Messages in this thread | | | Date | Mon, 17 Jan 2011 21:23:16 +0530 | From | Srivatsa Vaddagiri <> | Subject | Re: [RFC -v5 PATCH 2/4] sched: Add yield_to(task, preempt) functionality. |
| |
On Fri, Jan 14, 2011 at 01:29:52PM -0500, Rik van Riel wrote: > >I am not sure whether we are meeting that objective via this patch, as > >lock-spinning vcpu would simply yield after setting next buddy to preferred > >vcpu on target pcpu, thereby leaking some amount of bandwidth on the pcpu > >where it is spinning. > > Have you read the patch?
Sorry had mis-read the patch!
On reviewing it further, I am wondering if we can optimize yield_to() further for case when target and current are on same pcpu, by swapping vruntimes of two tasks (to let target run in current's place - as we do in task_fork_fair()).
- vatsa
| |