From: Mingming Cao Subject: Re: [PATCH] jbd jbd2: fix dio write returning EIO whentry_to_release_page fails Date: Wed, 06 Aug 2008 15:57:57 -0700 Message-ID: <1218063477.6383.41.camel@mingming-laptop> References: <6.0.0.20.2.20080804185338.03bcd488@172.19.0.2> <20080804145047.04794bf3.akpm@linux-foundation.org> <1217907353.7611.39.camel@think.oraclecorp.com> <6.0.0.20.2.20080805134429.044569a0@172.19.0.2> <1217953055.7899.11.camel@think.oraclecorp.com> <1217971027.7516.20.camel@mingming-laptop> <1218029114.15342.58.camel@think.oraclecorp.com> <20080806135337.GA3615@duck.suse.cz> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Chris Mason , Hisashi Hifumi , Andrew Morton , linux-ext4@vger.kernel.org, linux-fsdevel@vger.kernel.org To: Jan Kara Return-path: In-Reply-To: <20080806135337.GA3615@duck.suse.cz> Sender: linux-fsdevel-owner@vger.kernel.org List-Id: linux-ext4.vger.kernel.org =E5=9C=A8 2008-08-06=E4=B8=89=E7=9A=84 15:53 +0200=EF=BC=8CJan Kara=E5=86= =99=E9=81=93=EF=BC=9A > On Wed 06-08-08 09:25:13, Chris Mason wrote: > > On Tue, 2008-08-05 at 14:17 -0700, Mingming Cao wrote: > > > =E5=9C=A8 2008-08-05=E4=BA=8C=E7=9A=84 12:17 -0400=EF=BC=8CChris = Mason=E5=86=99=E9=81=93=EF=BC=9A > > > > On Tue, 2008-08-05 at 13:51 +0900, Hisashi Hifumi wrote: > > > > > >> >=20 > > > > > >> > diff -Nrup linux-2.6.27-rc1.org/fs/jbd/transaction.c=20 > > > > > >linux-2.6.27-rc1/fs/jbd/transaction.c > > > > > >> > --- linux-2.6.27-rc1.org/fs/jbd/transaction.c 2008-07-29= =20 > > > > > >19:28:47.000000000 +0900 > > > > > >> > +++ linux-2.6.27-rc1/fs/jbd/transaction.c 2008-07-29 20:= 40:12.000000000 +0900 > > > > > >> > @@ -1764,6 +1764,12 @@ int journal_try_to_free_buffers(j= ournal_ > > > > > >> > */ > > > > > >> > if (ret =3D=3D 0 && (gfp_mask & __GFP_WAIT) && (gfp_ma= sk & __GFP_FS)) { > > > > > >> > journal_wait_for_transaction_sync_data(journal); > > > > > >> > + > > > > > >> > + bh =3D head; > > > > > >> > + do { > > > > > >> > + while (atomic_read(&bh->b_count)) > > > > > >> > + schedule(); > > > > > >> > + } while ((bh =3D bh->b_this_page) !=3D head); > > > > > >> > ret =3D try_to_free_buffers(page); > > > > > >> > } > > > > > >>=20 > > > > > >> The loop is problematic. If the scheduler decides to keep= running this > > > > > >> task then we have a busy loop. If this task has realtime = policy then > > > > > >> it might even lock up the kernel. > > > > > >>=20 > > > > > > > > > > > >ocfs2 calls journal_try_to_free_buffers too, looping on b_co= unt might > > > > > >not be the best idea there either. > > > > > > > > > > > >This code gets called from releasepage, which is used other = places than > > > > > >the O_DIRECT invalidation paths, I'd be worried about perfor= mance > > > > > >problems here. > > > > > > > > > > >=20 > > > > > try_to_release_page has gfp_mask parameter. So when try_to_re= leasepage > > > > > is called from performance sensitive part, gfp_mask should no= t be set. > > > > > b_count check loop is inside of (gfp_mask & __GFP_WAIT) && (g= fp_mask & __GFP_FS) check. > > > >=20 > > > > Looks like try_to_free_pages will go into releasepage with wait= & fs > > > > both set. This kind of change would make me very nervous. > > > >=20 > > >=20 > > > Hi Chris, > > >=20 > > > The gfp_mask try_to_free_pages() takes from it's caller will past= it > > > down to try_to_release_page(). Based on the meaning of __GFP_WAI= T and > > > GFP_FS, if the upper level caller set these two flags, I assume = the > > > upper level caller expect delay and wait for fs to finish? > > >=20 > > >=20 > > > But I agree that using a loop in journal_try_to_free_buffers() to= wait > > > for the busy bh release the counter is expensive... > >=20 > > I rediscovered your old thread about trying to do this in a launder= _page > > call ;) > Yes, we thought about using launder_page() before :). >=20 > > Does it make more sense to fix do_launder_page to call into the FS = on > > every page, and let the FS check for PageDirty on its own? That wa= y > > invalidate_inode_pages2_range basically gets its own private call i= nto > > the FS that says wait around until this page is really free. > That would certainly work as well. But IMHO waiting for ->writepage= () > call to finish isn't really a big deal even in try_to_release_page() = if > __GFP_FS (and __GFP_WAIT) is set. The only problem is that there is n= o > effective way to do so and so Hisashi used that "wait for b_count to = drop" > which looks really scary and I don't like it as well. >=20 I was looking at the comment in invalidate_complete_page2(), which is now only called from DIO path, it saids /* * This is like invalidate_complete_page(), except it ignores the page'= s * refcount. We do this because invalidate_inode_pages2() needs stronger * invalidation guarantees, and cannot afford to leave pages behind because * shrink_page_list() has a temp ref on them, or because they're transiently * sitting in the lru_cache_add() pagevecs. */ I am wondering why we need stronger invalidate hurantees for DIO-> invalidate_inode_pages_range(),which force the page being removed from page cache? In case of bh is busy due to ext3 writeout, journal_try_to_free_buffers() could return different error number(EBUSY= ) to try_to_releasepage() (instead of EIO). In that case, could we just leave the page in the cache, clean pageuptodate() (to force later buffe= r read to read from disk) and then invalidate_complete_page2() return successfully? Any issue with this way? Mingming > Honza -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel= " in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html