[lkml]   [2010]   [Apr]   [19]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH 1/5] Add a global synchronization point for pvclock
On Fri, Apr 16, 2010 at 01:36:34PM -0700, Jeremy Fitzhardinge wrote:
> On 04/15/2010 11:37 AM, Glauber Costa wrote:
> > In recent stress tests, it was found that pvclock-based systems
> > could seriously warp in smp systems. Using ingo's time-warp-test.c,
> > I could trigger a scenario as bad as 1.5mi warps a minute in some systems.
> >
> Is that "1.5 million"?
Yes it is.

But as I said, this seem to be a very deep worst case scenario. Most of boxes
are not even close to being that bad.

> > (to be fair, it wasn't that bad in most of them). Investigating further, I
> > found out that such warps were caused by the very offset-based calculation
> > pvclock is based on.
> >
> Is the problem that the tscs are starting out of sync, or that they're
> drifting relative to each other over time? Do the problems become worse
> the longer the uptime? How large are the offsets we're talking about here?
The offsets usually seem pretty small, under a microsecond. So I don't think
it has anything to do with tscs starting out of sync. Specially because the
delta-based calculation has the exact purpose of handling that case.

 \ /
  Last update: 2010-04-19 16:29    [W:0.906 / U:2.244 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site