On Thu, Dec 17, 2015 at 8:44 PM, Andres Freund <and...@anarazel.de> wrote: > > On 2015-12-17 09:47:57 -0500, Robert Haas wrote: > > On Tue, Dec 15, 2015 at 7:25 AM, Andres Freund <and...@anarazel.de> wrote: > > > I'd consider using a LWLock instead of a spinlock here. I've seen this > > > contended in a bunch of situations, and the queued behaviour, combined > > > with directed wakeups on the OS level, ought to improve the worst case > > > behaviour measurably. > > > > Amit had the idea a while back of trying to replace the HASHHDR mutex > > with something based on atomic ops. It seems hard to avoid the > > attendant A-B-A problems but maybe there's a way. > > It'd really like to see it being replaced by a queuing lock > (i.e. lwlock) before we go there. And then maybe partition the freelist, > and make nentries an atomic. Just doing those might already be good > enough and should be a lot easier. >
makes sense to me, but I think we should as well try the Group leader idea used for ProcArrayLock optimisation as during those tests, I found that it gives better results as compare to partitioning. With Regards, Amit Kapila. EnterpriseDB: http://www.enterprisedb.com