I figured out what is going on here. The sipp csv file records the result code for each call, and records the time the call was _initiated_. The report sorts the call data by start time before generating the graph. Therefore calls that run long and then fail get reported as an IHS earlier in the graph than they do in the manager log (where they show up when the call _ends_). Part of the confusion (but only part) is because I was using very short steps while testing the benchmark system.
--David On Tue, 4 Nov 2008 at 10:52, [EMAIL PROTECTED] wrote: > I've got my modified benchmark pretty much running. There are anomalies > I'm trying to understand though. Here's one: > > The report that is generated shows an exponentially increasing IHS > percentage during the course of the test. However, in the manager log > I see zero IHS percentage until the last step. I've also turned on > tracing, and the very first time that a call results in anything other > than success occurs during the final step. All previous calls during all > previous steps end with success according to SIPP (result code 0x1...the > first failure is result code 0x13). > > So, what is the report using to calculate the IHS? What does the non-zero > percentage in the earlier steps mean? > > --RDM > ------------------------------------------------------------------------- This SF.Net email is sponsored by the Moblin Your Move Developer's challenge Build the coolest Linux based applications with Moblin SDK & win great prizes Grand prize is a trip for two to an Open Source event anywhere in the world http://moblin-contest.org/redirect.php?banner_id=100&url=/ _______________________________________________ Sipp-users mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/sipp-users
