From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bryan Mesich Subject: Re: Any benefity to write intent bitmaps on Raid1 Date: Wed, 8 Apr 2009 20:30:18 -0500 Message-ID: <20090409013018.GA3514@atlantis.cc.ndsu.NoDak.edu> References: <45635.60.234.49.2.1239236645.squirrel@webmail.stevencherie.net> Reply-To: Bryan Mesich Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="G4iJoqBmSsgzjUCe" Return-path: Content-Disposition: inline In-Reply-To: <45635.60.234.49.2.1239236645.squirrel@webmail.stevencherie.net> Sender: linux-raid-owner@vger.kernel.org To: Steven Ellis Cc: Linux RAID List-Id: linux-raid.ids --G4iJoqBmSsgzjUCe Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Thu, Apr 09, 2009 at 12:24:05PM +1200, Steven Ellis wrote: > Given I have a pair of 1TB drives Raid1 I'd prefer to reduce any recovery > sync time. Would an internal bitmap help dramatically, and are there any > other benefits. > If one of your drives goes pear shaped and needs to be replaced, then no, a write intent bitmap will not help you. When you replace the drive, the incomming drive will need to do a full resync. Many times a read/write error causes the drive to be failed. In this case, the bad block that caused the read/write error should get re-mapped by the HD firmware. If you have a write intent bitmap enabled, the re-add only resyncs the out-of-sync pages (not sure if page is the correct terminology). There is some overhead when using a write intent bitmap as the bitmap needs to be updated as data is written to the device. For most people, the overhead is not noticeable. If you really need performance, the bitmap can be moved to another disk(s) that is not a member of the RAID1 array in question. I've used write intent bitmaps many times in a SAN environment=20 in which FC initiators mirror 2 block devices. Both block devices=20 come from different FC targets. This makes maintiance much easier since all we have to do is break the RAID1 mirror on the initiator (we also have good uptime :). A write intent bitmap=20 speeds the re-syncing process up since we only resync the=20 out-of-sync data. Bryan --G4iJoqBmSsgzjUCe Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (GNU/Linux) iD8DBQFJ3U+qlSl3SAlkhEcRAuIRAJsF1lE7r3jzlIjl7P4n8OrZnmpmvQCfSSWs 1wYBoSk8maRcMmlutfXcW0E= =h4ZG -----END PGP SIGNATURE----- --G4iJoqBmSsgzjUCe--