From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bill Davidsen Subject: Re: Awful RAID5 random read performance Date: Wed, 03 Jun 2009 14:38:11 -0400 Message-ID: <4A26C313.6080700@tmr.com> References: <20090531154159405.TTOI3923@cdptpa-omta04.mail.rr.com> <200905311056.30521.tfjellstrom@shaw.ca> <4A25754F.5030107@tmr.com> <20090602194704.GA30639@rap.rap.dk> <4A25B201.2000705@anonymous.org.uk> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: In-Reply-To: <4A25B201.2000705@anonymous.org.uk> Sender: linux-raid-owner@vger.kernel.org To: John Robinson Cc: =?ISO-8859-1?Q?Keld_J=F8rn_Simonsen?= , Linux RAID List-Id: linux-raid.ids John Robinson wrote: > On 02/06/2009 20:47, Keld J=F8rn Simonsen wrote: > [...] >> My perception is that raid10,f2 is probably the fastest also for=20 >> small random >> reads because of the lower latency, and faster transfer times due to= =20 >> only >> using the outer disk sectors. For writes the elevator evens out the >> ramdom access. Benchmarks may not show this effect as they are often >> done on clean file systems, where the files are allocated in the >> beginning of the fs. >> >> For cases where you need cheap disk space, and have big files like >> .iso's then raid5 could be a good choice because it has the most spa= ce >> while maintaining fair to good performance for big files. >> In your case, using 3 disks, raid5 should give about 210 % of the=20 >> nominal >> single disk speed for big file reads, and maybe 180 % for big file >> writes. raid10,f2 should give about 290 % for big file reads and 140= % >> for big file writes. Random reads should be about the same for raid5= and >> raid10,f2 - raid10,f2 maybe 15 % faster, while random writes should = be >> mediocre for raid5, and good for raid10,f2. > > I'd be interested in reading about where you got these figures from=20 > and/or the rationale behind them; I'd have guessed differently... =46or small values of N, 10,f2 generally comes quite close to N*Sr, whe= re=20 N is # of disks and Sr is single drive read speed. This is assuming=20 fiarly large reads and adequate stripe buffer space. Obviously for=20 larger values of N that saturates something else in the system, like th= e=20 bus, before N gets too large. I don't generally see more than (N/2-1)*S= w=20 for write, at least for large writes. I came up with those numbers base= d=20 on testing 3-4-5 drive arrays which do large file transfers. If you wan= t=20 to read more than large file speed into them, feel free. All tests done on raw devices and raw arrays, and ext3 devices and=20 arrays. The ratios stay about the same, tuning stripe size (stride) can= =20 be helpful for improving write speed. Short summary - the numbers look close enough to mine that I would say=20 they are at least useful approximations. --=20 Bill Davidsen Even purely technical things can appear to be magic, if the documenta= tion is obscure enough. For example, PulseAudio is configured by dancing naked = around a fire at midnight, shaking a rattle with one hand and a LISP manual with= the other, while reciting the GNU manifesto in hexadecimal. The documentati= on fails to note that you must circle the fire counter-clockwise in the southern hemisphere. -- To unsubscribe from this list: send the line "unsubscribe linux-raid" i= n the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html