Horton

Re: Compressed TOAST Slicing

Andrey Borodin <x4mmm@yandex-team.ru>

View thread
From: Andrey Borodin <x4mmm@yandex-team.ru>
To: Tom Lane <tgl@sss.pgh.pa.us>
Cc: Andres Freund <andres@anarazel.de>, Paul Ramsey <pramsey@cleverelephant.ca>, Владимир Лесков <vladimirlesk@yandex-team.ru>, Stephen Frost <sfrost@snowman.net>, Daniel Verite <daniel@manitou-mail.org>, Simon Riggs <simon@2ndquadrant.com>, rafia.sabih@enterprisedb.com, PostgreSQL Hackers <pgsql-hackers@lists.postgresql.org>
Date: 2019-04-16T12:56:52Z
Lists: pgsql-hackers

Commits

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

  1. Add support for partial TOAST decompression

  2. Remove remaining hard-wired OID references in the initial catalog data.

  3. Rephrase references to "time qualification".


> 9 апр. 2019 г., в 22:30, Tom Lane <tgl@sss.pgh.pa.us> написал(а):
> 
> The proposal is kind of cute, but I'll bet it's a net loss for
> small copy lengths --- likely we'd want some cutoff below which
> we do it with the dumb byte-at-a-time loop.

Ture.
I've made simple extension to compare decompression time on pgbench-generated WAL [0]

Use of smart memcpy unless match length is smaller than 16 (sane random value) gives about 20% speedup to decompression time.
Sole use of memcpy gives smaller effect.

We will dig into this further.

Best regards, Andrey Borodin.


[0] https://github.com/x4m/test_pglz