From mboxrd@z Thu Jan 1 00:00:00 1970 From: Roman Mamedov Subject: Re: Write-intent bitmap decreases or increase performance of RAID5? Date: Wed, 30 Jun 2010 14:23:28 +0600 Message-ID: <20100630142328.6451f910@natsu> References: <20100629201153.GA13018@localhost> <20100630111854.006ec4d0@natsu> <20100630115927.090751dd@natsu> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=PGP-SHA1; boundary="Sig_/p7C.tAJtqP7o7HvzsSqMpm2"; protocol="application/pgp-signature" Return-path: In-Reply-To: Sender: linux-raid-owner@vger.kernel.org To: Mikael Abrahamsson Cc: Shaochun Wang , "linux-raid@vger.kernel.org" List-Id: linux-raid.ids --Sig_/p7C.tAJtqP7o7HvzsSqMpm2 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: quoted-printable On Wed, 30 Jun 2010 08:58:28 +0200 (CEST) Mikael Abrahamsson wrote: > On Wed, 30 Jun 2010, Roman Mamedov wrote: >=20 > > This is not necessary. See the dd man page about the conv=3Dfdatasync s= witch. > > You can even test with just 256 MB this way, and still get an extremely > > accurate result. >=20 > You're right, for writing this is ok. For read tests it's important to us= e=20 > more than ram though, to avoid doing performance testing from block cache= =20 > instead of from the actual drives. Yeah, though there's also an alternative way of mitigating the effect of the cache when testing read speed, see http://linux-mm.org/Drop_Caches --=20 With respect, Roman --Sig_/p7C.tAJtqP7o7HvzsSqMpm2 Content-Type: application/pgp-signature; name=signature.asc Content-Disposition: attachment; filename=signature.asc -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.10 (GNU/Linux) iEYEARECAAYFAkwq/wAACgkQTLKSvz+PZwivlQCeJRy8PWiUw+Snq+uhkW9e+wOM 4qsAn0zirsmYAIr4a+aptN4IAduoMfDu =U1zb -----END PGP SIGNATURE----- --Sig_/p7C.tAJtqP7o7HvzsSqMpm2--