Horton
Menu

Re: Deleting older versions in unique indexes to avoid page splits

Peter Geoghegan <pg@bowt.ie>

View thread
From: Peter Geoghegan <pg@bowt.ie>
To: Victor Yegorov <vyegorov@gmail.com>
Cc: PostgreSQL Hackers <pgsql-hackers@lists.postgresql.org>
Date: 2020-11-17T04:59:34Z
Lists: pgsql-hackers 
On Sun, Nov 15, 2020 at 2:29 PM Victor Yegorov <vyegorov@gmail.com> wrote:
> TPS
> ---
>      query      | Master TPS | Patched TPS |  diff
> ----------------+------------+-------------+-------
> UPDATE + SELECT |       2413 |        2473 | +2.5%
> 3 SELECT in txn |      19737 |       19545 | -0.9%
> 15min SELECT    |       0.74 |        1.03 |  +39%
>
> Based on the figures and also on the graphs attached, I can tell v8 has no visible regression
> in terms of TPS, IO pattern changes slightly, but the end result is worth it.
> In my view, this patch can be applied from a performance POV.

Great, thanks for testing!

-- 
Peter Geoghegan

Commits

Same data as JSON: GET /api/v1/messages/:b64id/commits the thread's linked commits as JSON, with link sources. API reference →

  1. Enhance nbtree index tuple deletion.

  2. Pass down "logically unchanged index" hint.

  3. Fix index deletion latestRemovedXid bug.

  4. Deprecate nbtree's BTP_HAS_GARBAGE flag.