summaryrefslogtreecommitdiff
path: root/src/platform/posix
Commit message (Collapse)AuthorAge
* Pass cancel of IPC and TCP all the way down to POSIX pipedescs.Garrett D'Amore2017-06-29
|
* Refactor stop again, closing numerous races (thanks valgrind!)Garrett D'Amore2017-06-28
|
* Convert to POSIX polled I/O for async; start of cancelable aio.Garrett D'Amore2017-06-27
| | | | | | | | | | | | | | | | | | This eliminates the two threads per pipe that were being used to provide basic I/O handling, replacing them with a single global thread for now, that uses poll and nonblocking I/O. This should lead to great scalability. The infrastructure is in place to easily expand to multiple polling worker threads. Some thought needs to be given about how to scale this to engage multiple CPUs. Horizontal scaling may also shorten the poll() lists easing C10K problem. We should look into better solutions than poll() for platforms that have them (epoll on Linux, kqueue on BSD, and event ports on illumos). Note that the file descriptors start out in blocking mode for now, but then are placed into non-blocking mode. This is because the negotiation phase is not yet callback driven, and so needs to be synchronous.
* More race condition fixes.Garrett D'Amore2017-06-26
|
* Adding mutex lock during fini to prevent false positive data race.Garrett D'Amore2017-06-25
|
* Clear the owner while *still* holding the lock.Garrett D'Amore2017-06-25
|
* Additional mutex debugging support.Garrett D'Amore2017-06-22
|
* Expose a library finalizer suitable for atexit().Garrett D'Amore2017-06-21
|
* ETIME may not be defined on various platforms (STREAMs specific).Garrett D'Amore2017-04-12
|
* IPC send/recv works asynchronously for POSIX.Garrett D'Amore2017-03-29
| | | | | | | | | | As with TCP, we're still using threads under the hood. But this completes the send/recv logic conversion for POSIX to our AIO framework, and hence represents a substantial milestone towards full asyncronous operation. We still need to do accept/connect operations asynchronously, then making. Windows overlapped IO work properly. After that, poll/epoll/kqueue, etc.
* Clean up some dead code.Garrett D'Amore2017-03-29
|
* TCP (POSIX) async send/recv working. Other changes.Garrett D'Amore2017-03-29
| | | | | | | Transport-level pipe initialization is now sepearate and explicit. The POSIX send/recv logic still uses threads under the hood, but makes use of the AIO framework for send/recv. This is a key stepping stone towards enabling poll() or similar async I/O approaches.
* Start of msgq aio.Garrett D'Amore2017-03-01
|
* Async I/O for POSIX implemented using threads (untested.)Garrett D'Amore2017-02-24
|
* Fix for SunOS/illumos.Garrett D'Amore2017-01-25
|
* Add nn_sendmsg (with NN_MSG support).Garrett D'Amore2017-01-23
|
* Initial start of compat layer with bind, connect, etc. Untested.Garrett D'Amore2017-01-22
|
* Event notification via pollable FDs verified working.Garrett D'Amore2017-01-22
|
* Whoops, forgot to add the pipe implementations to git!!Garrett D'Amore2017-01-21
|
* Initial swag at notification pipes (not used yet).Garrett D'Amore2017-01-21
|
* Add more platforms (the *BSDs, SunOS/illumos) and update docs slightly.Garrett D'Amore2017-01-21
|
* Fix synchronization problem in msgqueue with multiple consumers.Garrett D'Amore2017-01-19
|
* Address segfault in TCP, and fix wild card handling.Garrett D'Amore2017-01-18
|
* Reaper exits too soon, leaking bits.Garrett D'Amore2017-01-18
|
* Fixes for valgrind issues.Garrett D'Amore2017-01-18
|
* Start of event framework.Garrett D'Amore2017-01-16
| | | | | | | | | | This compiles correctly, but doesn't actually deliver events yet. As part of this, I've made most of the initializables in nng safe to tear-down if uninitialized (or set to zero e.g. via calloc). This makes it loads easier to write the teardown on error code, since I can deinit everything, without worrying about which things have been initialized and which have not.
* Compile static *and* shared libraries.Garrett D'Amore2017-01-15
| | | | | Test code needs to use the static libraries so that they can get access to the entire set of symbols, including private ones that are not exported.
* Windows TCP now working.Garrett D'Amore2017-01-14
| | | | | | | There are lots of changes here, mostly stuff we did in support of Windows TCP. However, there are some bugs that were fixed, and we added some new error codes, and generalized the handling of some failures during accept. Windows IPC (NamedPipes) is still missing.
* Many fixes for Windows. It compiles, and some tests work.Garrett D'Amore2017-01-13
| | | | | | Windows is getting there. Needs a couple of more more hours to enable everything, especially IPC, and most of the work at this point is probably some combination of debug and tweaking things like error handling.
* Pull out the posix clock stuff for plat_clock.Garrett D'Amore2017-01-12
|
* Block SIGPIPE. Ewww...Garrett D'Amore2017-01-12
|
* Add IPC (UNIX domain sockets) for POSIX, and test suite.Garrett D'Amore2017-01-12
|
* POSIX /dev/urandom compilation bug.Garrett D'Amore2017-01-08
|
* New ISAAC pRNG. This replaces other local hacks for random data.Garrett D'Amore2017-01-08
| | | | | | Platforms must seed the pRNGs by offering an nni_plat_seed_prng() routine. Implementations for POSIX using various options (including the /dev/urandom device) are supplied.
* Change a bunch of copyrights to 2017 for work done since the 1st.Garrett D'Amore2017-01-05
|
* Recv returns 0 on EOF.Garrett D'Amore2017-01-04
|
* Fix close related races (POSIX close is a PITA).Garrett D'Amore2017-01-04
|
* Compilation fixes for Linux.Garrett D'Amore2017-01-04
|
* TCP listen and accept test.Garrett D'Amore2017-01-04
| | | | There is an occasional use-after-free bug we need to fix still.
* Initial cut at TCP, totally untested beyond compilation.Garrett D'Amore2017-01-04
| | | | | This also adds checks in the protocols to verify that pipe peers are of the proper protocol.
* Working towards TCP support.Garrett D'Amore2017-01-03
|
* Fixes to enable REQ/REP to operate.Garrett D'Amore2017-01-02
| | | | | | | This uncovered a few problems - inproc was not moving the headers to the body on transmit, and the message chunk allocator had a serious bug leading to memory corruption. I've also added a message dumper, which turns out to be incredibly useful during debugging.
* Stack related fixes for valgrind platform test.Garrett D'Amore2017-01-01
|
* Final purge of old threading & synch stuff.Garrett D'Amore2017-01-01
|
* Pipe simplifications for thread management.Garrett D'Amore2017-01-01
| | | | | | | This may also address a race in closing down pipes. Now pipes are always registered with the socket. They also always have both a sender and receiver thread. If the protocol doesn't need one or the other, the stock thread just exits early.
* New thread infrastructure -- not used anywhere yet, but tested.Garrett D'Amore2017-01-01
|
* Condvars on MacOS X (even 10.12) don't work with monotonic times.Garrett D'Amore2016-12-27
|
* Substantial fixes for listen & dialers.Garrett D'Amore2016-12-25
| | | | | | | | | | At this point listening and dialing operations appear to function properly. As part of this I had to break the close logic up since otherwise we had a loop trying to reap a thread from itself. So there is now a separate reaper thread for pipes per-socket. I also changed lists to be a bit more rigid, and allocations now zero memory initially. (We had bugs due to uninitialized memory, and rather than hunt them all down, lets just init them to sane zero values.)
* Mix the PID into our random number seed.Garrett D'Amore2016-12-25
|
* Fix for incorrect nni_usleep(), found with newly created platform tests.Garrett D'Amore2016-12-23
|
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2026-02-18 11:52:30 +0000