[gpfsug-discuss] AFM performance under load

[Orlando Richards]

Hi folks,

We're trying to get our AFM stack to remain responsive when under a 
heavy write load from the cache -> home. It looks like read operations 
won't get scheduled when there's a large write queue, and operations 
like "ls" in a directory which isn't currently valid in the cache can 
take several minutes to return.

Does anyone have any ideas on how to stop AFM lookups running slowly 
when the AFM queues are big?

-----------
Orlando

-- 
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.