Flent-users discussion archives
 help / color / mirror / Atom feed
* [Flent-users] Query regarding aggregate netperf data points
@ 2018-04-04 11:47 Sourabh jain
  0 siblings, 0 replies; only message in thread
From: Sourabh jain @ 2018-04-04 11:47 UTC (permalink / raw)
  To: flent-users

[-- Attachment #1.1: Type: text/plain, Size: 779 bytes --]

Hello All,

I have a query regaring data aggregation functionality of Flent. In the
tests like tcp_8up and tcp_8down the interim value generated by different
instances of netperf are varying too much (between 0.2 to 0.58) though
interval is same for all i.e. 0.2 as compare to tcp_2up or tcp_2down

The point is system lag due to less core and process scheduling, the data
point collected during test may have different timestamps then how
aggregation is performed.

My question is how Flent handle this discrete time value of netperf to plot
total bandwidth graph?

Is Flent has some threshold that says that result for all process will be
consider for x point if they come within assumed threshold or there is some
other mechanism.

Thanks and Regards,
Sourabh Jain

[-- Attachment #1.2: Type: text/html, Size: 954 bytes --]

[-- Attachment #2: Type: text/plain, Size: 151 bytes --]

Flent-users mailing list

^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2018-04-04 11:48 UTC | newest]

Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-04-04 11:47 [Flent-users] Query regarding aggregate netperf data points Sourabh jain

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox