mysql-proxy-discuss team mailing list archive

[Adrienne Porter Felt <apf@xxxxxxxxxxxx>]

>
> No selects are involved in this run, correct?
>

No, that run was just INSERT run 100x.


> Are the queries run sequentially or in parallel?
>

All queries are run sequentially, not in parallel.


> Since you mentioned you use the funnel plugin, there's no chance of Lua
> being in
> the middle, since it doesn't support scripts at the moment.
>

Actually, I added Lua support back in for what I need to do. But for this
baseline I am not doing anything in Lua.

As an aside, we have seen speedups happen even without funnel:
> There are rare cases in certain workload mixes, database content, buffer
> pool sizes
> and a bit of mysqld thread scheduling chance, where the slight slowdown
> caused by
> proxy improves the concurrency in mysqld, thereby leading to a slight
> throughput
> increase. But this happens only in rare cases, and only with queries sent
> by
> many clients.
>

Unfortunately this can't be the answer: we are sending all queries from one
client, and we aren't mixing our workload.  We only send one query at a
time, and all queries in a trial are the same time.


> As for the improvements with larger result sets:
> This can be explained by the nature of event-based network i/o and also by
> using
> funnel (with a connection pool > 1).
>

We are using a connection pool = 1 with sequential statements, so this can't
be it either.


> Where do you measure the response times? I'm assuming in the client app,
> correct?
>

Yes, we have a small python script doing this.


> BTW, is this MySQL Proxy 0.7.x, or a custom built 0.8? 0.8 would be
> multithreaded
> already screwing my entire explanation even more ;)
>

It's 0.7.x, whichever came with funnel.

Thank you for the brainstorming........this is extremely puzzling.  Our test
code is very short and simple and none of us can find bugs in it; all we do
is change the port our connection goes through (either the proxy or not the
proxy) and time the statement.

Adrienne