Date: Thu, 30 Mar 2006 15:59:05 +0900 From: Ganbold <ganbold@micom.mng.net> To: "Thyer, Matthew" <Matthew.Thyer@dsto.defence.gov.au> Cc: freebsd-current@freebsd.org Subject: Re: mysql performance test results under FreeBSD-7.0-CURRENT Message-ID: <442B81B9.30206@micom.mng.net> In-Reply-To: <07018E951F2FBF42B40B3D61086788344C1D9D@ednex511.dsto.defence.gov.au> References: <07018E951F2FBF42B40B3D61086788344C1D9D@ednex511.dsto.defence.gov.au>
next in thread | previous in thread | raw e-mail | index | archive | help
Thyer, Matthew wrote: > A couple of things I have noticed in the kernel messages: > > WARNING: WITNESS option enabled, expect reduced performance. > Yes, I left this option in case if there comes something wrong. > You need to remove the WITNESS and the INVARIANTS options from your > kernel when benchmarking. > > ad0: DMA limited to UDMA33, controller found non-ATA66 cable > ad0: 28629MB <Seagate ST330630A 3.17> at ata0-master UDMA33 > ad1: DMA limited to UDMA33, controller found non-ATA66 cable > ad1: 28629MB <Seagate ST330630A 3.17> at ata0-slave UDMA33 > ad3: 38166MB <Seagate ST340810A 3.99> at ata1-slave UDMA100 > > You need to use the 80 core conductor cables instead of the old standard > 40 core conductor IDE cables to get the best performance from your hard > drives. Just use another cable like you already have connected to the > 40GB drive. > That is true, I don't have any UDMA100 cables right now:( Ganbold > -----Original Message----- > From: owner-freebsd-current@freebsd.org > [mailto:owner-freebsd-current@freebsd.org] On Behalf Of Ganbold > Sent: Thursday, 30 March 2006 4:55 PM > To: freebsd-current@freebsd.org > Cc: jasone@freebsd.org; deischen@freebsd.org; phk@phk.freebsd.dk; > rwatson@freebsd.org; davidxu@freebsd.org; grog@freebsd.org > Subject: mysql performance test results under FreeBSD-7.0-CURRENT > > Hi all, > > I did make some mysql performance tests under FreeBSD-7.0-CURRENT with > various > scheduler and compile time options. > It seems like mysql(BUILD_OPTIMIZED=yes, BUILD_STATIC=yes, > WITH_PROC_SCOPE_PTH=yes)-libpthread-tsc-sched_4bsd+preemption gives > better performance. > > The test results are at: > > http://www.mnbsd.org/ftp/mysql_test_results.txt > > There are several things I didn't test and this leads to some questions: > > 1. I didn't make test with Poul-Henning's CPU accounting patch. Somehow > I can't apply it (http://phk.freebsd.dk/patch/cpu_acct_2.patch) cleanly. > > Where can I find latest patch? > When this patch will be included in CURRENT? > > 2. I didn't make test with Robert Watson's patch > (http://www.watson.org/~robert/freebsd/clock/)? Does CURRENT src tree > include it? If not when this patch will be included in CURRENT? > > 3. I did make tests with default malloc in CURRENT. I'm confused what > malloc options should try (jemalloc? phkmalloc?) What is the default > malloc in CURRENT? How to use these different mallocs? > > thanks in advance, > > Ganbold > > > _______________________________________________ > freebsd-current@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-current > To unsubscribe, send any mail to > "freebsd-current-unsubscribe@freebsd.org" > > > >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?442B81B9.30206>