Sometimes we need to delegate some list processing to a function running
on another thread. In this case the list element will simply be queued
into a dedicated self-locked list and the task responsible for this list
will be woken up, calling the associated function which will run over the
list.
This is what work_list does. Such lists will be dedicated to a limited
type of work but will significantly ease such remote handling. A function
is provided to create these per-thread lists, their tasks and to properly
bind each task to a distinct thread, so that the caller only has to store
the resulting pointer to the start of the structure.
These structures should not be abused though as each head will consume
4 pointers per thread, hence 32 bytes per thread or 2 kB for 64 threads.
In commit 86eded6c6 ("CLEANUP: tasks: rename task_remove_from_tasklet_list()
to tasklet_remove_*") which consisted in removing the casts between tasks
and tasklet, I was a bit too fast to believe that we only saw tasklets in
this function since process_runnable_tasks() also uses it with tasks under
a cast. So removing the bookkeeping on task_list_size was not appropriate.
Bah, the joy of casts which hide the real thing...
This patch does two things at once to address this mess once for all:
- it restores the decrement of task_list_size when it's a real task,
but moves it to process_runnable_task() since it's the only place
where it's allowed to call it with a task
- it moves the increment there as well and renames
task_insert_into_tasklet_list() to tasklet_insert_into_tasklet_list()
of obvious consistency reasons.
This way the increment/decrement of task_list_size is made at the only
places where the cast is enforced, so it has less risks to be missed.
The comments on top of these functions were updated to reflect that they
are only supposed to be used with tasklets and that the caller is responsible
for keeping task_list_size up to date if it decides to enforce a task there.
Now we don't have to worry anymore about how these functions work outside
of the scheduler, which is better longterm-wise. Thanks to Christopher for
spotting this mistake.
No backport is needed.
The function really only operates on tasklets, its arguments are always
tasklets cast as tasks to match the function's type, to be cast back to
a struct tasklet. Let's rename it to tasklet_remove_from_tasklet_list(),
take a struct tasklet, and get rid of the undesired task casts.
With both I/O and tasks in the same tasklet list, we now have a very
smooth and responsive scheduler, providing a good fairness between I/O
activities. With the lower layers relying on tasklet a lot (I/O wakeup,
subscribe, etc), there may often be a large number of totally autonomous
tasklets doing their business such as forwarding data between two muxes.
But the task scheduler historically refrained from picking tasks from the
priority-ordered run queue to put them into the tasklet list until this
later had less than max_runqueue_depth entries. This was to make sure that
low-latency, high-priority tasks would have an opportunity to be dequeued
before others even if they arrive late. But the counter used for this is
still the tasklet list size, which contains countless I/O events. This
causes an unfairness between unbounded I/Os and bounded tasks, resulting
for example in the CLI responding slower when forwarding 40 Gbps of HTTP
traffic spread over a thousand of connections.
A good solution consists in sticking to the initial intent of
max_runqueue_depth which is to limit the number of tasks in the list
(to maintain fairness between them) and not to limit the number of these
tasks among tasklets. It just turns out that the task_list_size initially
was this task counter and changed over time to be a tasklet list size.
Let's simply refrain from updating it for pure tasklets so that it takes
back its original role of counting real tasks as its name implies. With
this change the CLI becomes instantly responsive under load again.
This patch may possibly be backported to 1.9 though it requires some
careful checks.
Remove the active_tasks_mask variable, we can deduce if we've work to do
by other means, and it is costly to maintain. Instead, introduce a new
function, thread_has_tasks(), that returns non-zero if there's tasks
scheduled for the thread, zero otherwise.
With the thread debugger it becomes visible that we can leave some
wandering pointers for a while in curr_task, which is inappropriate.
This patch addresses this by resetting curr_task to NULL before really
freeing the area. This way it becomes safe even regarding signals.
Since previous commit it's not needed anymore to test a task pointer
before calling task_destory() so let's just remove these tests from
the various callers before they become confusing. The function's
arguments were also documented. The same should probably be done
with tasklet_free() which involves a test in roughly half of the
call places.
Commit 3f795f7 ("MEDIUM: tasks: Merge task_delete() and task_free() into
task_destroy().") replaced task_delete() and task_free() with a single
function named task_destroy().
This patch adds a check for struct task* argument in function
task_destroy() to prevent a possible segfault on NULL and also to make
the function safer for use in other cases.
task_delete() was never used without calling task_free() just after, and
task_free() was only used on error pathes to destroy a just-created task,
so merge them into task_destroy(), that will remove the task from the
wait queue, and make sure the task is either destroyed immediately if it's
not in the run queue, or destroyed when it's supposed to run.
The wakeup condition in task_wakeup() is redundant as it is already
validated by the CAS. Better move the __task_wakeup() call there, it
also has the merit of being easier to audit this way. This also reduces
the code size by around 1.8 kB :
$ size haproxy-?
text data bss dec hex filename
2153806 100208 1307676 3561690 3658da haproxy-1
2152094 100208 1307676 3559978 36522a haproxy-2
Commit 0c7a4b6 ("MINOR: tasks: Don't set the TASK_RUNNING flag when
adding in the tasklet list.") revealed a hole in the way tasks may
be freed : they could be removed while in the run queue when the
TASK_QUEUED flag was present but not the TASK_RUNNING one. But it
seems the issue was emphasized by commit cde7902 ("MEDIUM: tasks:
improve fairness between the local and global queues") though the
code it replaces was already affected given how late the TASK_RUNNING
flag was set after removal from the global queue.
At the moment the task is picked from the global run queue, if it
is the last one, the global run queue lock is dropped, and then
the TASK_RUNNING flag was added. In the mean time another thread
might have performed a task_free(), and immediately after, the
TASK_RUNNING flag was re-added to the task, which was then added
to the tasklet list. The unprotected window was extremely faint
but does definitely exist and inconsistent task lists have been
observed a few times during very intensive tests over the last few
days. From this point various options are possible, the task might
have been re-allocated while running, and assigned state 0 and/or
state QUEUED while it was still running, resulting in the tast not
being put back into the tree.
This commit simply makes sure that tests on TASK_RUNNING before removing
the task also cover TASK_QUEUED.
It must be backported to 1.9 along with the previous ones touching
that area.
Now that we have the warranty that a task won't be added in the runqueue
while the TASK_QUEUED or the TASK_RUNNING flag is set, don't bother trying
to lock the task by setting leaf_p to 0x1 while inserting it in the runqueue
or having it in the tasklet_list, as nobody else will attempt to add it.
Make sure we set TASK_QUEUED in every case before adding the task to the
run queue. task_wakeup() now checks if either TASK_QUEUED or TASK_RUNNING
is set, and if neither is set, add TASK_QUEUED and effectively add the task
to the runqueue.
No longer use __task_wakeup() anywhere except in task_wakeup(), always use
task_wakeup() instead.
With the old code, process_runnable_task() may re-add a task in the runqueue
without setting the TASK_QUEUED flag, and there were race conditions that could
lead to a task having the TASK_QUEUED flag but not in the runqueue, thus
being unschedulable.
This should be backported to 1.9.
This one hasn't been used anymore since the scheduler changes after 1.8
but it kept being exported and maintained up to date while it's always
reset when scanning the trees. Let's stop exporting it and updating it.
Previous commit 3ea351368 ("BUG/MEDIUM: h2: Remove the tasklet from the
task list if unsubscribing.") uncovered an issue which needs to be
addressed in the scheduler's API. The function task_remove_from_task_list()
was initially designed to remove a task from the running tasklet list from
within the scheduler, and had to be used in h2 to abort pending I/O events.
However this function was not designed to be idempotent, occasionally
causing a double removal from the tasklet list, with the second doing
nothing but affecting the apparent tasks count and making haproxy use
100% CPU on some tests consisting in stopping the client during some
transfers. The h2_unsubscribe() function can sometimes be called upon
stream exit after an error where the tasklet was possibly already
removed, so it.
This patch does 2 things :
- it renames task_remove_from_task_list() to
__task_remove_from_tasklet_list() to discourage users from calling
it. Also note the fix in the naming since it's a tasklet list and
not a task list. This function is still uesd from the scheduler.
- it adds a new, idempotent, task_remove_from_tasklet_list() function
which does nothing if the task is already not in the tasklet list.
This patch will need to be backported where the commit above is backported.
In task_unlink_rq, to decide if we should logk the global runqueue lock,
use the TASK_GLOBAL flag instead of relying on t->thread_mask being tid_bit,
as it could be so while still being in the global runqueue if another thread
woke that task for us.
This should be backported to 1.9.
In this function we end up with successive locked operations then a
store barrier, and in addition the compiler has to emit less efficient
code due to a longer jump. There's no need for absolutely updating the
tasks_run_queue counter before clearing the task's leaf pointer, so
let's swap the two operations and benefit from a single barrier as much
as possible. This code is on the hot path and shows about half a percent
of improvement with 8 threads.
By using LIST_DEL_INIT() instead of LIST_DEL()+LIST_INIT() we manage
to bump the peak connection rate by no less than 3% on 8 threads.
The perf top profile shows much less contention in this area which
suffered from the second reload.
Calculate if the fd or task should be locked once, before locking, and
reuse the calculation when determing when to unlock.
Fixes a race condition added in 87d54a9a for fds, and b20aa9ee for tasks,
released in 1.9-dev4. When one thread modifies thread_mask to be a single
thread for a task or fd while a second thread has locked or is waiting on a
lock for that task or fd, the second thread will not unlock it. For FDs,
this is observable when a listener is polled by multiple threads, and is
closed while those threads have events pending. For tasks, this seems
possible, where task_set_affinity is called, but I did not observe it.
This must be backported to 1.9.
There's a very small but existing uncertainty window when waking another
thread up where it is possible for task_wakeup() not to wake the other
task up because it's still running while this once is in the process of
finishing and loses its TASK_RUNNING flag. In this case the wakeup will
be missed.
The problem is that we have a single flag to store 3 states, since the
transition from running to sleeping isn't atomic. Thus we need to have
another flag to cover this part. This patch introduces TASK_QUEUED to
mention that the task is already in the run queue, running or not. This
bit will be removed while TASK_RUNNING is kept once dequeued, and will
be used when removing TASK_RUNNING to check if the task has been requeued.
It might be possible to slightly improve this but the occurrence rate
is quite low and we don't really need to complexify the scheduler to
optimize for a rare case.
The impact with the current code is very low since we have few inter-
thread wakeups. Most of them are caused by checks killing sessions.
This must be backported to 1.9.
The master is not supposed to run (at the moment) any task before the
polling loop, the created tasks should be run only in the workers but in
the master they should be disabled or removed.
No backport needed.
signal_init(), init_log(), init_stream(), and init_task() all used to
only preset some values and lists. This needs to be done very early to
provide a reliable interface to all other users. The calls used to be
explicit in haproxy.c:init(). Now they're placed in initcalls at the
STG_PREPARE stage. The functions are not exported anymore.
Right now we measure for each task the cumulated time spent waiting for
the CPU and using it. The timestamp uses a 64-bit integer to report a
nanosecond-level date. This is only enabled when "profiling.tasks" is
enabled, and consumes less than 1% extra CPU on x86_64 when enabled.
The cumulated processing time and wait time are reported in "show sess".
The task's counters are also reset when an HTTP transaction is reset
since the HTTP part pretends to restart on a fresh new stream. This
will make sure we always report correct numbers for each request in
the logs.
Currently we have per-thread arrays of trees and counts, but these
ones unfortunately share cache lines and are accessed very often. This
patch moves the task-specific stuff into a structure taking a multiple
of a cache line, and has one such per thread. Just doing this has
reduced the cache miss ratio from 19.2% to 18.7% and increased the
12-thread test performance by 3%.
It starts to become visible that we really need a process-wide per-thread
storage area that would cover more than just these parts of the tasks.
The code was arranged so that it's easy to move the pieces elsewhere if
needed.
Now we still have a main contention point with the timers in the main
wait queue, but the vast majority of the tasks are pinned to a single
thread. This patch creates a per-thread wait queue and queues a task
to the local wait queue without any locking if the task is bound to a
single thread (the current one) otherwise to the shared queue using
locking. This significantly reduces contention on the wait queue. A
test with 12 threads showed 11 ms spent in the WQ lock compared to
4.7 seconds in the same test without this change. The cache miss ratio
decreased from 19.7% to 19.2% on the 12-thread test, and its performance
increased by 1.5%.
Another indirect benefit is that the average queue size is divided
by the number of threads, which roughly removes log(nbthreads) levels
in the tree and further speeds up lookups.
In tasklet_free(), if we're currently in the runnable task list, don't
forget to decrement taks_list_size, or it'll end up being to big, and we may
not process tasks in the global runqueue.
Set the flag for the current thread in active_threads_mask when waking a
tasklet, or we will never run it if no tasks are available.
This is 1.9-specific, no backport is needed.
Modify tasklet_wakeup() so that it handles a task as well, and inserts it
directly into the tasklet list, making it effectively a tasklet.
This should make future developments easier.
As __task_wakeup() is responsible for increasing
rqueue_local[tid]/global_rqueue_size, make __task_unlink_rq responsible for
decreasing it, as process_runnable_tasks() isn't the only one that removes
tasks from runqueues.
Up until now, a tasklet couldn't be free'd while it was in the list, it is
no longer the case, so make sure we remove it from the list before freeing it.
To do so, we have to make sure we correctly initialize it, so use LIST_INIT,
instead of setting the pointers to NULL.
To make sure we don't inadvertently insert task in the global runqueue,
while only the local runqueue is used without threads, make its definition
and usage conditional on USE_THREAD.
When building without threads enabled, instead of just using the global
runqueue, just use the local runqueue associated with the only thread, as
that's what is now expected for a single thread in prcoess_runnable_tasks().
This should fix haproxy when built without threads.
This function returns true is some notifications are registered.
This function is usefull for the following patch
BUG/MEDIUM: lua/socket: Sheduling error on write: may dead-lock
It should be backported in 1.6, 1.7 and 1.8
Don't forget to increase tasks_run_queue when we're adding a task to the
tasklet list, and to decrease it when we remove a task from a runqueue,
or its value won't be accurate, and could lead to tasks not being executed
when put in the global run queue.
1.9-dev only, no backport is needed.
Introduce tasklets, lightweight tasks. They have no notion of priority,
they are just run as soon as possible, and will probably be used for I/O
later.
For the moment they're used to replace the temporary thread-local list
that was used in the scheduler. The first part of the struct is common
with tasks so that tasks can be cast to tasklets and queued in this list.
Once a task is in the tasklet list, it has its leaf_p set to 0x1 so that
it cannot accidently be confused as not in the queue.
Pure tasklets are identifiable by their nice value of -32768 (which is
normally not possible).
A lot of tasks are run on one thread only, so instead of having them all
in the global runqueue, create a per-thread runqueue which doesn't require
any locking, and add all tasks belonging to only one thread to the
corresponding runqueue.
The global runqueue is still used for non-local tasks, and is visited
by each thread when checking its own runqueue. The nice parameter is
thus used both in the global runqueue and in the local ones. The rare
tasks that are bound to multiple threads will have their nice value
used twice (once for the global queue, once for the thread-local one).
While running a task, we may try to delete and free a task that is about to
be run, because it's part of the local tasks list, or because rq_next points
to it.
So flag any task that is in the local tasks list to be deleted, instead of
run, by setting t->process to NULL, and re-make rq_next a global,
thread-local variable, that is modified if we attempt to delete that task.
Many thanks to PiBa-NL for reporting this and analysing the problem.
This should be backported to 1.8.
The thread patches adds refcount for notifications. The notifications are
used with the Lua cosocket. These refcount free the notifications when
the session is cleared. In the Lua task case, it not have sessions, so
the nofications are never cleraed.
This patch adds a garbage collector for signals. The garbage collector
just clean the notifications for which the end point is disconnected.
This patch should be backported in 1.8
