* Async I/O is being used for reading and writing http request and
response respectively. This causes the worker core to steal new tasks as
when one sandbox blocks on "read" or "write". This causes true
round-robin on timer interrupts, leading to those high latencies.
* Ideally, the request/response should be synchronous I belive because
we are expected to have "low"/near-realtime latencies and the read/writes
are only performed when a client connects, so ideally not block!
Plus, we expect only small data transfers (in KBs) so that should also
support synchronous request/response processing.
* Major:
- Moved sandbox data struct into linear memory of a sandbox.
- (Should work well with other sandboxing mechanisms).
- Removed all mallocs from within uv usage, using a pre-allocated
memory within sandbox data-struct for read/write.
- TODO: convert prints on stdout to a string and send it out with
function response body.
- TODO: for each function loaded, what is the request and response
http header/body specification.
To start, keep headers minimal.
body either: json, plain.
- TODO: track TIMEOUTS. If we go beyond that, return a HTTP 408?
* silverfish is a submodule now
* memory modules from silverfish runtime is copied in to the aWsm runtime.
* runtime/tests/Makefile compiles different tests and silverfish/code_benches..
phani
Sean McBride