Messages in this thread | | | Date | Wed, 22 Oct 2008 14:42:40 +0200 | From | Ingo Molnar <> | Subject | Re: [PATCH 0/4] pending scheduler updates |
| |
* Mike Galbraith <efault@gmx.de> wrote:
> > > With that patch, pgsql+oltp scales perfectly. > > > > hm, tempting. > > I disagree. Postgres's scaling problem is trivially corrected by > twiddling knobs (or whatnot). [...]
okay, then we need to document it a bit more: what knobs need twiddling to make it scale perfectly?
> [...] With that patch, you can't twiddle mysql throughput back, or > disk intensive loads for that matter. You can tweak the preempt > number, but it has nothing to do with lag, so anybody can preempt > anybody else as you turn the knob toward zero. Chaos.
okay, convinced.
> > Have you tried to hack/fix pgsql to do proper wakeups? > > No, I tried to build without spinlocks to verify, but build croaked. > Never went back to slogging through the code.
if it falls back to IPC semaphores that's a bad trade from a performance POV. The best would be if it used proper futexes (i.e. pthread_mutex() and friends) not some home-grown user-space spinlock thing.
Ingo
| |