sched_clock() rather than using callouts. This means we no longer have to
take the load of the callout thread into consideration while balancing and
should make the balancing decisions simpler and more accurate.
Tested on: x86/UP, amd64/SMP
sched_ule, in January 2004. Looking at this, "pagezero" is (one of) the
culprit(s). We had no provision for processes with P_NOLOAD set. With
pagezero not running at PRI_ITHD, kseq_load_{add,rem} count pagezero as
another-normal-process, thus the "expected-plus-one" load reported in
the above thread.
Submitted by: Nikos Ntarmos <ntarmos@ceid.upatras.gr>
SCHED_INTERACT_MAX was used where SCHED_SLP_RUN_MAX was needed. This was
causing the interactivity scaler to lose history at a more dramatic rate
than intended.
long as there are still explicit uses of int, whether in types or
in function names (such as atomic_set_int() in sched_ule.c), we can
not change cpumask_t to be anything other than u_int. See also the
commit log for sys/sys/types.h, revision 1.84.
activation (i.e., applications are using libpthread). This is because
SCHED_ULE sometimes puts P_SA processes into ksq_next unnecessarily.
Which doesn't give fair amount of CPU time to processes which are
using scheduler-activation-based threads when other (semi-)CPU-intensive,
non-P_SA processes are running.
Further work will no doubt be done by jeffr at a later date.
Submitted by: Taku YAMAMOTO <taku@cent.saitama-u.ac.jp>
Reviewed by: rwatson, freebsd-current@
sleep queue interface:
- Sleep queues attempt to merge some of the benefits of both sleep queues
and condition variables. Having sleep qeueus in a hash table avoids
having to allocate a queue head for each wait channel. Thus, struct cv
has shrunk down to just a single char * pointer now. However, the
hash table does not hold threads directly, but queue heads. This means
that once you have located a queue in the hash bucket, you no longer have
to walk the rest of the hash chain looking for threads. Instead, you have
a list of all the threads sleeping on that wait channel.
- Outside of the sleepq code and the sleep/cv code the kernel no longer
differentiates between cv's and sleep/wakeup. For example, calls to
abortsleep() and cv_abort() are replaced with a call to sleepq_abort().
Thus, the TDF_CVWAITQ flag is removed. Also, calls to unsleep() and
cv_waitq_remove() have been replaced with calls to sleepq_remove().
- The sched_sleep() function no longer accepts a priority argument as
sleep's no longer inherently bump the priority. Instead, this is soley
a propery of msleep() which explicitly calls sched_prio() before
blocking.
- The TDF_ONSLEEPQ flag has been dropped as it was never used. The
associated TDF_SET_ONSLEEPQ and TDF_CLR_ON_SLEEPQ macros have also been
dropped and replaced with a single explicit clearing of td_wchan.
TD_SET_ONSLEEPQ() would really have only made sense if it had taken
the wait channel and message as arguments anyway. Now that that only
happens in one place, a macro would be overkill.
track the load for the sched_load() function. In the SMP case this member
is not defined because it would be redundant with the ksg_load member
which already tracks the non ithd load.
- For sched_load() in the UP case simply return ksq_sysload. In the SMP
case traverse the list of kseq groups and sum up their ksg_load fields.
SW_INVOL. Assert that one of these is set in mi_switch() and propery
adjust the rusage statistics. This is to simplify the large number of
users of this interface which were previously all required to adjust the
proper counter prior to calling mi_switch(). This also facilitates more
switch and locking optimizations.
- Change all callers of mi_switch() to pass the appropriate paramter and
remove direct references to the process statistics.
cpu could have been bogged down with non-transferable load and still not
migrated a new thread to an idle cpu. This required some benchmarking and
tuning to get right as the comment above it suggests.
- In sched_add(), do the idle check prior to the transfer check so that we
don't try to transfer load from an idle cpu. This fixes panics caused by
IPIs on UP machines running SMP kernels.
Reported/Debugged by: seanc
- The new sched_balance_groups() function does intra-group balancing while
sched_balance() balances the available groups.
- Pick a random time between 0 ticks and hz * 2 ticks to restart each
balancing process. Each balancer has its own timeout.
- Pick a random place in the list of groups to start the search for lowest
and highest group loads. This prevents us from prefering a group based on
numeric position.
- Use a nasty hack to stop us from preferring cpu 0. The problem is that
softclock always runs on cpu 0, so it always has a little extra load. We
ignore this load in the balancer for now. In the future softclock should
run on a random cpu and these hacks can go away.
cpu are added to a group.
- Don't place a cpu into the kseq_idle bitmask until all cpus in that group
have idled.
- Prefer idle groups over idle group members in the new kseq_transfer()
function. In this way we will prefer to balance load across full cores
rather than add further load a partial core.
- Before a cpu goes idle, check the other group members for threads. Since
SMT cpus may freely share threads, this is cheap.
- SMT cores may be individually pinned and bound to now. This contrasts the
old mechanism where binding or pinning would have allowed a thread to run
on any available cpu.
- Remove some unnecessary logic from sched_switch(). Priority propagation
should be properly taken care of in sched_prio() now.
Be sure to shift (long)1 << 33 and higher, not (int)1. Otherwise bad
things happen(TM). This is why beast.freebsd.org paniced with ULE.
Reviewed by: jeff
1) mp_maxid is a valid FreeBSD CPU ID in the range 0 .. MAXCPU - 1.
2) For all active CPUs in the system, PCPU_GET(cpuid) <= mp_maxid.
Approved by: re (scottl)
Tested on: i386, amd64, alpha
kses from the run queues. Also, on SMP, we track the transferable
count here. Threads are transferable only as long as they are on the
run queue.
- Previously, we adjusted our load balancing based on the transferable count
minus the number of actual cpus. This was done to account for the threads
which were likely to be running. All of this logic is simpler now that
transferable accounts for only those threads which can actually be taken.
Updated various places in sched_add() and kseq_balance() to account for
this.
- Rename kseq_{add,rem} to kseq_load_{add,rem} to reflect what they're
really doing. The load is accounted for seperately from the runq because
the load is accounted for even as the thread is running.
- Fix a bug in sched_class() where we weren't properly using the PRI_BASE()
version of the kg_pri_class.
- Add a large comment that describes the impact of a seemingly simple
conditional in sched_add().
- Also in sched_add() check the transferable count and KSE_CAN_MIGRATE()
prior to checking kseq_idle. This reduces the frequency of access for
kseq_idle which is a shared resource.
idle. They figure out that we're idle fast enough that the cache pollution
introduces by scanning their run queue is more expensive than waiting
a little longer.
- Add kseq_setidle() to mark us as being idle. Use this in place of
kseq_find().
- Remove kseq_load_highest(), kseq_find() was the only consumer of this
interface. kseq_balance() has it's own customized version that finds the
lowest and highest loads simultaneously.
Continuously told that this would be faster by: terry
the total load, the timeshare load, and the number of threads that can
be migrated to another cpu. Account for these seperately.
- Introduce a KSE_CAN_MIGRATE() macro which determines whether or not a KSE
can be migrated to another CPU. Currently, this only checks to see if
we're an interrupt handler. Eventually this will also be used to support
CPU binding.
slice assignment. Add a comment describing what it does.
- Remove a stale XXX comment, the nice should not impact the interactivity,
nice adjustments only effect non-interactive tasks in ULE.
- Don't allow nice -20 tasks to totally starve nice 0 tasks. Give them at
least SCHED_SLICE_MIN ticks. We still allow nice 0 tasks to starve nice
+20 tasks as intended.
- SCHED_PRI_NRESV does not have the off by one error in PRIO_TOTAL so we
do not have to account for it in the few places that we use it.
Requested by: bde
0 and SCHED_SLP_RUN_MAX * 2. This allows us to simplify the algorithm
quite a bit. Before, it dealt with arbitrary values which required us
to do nasty integer division tricks that didn't quite work out correctly.
- Chnage sched_wakeup() to detect conditions where the slp+runtime could
exceed SCHED_SLP_RUN_MAX * 2. This can happen if we go to sleep for
longer than 6 seconds. In this case, we'll just clear the runtime and
set the sleep time to the max.
- Define a new function, sched_interact_fork() which updates the slp+runtime
of a newly forked thread. We want to limit the amount of history retained
from the parent so that we learn the child's behavior quickly. We don't,
however want to decay it to nothing. Previously, we would simply divide
each parameter by 100 whenever we forked. After a few forks the values
would reach 0 and tasks would not be considered interactive.
- Add another KTR entry, cleanup some existing entries.
- Remove a useless sched_interact_update() from sched_priority(). This is
already done by the callers that require it.
- Add an IPI based mechanism for migrating kses. This mechanism is
broken down into several components. This is intended to reduce cache
thrashing by eliminating most cases where one cpu touches another's
run queues.
- kseq_notify() appends a kse to a lockless singly linked list and
conditionally sends an IPI to the target processor. Right now this is
protected by sched_lock but at some point I'd like to get rid of the
global lock. This is why I used something more complicated than a
standard queue.
- kseq_assign() processes our list of kses that have been assigned to us
by other processors. This simply calls sched_add() for each item on the
list after clearing the new KEF_ASSIGNED flag. This flag is used to
indicate that we have been appeneded to the assigned queue but not
added to the run queue yet.
- In sched_add(), instead of adding a KSE to another processor's queue we
use kse_notify() so that we don't touch their queue. Also in sched_add(),
if KEF_ASSIGNED is already set return immediately. This can happen if
a thread is removed and readded so that the priority is recorded properly.
- In sched_rem() return immediately if KEF_ASSIGNED is set. All callers
immediately readd simply to adjust priorites etc.
- In sched_choose(), if we're running an IDLE task or the per cpu idle thread
set our cpumask bit in 'kseq_idle' so that other processors may know that
we are idle. Before this, make a single pass through the run queues of
other processors so that we may find work more immediately if it is
available.
- In sched_runnable(), don't scan each processor's run queue, they will IPI
us if they have work for us to do.
- In sched_add(), if we're adding a thread that can be migrated and we have
plenty of work to do, try to migrate the thread to an idle kseq.
- Simplify the logic in sched_prio() and take the KEF_ASSIGNED flag into
consideration.
- No longer use kseq_choose() to steal threads, it can lose it's last
argument.
- Create a new function runq_steal() which operates like runq_choose() but
skips threads based on some criteria. Currently it will not steal
PRI_ITHD threads. In the future this will be used for CPU binding.
- Create a kseq_steal() that checks each run queue with runq_steal(), use
kseq_steal() in the places where we used kseq_choose() to steal with
before.
begin with sched_lock held but not recursed, so this variable was
always 0.
Removed fixup of sched_lock.mtx_recurse after context switches in
sched_switch(). Context switches always end with this variable in the
same state that it began in, so there is no need to fix it up. Only
sched_lock.mtx_lock really needs a fixup.
Replaced fixup of sched_lock.mtx_recurse in fork_exit() by an assertion
that sched_lock is owned and not recursed after it is fixed up. This
assertion much match the one in mi_switch(), and if sched_lock were
recursed then a non-null fixup of sched_lock.mtx_recurse would probably
be needed again, unlike in sched_switch(), since fork_exit() doesn't
return to its caller in the normal way.
Contributed by: Thomaswuerfl@gmx.de
- In sched_prio(), adjust the run queue for threads which may need to move
to the current queue due to priority propagation .
- In sched_switch(), fix style bug introduced when the KSE support went in.
Columns are 80 chars wide, not 90.
- In sched_switch(), Fix the comparison in the idle case and explicitly
re-initialize the runq in the not propagated case.
- Remove dead code in sched_clock().
- In sched_clock(), If we're an IDLE class td set NEEDRESCHED so that threads
that have become runnable will get a chance to.
- In sched_runnable(), if we're not the IDLETD, we should not consider
curthread when examining the load. This mimics the 4BSD behavior of
returning 0 when the only runnable thread is running.
- In sched_userret(), remove the code for setting NEEDRESCHED entirely.
This is not necessary and is not implemented in 4BSD.
- Use the correct comparison in sched_add() when checking to see if an idle
prio task has had it's priority temporarily elevated.
rounding errors. This was the source of the majority of the
interactivity problems. Reintroduce the old algorithm and its XXX.
- Up the interactivity threshold to 30. It really could stand to be even
a tiny bit higher.
- Let the sleep and run time accumulate up to 5 seconds of history rather
than two. This helps stop XFree86 from becoming non-interactive during
bursts of activity.
elevated either due to priority propagation or because we're in the
kernel in either case, put us on the current queue so that we dont
stop others from using important resources. At some point the priority
elevations from sleeping in the kernel should go away.
- Remove an optimization in sched_userret(). Before we would only set
NEEDRESCHED if there was something of a higher priority available. This
is a trivial optimization and it breaks priority propagation because it
doesn't take threads which we may be blocking into account. Notice that
the thread which is blocking others gets up to one tick of cpu time before
we honor this NEEDRESCHED in sched_clock().
