From: Andre Noll Subject: Re: [PATCH] md: raid0: Replace hash table lookup by looping over all strip_zones. Date: Fri, 15 May 2009 19:30:40 +0200 Message-ID: <20090515173040.GN6403@skl-net.de> References: <1242297833-13908-1-git-send-email-maan@systemlinux.org> <1242297833-13908-2-git-send-email-maan@systemlinux.org> <18956.3337.786085.284689@notabene.brown> <1242316280.11444.4.camel@raz> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="Zl+NncWK+U5aSfTo" Return-path: Content-Disposition: inline In-Reply-To: <1242316280.11444.4.camel@raz> Sender: linux-raid-owner@vger.kernel.org To: raz ben yehuda Cc: Neil Brown , linux-raid@vger.kernel.org List-Id: linux-raid.ids --Zl+NncWK+U5aSfTo Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On 18:51, raz ben yehuda wrote: > > and as we aren't using ->sectors in this loop any more, I think it > > can be discarded completely, just making struct strip_zone 20% smaller > > and improving cache performance. > >=20 > > What do you think? > hamm.. please do not do it now. I think i need it for the reshape > because I have to traverse each zone up to its end.=20 Well, you can always get the zone size of zone #i by z[i].zone_end - z[i - 1].zone_end (with z[-1].zone_end :=3D 0). Since reshape is a slow operation anyway, the additional subtraction won't hurt, and we'd have the smaller cache footprint during normal operation. So I'd be inclined to kill ->sectors as well. Andre --=20 The only person who always got his work done by Friday was Robinson Crusoe --Zl+NncWK+U5aSfTo Content-Type: application/pgp-signature; name="signature.asc" Content-Description: Digital signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.1 (GNU/Linux) iD8DBQFKDabAWto1QDEAkw8RAoEmAKCqYyRinCYIuXWi4fhJSLKfj//2XgCfYTfp z0lX/gg5fAfGb8IM0XKOAl4= =ShCN -----END PGP SIGNATURE----- --Zl+NncWK+U5aSfTo--