Postgres Pro
Downloads
Home   >   mailing lists

Re: Reducing the chunk header sizes on all memory context types - Mailing list pgsql-hackers

From David Rowley
Subject Re: Reducing the chunk header sizes on all memory context types
Date
Msg-id CAApHDvqtpeG8fdgVwkrJ1QDpy53q7avMHzpuGVpuEBPEePVsmw@mail.gmail.com
Whole thread Raw
In response to Re: Reducing the chunk header sizes on all memory context types  (Tomas Vondra <tomas.vondra@enterprisedb.com>)
List pgsql-hackers
Tree view 
On Tue, 30 Aug 2022 at 13:58, Tomas Vondra
<tomas.vondra@enterprisedb.com> wrote:
> armv7l (32-bit rpi4)
>
> +WARNING:  chunkSize 216 fullChunkSize 232 header 16
> +WARNING:  chunkSize 64 fullChunkSize 80 header 16
>
> aarch64 (64-bit rpi4)
>
> +WARNING:  chunkSize 304 fullChunkSize 320 header 16
> +WARNING:  chunkSize 80 fullChunkSize 96 header 16
>
> So indeed, those are *perfect* matches and thus the sentinel_ok() never
> executed. So no failures until now. On x86-64 I get the same thing as on
> aarch64. I guess that explains why it never failed. Seems like a pretty
> amazing coincidence ...

hmm, I'm not so sure I agree that it's an amazing coincidence. Isn't
it quite likely that the chunksize being given to SlabContextCreate()
is the same as MAXALIGN(chunksize)? Isn't that all it would take?

David

pgsql-hackers by date:

Previous
From: "houzj.fnst@fujitsu.com"
Date:
Subject: RE: Data is copied twice when specifying both child and parent table in publication
Next
From: David Rowley
Date:
Subject: Re: Reducing the chunk header sizes on all memory context types