| From: | Andres Freund <andres(at)2ndquadrant(dot)com> |
|---|---|
| To: | Robert Haas <robertmhaas(at)gmail(dot)com> |
| Cc: | "pgsql-hackers(at)postgresql(dot)org" <pgsql-hackers(at)postgresql(dot)org> |
| Subject: | Re: Lockless StrategyGetBuffer() clock sweep |
| Date: | 2014-12-23 21:51:40 |
| Message-ID: | 20141223215140.GG23613@alap3.anarazel.de |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On 2014-12-23 16:42:41 -0500, Robert Haas wrote:
> I don't think I have anything to say about the substance of the patch.
> If fetch-and-add is faster than a spinlock cycle, then it is. And
> it's good to be fast.
I don't think the primary advantage is that it's fast (even though it
should be as fast as a single TAS on x86). It's that you can never sleep
while holding the spinlock when there's no such spinlock and that
everytime you transfer the cacheline from another cpu to you you'll also
make progress...
Will fix the other stuff.
Greetings,
Andres Freund
--
Andres Freund http://www.2ndQuadrant.com/
PostgreSQL Development, 24x7 Support, Training & Services
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Andreas Karlsson | 2014-12-23 23:41:13 | Re: Using 128-bit integers for sum, avg and statistics aggregates |
| Previous Message | Robert Haas | 2014-12-23 21:42:41 | Re: Lockless StrategyGetBuffer() clock sweep |