Horton

Re: [PoC] Improve dead tuple storage for lazy vacuum

Andres Freund <andres@anarazel.de>

View thread View on postgr.es
From: Andres Freund <andres@anarazel.de>
To: Masahiko Sawada <sawada.mshk@gmail.com>
Cc: PostgreSQL-development <pgsql-hackers@postgresql.org>
Date: 2021-07-20T00:00:12Z
Lists: 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

Commits

  1. radixtree: Fix SIGSEGV at update of embeddable value to non-embeddable.

  2. Get rid of anonymous struct

  3. Teach radix tree to embed values at runtime

  4. Teach TID store to skip bitmap for small numbers of offsets

  5. Use bump context for TID bitmaps stored by vacuum

  6. Fix alignment of stack variable

  7. Use TidStore for dead tuple TIDs storage during lazy vacuum.

  8. Rethink create and attach APIs of shared TidStore.

  9. Fix inconsistent function prototypes with function definitions.

  10. Fix a calculation in TidStoreCreate().

  11. Fix potential integer handling issue in radixtree.h.

  12. Add TIDStore, to store sets of TIDs (ItemPointerData) efficiently.

  13. Fix link error for test_radixtree module on Windows

  14. Blind attempt to fix ODR violations

  15. Fix incorrect format specifier for int64

  16. Fix redefinition of typedefs

  17. Add template for adaptive radix tree

  18. Fix signedness error in 9f225e992 for gcc

  19. Introduce helper SIMD functions for small byte arrays

  20. Optimize vacuuming of relations with no indexes.

  21. Add bound check before bsearch() for performance

  22. Allocate consecutive blocks during parallel seqscans