fixes #352 aio lock is burning hot

fixes #326 consider nni_taskq_exec_synch()
fixes #410 kqueue implementation could be smarter
fixes #411 epoll_implementation could be smarter
fixes #426 synchronous completion can lead to panic
fixes #421 pipe close race condition/duplicate destroy

This is a major refactoring of two significant parts of the code base,
which are closely interrelated.

First the aio and taskq framework have undergone a number of simplifications,
and improvements.  We have ditched a few parts of the internal API (for
example tasks no longer support cancellation) that weren't terribly useful
but added a lot of complexity, and we've made aio_schedule something that
now checks for cancellation or other "premature" completions.  The
aio framework now uses the tasks more tightly, so that aio wait can
devolve into just nni_task_wait().  We did have to add a "task_prep()"
step to prevent race conditions.

Second, the entire POSIX poller framework has been simplified, and made
more robust, and more scalable.  There were some fairly inherent race
conditions around the shutdown/close code, where we *thought* we were
synchronizing against the other thread, but weren't doing so adequately.
With a cleaner design, we've been able to tighten up the implementation
to remove these race conditions, while substantially reducing the chance
for lock contention, thereby improving scalability.  The illumos poller
also got a performance boost by polling for multiple events.

In highly "busy" systems, we expect to see vast reductions in lock
contention, and therefore greater scalability, in addition to overall
improved reliability.

One area where we currently can do better is that there is still only
a single poller thread run.  Scaling this out is a task that has to be done
differently for each poller, and carefuly to ensure that close conditions
are safe on all pollers, and that no chance for deadlock/livelock waiting
for pfd finalizers can occur.

1 files changed, 7 insertions, 13 deletions

diff --git a/src/core/taskq.h b/src/core/taskq.h
index 40b5dc00..513b15bb 100644
--- a/src/core/taskq.h
+++ b/src/core/taskq.h
@@ -1,6 +1,6 @@
 //
-// Copyright 2017 Garrett D'Amore <garrett@damore.org>
-// Copyright 2017 Capitar IT Group BV <info@capitar.com>
+// Copyright 2018 Staysail Systems, Inc. <info@staysail.tech>
+// Copyright 2018 Capitar IT Group BV <info@capitar.com>
 //
 // This software is supplied under the terms of the MIT License, a
 // copy of which should be located in the distribution where this
@@ -17,28 +17,22 @@
 typedef struct nni_taskq nni_taskq;
 typedef struct nni_task  nni_task;
 
-// nni_task is a structure representing a task.  Its intended to inlined
-// into structures so that taskq_dispatch can be a guaranteed operation.
-struct nni_task {
-	nni_list_node task_node;
-	void *        task_arg;
-	nni_cb        task_cb;
-	nni_taskq *   task_tq;
-};
-
 extern int  nni_taskq_init(nni_taskq **, int);
 extern void nni_taskq_fini(nni_taskq *);
-extern void nni_taskq_drain(nni_taskq *);
 
 // nni_task_dispatch sends the task to the queue.  It is guaranteed to
 // succeed.  (If the queue is shutdown, then the behavior is undefined.)
 extern void nni_task_dispatch(nni_task *);
+extern void nni_task_exec(nni_task *);
+extern void nni_task_prep(nni_task *);
+extern void nni_task_unprep(nni_task *);
 
 // nni_task_cancel cancels the task.  It will wait for the task to complete
 // if it is already running.
 extern int  nni_task_cancel(nni_task *);
 extern void nni_task_wait(nni_task *);
-extern void nni_task_init(nni_taskq *, nni_task *, nni_cb, void *);
+extern int  nni_task_init(nni_task **, nni_taskq *, nni_cb, void *);
+extern void nni_task_fini(nni_task *);
 
 extern int  nni_taskq_sys_init(void);
 extern void nni_taskq_sys_fini(void);