 +0900 Message-ID: <53BB7714.2020102@lge.com> References: <53B664E5.5060102@lge.com> <20140707155252.15e81dff6683393ba3590478@linux-foundation.org> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Laura Abbott , Michal Nazarewicz , Marek Szyprowski , Joonsoo Kim , Alexander Viro , linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, =?UTF-8?B?7J206rG07Zi4?= , Gi-Oh Kim To: Andrew Morton Return-path: In-Reply-To: <20140707155252.15e81dff6683393ba3590478@linux-foundation.org> Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-fsdevel.vger.kernel.org It's my fault. I'm going to send another patch ASAP. 2014-07-08 =EC=98=A4=EC=A0=84 7:52, Andrew Morton =EC=93=B4 =EA=B8=80: > On Fri, 04 Jul 2014 17:25:09 +0900 Gioh Kim wrote: > >> From: Gioh Kim >> Date: Fri, 4 Jul 2014 16:53:22 +0900 >> Subject: [PATCH] [RFC] CMA: clear buffer-head lru before page migrat= ion >> >> When CMA try to migrate page, some buffer-heads can exist on lru. >> The bh on lru has non-zero count value so that it cannot be dropped >> even-if it is not used. We can drop only buffers related to the >> migrated page, but it can take long time more than dropping all >> because of searching list. There all buffers in lru are dropped. >> >> Signed-off-by: Laura Abbott >> Signed-off-by: Gioh Kim >> --- >> fs/buffer.c | 13 +++++++++++++ >> 1 file changed, 13 insertions(+) >> >> diff --git a/fs/buffer.c b/fs/buffer.c >> index eba6e4f..4f11b7a 100644 >> --- a/fs/buffer.c >> +++ b/fs/buffer.c >> @@ -3233,6 +3233,19 @@ int try_to_free_buffers(struct page *page) >> if (PageWriteback(page)) >> return 0; >> >> +#ifdef CONFIG_CMA >> + /* >> + * When CMA try to migrate page, some buffer-heads can exist= on lru. >> + * The bh on lru has non-zero count value so that it cannot >> + * be dropped even-if it is not used. >> + * We can drop only buffers related to the migrated page, >> + * but it can take long time more than dropping all >> + * because of searching list. >> + * There all buffers in lru are dropped first. >> + */ >> + invalidate_bh_lrus(); >> +#endif > > No, this will be tremendously expensive. > > What I proposed is that CMA call invalidate_bh_lrus() right at the > outset. Something along the lines of > > --- a/mm/page_alloc.c~a > +++ a/mm/page_alloc.c > @@ -6329,6 +6329,14 @@ int alloc_contig_range(unsigned long sta > }; > INIT_LIST_HEAD(&cc.migratepages); > > +#ifdef CONFIG_CMA > + /* > + * Comment goes here > + */ > + if (migratetype =3D=3D MIGRATE_CMA) > + invalidate_bh_lrus(); > +#endif > + > /* > * What we do here is we mark all pageblocks in range as > * MIGRATE_ISOLATE. Because pageblock and max order pages may > > > - I'd have thought that it would make sense to do this for huge pages > as well (MIGRATE_MOVABLE) but nobody really seems to know. > > - There's a patch floating around ("Allow increasing the buffer-head > per-CPU LRU size") which will double the size of the bh lrus, so t= his > all becomes more important. > > - alloc_contig_range() does lru_add_drain_all() and drain_all_pages() > *after* performing the allocation. I can't work out why this is t= he > case and of course it is undocumented. If this is indeed not a bu= g > then probably the invalidate_bh_lrus() should happen in the same > place. >