> Any good applications that would show me each cpus loads
it doesn't work that way. "load average" in Unix means "length of the run
queue". there is just one run queue, not one for each processor. since the
scheduler will load balance, per-processor load is approximately loadav/ncpu.
somewhere in 2.1 there was some SMP profiling code in the kernel which would
give you some hints about time spent in spinlocks; I don't recall whether it
also told you how often each processor idled.
-
Linux SMP list: FIRST see FAQ at http://www.irisa.fr/prive/mentre/smp-faq/
To Unsubscribe: send "unsubscribe linux-smp" to [EMAIL PROTECTED]
