ZeroMQ

Zero-Copy

ØMQ’s message API lets you send and receive messages directly to and from application buffers without copying data. We call it zero-copy, and it can improve performance in some applications. Like all optimizations, use this when you know it helps, and measure before and after. Zero-copy makes your code more complex.

To do zero-copy, you use zmq_msg_init_data() to create a message that refers to a block of data already allocated on the heap with malloc(), and then you pass that to zmq_msg_send(). When you create the message, you also pass a function that ØMQ will call to free the block of data, when it has finished sending the message. This is the simplest example, assuming “buffer” is a block of 1,000 bytes allocated on the heap:

void my_free (void *data, void *hint) {
    free (data);
}
//  Send message from buffer, which we allocate and 0MQ will free for us
zmq_msg_t message;
zmq_msg_init_data (&message, buffer, 1000, my_free, NULL);
zmq_msg_send (socket, &message, 0);

There is no way to do zero-copy on receive: ØMQ delivers you a buffer that you can store as long as you wish, but it will not write data directly into application buffers.

On writing, ØMQ’s multipart messages work nicely together with zero-copy. In traditional messaging, you need to marshal different buffers together into one buffer that you can send. That means copying data. With ØMQ, you can send multiple buffers coming from different sources as individual message frames. Send each field as a length-delimited ...