Date: Sun, 14 Mar 1999 13:53:10 -0700 (MST) From: "Kenneth D. Merry" <ken@plutotech.com> To: jmz@FreeBSD.ORG (Jean-Marc Zucconi) Cc: roberto@keltia.freenix.fr, freebsd-scsi@FreeBSD.ORG Subject: Re: cvs commit: src/sys/cam cam_xpt.c Message-ID: <199903142053.NAA13995@panzer.plutotech.com> In-Reply-To: <199903141441.PAA71438@qix> from Jean-Marc Zucconi at "Mar 14, 1999 3:41:29 pm"
next in thread | previous in thread | raw e-mail | index | archive | help
Jean-Marc Zucconi wrote... > >>>>> Ollivier Robert writes: > > > According to Kenneth Merry: > >> Log: > >> Disable tagged queueing for the IBM DCAS drives. These drives have poor > >> write performance when tagged queueing is enabled. > > > Do you call that poor performance ? I have two 4 gig drives and they don't > > seem that slow for me... > > > Seeker 1...Seeker 3...Seeker 2...start 'em...done...done...done... > > -------Sequential Output-------- ---Sequential Input-- --Random-- > > -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks--- > > Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU > > dcas4 256 2891 37.3 2534 9.8 1797 7.9 5913 48.2 5916 19.2 96.0 3.5 > > > Writing the 256 Megabyte file, 'iozone.tmp'...95.656250 seconds > > Reading the file...43.687500 seconds > > > IOZONE performance measurements: > > 2806251 bytes/second for writing the file > > 6144445 bytes/second for reading the file > > Yes this is very poor for a wide drive. On my narrow DCAS-34330: > Writing the 250 Megabyte file, 'iozone.tmp'...80.351562 seconds > Reading the file...38.601562 seconds > > IOZONE performance measurements: > 3262463 bytes/second for writing the file > 6791020 bytes/second for reading the file > da1 at ahc0 bus 0 target 1 lun 0 > da1: <IBM DCAS-34330 S65A> Fixed Direct Access SCSI-2 device > da1: 20.000MB/s transfers (20.000MHz, offset 15), Tagged Queueing Enabled > da1: 4134MB (8467200 512 byte sectors: 255H 63S/T 527C) > > > ncr0: <ncr 53c875 fast20 wide scsi> rev 0x03 int a irq 9 on pci0.11.0 > > da1 at ncr0 bus 0 target 1 lun 0 > > da1: <IBM DCAS-34330W S65A> Fixed Direct Access SCSI-2 device > > da1: 40.00MB/s transfers (20.00MHz, offset 15, 16bit), Tagged Queueing Enabled > > da1: 4134MB (8467200 512 byte sectors: 255H 63S/T 527C) > > da0 at ncr0 bus 0 target 0 lun 0 > > da0: <IBM DCAS-34330W S65A> Fixed Direct Access SCSI-2 device > > da0: 40.00MB/s transfers (20.00MHz, offset 15, 16bit), Tagged Queueing Enabled > > da0: 4134MB (8467200 512 byte sectors: 255H 63S/T 527C) The issue isn't really whether it's "poor performance" or "poor for a wide drive", but whether the performance you're getting out of the drive is what the drive is capable of. If you look at PR 10398, you'll see that the 4G DCAS drive is *capable* of 6.8MB/sec sequential write performance for block writes. Both of you have just shown write performance for the same drive that is substantially less than that. My goal in disabling tagged queueing for the DCAS drives is to increase performance, based on the assertion that they don't perform as well when tagged queueing is enabled. That is very unusual for an IBM drive, but I guess I've come to expect the unexpected from drive vendors. Ken -- Kenneth Merry ken@plutotech.com 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?199903142053.NAA13995>