[rabbitmq-discuss] Looking for guidance on R14B04 vs. R13B03 performance
mpietrek at skytap.com
Mon Feb 20 23:50:31 GMT 2012
| 25 ms is the timeout I think.
If so, this matches up very well with my experimental results, which was
showing that that a single publisher never went over ~37 message/sec. With
a 25 ms window, the max theoretical throughput would be 40/sec if I'm
understanding you correctly.
On Mon, Feb 20, 2012 at 2:58 PM, Matthew Sackman <matthew at rabbitmq.com>wrote:
> On Mon, Feb 20, 2012 at 10:22:15AM -0800, Matt Pietrek wrote:
> > Ah, thanks so much for this reply Matthew. It's extremely enlightening
> > seems to explain what we're seeing.
> > A follow up question just for my understanding: Are these "windows"
> > in nature (e.g., varying length, varying frequency, somehow tied to
> > load)? Or are they more static (e.g. "Once every 20 milliseconds").
> 25 ms is the timeout I think. If the queue goes "idle" before then (i.e.
> has no more work to do) then it will issue the fsync immediately. Thus
> this helps prevent latency go up too much for the single-publisher case.
> rabbitmq-discuss mailing list
> rabbitmq-discuss at lists.rabbitmq.com
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the rabbitmq-discuss