| From: | Alvaro Herrera <alvherre(at)2ndquadrant(dot)com> |
|---|---|
| To: | Andres Freund <andres(at)anarazel(dot)de> |
| Cc: | pgsql-hackers(at)lists(dot)postgresql(dot)org, Jaime Casanova <jaime(dot)casanova(at)2ndquadrant(dot)com> |
| Subject: | Re: LogwrtResult contended spinlock |
| Date: | 2021-11-22 21:56:43 |
| Message-ID: | 202111222156.xmo2yji5ifi2@alvherre.pgsql |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
There was an earlier comment by Andres that asyncXactLSN should also be
atomic, to avoid an ugly spinlock interaction with the new atomic-based
logwrtResult. The 0002 here is an attempt at doing that; I found that
it also needed to change WalWriterSleeping to use atomics, to avoid
XLogSetAsyncXactLSN having to grab the spinlock for that.
--
Álvaro Herrera Valdivia, Chile — https://www.EnterpriseDB.com/
"Learn about compilers. Then everything looks like either a compiler or
a database, and now you have two problems but one of them is fun."
https://twitter.com/thingskatedid/status/1456027786158776329
| Attachment | Content-Type | Size |
|---|---|---|
| v5-0001-make-LogwrtResult-atomic.patch | text/x-diff | 21.0 KB |
| v5-0002-more-atomics.patch | text/x-diff | 4.0 KB |
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Tom Lane | 2021-11-22 22:32:21 | Re: Reduce function call costs on ELF platforms |
| Previous Message | Andres Freund | 2021-11-22 21:50:48 | Reduce function call costs on ELF platforms |