Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759360AbXKLQsd (ORCPT ); Mon, 12 Nov 2007 11:48:33 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753841AbXKLQsZ (ORCPT ); Mon, 12 Nov 2007 11:48:25 -0500 Received: from viefep18-int.chello.at ([213.46.255.22]:27749 "EHLO viefep33-int.chello.at" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1752349AbXKLQsY (ORCPT ); Mon, 12 Nov 2007 11:48:24 -0500 Subject: Re: iozone write 50% regression in kernel 2.6.24-rc1 From: Peter Zijlstra To: Benny Halevy Cc: "Zhang, Yanmin" , LKML , Linus Torvalds , aneesh.kumar@linux.vnet.ibm.com In-Reply-To: <47386BC4.3050403@panasas.com> References: <1194601672.20251.60.camel@ymzhang> <1194602064.6289.157.camel@twins> <1194833640.20251.80.camel@ymzhang> <1194860728.7179.6.camel@twins> <1194861112.20251.124.camel@ymzhang> <1194873980.7179.31.camel@twins> <47386BC4.3050403@panasas.com> Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-i1pnZYr0NaGe/YhSV/NN" Date: Mon, 12 Nov 2007 17:48:20 +0100 Message-Id: <1194886100.9713.13.camel@twins> Mime-Version: 1.0 X-Mailer: Evolution 2.12.0 Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5562 Lines: 187 --=-i1pnZYr0NaGe/YhSV/NN Content-Type: text/plain Content-Transfer-Encoding: quoted-printable On Mon, 2007-11-12 at 17:05 +0200, Benny Halevy wrote: > On Nov. 12, 2007, 15:26 +0200, Peter Zijlstra wr= ote: > > Single socket, dual core opteron, 2GB memory > > Single SATA disk, ext3 > >=20 > > x86_64 kernel and userland > >=20 > > (dirty_background_ratio, dirty_ratio) tunables > >=20 > > ---- (5,10) - default > >=20 > > 2.6.23.1-42.fc8 #1 SMP > >=20 > > 524288 4 59580 60356 > > 524288 4 59247 61101 > > 524288 4 61030 62831 > >=20 > > 2.6.24-rc2 #28 SMP PREEMPT > >=20 > > 524288 4 49277 56582 > > 524288 4 50728 61056 > > 524288 4 52027 59758 > > 524288 4 51520 62426 > >=20 > >=20 > > ---- (20,40) - similar to your 8GB > >=20 > > 2.6.23.1-42.fc8 #1 SMP > >=20 > > 524288 4 225977 447461 > > 524288 4 232595 496848 > > 524288 4 220608 478076 > > 524288 4 203080 445230 > >=20 > > 2.6.24-rc2 #28 SMP PREEMPT > >=20 > > 524288 4 54043 83585 > > 524288 4 69949 516253 > > 524288 4 72343 491416 > > 524288 4 71775 492653 > >=20 > > ---- (60,80) - overkill > >=20 > > 2.6.23.1-42.fc8 #1 SMP > >=20 > > 524288 4 208450 491892 > > 524288 4 216262 481135 > > 524288 4 221892 543608 > > 524288 4 202209 574725 > > 524288 4 231730 452482 > >=20 > > 2.6.24-rc2 #28 SMP PREEMPT > >=20 > > 524288 4 49091 86471 > > 524288 4 65071 217566 > > 524288 4 72238 492172 > > 524288 4 71818 492433 > > 524288 4 71327 493954 > >=20 > >=20 > > While I see that the write speed as reported under .24 ~70MB/s is much > > lower than the one reported under .23 ~200MB/s, I find it very hard to > > believe my poor single SATA disk could actually do the 200MB/s for > > longer than its cache 8/16 MB (not sure). > >=20 > > vmstat shows that actual IO is done, even though the whole 512MB could > > fit in cache, hence my suspicion that the ~70MB/s is the most realistic > > of the two. >=20 > Even 70 MB/s seems too high. What throughput do you see for the > raw disk partition/ >=20 > Also, are the numbers above for successive runs? > It seems like you're seeing some caching effects so > I'd recommend using a file larger than your cache size and > the -e and -c options (to include fsync and close in timings) > to try to eliminate them. ------ iozone -i 0 -r 4k -s 512m -e -c .23 (20,40) 524288 4 31750 33560 524288 4 29786 32114 524288 4 29115 31476 .24 (20,40) 524288 4 25022 32411 524288 4 25375 31662 524288 4 26407 33871 ------ iozone -i 0 -r 4k -s 4g -e -c .23 (20,40) 4194304 4 39699 35550 4194304 4 40225 36099 .24 (20,40) 4194304 4 39961 41656 4194304 4 39244 39673 Yanmin, for that benchmark you ran, what was it meant to measure? =46rom what I can make of it its just write cache benching. One thing I don't understand is how the write numbers are so much lower than the rewrite numbers. The iozone code (which gives me headaches, damn what a mess) seems to suggest that the only thing that is different is the lack of block allocation. Linus posted a patch yesterday fixing up a regression in the ext3 bitmap block allocator, /me goes apply that patch and rerun the tests. > > ---- (20,40) - similar to your 8GB > >=20 > > 2.6.23.1-42.fc8 #1 SMP > >=20 > > 524288 4 225977 447461 > > 524288 4 232595 496848 > > 524288 4 220608 478076 > > 524288 4 203080 445230 > >=20 > > 2.6.24-rc2 #28 SMP PREEMPT > >=20 > > 524288 4 54043 83585 > > 524288 4 69949 516253 > > 524288 4 72343 491416 > > 524288 4 71775 492653 2.6.24-rc2 + patches/wu-reiser.patch patches/writeback-early.patch patches/bdi-task-dirty.patch patches/bdi-sysfs.patch patches/sched-hrtick.patch patches/sched-rt-entity.patch patches/sched-watchdog.patch patches/linus-ext3-blockalloc.patch 524288 4 179657 487676 524288 4 173989 465682 524288 4 175842 489800 Linus' patch is the one that makes the difference here. So I'm unsure how you bisected it down to: 04fbfdc14e5f48463820d6b9807daa5e9c92c51f These results seem to point to 7c9e69faa28027913ee059c285a5ea8382e24b5d as being the offending patch. --=-i1pnZYr0NaGe/YhSV/NN Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (GNU/Linux) iD8DBQBHOIPUXA2jU0ANEf4RAs+bAJwMYiLQODdFj6pjvqUoVX3BWVtC0QCeOCbQ 6ImnYvoIKHMFcHkbm3U0uEU= =VeYk -----END PGP SIGNATURE----- --=-i1pnZYr0NaGe/YhSV/NN-- - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/