eCAL VS iceoryx

New version (5.94) of the high performance interprocess / interhost communication framework eCAL is available. eCAL supports different transport layer like shared memory for interprocess and udp multicast for interhost communication. It does not force the user to use a specific serialization format but supports some of the standards like google protobuf, capnproto or flatbuffers. The API is wrapped to C, C++, Python, C#, Rust and Go (the last two I never tested ;-)). Here you can find all the documentation. Check out the great applications for monitoring, record and replay. eCAL is Apache 2 licensed, repository hosted here. Have fun :-)

I you just need a fast publish / subscribe framework for windows you can give eCAL a try. The setup is done in less a minute and their is no dependency hell. Just to mention it as alternative. Documentation here

I would concider using eCAL since it blasts everything out of the water in terms of performance and comes with some handy tooling for inspection of messages in-travel.

Source on GitHub: https://github.com/continental/ecal

Check out eCal.

This really makes me want to try https://github.com/continental/ecal with https://github.com/google/flatbuffers to see how they compare. I also know that gpc for cpp at least stops functioning by about 4 MB of request size. Which I find stupid. What if I want to send uncompressed bitmaps!

Congratulations. Well done. eCAL will update as soon as possible to the new release. The new custom header and the n:m pub/sub support are really welcome new features.

Here is their counter callback example: https://github.com/continental/ecal/blob/master/samples/cpp/counter/counter_rec_cb/src/counter_rec_cb.cpp

Also, when you want to perform some access control with access rights, you have to face sid— and ace-strings - oh they are fun. And, of course, there are all the nasty details; for instance, Windows defines macros that lead to compilation failures since they collide with internal naming. Take a look at this here, maybe it makes your efforts less painless: https://github.com/eclipse-iceoryx/iceoryx/blob/master/iceor...

You could reuse the iceoryx platform layer that enables iceoryx to run on every platform from qnx, linux, freertos, mac, windows. Maybe it can help you as well: https://github.com/eclipse-iceoryx/iceoryx/blob/master/doc/w...

Does the schema help a lot? For C++ you can get very fast without, for example with IceOryx https://github.com/eclipse-iceoryx/iceoryx

In contrast to Cap'n'Proto you get compiler optimized struct layout as benefit from using raw structs. Benchmarks are here https://iceoryx.io/v2.0.2/examples/iceperf/

full release notes: https://github.com/eclipse-iceoryx/iceoryx/blob/master/doc/website/release-notes/iceoryx-v2-0-0.md

True, a better comparison for Shadesmar would be with libraries like iceoryx and alephzero.

This is the tracking issue for Windows support https://github.com/eclipse-iceoryx/iceoryx/issues/33