[PATCH] mempool perf test: test random bulk sizes

[Morten Brørup]

> From: Andrew Rybchenko [mailto:andrew.rybchenko at oktetlabs.ru]
> Sent: Sunday, 30 March 2025 10.29
> 
> On 2/28/25 19:48, Morten Brørup wrote:
> > Bulk requests to get or put objects in a mempool often vary in size.
> > A series of tests with pseudo random request sizes, to mitigate the
> > benefits of the CPU's dynamic branch predictor, was added.
> >
> > Also, various other minor changes:
> > - Improved the output formatting for readability.
> > - Added test for the "default" mempool with cache.
> > - Skip the tests for the "default" mempool, if it happens to use the
> same
> >    driver (i.e. operations) as already tested.
> > - Replaced bare use of "unsigned" with "unsigned int",
> >    to make checkpatches happy.
> 
> IMHO, it would be much better and easier to review if all above changes
> are done one by one in separate patches.
> 
> >
> > Signed-off-by: Morten Brørup <mb at smartsharesystems.com>
> 
> Overall the idea looks good, so
> Acked-by: Andrew Rybchenko <andrew.rybchenko at oktetlabs.ru>
> 
> but I'd be thankful if you split the patch.

OK.
I'll post a v2 with changes one by one in a series of patches.
<sarcasm about the write-only mailing list>
Let's hope someone else finds the series of simple patches sufficiently readable to care to review. ;-)
</sarcasm>

Thanks, Andrew.