On 27 September 2013 07:27, Sebastiano Spicuglia <[email protected]> wrote: > Hi, > > thank you for the reply.
What is the JMeter version? Are you running the test in stand-alone or client-server mode? > Sorry I'm quite new with JMeter, where could I find the > timestamp of the readings? In the jmeter.log file > Btw: I checked what is the maximum throughput of that server > (the same info I was trying to collect with JMeter) with another load > generator (httperf). It is around 20req/s. > Therefore the last line of Jmeter's log seems to report a reasonable > number. > > Is it possible that the cumulative and the delta are computed > totally independently? No, the same data is used. > > - Sebastiano > > On Thu, Sep 26, 2013 at 5:52 PM, sebb <[email protected]> wrote: >> On 26 September 2013 14:24, Sebastiano Spicuglia >> <[email protected]> wrote: >>> Hello all, >>> >>> I have a question about the throughput calculation in Jmeter. >> >> Which version of JMeter? >> >>> I set up a simple test plan and I configured jmeter to print information >>> about the throughput using the information found in: >>> >>> http://jmeter.apache.org/usermanual/component_reference.html#Generate_Summary_Results >>> >>> The results I got are the following: >>> >>> summary + 1 in 0.2s = 4.6/s Avg: 218 Min: 218 Max: 218 >>> Err: 0 (0.00%) Active: 3 Started: 3 Finished: 0 >>> summary + 92 in 5.3s = 17.2/s Avg: 784 Min: 199 Max: 1409 >>> Err: 0 (0.00%) Active: 34 Started: 34 Finished: 0 >>> summary = 93 in 5.3s = 17.4/s Avg: 778 Min: 199 Max: 1409 >>> Err: 0 (0.00%) >>> summary + 113 in 7.3s = 15.4/s Avg: 2068 Min: 1413 Max: 2638 >>> Err: 0 (0.00%) Active: 60 Started: 60 Finished: 0 >>> summary = 206 in 11.3s = 18.2/s Avg: 1485 Min: 199 Max: 2638 >>> Err: 0 (0.00%) >>> summary + 130 in 9s = 14.7/s Avg: 2829 Min: 2461 Max: 3128 >>> Err: 0 (0.00%) Active: 60 Started: 60 Finished: 0 >>> summary = 336 in 17.4s = 19.3/s Avg: 2005 Min: 199 Max: 3128 >>> Err: 0 (0.00%) >>> summary + 123 in 9s = 13.8/s Avg: 2878 Min: 2574 Max: 3082 >>> Err: 0 (0.00%) Active: 60 Started: 60 Finished: 0 >>> summary = 459 in 23.3s = 19.7/s Avg: 2239 Min: 199 Max: 3128 >>> Err: 0 (0.00%) >>> summary + 127 in 9s = 14.3/s Avg: 2873 Min: 2554 Max: 3200 >>> Err: 0 (0.00%) Active: 60 Started: 60 Finished: 0 >>> summary = 586 in 29.3s = 20.0/s Avg: 2376 Min: 199 Max: 3200 >>> Err: 0 (0.00%) >>> summary + 125 in 9s = 14.0/s Avg: 2876 Min: 2614 Max: 3090 >>> Err: 0 (0.00%) Active: 60 Started: 60 Finished: 0 >>> summary = 711 in 35.3s = 20.1/s Avg: 2464 Min: 199 Max: 3200 >>> Err: 0 (0.00%) >>> >>> I am a little bit lost here. >>> >>> Why is the sum of all the intermediate intervals higher than final time? >> >> Rounding may account for some of the discrepancy, but it does seem odd >> that the final few intermediates are 9s apart whereas the totals are >> about 6s apart. >> >> Can you provide the timestamps for the readings? >> >>> If I did the math right the sum should be 48.8 while the final interval is >>> 35.3. >>> >>> Why is the final throughput (that should be the cumulative) higher >>> than all the intermediate? >> >> The throughput is samples/time so if the times are different the >> throughput will also be different. >> >>> Could you please explain me how to read those results? >> >> The '+' lines are current interval only and the '=' are cumulative. >> >> The output is intended as a guide to how the test is progressing, not >> for formal reporting. >> >>> Thank you very much for you support and congratulation for your job >>> Best regards >>> Sebastiano >>> >>> --------------------------------------------------------------------- >>> To unsubscribe, e-mail: [email protected] >>> For additional commands, e-mail: [email protected] >>> >> >> --------------------------------------------------------------------- >> To unsubscribe, e-mail: [email protected] >> For additional commands, e-mail: [email protected] >> > > --------------------------------------------------------------------- > To unsubscribe, e-mail: [email protected] > For additional commands, e-mail: [email protected] > --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
