← Back to team overview

maria-developers team mailing list archive

Re: parallel replication performance


Axel Schwenke <axel@xxxxxxxxxxxx> writes:

> The poor performance of MySQL with 1 database is expected. However MySQL is
> much better with 32 databases. Even better than MariaDB :(

I haven't had time to go through all the numbers and details yet, but just a
quick check:

In this test, are you sure that you are running MariaDB in GTID mode?

    CHANGE MASTER TO master_use_gtid=slave_pos

If not, you won't get any parallelism out of using 32 databases with different

So two interesting, but different  comparisons to make here:

1. MySQL multi-threaded slave compared to MariaDB GTID with different
domain_id per database. If MySQL is significantly better here it could
indicate some problem in MariaDB parallel replication that should be
investigated; this is possible as this part has not been tested a lot.

2. MySQL multi-threaded slave with load split into multiple databases,
compared to MariaDB without configuring different domains. Or just MariaDB
compared without and with different domain ids. This is an "unfair" benchmark;
by explicitly declaring that different databases/domains can run in parallel,
more opportunity for parallellism is available. But it could still be
interesting to see how much of that can be obtained from group commit
parallelism, without changing applications.

Both of these are interesting, but it was not clear to me which of them you
were describing?

 - Kristian.

Follow ups