http://defect.opensolaris.org/bz/show_bug.cgi?id=6057
Summary: excessive # of p-state transitions observed under load
Classification: Development
Product: power-mgmt
Version: unspecified
Platform: Other
OS/Version: Solaris
Status: ACCEPTED
Severity: normal
Priority: P3
Component: PAD
AssignedTo: eric.saxe at sun.com
ReportedBy: eric.saxe at sun.com
QAContact: patrick.bredenberg at sun.com
CC: tesla-dev at opensolaris.org
Aubrey reports that under moderate to high load there are still far too many
P-state transitions taking place. From data just before the holiday:
avg workload pstate change times/minutes
(1) (2) Avg
=========================================
0% 72 24 48
13% 3696 3784 3740
27% 6544 6712 6628
40% 9512 9536 9524
53% 11152 11144 11148
65% 12648 12296 12472
77% 11008 11800 11404
88% 8888 8776 8832
100% 8656 8740 8698
This was observed via DTracing the ess_transition probe. This needs to be fixed
before integration. Logic has been put in place to filter out P-state
transitions that would happen as a result of transient threads on an otherwise
idle system. But from this data it seems clear that more is needed to handle a
moderately busy system running real workload the frequently yields the CPU.
What I don't understand is why these P-state transitions are happening at all
during the moderate loads...since we should only request a P-state transition
if all the CPUs in the P-state domain become idle or when the first CPU on an
idle domain becomes busy. Intuitively, that should be fairly
rare...particularly above 50% utilization.
--
Configure bugmail: http://defect.opensolaris.org/bz/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are on the CC list for the bug.
