Hi Donald,

I've made an agnostic eventloop version of API-Hour to test aiouv, I'll
publish that soon.
But, for now, only based on my benchmarks, the performances compare to with
AsyncIO official event-loop are worse I've hoped:
The best results I've it's 10% better than AsyncIO event-loop.
I've also tested with quasmash, it's catastrophic.
But, don't conclude to quickly and kill the baby in the bathroom: certainly
aiouv or at least quasmash internals could be improved.

Regards.

--
Ludovic Gasc

On Tue, Feb 17, 2015 at 12:42 AM, Donald Stufft <[email protected]> wrote:

>
> > On Feb 16, 2015, at 6:05 PM, Victor Stinner <[email protected]>
> wrote:
> >
> > Hi,
> >
> > Mike Bayer, the author of SQLAchemy, wrote a long article about
> > asyncio and databases:
> > http://techspot.zzzeek.org/2015/02/15/asynchronous-python-and-databases/
> >
> > IMO the most interesting part if the benchmark written for this article:
> > https://bitbucket.org/zzzeek/bigdata/
> >
> > The benchmark inserts a lot of rows (more than 9 millions) in a
> > PosgreSQL server using psycopg2 and aiopg. It compares performances of
> > threads, gevent and asyncio. Bad news: asyncio is much slower on this
> > benchmark (between 1.3x and 3.3x slower).
> >
> > It's not easy to create the setup to run the benchmark (ex: you have
> > to install a PostgreSQL server and configure it to run the benchmark),
> > you have to find the best pool size for your setup and then you have
> > to analyze bencmark results (there is no unique number at the end,
> > just a long list of numbers). On my first setup (desktop: benchmark,
> > laptop: server, slow LAN), I had to stop the benchmark after 2 hours.
> >
> > Mike see between 6,000 and 26,000 SQL INSERT queries per second
> > depending on his setup and on the benchmark parameter. Ah yes, there
> > are also options to tune the benchmark, but I don't think that you are
> > supposed to use them.
> >
> > I'm trying to reproduce the benchmark to check if I get similar
> > results and then to try to run asyncio in a profiler. I never used
> > aiopg, nor psycopg2, and I don't remember when I installed a
> > PostgreSQL server for the last time :-)
> >
> > Victor
>
> I wonder how much of the asyncio difference is because of asyncio and
> how much is because of the default event loop. It would be interesting
> to see what the gevent numbers would be running on the asyncio eventloop,
> or the asyncio numbers would be running on the gevent eventloop. Another
> interesting option is something like https://github.com/saghul/aiouv.
>
> In other words, is asyncio the cause of the drastically lower req/s or
> is the event loop the problem.
>
> ---
> Donald Stufft
> PGP: 7C6B 7C5D 5E2B 6356 A926 F04F 6E3C BCE9 3372 DCFA
>
>

Reply via email to