Messages in this thread | | | Date | Fri, 10 Nov 2006 18:51:10 -0800 (PST) | From | Christoph Lameter <> | Subject | RE: + sched-use-tasklet-to-call-balancing.patch added to -mm tree |
| |
On Fri, 10 Nov 2006, Chen, Kenneth W wrote:
> So designate only one CPU within a domain to do load balance between groups > for that specific sched domain should in theory fix the 2nd problem you > identified. Did you get a chance to look at the patch Suresh posted?
Yes, I am still thinking about how this would work. This would mean that the first cpu on a system would move busy processes to itself from all 1023 other processes? That does not sound appealing.
Processes in the allnodes domain would move to processor #0. The next lower layer are the nodes groups. Not all of the groups at that layer contain processor #0. So we would never move processes into those sched domains?
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |