| From: | Peter Geoghegan <pg(at)bowt(dot)ie> |
|---|---|
| To: | Thomas Munro <thomas(dot)munro(at)gmail(dot)com> |
| Cc: | Andres Freund <andres(at)anarazel(dot)de>, pgsql-hackers(at)postgresql(dot)org |
| Subject: | Re: ReadRecentBuffer() doesn't scale well |
| Date: | 2023-06-27 03:44:27 |
| Message-ID: | CAH2-Wz=RC968tkLzVz+T2MOKpkk4Bpp-pUSy+5YSi+X8bTgtZg@mail.gmail.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Mon, Jun 26, 2023 at 8:34 PM Thomas Munro <thomas(dot)munro(at)gmail(dot)com> wrote:
> Yeah. Aside from inherent nastiness of user-space spinlocks, this new
> use case is also enormously more likely to contend and then get into
> trouble by being preempted due to btree root pages being about the
> hottest pages in the universe than the use case I was focusing on at
> the time.
They're not just the hottest. They're also among the least likely to
change from one moment to the next. (If that ever failed to hold then
it wouldn't take long for the index to become grotesquely tall.)
--
Peter Geoghegan
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Jaime Casanova | 2023-06-27 04:05:43 | Assert !bms_overlap(joinrel->relids, required_outer) |
| Previous Message | Thomas Munro | 2023-06-27 03:33:57 | Re: ReadRecentBuffer() doesn't scale well |