Re: [HACKERS] Separating Buffer LWlocks

2015-09-08 Thread Andres Freund
On 2015-09-08 14:31:53 -0400, Robert Haas wrote: > On Tue, Sep 8, 2015 at 2:19 PM, Andres Freund wrote: > > On 2015-09-08 14:15:32 -0400, Robert Haas wrote: > >> We could do that, but I'm not sure just calling LWLockNewTrancheId() > >> for all of the tranches would be so bad either. > > > > To me

Re: [HACKERS] Separating Buffer LWlocks

2015-09-08 Thread Robert Haas
On Tue, Sep 8, 2015 at 2:19 PM, Andres Freund wrote: > On 2015-09-08 14:15:32 -0400, Robert Haas wrote: >> We could do that, but I'm not sure just calling LWLockNewTrancheId() >> for all of the tranches would be so bad either. > > To me that seems either fragile or annoying to use. If all backends

Re: [HACKERS] Separating Buffer LWlocks

2015-09-08 Thread Andres Freund
On 2015-09-08 14:15:32 -0400, Robert Haas wrote: > We could do that, but I'm not sure just calling LWLockNewTrancheId() > for all of the tranches would be so bad either. To me that seems either fragile or annoying to use. If all backends call LWLockNewTrancheId() we need to a be sure the callbacks

Re: [HACKERS] Separating Buffer LWlocks

2015-09-08 Thread Robert Haas
On Tue, Sep 8, 2015 at 1:54 PM, Andres Freund wrote: > On 2015-09-08 13:29:28 -0400, Robert Haas wrote: >> I like this approach, though I think clearly it needs more performance >> testing. > > Yea, obviously. I did run this on a slightly bigger machine yesterday > and it gave consistent ~8% perf

Re: [HACKERS] Separating Buffer LWlocks

2015-09-08 Thread Andres Freund
On 2015-09-08 13:29:28 -0400, Robert Haas wrote: > I like this approach, though I think clearly it needs more performance > testing. Yea, obviously. I did run this on a slightly bigger machine yesterday and it gave consistent ~8% performance improvements. > The method of determining the tranche

Re: [HACKERS] Separating Buffer LWlocks

2015-09-08 Thread Robert Haas
On Mon, Sep 7, 2015 at 1:59 PM, Andres Freund wrote: > On 2015-09-06 15:28:40 +0200, Andres Freund wrote: >> Hm. I found that the buffer content lwlocks can actually also be a >> significant source of contention - I'm not sure reducing padding for >> those is going to be particularly nice. I think

Re: [HACKERS] Separating Buffer LWlocks

2015-09-07 Thread Andres Freund
On 2015-09-06 15:28:40 +0200, Andres Freund wrote: > Hm. I found that the buffer content lwlocks can actually also be a > significant source of contention - I'm not sure reducing padding for > those is going to be particularly nice. I think we should rather move > the *content* lock inline into the

Re: [HACKERS] Separating Buffer LWlocks

2015-09-06 Thread Andres Freund
Hi, On 2015-09-06 14:10:24 +0100, Simon Riggs wrote: > It separates the Buffer LWLocks from the main LW locks, allowing them to > have different padding. > > Tests showed noticeable/significant performance gain due to reduced false > sharing on main LWlocks, though without wasting memory on the b