1A note about CPU utilization... 2 3For HP-UX 11.0 <= system < 11.23 the configure script will select the 4"pstat" CPU utilization mechanism. This mechanism is the familiar 5HP-UX idle counter mechanism (for all incense and porpoises) and 6requires calibration. See src/netcpu_pstat.c for all the details. 7 8For HP-UX 11.23 >= system, the configure script will select the 9"pstatnew" CPU utilization mechanism. 11.23 adds cycle counts for 10user, kernel and interrupt modes to the idle cycle counter. As such, 11it _should_ be possible to simply take the sum of the four and the 12fractions and know how much time was spent in each mode. 13HOWEVER... there is a bug in the accounting for interrupt cycles, 14where interrupt cycles go missing. SOOO, since there is an accurate 15way to know what the total number of cycles should have been over the 16interval, and we know (ass-u-me) that the idle cycle counter is good 17(since the pstat mechanism has tested that one OK), we will take the 18ratio of idle to total cycles to compute CPU util. 19 20We will still calculate fractions for user, kernel and interrupt, and 21report them in debug (-d) output, but with a warning for interrupt 22time. See src/netcpu_pstatnew.c for all the details. 23 24Up through HP-UX 11.23 (aka 11iV2) if you enable burst mode, and 25happen to send sub-MSS requests and/or responses you _cannot_ assume 26that the packet per second rate on the wire will match the transaction 27per second rate reported by netperf, even if you set TCP_NODELAY with 28the test-specific -D option. The HP-UX 11.X TCP stack likely will be 29generating some immediate 'standalone' ACKnowledgements which may not 30be generated by other stacks. This has been reported to the HP-UX TCP 31folks, and an announcement will be made when that issue is resolved. 32