[zeromq-dev] Multicore Magic
pieterh at gmail.com
Mon Apr 26 21:13:22 CEST 2010
On Mon, Apr 26, 2010 at 9:07 PM, Martin Sustrik <sustrik at 250bpm.com> wrote:
> 1. Control events still have to be transferred via some IPC mechanism
> even if message payload is stored in shmem. So there's no way to improve
> latency to the level of inproc transport.
Sorry if my questions are utterly ignorant :-)
> 2. Allocating shmem is not free. Allocating shmem buffer for each
> message would turn to performance bottleneck.
Wouldn't happen like that, rather allocate fixed shmem buffers that
are reused for smaller messages. And use signals to indicate new
More information about the zeromq-dev