Date: Fri, 15 Oct 1999 21:06:14 +0200 (MET DST) From: Gerard Roudier <groudier@club-internet.fr> To: "Chris D. Faulhaber" <cdf.lists@fxp.org> Cc: Andrew Gallatin <gallatin@cs.duke.edu>, "Kenneth D. Merry" <ken@kdm.org>, scsi@FreeBSD.ORG Subject: Re: FreeBSD 3.2 / Slow SCSI Dell PowerEdge 4300 Message-ID: <Pine.LNX.3.95.991015204553.388A-100000@localhost> In-Reply-To: <Pine.BSF.4.10.9910151109140.98623-100000@pawn.primelocation.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, 15 Oct 1999, Chris D. Faulhaber wrote: > da0: <WDIGTL WDE9100 1.50> Fixed Direct Access SCSI-2 device > da0: 40.000MB/s transfers (20.000MHz, offset 8, 16bit) > da0: 8683MB (17783204 512 byte sectors: 255H 63S/T 1106C) >=20 > After enabling tagged queuing on this drive (by removing the quirk entry) > and found performance about 10% slower. What kind of performance are you measuring ? Tagged command queuing is intended to improve _multithreaded IOs that is a lot more realistic IO pattern than single-threaded sequential IO. I also read some decrease of performance for DCAS for single-threaded sequential IO when increasing number of tags. Unless, guys, you just want to eat the cake and to have it, I donnot see any serious problem for these drives. May-be there is some room for improvement in their firmware. They should _not_ have been quirked to 0 tags, in my opinion, if the decrease of performance observed is for sequential IOs. At most, user should be advised to use a reasonnable number of tags or the quirk should have been more soft.=20 For the DCAS, the decrease of performances has been observed for sequential write IOs that is a great stress for a disk when write behing caching is enabled with tags enabled, but still nothing has been reported for read and especially multithreaded read IOs. Castrating a disk model=20 regarding tags due to such unreaslistic results has been unserious in my opinion.=20 When tags are enabled, the drive can overlap writes by disconnecting previous to the data phase and so get rid of part of IO latency. In such a situation, write behind caching can be disabled for some good disks without significant decrease of performances, allowing drives to perform more prefetching for read. Indeed, writing meta-data synchronously does not help, but softupdate may do.=20 G=E9rard. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.LNX.3.95.991015204553.388A-100000>