Re: CRC32C Parallel Computation Optimization on ARM

On Thu, Oct 26, 2023 at 2:23 PM Xiang Gao <Xiang.Gao@arm.com> wrote:
>
> On  Tue,  24 Oct,  2023 20:45:39PM -0500, Nathan Bossart wrote:
> >I tried this.  pg_waldump on 2 million ~8kB records took around 8.1 seconds
> >without the patch and around 7.4 seconds with it (an 8% improvement).
> >pg_waldump on 1 million ~16kB records took around 3.2 seconds without the
> >patch and around 2.4 seconds with it (a 25% improvement).
>
> Could you please provide details on how to generate these 8kB size or 16kB size data? Thanks!

Here's a script that I use to generate WAL records of various sizes,
change it to taste if useful:

for m in 16 64 256 1024 4096 8192 16384
do
    echo "Start of run with WAL size \$m bytes at:"
    date
    echo "SELECT pg_logical_emit_message(true, 'mymessage',
repeat('d', \$m));" >> $JUMBO/scripts/dumbo\$m.sql
    for c in 1 2 4 8 16 32 64 128 256 512 768 1024 2048 4096
    do
      $PGWORKSPACE/pgbench -n postgres -c\$c -j\$c -T60 -f
$JUMBO/scripts/dumbo\$m.sql > $JUMBO/results/dumbo\$m:\$c.out
    done
    echo "End of run with WAL size \$m bytes at:"
    date
    echo "\n"
done

--
Bharath Rupireddy
PostgreSQL Contributors Team
RDS Open Source Databases
Amazon Web Services: https://aws.amazon.com