ZFS livelock / deadlock on pure SSD pool

[Grant Gray]

On 09/04/2013 04:02 PM, Andriy Gapon wrote:
> on 03/09/2013 13:35 Grant Gray said the following:
>> On 3/09/2013 7:27 PM, Andriy Gapon wrote:
>>> arc_lowmem+0x38 kmem_malloc+0xb0
>> Thanks for the feedback. Do you think it may be triggered when the ARC is
>> evicting pages because it is full, or a genuine low-memory case? The system has
>> 32GB of RAM, of which the ARC is typically about 24G (I think).
> Given the kmem_malloc -> arc_lowmem call chain it was a KVA shortage.  Probably
> because of KVA fragmentation.
> Setting KVA size to a value larger than your physical memory size (1.5x or 2x)
> may work around this problem.  The cost of the workaround is that some memory
> will be used for the additional page table pages.
>
> Some recent changes in head are supposed to help with the KVA fragmentation
> problem in general.

I've had to revert the problem server to spinning disks as my customer 
can't bear any more downtime.

I'm happy to test any proposed patches/workarounds on a non-production 
system.

I have no idea how the FreeBSD allocator works. Does the suggested 
increase in KVA size merely defer the problem as it will still 
eventually run out of contiguous pages?

PR has been submitted:
http://www.freebsd.org/cgi/query-pr.cgi?pr=181791