Next Steps to Debug ZFS Hang?

[Daniel Staal]

--As of October 8, 2014 9:28:05 PM -0700, Nick Sivo is alleged to have said:

>> Not sure if this will be helpful, but at least it shouldn't hurt:  When
>> was the last time you ran a scrub?  Also, how much RAM do you have and
>> where is your swap?  (The only times I've had permanent hangs from ZFS
>> was when I ran out of RAM and was trying to swap to ZFS...)
>
> The server has 64GB ECC RAM, and no swap at the moment. I've since
> rebooted the box, but a scrub today revealed no errors, and there was
> nothing in the console or any log files about disk or controller
> errors or timeouts.

--As for the rest, it is mine.

Note that I'm still just going by 'standard checks', but why don't you have 
any swap?  I know you probably wouldn't use it with that much RAM around, 
but FreeBSD still performs better with it - and it wouldn't surprise me 
completely if that was causing your issue.  (It shouldn't, in an ideal 
world - but it's an oddity on your system that might be causing issues, if 
there's an uncovered corner case.)

Setting up a small ramdisk for swap - or even putting some small 
swap-on-zfs - might be worth checking to see if it seems to prevent the 
issue.  (Note that swap-on-zfs has a 'worst case' scenario that crashes the 
box if you run out of RAM.  It's happened to me, and I was able to recover, 
but it took a while.)

Anyway, I'm mostly trying to keep your question alive in hopes that someone 
who's more knowledgeable can answer it.  ;)

Daniel T. Staal

---------------------------------------------------------------
This email copyright the author.  Unless otherwise noted, you
are expressly allowed to retransmit, quote, or otherwise use
the contents for non-commercial purposes.  This copyright will
expire 5 years after the author's death, or in 30 years,
whichever is longer, unless such a period is in excess of
local copyright law.
---------------------------------------------------------------