tech-kern archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

Re: identifying I/O pigs



On Tue, Feb 07, 2012 at 12:27:33PM -0500, Thor Lancelot Simon wrote:
> On Tue, Feb 07, 2012 at 04:37:53PM +0000, Emmanuel Dreyfus wrote:
> > Hi
> > 
> > As I undertand, when we see a NetBSD box on its knees because of high 
> > disk I/O, we have no way to find the offending process, and within 
> > the process. Am I right? If I am, it would be a nice feature to add.
> > Anyone already thought about it?
> 
> There was a summer of code project for this, which kind of went to
> hell in a handbasket.

To clarify: I'm not blaming the student and certainly not the mentor.
it's a hard problem and, to me anyway, the results reflected that it
was probably too hard for one summer's work.

Thor


Home | Main Index | Thread Index | Old Index