Re: a heavy duty operation on an "unused" table kills my server

Matthew Wakeling wrote:
> On Fri, 15 Jan 2010, Greg Smith wrote:
>> My theory has been that the "extra processing it has to perform" you
>> describe just doesn't matter in the context of a fast system where
>> physical I/O is always the bottleneck.
>
> Basically, to an extent, that's right. However, when you get 16 drives
> or more into a system, then it starts being an issue.

I guess if I test a system with *only* 16 drives in it one day, maybe
I'll find out.

Seriously though, there is some difference between a completely
synthetic test like you noted issues with here, and anything you can see
when running the database. I was commenting more on the state of things
from the perspective of a database app, where I just haven't seen any of
the CFQ issues I hear reports of in other contexts. I'm sure there are
plenty of low-level tests where the differences between the schedulers
is completely obvious and it doesn't look as good anymore, and I'll take
a look at whether I can replicate the test case you saw a specific
concern with here.

--
Greg Smith 2ndQuadrant Baltimore, MD
PostgreSQL Training, Services and Support
greg(at)2ndQuadrant(dot)com www.2ndQuadrant.com