[ovs-dev] [PATCH v4 3/9] test-classifier: Add benchmark.
Jarno Rajahalme
jrajahalme at nicira.com
Fri Aug 21 20:18:38 UTC 2015
I applied this before pushing to master, thanks!
Jarno
> On Aug 21, 2015, at 7:39 AM, Ben Pfaff <blp at nicira.com> wrote:
>
> On Fri, Aug 21, 2015 at 07:37:51AM -0700, Ben Pfaff wrote:
>> On Fri, Aug 07, 2015 at 04:57:36PM -0700, Jarno Rajahalme wrote:
>>> Add a benchmark command for classifier lookup performance testing.
>>>
>>> Usage:
>>
>> This usage note is good, but putting it just in the commit log will mean
>> that it gets lost. It should be in a --help message, or failing that in
>> a source code comment.
>>
>> I'm not sure I believe in the realism of random priorities. Random
>> priorities are are worst case for the optimization that skips subtables
>> based on priorities. Our NSDI paper showed that subtables tend to have
>> a small number of priorities (often just one) in practice.
>>
>> If n_rules < n_subtables, or if the random numbers come out just right,
>> then I think that the classifier will have fewer than the requested
>> number of subtables. Also, if the same rule is generated more than
>> once, the classifier will have fewer than the requested number of rules.
>>
>> Acked-by: Ben Pfaff <blp at nicira.com>
>
> Also a minor spelling fix:
>
> diff --git a/tests/test-classifier.c b/tests/test-classifier.c
> index 54b595f..b2d4afd 100644
> --- a/tests/test-classifier.c
> +++ b/tests/test-classifier.c
> @@ -1302,7 +1302,7 @@ run_benchmarks(struct ovs_cmdl_context *ctx)
> n_lookups = strtol(ctx->argv[5], NULL, 10);
>
> printf("\nBenchmarking with:\n"
> - "%d rules with %d prioritites in %d tables, "
> + "%d rules with %d priorities in %d tables, "
> "%d threads doing %d lookups each\n",
> n_rules, n_priorities, n_tables, n_threads, n_lookups);
>
More information about the dev
mailing list