Peter Cudhea wrote: > Thanks, this is helpful. I was definitely misunderstanding the part that > the ZIL plays in ZFS. > > I found Richard Elling's discussion of the FMA response to the failure > very informative. I see how the device driver, the fault analysis > layer and the ZFS layer are all working together. Though the > customer's complaint that the change in state from "working" to "not > working" is taking too long seems pretty valid. >
I wish there was a simple answer to the can-of-worms^TM that this question opens. But there really isn't. As Paul Fisher points out, logging 17,951 e-reports in 9 minutes seems like a lot, but I'm quite sure that is CPU bound and I could log more with a faster system :-) The key here is that 9 minutes represents some combination of timeouts in the sd/scsa2usb/usb stack. The myth of layered software says that timeouts compound, so digging around for a better collection might or might not be generally satisfying. Since this is not a ZFS timeout, perhaps the conversation should be continued in a more appropriate forum? -- richard _______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
