[zeromq-dev] Fwd: Exact matching on subscription topics

[Staffan Gimåker]

On Thu, Jan 19, 2012 at 2:53 AM, Andrew Hume <andrew at research.att.com>wrote:

> on the other hand, i don't get this use case.
> can anyone share why we need this complexity of subscription stuff?
> someone mentioned having tens of thousands of "topics" -- what is this
> about?
>

Tens of millions of topics is the case we have.

We want to do exact matching for two reasons:
 * The trie uses a metric shit ton of memory, exact matching would allow us
to use less memory with comparable throughput.
 * We need exact matching semantics to do other funky stuff to handle our
load, e.g. sharding of subscription information.

/S
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.zeromq.org/pipermail/zeromq-dev/attachments/20120119/38b38e5b/attachment-0001.htm>