Re: high load, no bottleneck

[Greg Oster <oster%cs.usask.ca@localhost>]

On Thu, 19 Sep 2013 18:41:45 +0200
manu%netbsd.org@localhost (Emmanuel Dreyfus) wrote:

> Greg Oster <oster%cs.usask.ca@localhost> wrote:
> 
> > > sysctl to the rescue.
> > 
> > The appropriate 'bit to twiddle' is likely raidPtr->openings.
> > Increasing the value can be done while holding raidPtr->mutex.
> > Decreasing the value can also be done while holding raidPtr->mutex,
> > but will need some care if attempting to decrease it by more than
> > the number of outstanding IOs.
> 
> This suggests that in my problem, RAIDframe would be the bottleneck
> given too many concurent I/O sent by WAPBL. But how is it possible?
> Aren't WAPBL flushes serialized?

RAIDframe only allows 6 IOs to be active, by default.  This number was
based on what provided 'reasonable performance' vs. 'requiring a lot of
kernel memory for degraded operation' back in the day.  On a modern
system, 6 is likely too low... 

> The change you sugest would be set by raidctl rather than sysctl,
> right?

It's probably easier to do by raidctl right now.  I'm not opposed to
having RAIDframe grow a sysctl interface as well if folks think that
makes sense. The 'openings' value is currently set on a per-RAID basis,
so a sysctl would need to be able to handle individual RAID sets as
well as overall configuration parameters.

Later...

Greg Oster