There are some simple things like: try to ensure that no one else is using
the systems being measured besides you, and even that you yourself are
doing nothing with those systems other than the runs you are trying to
measure.  Measure what the load on the machines is before you start your
experiments, and ideally during (e.g. via a command like top) to see if
anything else is taking much CPU time.

Note: If part of what you are trying to do is measure the performance
*while the machines are being used for other purposes, too*, then that is
much tougher to characterize, because it will very heavily depend on what
those "other purposes" are.  Hopefully that isn't part of your task.

Run your experiment multiple times, timing each one.  Report not a single
value, but statistics like min, max, median, arithmetic mean, 10th
percentile, 90th percentile, etc.

If it is important to have statistically rigorous results, I don't know off
hand how to calculate what number of runs you will need.  If you can, find
someone who knows more about statistics and ask them.  If not, start with
something like 5 to 10 runs and see what kind of variance you get.  The
more variance you get, the more times you will need to repeat the
experiment to get results where you can be confident that they characterize
the range of run times that are likely to occur.

Andy


On Wed, Jun 11, 2014 at 10:14 AM, sindhu hosamane <sindh...@gmail.com>
wrote:

> Ya right .thanks for this info . If it is the case , how can one make
> performance tests ? I really have to make some performance comparisons on
> single node and multinode hadoop. Are there any other work arounds ? I want
> results to be atleast somewhat close to accurate.
> Or can u suggest me any other performance tests or method thats makes   sense
> to the scenario ? or any other scenarios may be other than time expr.
>
> Regards,
> Sindhu
>
> --
> You received this message because you are subscribed to the Google
> Groups "Clojure" group.
> To post to this group, send email to clojure@googlegroups.com
> Note that posts from new members are moderated - please be patient with
> your first post.
> To unsubscribe from this group, send email to
> clojure+unsubscr...@googlegroups.com
> For more options, visit this group at
> http://groups.google.com/group/clojure?hl=en
> ---
> You received this message because you are subscribed to the Google Groups
> "Clojure" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to clojure+unsubscr...@googlegroups.com.
> For more options, visit https://groups.google.com/d/optout.
>

-- 
You received this message because you are subscribed to the Google
Groups "Clojure" group.
To post to this group, send email to clojure@googlegroups.com
Note that posts from new members are moderated - please be patient with your 
first post.
To unsubscribe from this group, send email to
clojure+unsubscr...@googlegroups.com
For more options, visit this group at
http://groups.google.com/group/clojure?hl=en
--- 
You received this message because you are subscribed to the Google Groups 
"Clojure" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to clojure+unsubscr...@googlegroups.com.
For more options, visit https://groups.google.com/d/optout.

Reply via email to