On 4/11/06, Eric C. Saxe <[EMAIL PROTECTED]> wrote: > > I have a related comment: I think it may be better to > > change the > > traverse code to scan local CPU first - in the order > > local core, local > > board, local machine and then all remaining boards - > > to avoid massive > > communication overhead in NUMA/COMA machines. > > The code already traverses other CPUs in distance order. > Consideration of sub-chip groupings (like core) is on the way. > The logic in cpu_wakeup() also really needs this.
Do you have the bug# around for these problems? Holger _______________________________________________ perf-discuss mailing list perf-discuss@opensolaris.org
