Re: Errors from the ata disk driver
It seems Andrew Gallatin wrote: These are UDMA CRC errors, if you upgrade to the latest current, ata knows to retry these, only if they persist, something is wrong. However it could indicate cable problems, ie bad connectors or maybe too long cables.. He said the disk was attached to a Promise Ultra/33. Does the backdown to PIO on Promise Ultra controllers work now? I've been watching the commits to the ata driver, and haven't seen anything that makes me think that it would.. but I haven't tried it since last week. I've fixed it here (I hope), and it will be in the next batch of fixes. I hope to get through my mailbox today :) -Søren To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-current" in the body of the message
Re: Errors from the ata disk driver
It seems [EMAIL PROTECTED] wrote: Will the backdown to PIO mode be permanent till the next reboot of the machine, or will the driver be able to attempt to return to DMA mode after a timeout period. I'm only seeing these errors under really heavy disk activity (mutlitple nfs readers and writers plus rsync/mirror jobs to the vinum volume in question). The fallback is permanent, but it only occurs after 3 retries on the failed request. If it fails 3 times in a row, there is something really wrong on that channel, ie bad cableing etc etc... -Søren To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-current" in the body of the message
Re: Errors from the ata disk driver
Soren Schmidt writes: It seems Andrew Gallatin wrote: These are UDMA CRC errors, if you upgrade to the latest current, ata knows to retry these, only if they persist, something is wrong. However it could indicate cable problems, ie bad connectors or maybe too long cables.. He said the disk was attached to a Promise Ultra/33. Does the backdown to PIO on Promise Ultra controllers work now? I've been watching the commits to the ata driver, and haven't seen anything that makes me think that it would.. but I haven't tried it since last week. I've fixed it here (I hope), and it will be in the next batch of fixes. I hope to get through my mailbox today :) Thanks. I'm running a kernel built with them now. If/when we see CRC errors, I'll let you know what happens. We don't see them frequently (a few times a month), so it might be a while. Thanks again, Drew To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-current" in the body of the message
Re: Errors from the ata disk driver
Andrew Gallatin writes: Soren Schmidt writes: I've fixed it here (I hope), and it will be in the next batch of fixes. I hope to get through my mailbox today :) Thanks. I'm running a kernel built with them now. If/when we see CRC errors, I'll let you know what happens. We don't see them frequently (a few times a month), so it might be a while. Looks like the world is safe for Promise Ultra users: Dec 13 18:42:37 waffle /kernel.test: ad2: UDMA CRC READ ERROR blk #22057647 retrying Dec 13 18:49:21 waffle xntpd[122]: time reset (step) 0.389151 s Dec 13 19:11:45 waffle xntpd[122]: time reset (step) 0.381460 s Dec 13 19:35:13 waffle xntpd[122]: time reset (step) 0.459194 s Dec 13 19:40:47 waffle /kernel.test: ad4: UDMA CRC READ ERROR blk #16658928 retrying Thanks! Drew -- Andrew Gallatin, Sr Systems Programmer http://www.cs.duke.edu/~gallatin Duke University Email: [EMAIL PROTECTED] Department of Computer Science Phone: (919) 660-6590 To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-current" in the body of the message
Re: Errors from the ata disk driver
It seems [EMAIL PROTECTED] wrote: I've got a striped vinum partition that is occasionally going stale when I get spurrious errors from the ata driver. I can setstate the drives and the volume back up and an fsck of the partition doesn't show any obvious corruption. What do these errors indicate? ad5: status=51 error=84 ad_interrupt: hard error vinum0.p0.s3: fatal read I/O error ad6: status=51 error=84 These are UDMA CRC errors, if you upgrade to the latest current, ata knows to retry these, only if they persist, something is wrong. However it could indicate cable problems, ie bad connectors or maybe too long cables.. -Søren To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-current" in the body of the message
Re: Errors from the ata disk driver
Soren Schmidt writes: It seems [EMAIL PROTECTED] wrote: I've got a striped vinum partition that is occasionally going stale when I get spurrious errors from the ata driver. I can setstate the drives and the volume back up and an fsck of the partition doesn't show any obvious corruption. What do these errors indicate? ad5: status=51 error=84 ad_interrupt: hard error vinum0.p0.s3: fatal read I/O error ad6: status=51 error=84 These are UDMA CRC errors, if you upgrade to the latest current, ata knows to retry these, only if they persist, something is wrong. However it could indicate cable problems, ie bad connectors or maybe too long cables.. He said the disk was attached to a Promise Ultra/33. Does the backdown to PIO on Promise Ultra controllers work now? I've been watching the commits to the ata driver, and haven't seen anything that makes me think that it would.. but I haven't tried it since last week. Thanks, Drew -- Andrew Gallatin, Sr Systems Programmer http://www.cs.duke.edu/~gallatin Duke University Email: [EMAIL PROTECTED] Department of Computer Science Phone: (919) 660-6590 To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-current" in the body of the message
Re: Errors from the ata disk driver
Will the backdown to PIO mode be permanent till the next reboot of the machine, or will the driver be able to attempt to return to DMA mode after a timeout period. I'm only seeing these errors under really heavy disk activity (mutlitple nfs readers and writers plus rsync/mirror jobs to the vinum volume in question). On the vinum front, does vinum have the ability to retry writing a block (or whatever the correct abstration is) to the same device if an error like this comes up from the underlying device? Thanks, keep up the great work (Yes, I know I should be using scsi for something like this, but the price of a 200GB raid0 unit built out of IDE equipment compared to the same built out of SCSI hardware is quite shocking. Especially for a non-mission critical role.) On Sat, 11 Dec 1999, Andrew Gallatin wrote: These are UDMA CRC errors. Whatever you do, DO NOT upgrade to a recent current without reading the ata driver's commit logs very carefully. The ata-driver has recently grown recovery code where it will try to back down to PIO mode to fetch such blocks. As recently as last week, the ata driver would lock a machine solid (unpingable, reset or power-cycle required) when attempting to back down to PIO mode when the drive in question was attached to a Promise Ultra controller. Soren knows about the problem is going to fix it. -- Andrew Gallatin, Sr Systems Programmer http://www.cs.duke.edu/~gallatin Duke University Email:[EMAIL PROTECTED] Department of Computer SciencePhone: (919) 660-6590 To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-current" in the body of the message