I have a P3 system running STABLE built on March 7. I installed a new IBM DTLA disk drive and was distressed at its slowness, so I tried turning on tagging to see if that would help. It seemed to, until... 3 AM when my periodic tasks started running. The system lost all disk access and logged lots of errors (a few of which I added to the end of this message). I rebooted the system this morning and the problem re-appeared when fsck ran. I then turned off tagged queuing and the system came up normally. Is there some problem with the DTLA drive or is this a driver problem? R. Kevin Oberman, Network Engineer Energy Sciences Network (ESnet) Ernest O. Lawrence Berkeley National Laboratory (Berkeley Lab) E-mail: oberman@es.net Phone: +1 510 486-8634 03:01:18 ptavv /kernel: ad0: no request for tag=0 03:01:18 ptavv /kernel: ad0: invalidating queued requests 03:01:18 ptavv /kernel: ad0: no request for tag=0 03:01:18 ptavv /kernel: ad0: invalidating queued requests 03:01:28 ptavv /kernel: ad0: READ command timeout tag=0 serv=1 - resetting 03:01:28 ptavv /kernel: ad0: invalidating queued requests 03:01:28 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued requests 03:01:28 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 cable or device 03:01:28 ptavv /kernel: done 03:01:28 ptavv /kernel: ad0: no request for tag=0 03:01:28 ptavv /kernel: ad0: invalidating queued requests 03:01:28 ptavv /kernel: ad0: no request for tag=1 03:01:28 ptavv /kernel: ad0: invalidating queued requests 03:01:39 ptavv /kernel: ad0: READ command timeout tag=0 serv=1 - resetting 03:01:39 ptavv /kernel: ad0: invalidating queued requests 03:01:39 ptavv /kernel: ad0: timeout waiting for READY 03:01:39 ptavv /kernel: ad0: invalidating queued requests 03:01:39 ptavv /kernel: - resetting 03:01:39 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued requests 03:01:39 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 cable or device 03:01:39 ptavv /kernel: done 03:01:39 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued requests 03:01:39 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 cable or device 03:01:39 ptavv /kernel: done 03:01:39 ptavv /kernel: ad0: WRITE command timeout tag=3 serv=0 - resetting 03:01:39 ptavv /kernel: ad0: invalidating queued requests 03:01:39 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued requests 03:01:39 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 cable or device 03:01:39 ptavv /kernel: done 03:01:39 ptavv /kernel: ad0: WRITE command timeout tag=2 serv=0 - resetting 03:01:39 ptavv /kernel: ad0: invalidating queued requests 03:01:39 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued requests 03:01:39 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 cable or device 03:01:39 ptavv /kernel: done 03:01:39 ptavv /kernel: ad0: READ command timeout tag=1 serv=0 - resetting 03:01:39 ptavv /kernel: ad0: invalidating queued requests 03:01:39 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued requests 03:01:39 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 cable or device 03:01:39 ptavv /kernel: done 03:01:39 ptavv /kernel: ad0: no request for tag=1 03:01:39 ptavv /kernel: ad0: invalidating queued requests 03:01:49 ptavv /kernel: ad0: READ command timeout tag=0 serv=0 - resetting 03:01:49 ptavv /kernel: ad0: invalidating queued requests 03:01:49 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued requests 03:01:49 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 cable or device 03:01:49 ptavv /kernel: done 03:01:49 ptavv /kernel: ad0: READ command timeout tag=0 serv=1 - resetting 03:01:49 ptavv /kernel: ad0: invalidating queued requests 03:01:49 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued requests 03:01:49 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 cable or device 03:01:49 ptavv /kernel: done 03:01:49 ptavv /kernel: ad0: WRITE command timeout tag=3 serv=0 - resetting 03:01:49 ptavv /kernel: ad0: invalidating queued requests 03:01:49 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued requests 03:01:49 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 cable or device 03:01:49 ptavv /kernel: done 03:01:49 ptavv /kernel: ad0: WRITE command timeout tag=2 serv=0 - resetting 03:01:49 ptavv /kernel: ad0: invalidating queued requests 03:01:49 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued requests 03:01:49 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 cable or device 03:01:49 ptavv /kernel: done 03:01:49 ptavv /kernel: ad0: READ command timeout tag=1 serv=0 - resetting 03:01:49 ptavv /kernel: ad0: invalidating queued requests 03:01:49 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued requests 03:01:49 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 cable or device 03:01:49 ptavv /kernel: done
On Saturday 29 March 2003 6:42 pm, Kevin Oberman wrote:> I have a P3 system running STABLE built on March 7. I installed a new > IBM DTLA disk drive and was distressed at its slowness, so I tried > turning on tagging to see if that would help. It seemed to, until...What do you mean by *new*? These drives were renamed some long time ago. IIRC quality was a bit poor for early drives.> > 3 AM when my periodic tasks started running. The system lost all disk > access and logged lots of errors (a few of which I added to the end of > this message). > > I rebooted the system this morning and the problem re-appeared when fsck > ran. I then turned off tagged queuing and the system came up normally. > > Is there some problem with the DTLA drive or is this a driver problem?Yes, the drive could be DOA. However it's equally likely to be the controller or the cable. Lots of M/Bs have suspect UDMA implementations. My IC35L080's are fine (GigaByte 7VTXE+) Take a look at this for starters (wrapped). http://ssddom01.hgst.com/tech/techlib.nsf/techdocs/\ 85256AB8006A31E587256A7800700048/$file/dtla_com2.pdf> > R. Kevin Oberman, Network Engineer > Energy Sciences Network (ESnet) > Ernest O. Lawrence Berkeley National Laboratory (Berkeley Lab) > E-mail: oberman@es.net Phone: +1 510 486-8634 > > 03:01:18 ptavv /kernel: ad0: no request for tag=0 > 03:01:18 ptavv /kernel: ad0: invalidating queued requests > 03:01:18 ptavv /kernel: ad0: no request for tag=0 > 03:01:18 ptavv /kernel: ad0: invalidating queued requests > 03:01:28 ptavv /kernel: ad0: READ command timeout tag=0 serv=1 - resetting > 03:01:28 ptavv /kernel: ad0: invalidating queued requests > 03:01:28 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued > requests 03:01:28 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 > cable or device 03:01:28 ptavv /kernel: done > 03:01:28 ptavv /kernel: ad0: no request for tag=0 > 03:01:28 ptavv /kernel: ad0: invalidating queued requests > 03:01:28 ptavv /kernel: ad0: no request for tag=1 > 03:01:28 ptavv /kernel: ad0: invalidating queued requests > 03:01:39 ptavv /kernel: ad0: READ command timeout tag=0 serv=1 - resetting > 03:01:39 ptavv /kernel: ad0: invalidating queued requests > 03:01:39 ptavv /kernel: ad0: timeout waiting for READY > 03:01:39 ptavv /kernel: ad0: invalidating queued requests > 03:01:39 ptavv /kernel: - resetting > 03:01:39 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued > requests 03:01:39 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 > cable or device 03:01:39 ptavv /kernel: done > 03:01:39 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued > requests 03:01:39 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 > cable or device 03:01:39 ptavv /kernel: done > 03:01:39 ptavv /kernel: ad0: WRITE command timeout tag=3 serv=0 - resetting > 03:01:39 ptavv /kernel: ad0: invalidating queued requests > 03:01:39 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued > requests 03:01:39 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 > cable or device 03:01:39 ptavv /kernel: done > 03:01:39 ptavv /kernel: ad0: WRITE command timeout tag=2 serv=0 - resetting > 03:01:39 ptavv /kernel: ad0: invalidating queued requests > 03:01:39 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued > requests 03:01:39 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 > cable or device 03:01:39 ptavv /kernel: done > 03:01:39 ptavv /kernel: ad0: READ command timeout tag=1 serv=0 - resetting > 03:01:39 ptavv /kernel: ad0: invalidating queued requests > 03:01:39 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued > requests 03:01:39 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 > cable or device 03:01:39 ptavv /kernel: done > 03:01:39 ptavv /kernel: ad0: no request for tag=1 > 03:01:39 ptavv /kernel: ad0: invalidating queued requests > 03:01:49 ptavv /kernel: ad0: READ command timeout tag=0 serv=0 - resetting > 03:01:49 ptavv /kernel: ad0: invalidating queued requests > 03:01:49 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued > requests 03:01:49 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 > cable or device 03:01:49 ptavv /kernel: done > 03:01:49 ptavv /kernel: ad0: READ command timeout tag=0 serv=1 - resetting > 03:01:49 ptavv /kernel: ad0: invalidating queued requests > 03:01:49 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued > requests 03:01:49 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 > cable or device 03:01:49 ptavv /kernel: done > 03:01:49 ptavv /kernel: ad0: WRITE command timeout tag=3 serv=0 - resetting > 03:01:49 ptavv /kernel: ad0: invalidating queued requests > 03:01:49 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued > requests 03:01:49 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 > cable or device 03:01:49 ptavv /kernel: done > 03:01:49 ptavv /kernel: ad0: WRITE command timeout tag=2 serv=0 - resetting > 03:01:49 ptavv /kernel: ad0: invalidating queued requests > 03:01:49 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued > requests 03:01:49 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 > cable or device 03:01:49 ptavv /kernel: done > 03:01:49 ptavv /kernel: ad0: READ command timeout tag=1 serv=0 - resetting > 03:01:49 ptavv /kernel: ad0: invalidating queued requests > 03:01:49 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued > requests 03:01:49 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 > cable or device 03:01:49 ptavv /kernel: done > _______________________________________________ > freebsd-stable@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-stable > To unsubscribe, send any mail to "freebsd-stable-unsubscribe@freebsd.org"-- ian j hart Quoth the raven, bite me! Salem Saberhagen (Episode LXXXI: The Phantom Menace)
On Sat, 29 Mar 2003 at 10:42:36 -0800, Kevin Oberman wrote: --snip--> 03:01:49 ptavv /kernel: ad0: invalidating queued requests > 03:01:49 ptavv /kernel: ata0: resetting devices .. ad0: invalidating queued requests > 03:01:49 ptavv /kernel: ad0: DMA limited to UDMA33, non-ATA66 cable or device > 03:01:49 ptavv /kernel: done > _______________________________________________ > freebsd-stable@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-stable > To unsubscribe, send any mail to "freebsd-stable-unsubscribe@freebsd.org"Just to point out/ask the obvious, you do have a udma cable on the harddrive, it is on correctly (blue end to mainboard typically), and its its at the end of the of the cable, leaving the middle connector for your slave drive, correct? also, from what I have seen, the ibm drives and tagging has always seemed to be a problem. I dont think this has changed recently. -Andrew -- Andrew Stuart http://www.tekrealm.net Experience is something you don't get until just after you need it. -- Olivier -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 187 bytes Desc: not available Url : http://lists.freebsd.org/pipermail/freebsd-stable/attachments/20030329/07ad203c/attachment.bin
"Kevin Oberman" <oberman@es.net> writes:> I have a P3 system running STABLE built on March 7. I installed a new > IBM DTLA disk drive and was distressed at its slowness, so I tried > turning on tagging to see if that would help. It seemed to, until...The DTLA series is known bad. Take it back to the dealer and harass him into replacing it with a DTTA or newer. DES -- Dag-Erling Sm?rgrav - des@ofug.org
Not all IBM DTLA drives are bad; actually, they are not bad at all (because all bad are already dead :) DTLA-5 drives (5400rpm) do not support tagged queueing, unlike DTLA-7 (7200rpm). They offer good performance considering spindle speed and 512K of cache (in fact, 380K; firmware takes the rest). About "new drive" and "its slowness", what did you expect from 2-year old drive featuring 20Gb per plate? --- Regards, Rhett Dag-Erling Sm?rgrav wrote:> > "Kevin Oberman" <oberman@es.net> writes: > > I have a P3 system running STABLE built on March 7. I installed a new > > IBM DTLA disk drive and was distressed at its slowness, so I tried > > turning on tagging to see if that would help. It seemed to, until... > > The DTLA series is known bad. Take it back to the dealer and harass > him into replacing it with a DTTA or newer. > > DES > -- > Dag-Erling Sm?rgrav - des@ofug.org >__________________________________________________ Yahoo! Plus For a better Internet experience http://www.yahoo.co.uk/btoffer
In article <20030329184236.71A3C69@ptavv.es.net>, Kevin Oberman <oberman@es.net> wrote:>I have a P3 system running STABLE built on March 7. I installed a new >IBM DTLA disk drive and was distressed at its slowness, so I tried >turning on tagging to see if that would help. It seemed to, until... > >3 AM when my periodic tasks started running. The system lost all disk >access and logged lots of errors (a few of which I added to the end of >this message).This combination worked beautifully until the ATA MFC just after 4.5, and it has since been declared that those IBM drives don't do tagging correctly. Since I've got a semi-production server with the DTLAs in it, I gave up on tagging, just using UDMA, it's good enough. -- Steve Watt KD6GGD PP-ASEL-IA ICBM: 121W 56' 57.8" / 37N 20' 14.9" Internet: steve @ Watt.COM Whois: SW32 Free time? There's no such thing. It just comes in varying prices...