Horton

Re: PG 16 draft release notes ready

David Rowley <dgrowleyml@gmail.com>

View thread
From: David Rowley <dgrowleyml@gmail.com>
To: Bruce Momjian <bruce@momjian.us>
Cc: Andres Freund <andres@anarazel.de>, PostgreSQL-development <pgsql-hackers@postgresql.org>
Date: 2023-05-31T06:03:01Z
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. Revert MAINTAIN privilege and pg_maintain predefined role.

  2. doc: PG 16 relnotes, remove "Have initdb use ICU by default"

  3. initdb: change default --locale-provider back to libc.

  4. doc: PG 16 relnotes, add author

  5. doc: PG 16 relnotes, move memory item and reword OUTER item

  6. doc: PG 16 relnotes, add memory overhead reduction item

  7. doc: PG 16 relnotes, adjust subscription origin mention

  8. doc: PG 16 relnotes, adjust auto_explain logging item

  9. doc: PG 16 relnotes: adjust outer/full hash join parallelization

  10. doc: PG 16 relnotes, fix duplicate author and commit

  11. doc: PG 16 relnotes, fix "locale" typo and windows locale text

  12. doc: PG 16 relnotes, add author from previous merge

  13. doc: PG 16 relnotes, wording adjustments

  14. doc: PG 16 relnotes, merge and move vector items

  15. doc: PG 16 relnotes, update xid/subxid searches item

  16. doc: PG 16 relnotes, SIMD improvements

  17. doc: PG 16 relnotes, add major features list

  18. doc: PG 16 relnotes, misc merged items and bootstrap detail

  19. doc: PG 16 relnotes, misc. updates

  20. doc: PG 16 relnotes, add commits

  21. Allow logical decoding on standbys

  22. Fix ts_headline() edge cases for empty query and empty search text.

  23. Add a hook for modifying the ldapbind password

  24. Rework design of functions in pg_walinspect

  25. initdb: derive encoding from locale for ICU; similar to libc.

  26. Doc: add XML ID attributes to <sectN> and <varlistentry> tags.

  27. Simplify the implementations of the to_reg* functions.

  28. Rename pg_dissect_walfile_name() to pg_split_walfile_name()

  29. Make materialized views participate in predicate locking

  30. Improve performance of and reduce overheads of memory management

  31. Allow grant-level control of role inheritance behavior.

On Wed, 31 May 2023 at 11:32, Bruce Momjian <bruce@momjian.us> wrote:
>
> On Thu, May 25, 2023 at 05:57:25PM +1200, David Rowley wrote:
> > On 64-bit builds, it was 16 bytes for AllocSet contexts, 24 bytes for
> > generation contexts and 16 bytes for slab contexts.
>
> Okay, item added to Source Code:

I don't think this should go under "E.1.3.11. Source Code".  The patch
was entirely aimed to increase performance, not just of allocations
themselves, but of any operations which uses palloc'd memory. This is
due to the patch increasing the density of memory allocation on blocks
malloc'd by our memory context code so that fewer CPU cache lines need
to be touched in the entire backend process for *all* memory that's
allocated with palloc. The performance increase here can be fairly
significant for small-sized palloc requests when CPU cache pressure is
high. Since CPU caches aren't that big, it does not take much of a
query to put the cache pressure up. Hashing or sorting a few million
rows is going to do that.

The patch here was born out of the regression report I made in [1],
which I mention in [2] about the prototype patch Andres wrote to fix
the performance regression.

I think "E.1.3.1.2. General Performance" might be a better location.
Having it under "Source Code" makes it sound like it was some
refactoring work. That's certainly not the case.

A bit more detail:

Here's a small histogram of the number of allocations in various size
buckets from running make check with some debug output in
AllocSetAlloc and GenerationAlloc to record the size of the
allocation:

     bucket     | number_of_allocations | percent_of_total_allocations
----------------+-----------------------+---------
 up to 16 bytes |               8,881,106 |   31.39
 up to 32 bytes |               4,579,608 |   16.18
 up to 64 bytes |               6,574,107 |   23.23
 above 64 bytes |               8,260,714 |   29.19

So quite a large portion of our allocations (at least in our test
suite) are small. Halving the 16-byte chunk header down 8 bytes on a
16-byte allocation means a 25% memory saving.

David

[1] https://www.postgresql.org/message-id/CAApHDvqXpLzav6dUeR5vO_RBh_feHrHMLhigVQXw9jHCyKP9PA%40mail.gmail.com
[2] https://www.postgresql.org/message-id/CAApHDvowHNSVLhMc0cnovg8PfnYQZxit-gP_bn3xkT4rZX3G0w%40mail.gmail.com