ZFS: arc_reclaim_thread running 100%, 8.1-RELEASE, LBOLT related

[Andriy Gapon]

on 31/05/2011 18:57 Steven Hartland said the following:
> ----- Original Message -----
>> However, the arc_reclaim_thread does not have a ~24 day rollover - it
>> does not use clock_t.  I think this rollover in the integer results
>> in LBOLT going negative, after about 106-107 days.  We haven't noticed
>> this until actually 112-115 days of uptime.  I think it is also related
>> to L1 ARC sizing, and load.  Our systems with arc set to min-max of
>> 512M/2G ARC haven't developed the issue - at least the CPU hogging thread
>> - but the systems with 12G+ of ARC, and lots of rsync and du activity
>> along side of random reads from the zpool develop the issue.
> 
> 
> Looks like we had this on machine today which had only been up 66 days.

Sorry, but 'looks' is not very definitive.

> A reboot cleared it, but 66 days up time is nearly half previously reported
> making it a bit more serious.

It could have been some other bug or something else altogether.
Without proper debugging/investigation it's impossible to tell.

-- 
Andriy Gapon