On Tue, Oct 11, 2011 at 10:23 PM, Steven McCoy <[email protected]> wrote:

> Took me a while as I couldn't see it in Google Preview:
>   999 instances of ~999ns or whatever the time scale is and a final one at
> ~20,000ns.

This is over TCP?

This is probably an artefact of the way you're measuring latency. 0MQ
batches messages aggressively so you're probably seeing two batches,
with a single message in the second batch. Naturally it'll arrive with
an apparent spike in latency.

-Pieter
_______________________________________________
zeromq-dev mailing list
[email protected]
http://lists.zeromq.org/mailman/listinfo/zeromq-dev

Reply via email to