Re: [PoC] Improve dead tuple storage for lazy vacuum - Mailing list pgsql-hackers

From Andres Freund
Subject Re: [PoC] Improve dead tuple storage for lazy vacuum
Date
Msg-id 20210720000012.r4eysuytdcfa35t5@alap3.anarazel.de
Whole thread Raw
In response to Re: [PoC] Improve dead tuple storage for lazy vacuum  (Andres Freund <andres@anarazel.de>)
List pgsql-hackers
Hi,

On 2021-07-19 16:49:15 -0700, Andres Freund wrote:
> E.g. for
> 
> select prepare(
> 1000000, -- max block
> 20, -- # of dead tuples per page
> 10, -- dead tuples interval within a page
> 1 -- page inteval
> );
>         attach  size    shuffled    ordered
> array    69 ms  120 MB  84.87 s          8.66 s
> intset  173 ms   65 MB  68.82 s         11.75 s
> rtbm    201 ms   67 MB  11.54 s          1.35 s
> tbm     232 ms  100 MB   8.33 s          1.26 s
> vtbm    162 ms   58 MB  10.01 s          1.22 s
> radix    88 ms   42 MB  11.49 s          1.67 s
> 
> and for
> select prepare(
> 1000000, -- max block
> 10, -- # of dead tuples per page
> 1, -- dead tuples interval within a page
> 1 -- page inteval
> );
> 
>         attach  size    shuffled    ordered
> array    24 ms   60MB   3.74s            1.02 s
> intset   97 ms   49MB   3.14s            0.75 s
> rtbm    138 ms   36MB   0.41s            0.14 s
> tbm     198 ms  101MB   0.41s            0.14 s
> vtbm    118 ms   27MB   0.39s            0.12 s
> radix    33 ms   10MB   0.28s            0.10 s

Oh, I forgot: The performance numbers are with the fixes in
https://www.postgresql.org/message-id/20210717194333.mr5io3zup3kxahfm%40alap3.anarazel.de
applied.

Greetings,

Andres Freund



pgsql-hackers by date:

Previous
From: Peter Geoghegan
Date:
Subject: Re: Transactions and indexes
Next
From: Alvaro Herrera
Date:
Subject: Re: Rename of triggers for partitioned tables