From: Jon Nelson Subject: Re: hunt for 2.6.37 dm-crypt+ext4 corruption? (was: Re: dm-crypt barrier support is effective) Date: Tue, 7 Dec 2010 21:55:13 -0600 Message-ID: References: <4CF692D1.1010906@redhat.com> <4CF6B3E8.2000406@redhat.com> <20101201212310.GA15648@redhat.com> <20101204193828.GB13871@redhat.com> <20101207142145.GA27861@think> <20101207182243.GB21112@redhat.com> <1291747731-sup-3099@think> <1291751698-sup-9297@think> <1291754340-sup-1631@think> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Mike Snitzer , Matt , Milan Broz , Andi Kleen , linux-btrfs , dm-devel , Linux Kernel , htd , htejun , linux-ext4 To: Chris Mason Return-path: In-Reply-To: <1291754340-sup-1631@think> Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-ext4.vger.kernel.org On Tue, Dec 7, 2010 at 2:41 PM, Chris Mason wr= ote: > Excerpts from Jon Nelson's message of 2010-12-07 15:25:47 -0500: >> On Tue, Dec 7, 2010 at 2:02 PM, Chris Mason = wrote: >> > Excerpts from Jon Nelson's message of 2010-12-07 14:34:40 -0500: >> >> On Tue, Dec 7, 2010 at 12:52 PM, Chris Mason wrote: >> >> >> postgresql errors. Typically, header corruption but from the l= imited >> >> >> visibility I've had into this via strace, what I see is zeroed= pages >> >> >> where there shouldn't be. >> >> > >> >> > This sounds a lot like a bug higher up than dm-crypt. =C2=A0Zer= os tend to >> >> > come from some piece of code explicitly filling a page with zer= os, and >> >> > that often happens in the corner cases for O_DIRECT and a few o= ther >> >> > places in the filesystem. >> >> > >> >> > Have you tried triggering this with a regular block device? >> >> >> >> I just tried the whole set of tests, but with /dev/sdb directly (= as >> >> ext4) without any crypt-y bits. >> >> It takes more iterations but out of 6 tests I had one failure: sa= me >> >> type of thing, 'invalid page header in block ....'. >> >> >> >> I can't guarantee that it is a full-page of zeroes, just what I s= aw >> >> from the (limited) stracing I did. >> > >> > Fantastic. Now for our usual suspects: >> > >> > 1) Is postgres using O_DIRECT? =C2=A0If yes, please turn it off >> >> According to strace, O_DIRECT didn't show up once during the test. >> >> > 2) Is postgres allocating sparse files? =C2=A0If yes, please have = it fully >> > allocate the file instead. >> >> That's a tough one. I don't think postgresql does that, but I'm not = an >> expert here. > > Ok, please compare du -k and du -k --apparent-size for each of the > files involved in the postgres run. One of the files (the table itself) is very slightly sparse: 588240 (apparent) vs 588244 --=20 Jon