Neha and I have been doing so work on perf testing. My past experience with
these perf and integration testing frameworks is that

   1. This kind of testing is extremely important. At least as important as
   unit testing. A lot of the bugs that are caught in production could be
   caught be good integration tests but likely will never be caught be unit
   tests.
   2. It is hard to get all your pieces scripted up so that you can fully
   automate the perf analysis you want to do and run this every day.
   3. It requires dedicated hardware that doesn't change from day to day.
   4. One of the biggest problems is that perf code is always kind of an
   afterthought. As a result one never gets to a framework that is good enough
   to use. Instead you keep re-writing the same test harnesses over and over
   but with little tweaks for each new test you need to run, then throwing that
   code away because it is so specific it can't be reused.

To hopefully help I started a wiki where we could work out some ideas for
this. The idea is basically just to dump out all the stats we have now to
CSV and do some analysis in R. Then script this up in a way that we can
craft "test scenarios" and run a bunch of these different configurations.

Wiki here:
https://cwiki.apache.org/confluence/display/KAFKA/Performance+testing

Would love to hear people's thoughts.

-Jay

Thanks for starting this discussion Jay !

>> dstat - This is the existing perf tool to get read/write/fs stats

My only concern about dstat is that it doesn't seem to give some
important IO stats like

avgrq-sz - size of the write request after merging several writes
together into one big write ( indicates how sequential the IO is)
wrqm_s - write requests merged per sec (also, could indicate how much
of the total IO is sequential and can be grouped into one write on the
disk)
w/s - write IO requests per sec (indicates how many flushes the kafka
broker is doing per sec)
% busy - indicates how busy the disks are.

At the very least, %busy is what we would like to know. Maybe I
couldn't pass the right options to dstat.

Does anyone have more ideas about dstat or some other perf tool,
preferably one that would work on Linux ?

Thanks,
Neha

On Mon, Oct 24, 2011 at 12:06 PM, Jay Kreps <[EMAIL PROTECTED]> wrote:
> Neha and I have been doing so work on perf testing. My past experience with
> these perf and integration testing frameworks is that
>
>   1. This kind of testing is extremely important. At least as important as
>   unit testing. A lot of the bugs that are caught in production could be
>   caught be good integration tests but likely will never be caught be unit
>   tests.
>   2. It is hard to get all your pieces scripted up so that you can fully
>   automate the perf analysis you want to do and run this every day.
>   3. It requires dedicated hardware that doesn't change from day to day.
>   4. One of the biggest problems is that perf code is always kind of an
>   afterthought. As a result one never gets to a framework that is good enough
>   to use. Instead you keep re-writing the same test harnesses over and over
>   but with little tweaks for each new test you need to run, then throwing that
>   code away because it is so specific it can't be reused.
>
> To hopefully help I started a wiki where we could work out some ideas for
> this. The idea is basically just to dump out all the stats we have now to
> CSV and do some analysis in R. Then script this up in a way that we can
> craft "test scenarios" and run a bunch of these different configurations.
>
> Wiki here:
> https://cwiki.apache.org/confluence/display/KAFKA/Performance+testing
>
> Would love to hear people's thoughts.
>
> -Jay
>

On 10/24/2011 03:27 PM, Neha Narkhede wrote:
> % busy - indicates how busy the disks are.

To my knowledge there isn't a god way to get this if disks is > 1.
iostat's %util becomes "percent of time waiting on at least one disk".