On Mon, 2013-01-07 at 09:47 -0800, Tejun Heo wrote: +AD4- On Fri, Jan 04, 2013 at 01:15:00PM -0500, Trond Myklebust wrote: +AD4- +AD4- +- +ACo- Tejun Heo states: +AD4- +AD4- +- +ACo- +ACI-Workqueue currently considers two work items to be the same if they're +AD4- +AD4- +- +ACo- on the same address and won't execute them concurrently - ie. it +AD4- +AD4- +- +ACo- makes a work item which is queued again while being executed wait +AD4- +AD4- +- +ACo- for the previous execution to complete. +AD4- +AD4- +- +ACo- +AD4- +AD4- +- +ACo- If a work function frees the work item, and then waits for an event +AD4- +AD4- +- +ACo- which should be performed by another work item and +ACo-that+ACo- work item +AD4- +AD4- +- +ACo- recycles the freed work item, it can create a false dependency loop. +AD4- +AD4- +- +ACo- There really is no reliable way to detect this short of verifying +AD4- +AD4- +- +ACo- every memory free.+ACI- +AD4- +AD4- I will document it in Documentation/workqueue.txt. Thanks Tejun+ACE- -- Trond Myklebust Linux NFS client maintainer NetApp Trond.Myklebust+AEA-netapp.com www.netapp.com -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
