f5c157d986
schedulers a bit to ensure more correct handling of priorities and fewer priority inversions: - Add two functions to the sched(9) API to handle priority lending: sched_lend_prio() and sched_unlend_prio(). The turnstile code uses these functions to ask the scheduler to lend a thread a set priority and to tell the scheduler when it thinks it is ok for a thread to stop borrowing priority. The unlend case is slightly complex in that the turnstile code tells the scheduler what the minimum priority of the thread needs to be to satisfy the requirements of any other threads blocked on locks owned by the thread in question. The scheduler then decides where the thread can go back to normal mode (if it's normal priority is high enough to satisfy the pending lock requests) or it it should continue to use the priority specified to the sched_unlend_prio() call. This involves adding a new per-thread flag TDF_BORROWING that replaces the ULE-only kse flag for priority elevation. - Schedulers now refuse to lower the priority of a thread that is currently borrowing another therad's priority. - If a scheduler changes the priority of a thread that is currently sitting on a turnstile, it will call a new function turnstile_adjust() to inform the turnstile code of the change. This function resorts the thread on the priority list of the turnstile if needed, and if the thread ends up at the head of the list (due to having the highest priority) and its priority was raised, then it will propagate that new priority to the owner of the lock it is blocked on. Some additional fixes specific to the 4BSD scheduler include: - Common code for updating the priority of a thread when the user priority of its associated kse group has been consolidated in a new static function resetpriority_thread(). One change to this function is that it will now only adjust the priority of a thread if it already has a time sharing priority, thus preserving any boosts from a tsleep() until the thread returns to userland. Also, resetpriority() no longer calls maybe_resched() on each thread in the group. Instead, the code calling resetpriority() is responsible for calling resetpriority_thread() on any threads that need to be updated. - schedcpu() now uses resetpriority_thread() instead of just calling sched_prio() directly after it updates a kse group's user priority. - sched_clock() now uses resetpriority_thread() rather than writing directly to td_priority. - sched_nice() now updates all the priorities of the threads after the group priority has been adjusted. Discussed with: bde Reviewed by: ups, jeffr Tested on: 4bsd, ule Tested on: i386, alpha, sparc64
121 lines
3.9 KiB
C
121 lines
3.9 KiB
C
/*-
|
|
* Copyright (c) 2002, Jeffrey Roberson <jeff@freebsd.org>
|
|
* All rights reserved.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions
|
|
* are met:
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
* notice unmodified, this list of conditions, and the following
|
|
* disclaimer.
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
* documentation and/or other materials provided with the distribution.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
|
|
* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
|
|
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
|
|
* IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
|
|
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
|
|
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
|
|
* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
*
|
|
* $FreeBSD$
|
|
*/
|
|
|
|
#ifndef _SYS_SCHED_H_
|
|
#define _SYS_SCHED_H_
|
|
|
|
/*
|
|
* General scheduling info.
|
|
*
|
|
* sched_load:
|
|
* Total runnable non-ithread threads in the system.
|
|
*
|
|
* sched_runnable:
|
|
* Runnable threads for this processor.
|
|
*/
|
|
int sched_load(void);
|
|
int sched_rr_interval(void);
|
|
int sched_runnable(void);
|
|
|
|
/*
|
|
* Proc related scheduling hooks.
|
|
*/
|
|
void sched_exit(struct proc *p, struct thread *childtd);
|
|
void sched_fork(struct thread *td, struct thread *childtd);
|
|
|
|
/*
|
|
* KSE Groups contain scheduling priority information. They record the
|
|
* behavior of groups of KSEs and threads.
|
|
*/
|
|
void sched_class(struct ksegrp *kg, int class);
|
|
void sched_exit_ksegrp(struct ksegrp *kg, struct thread *childtd);
|
|
void sched_fork_ksegrp(struct thread *td, struct ksegrp *child);
|
|
void sched_nice(struct proc *p, int nice);
|
|
|
|
/*
|
|
* Threads are switched in and out, block on resources, have temporary
|
|
* priorities inherited from their ksegs, and use up cpu time.
|
|
*/
|
|
void sched_exit_thread(struct thread *td, struct thread *child);
|
|
void sched_fork_thread(struct thread *td, struct thread *child);
|
|
fixpt_t sched_pctcpu(struct thread *td);
|
|
void sched_prio(struct thread *td, u_char prio);
|
|
void sched_lend_prio(struct thread *td, u_char prio);
|
|
void sched_sleep(struct thread *td);
|
|
void sched_switch(struct thread *td, struct thread *newtd, int flags);
|
|
void sched_unlend_prio(struct thread *td, u_char prio);
|
|
void sched_userret(struct thread *td);
|
|
void sched_wakeup(struct thread *td);
|
|
|
|
/*
|
|
* Threads are moved on and off of run queues
|
|
*/
|
|
void sched_add(struct thread *td, int flags);
|
|
void sched_clock(struct thread *td);
|
|
void sched_rem(struct thread *td);
|
|
|
|
/*
|
|
* Binding makes cpu affinity permanent while pinning is used to temporarily
|
|
* hold a thread on a particular CPU.
|
|
*/
|
|
void sched_bind(struct thread *td, int cpu);
|
|
static __inline void sched_pin(void);
|
|
void sched_unbind(struct thread *td);
|
|
static __inline void sched_unpin(void);
|
|
|
|
/*
|
|
* These procedures tell the process data structure allocation code how
|
|
* many bytes to actually allocate.
|
|
*/
|
|
int sched_sizeof_ksegrp(void);
|
|
int sched_sizeof_proc(void);
|
|
int sched_sizeof_thread(void);
|
|
|
|
static __inline void
|
|
sched_pin(void)
|
|
{
|
|
curthread->td_pinned++;
|
|
}
|
|
|
|
static __inline void
|
|
sched_unpin(void)
|
|
{
|
|
curthread->td_pinned--;
|
|
}
|
|
|
|
/* temporarily here */
|
|
void schedinit(void);
|
|
void sched_init_concurrency(struct ksegrp *kg);
|
|
void sched_set_concurrency(struct ksegrp *kg, int cuncurrency);
|
|
void sched_schedinit(void);
|
|
void sched_newproc(struct proc *p, struct ksegrp *kg, struct thread *td);
|
|
void sched_thread_exit(struct thread *td);
|
|
void sched_newthread(struct thread *td);
|
|
|
|
#endif /* !_SYS_SCHED_H_ */
|