d/freebsd-skq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
d7b44ae42b
freebsd-skq/sys/kern/kern_switch.c

514 lines
13 KiB
C
Raw Normal View History

/* -> /*- for copyright notices, minor format tweaks as necessary
2005-01-06 23:35:40 +00:00
/*-
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
* Copyright (c) 2001 Jake Burkholder <jake@FreeBSD.org>
* All rights reserved.
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
*
* 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, 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 AND CONTRIBUTORS ``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 OR CONTRIBUTORS 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.
*/
Use __FBSDID().
2003-06-11 00:56:59 +00:00
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
Give the 4bsd scheduler the ability to wake up idle processors when there is new work to be done. MFC after: 5 days
2004-09-01 06:42:02 +00:00
#include "opt_sched.h"
Implement preemption of kernel threads natively in the scheduler rather than as one-off hacks in various other parts of the kernel: - Add a function maybe_preempt() that is called from sched_add() to determine if a thread about to be added to a run queue should be preempted to directly. If it is not safe to preempt or if the new thread does not have a high enough priority, then the function returns false and sched_add() adds the thread to the run queue. If the thread should be preempted to but the current thread is in a nested critical section, then the flag TDF_OWEPREEMPT is set and the thread is added to the run queue. Otherwise, mi_switch() is called immediately and the thread is never added to the run queue since it is switch to directly. When exiting an outermost critical section, if TDF_OWEPREEMPT is set, then clear it and call mi_switch() to perform the deferred preemption. - Remove explicit preemption from ithread_schedule() as calling setrunqueue() now does all the correct work. This also removes the do_switch argument from ithread_schedule(). - Do not use the manual preemption code in mtx_unlock if the architecture supports native preemption. - Don't call mi_switch() in a loop during shutdown to give ithreads a chance to run if the architecture supports native preemption since the ithreads will just preempt DELAY(). - Don't call mi_switch() from the page zeroing idle thread for architectures that support native preemption as it is unnecessary. - Native preemption is enabled on the same archs that supported ithread preemption, namely alpha, i386, and amd64. This change should largely be a NOP for the default case as committed except that we will do fewer context switches in a few cases and will avoid the run queues completely when preempting. Approved by: scottl (with his re@ hat)
2004-07-02 20:21:44 +00:00
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
#include <sys/param.h>
#include <sys/systm.h>
Update for the KDB framework: o Make debugging code conditional upon KDB instead of DDB. o Call kdb_enter() instead of Debugger(). o Call kdb_backtrace() instead of db_print_backtrace() or backtrace(). kern_mutex.c: o Replace checks for db_active with checks for kdb_active and make them unconditional. kern_shutdown.c: o s/DDB_UNATTENDED/KDB_UNATTENDED/g o s/DDB_TRACE/KDB_TRACE/g o Save the TID of the thread doing the kernel dump so the debugger knows which thread to select as the current when debugging the kernel core file. o Clear kdb_active instead of db_active and do so unconditionally. o Remove backtrace() implementation. kern_synch.c: o Call kdb_reenter() instead of db_error().
2004-07-10 21:36:01 +00:00
#include <sys/kdb.h>
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
#include <sys/kernel.h>
Major update to the way synchronization is done in the kernel. Highlights include: * Mutual exclusion is used instead of spl*(). See mutex(9). (Note: The alpha port is still in transition and currently uses both.) * Per-CPU idle processes. * Interrupts are run in their own separate kernel threads and can be preempted (i386 only). Partially contributed by: BSDi (BSD/OS) Submissions by (at least): cp, dfr, dillon, grog, jake, jhb, sheldonh
2000-09-07 01:33:02 +00:00
#include <sys/ktr.h>
Catch up to header include changes: - <sys/mutex.h> now requires <sys/systm.h> - <sys/mutex.h> and <sys/sx.h> now require <sys/lock.h>
2001-03-28 09:17:56 +00:00
#include <sys/lock.h>
Catch up to moving headers: - machine/ipl.h -> sys/ipl.h - machine/mutex.h -> sys/mutex.h
2000-10-20 07:58:15 +00:00
#include <sys/mutex.h>
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
#include <sys/proc.h>
#include <sys/queue.h>
- Create a new scheduler api that is defined in sys/sched.h - Begin moving scheduler specific functionality into sched_4bsd.c - Replace direct manipulation of scheduler data with hooks provided by the new api. - Remove KSE specific state modifications and single runq assumptions from kern_switch.c Reviewed by: -arch
2002-10-12 05:32:24 +00:00
#include <sys/sched.h>
Commit a partial lazy thread switch mechanism for i386. it isn't as lazy as it could be and can do with some more cleanup. Currently its under options LAZY_SWITCH. What this does is avoid %cr3 reloads for short context switches that do not involve another user process. ie: we can take an interrupt, switch to a kthread and return to the user without explicitly flushing the tlb. However, this isn't as exciting as it could be, the interrupt overhead is still high and too much blocks on Giant still. There are some debug sysctls, for stats and for an on/off switch. The main problem with doing this has been "what if the process that you're running on exits while we're borrowing its address space?" - in this case we use an IPI to give it a kick when we're about to reclaim the pmap. Its not compiled in unless you add the LAZY_SWITCH option. I want to fix a few more things and get some more feedback before turning it on by default. This is NOT a replacement for Bosko's lazy interrupt stuff. This was more meant for the kthread case, while his was for interrupts. Mine helps a little for interrupts, but his helps a lot more. The stats are enabled with options SWTCH_OPTIM_STATS - this has been a pseudo-option for years, I just added a bunch of stuff to it. One non-trivial change was to select a new thread before calling cpu_switch() in the first place. This allows us to catch the silly case of doing a cpu_switch() to the current process. This happens uncomfortably often. This simplifies a bit of the asm code in cpu_switch (no longer have to call choosethread() in the middle). This has been implemented on i386 and (thanks to jake) sparc64. The others will come soon. This is actually seperate to the lazy switch stuff. Glanced at by: jake, jhb
2003-04-02 23:53:30 +00:00
#include <sys/smp.h>
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
#include <sys/sysctl.h>
Give the 4bsd scheduler the ability to wake up idle processors when there is new work to be done. MFC after: 5 days
2004-09-01 06:42:02 +00:00
Commit 1/14 of sched_lock decomposition. - Move all scheduler locking into the schedulers utilizing a technique similar to solaris's container locking. - A per-process spinlock is now used to protect the queue of threads, thread count, suspension count, p_sflags, and other process related scheduling fields. - The new thread lock is actually a pointer to a spinlock for the container that the thread is currently owned by. The container may be a turnstile, sleepqueue, or run queue. - thread_lock() is now used to protect access to thread related scheduling fields. thread_unlock() unlocks the lock and thread_set_lock() implements the transition from one lock to another. - A new "blocked_lock" is used in cases where it is not safe to hold the actual thread's lock yet we must prevent access to the thread. - sched_throw() and sched_fork_exit() are introduced to allow the schedulers to fix-up locking at these points. - Add some minor infrastructure for optionally exporting scheduler statistics that were invaluable in solving performance problems with this patch. Generally these statistics allow you to differentiate between different causes of context switches. Tested by: kris, current@ Tested on: i386, amd64, ULE, 4BSD, libthr, libkse, PREEMPTION, etc. Discussed with: kris, attilio, kmacy, jhb, julian, bde (small parts each)
2007-06-04 23:50:30 +00:00
#include <machine/cpu.h>
Restore KTR_CRITICAL but conditionally compile it in as KTR_SCHED. Requested by: scottl, jhb
2005-12-18 18:10:57 +00:00
/* Uncomment this to enable logging of critical_enter/exit. */
#if 0
#define KTR_CRITICAL KTR_SCHED
#else
#define KTR_CRITICAL 0
#endif
Turn PREEMPTION into a kernel option. Make sure that it's defined if FULL_PREEMPTION is defined. Add a runtime warning to ULE if PREEMPTION is enabled (code inspired by the PREEMPTION warning in kern_switch.c). This is a possible MT5 candidate.
2004-09-02 18:59:15 +00:00
#ifdef FULL_PREEMPTION
#ifndef PREEMPTION
#error "The FULL_PREEMPTION option requires the PREEMPTION option"
#endif
#endif
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
Make the run queue parameters machine dependent. Optimize 64 bit architectures by using a 64 bit word for the bit array which keeps track of non-empty queues. Reviewed by: peter
2002-05-25 01:12:23 +00:00
CTASSERT((RQB_BPW * RQB_LEN) == RQ_NQS);
Add a read-only kern.sched.preemption sysctl so that user space can tell if "options PREEMPTION" is compiled into the kernel.
2005-03-20 17:05:12 +00:00
/*
* kern.sched.preemption allows user space to determine if preemption support
* is compiled in or not. It is not currently a boot or runtime flag that
* can be changed.
*/
#ifdef PREEMPTION
static int kern_sched_preemption = 1;
#else
static int kern_sched_preemption = 0;
#endif
SYSCTL_INT(_kern_sched, OID_AUTO, preemption, CTLFLAG_RD,
&kern_sched_preemption, 0, "Kernel preemption enabled");
- Make SCHED_STATS more generic by adding a wrapper to create the variables and sysctl nodes. - In reset walk the children of kern_sched_stats and reset the counters via the oid_arg1 pointer. This allows us to add arbitrary counters to the tree and still reset them properly. - Define a set of switch types to be passed with flags to mi_switch(). These types are named SWT_*. These types correspond to SCHED_STATS counters and are automatically handled in this way. - Make the new SWT_ types more specific than the older switch stats. There are now stats for idle switches, remote idle wakeups, remote preemption ithreads idling, etc. - Add switch statistics for ULE's pickcpu algorithm. These stats include how much migration there is, how often affinity was successful, how often threads were migrated to the local cpu on wakeup, etc. Sponsored by: Nokia
2008-04-17 04:20:10 +00:00
/*
* Support for scheduler stats exported via kern.sched.stats. All stats may
* be reset with kern.sched.stats.reset = 1. Stats may be defined elsewhere
* with SCHED_STAT_DEFINE().
*/
Commit 1/14 of sched_lock decomposition. - Move all scheduler locking into the schedulers utilizing a technique similar to solaris's container locking. - A per-process spinlock is now used to protect the queue of threads, thread count, suspension count, p_sflags, and other process related scheduling fields. - The new thread lock is actually a pointer to a spinlock for the container that the thread is currently owned by. The container may be a turnstile, sleepqueue, or run queue. - thread_lock() is now used to protect access to thread related scheduling fields. thread_unlock() unlocks the lock and thread_set_lock() implements the transition from one lock to another. - A new "blocked_lock" is used in cases where it is not safe to hold the actual thread's lock yet we must prevent access to the thread. - sched_throw() and sched_fork_exit() are introduced to allow the schedulers to fix-up locking at these points. - Add some minor infrastructure for optionally exporting scheduler statistics that were invaluable in solving performance problems with this patch. Generally these statistics allow you to differentiate between different causes of context switches. Tested by: kris, current@ Tested on: i386, amd64, ULE, 4BSD, libthr, libkse, PREEMPTION, etc. Discussed with: kris, attilio, kmacy, jhb, julian, bde (small parts each)
2007-06-04 23:50:30 +00:00
#ifdef SCHED_STATS
- Make SCHED_STATS more generic by adding a wrapper to create the variables and sysctl nodes. - In reset walk the children of kern_sched_stats and reset the counters via the oid_arg1 pointer. This allows us to add arbitrary counters to the tree and still reset them properly. - Define a set of switch types to be passed with flags to mi_switch(). These types are named SWT_*. These types correspond to SCHED_STATS counters and are automatically handled in this way. - Make the new SWT_ types more specific than the older switch stats. There are now stats for idle switches, remote idle wakeups, remote preemption ithreads idling, etc. - Add switch statistics for ULE's pickcpu algorithm. These stats include how much migration there is, how often affinity was successful, how often threads were migrated to the local cpu on wakeup, etc. Sponsored by: Nokia
2008-04-17 04:20:10 +00:00
SYSCTL_NODE(_kern_sched, OID_AUTO, stats, CTLFLAG_RW, 0, "switch stats");
- Use DPCPU for SCHED_STATS. This is somewhat awkward because the offset of the stat is not known until link time so we must emit a function to call SYSCTL_ADD_PROC rather than using SYSCTL_PROC directly. - Eliminate the atomic from SCHED_STAT_INC now that it's using per-cpu variables. Sched stats are always incremented while we're holding a spinlock so no further protection is required. Reviewed by: sam
2009-06-25 01:33:51 +00:00
/* Switch reasons from mi_switch(). */
DPCPU_DEFINE(long, sched_switch_stats[SWT_COUNT]);
SCHED_STAT_DEFINE_VAR(uncategorized,
&DPCPU_NAME(sched_switch_stats[SWT_NONE]), "");
SCHED_STAT_DEFINE_VAR(preempt,
&DPCPU_NAME(sched_switch_stats[SWT_PREEMPT]), "");
SCHED_STAT_DEFINE_VAR(owepreempt,
&DPCPU_NAME(sched_switch_stats[SWT_OWEPREEMPT]), "");
SCHED_STAT_DEFINE_VAR(turnstile,
&DPCPU_NAME(sched_switch_stats[SWT_TURNSTILE]), "");
SCHED_STAT_DEFINE_VAR(sleepq,
&DPCPU_NAME(sched_switch_stats[SWT_SLEEPQ]), "");
Revert for r277213: FreeBSD developers need more time to review patches in the surrounding areas like the TCP stack which are using MPSAFE callouts to restore distribution of callouts on multiple CPUs. Bump the __FreeBSD_version instead of reverting it. Suggested by: kmacy, adrian, glebius and kib Differential Revision: https://reviews.freebsd.org/D1438
2015-01-22 11:12:42 +00:00
SCHED_STAT_DEFINE_VAR(sleepqtimo,
&DPCPU_NAME(sched_switch_stats[SWT_SLEEPQTIMO]), "");
- Use DPCPU for SCHED_STATS. This is somewhat awkward because the offset of the stat is not known until link time so we must emit a function to call SYSCTL_ADD_PROC rather than using SYSCTL_PROC directly. - Eliminate the atomic from SCHED_STAT_INC now that it's using per-cpu variables. Sched stats are always incremented while we're holding a spinlock so no further protection is required. Reviewed by: sam
2009-06-25 01:33:51 +00:00
SCHED_STAT_DEFINE_VAR(relinquish,
&DPCPU_NAME(sched_switch_stats[SWT_RELINQUISH]), "");
SCHED_STAT_DEFINE_VAR(needresched,
&DPCPU_NAME(sched_switch_stats[SWT_NEEDRESCHED]), "");
SCHED_STAT_DEFINE_VAR(idle,
&DPCPU_NAME(sched_switch_stats[SWT_IDLE]), "");
SCHED_STAT_DEFINE_VAR(iwait,
&DPCPU_NAME(sched_switch_stats[SWT_IWAIT]), "");
SCHED_STAT_DEFINE_VAR(suspend,
&DPCPU_NAME(sched_switch_stats[SWT_SUSPEND]), "");
SCHED_STAT_DEFINE_VAR(remotepreempt,
&DPCPU_NAME(sched_switch_stats[SWT_REMOTEPREEMPT]), "");
SCHED_STAT_DEFINE_VAR(remotewakeidle,
&DPCPU_NAME(sched_switch_stats[SWT_REMOTEWAKEIDLE]), "");
- Make SCHED_STATS more generic by adding a wrapper to create the variables and sysctl nodes. - In reset walk the children of kern_sched_stats and reset the counters via the oid_arg1 pointer. This allows us to add arbitrary counters to the tree and still reset them properly. - Define a set of switch types to be passed with flags to mi_switch(). These types are named SWT_*. These types correspond to SCHED_STATS counters and are automatically handled in this way. - Make the new SWT_ types more specific than the older switch stats. There are now stats for idle switches, remote idle wakeups, remote preemption ithreads idling, etc. - Add switch statistics for ULE's pickcpu algorithm. These stats include how much migration there is, how often affinity was successful, how often threads were migrated to the local cpu on wakeup, etc. Sponsored by: Nokia
2008-04-17 04:20:10 +00:00
Commit 1/14 of sched_lock decomposition. - Move all scheduler locking into the schedulers utilizing a technique similar to solaris's container locking. - A per-process spinlock is now used to protect the queue of threads, thread count, suspension count, p_sflags, and other process related scheduling fields. - The new thread lock is actually a pointer to a spinlock for the container that the thread is currently owned by. The container may be a turnstile, sleepqueue, or run queue. - thread_lock() is now used to protect access to thread related scheduling fields. thread_unlock() unlocks the lock and thread_set_lock() implements the transition from one lock to another. - A new "blocked_lock" is used in cases where it is not safe to hold the actual thread's lock yet we must prevent access to the thread. - sched_throw() and sched_fork_exit() are introduced to allow the schedulers to fix-up locking at these points. - Add some minor infrastructure for optionally exporting scheduler statistics that were invaluable in solving performance problems with this patch. Generally these statistics allow you to differentiate between different causes of context switches. Tested by: kris, current@ Tested on: i386, amd64, ULE, 4BSD, libthr, libkse, PREEMPTION, etc. Discussed with: kris, attilio, kmacy, jhb, julian, bde (small parts each)
2007-06-04 23:50:30 +00:00
static int
sysctl_stats_reset(SYSCTL_HANDLER_ARGS)
{
- Make SCHED_STATS more generic by adding a wrapper to create the variables and sysctl nodes. - In reset walk the children of kern_sched_stats and reset the counters via the oid_arg1 pointer. This allows us to add arbitrary counters to the tree and still reset them properly. - Define a set of switch types to be passed with flags to mi_switch(). These types are named SWT_*. These types correspond to SCHED_STATS counters and are automatically handled in this way. - Make the new SWT_ types more specific than the older switch stats. There are now stats for idle switches, remote idle wakeups, remote preemption ithreads idling, etc. - Add switch statistics for ULE's pickcpu algorithm. These stats include how much migration there is, how often affinity was successful, how often threads were migrated to the local cpu on wakeup, etc. Sponsored by: Nokia
2008-04-17 04:20:10 +00:00
struct sysctl_oid *p;
- Use DPCPU for SCHED_STATS. This is somewhat awkward because the offset of the stat is not known until link time so we must emit a function to call SYSCTL_ADD_PROC rather than using SYSCTL_PROC directly. - Eliminate the atomic from SCHED_STAT_INC now that it's using per-cpu variables. Sched stats are always incremented while we're holding a spinlock so no further protection is required. Reviewed by: sam
2009-06-25 01:33:51 +00:00
uintptr_t counter;
Commit 1/14 of sched_lock decomposition. - Move all scheduler locking into the schedulers utilizing a technique similar to solaris's container locking. - A per-process spinlock is now used to protect the queue of threads, thread count, suspension count, p_sflags, and other process related scheduling fields. - The new thread lock is actually a pointer to a spinlock for the container that the thread is currently owned by. The container may be a turnstile, sleepqueue, or run queue. - thread_lock() is now used to protect access to thread related scheduling fields. thread_unlock() unlocks the lock and thread_set_lock() implements the transition from one lock to another. - A new "blocked_lock" is used in cases where it is not safe to hold the actual thread's lock yet we must prevent access to the thread. - sched_throw() and sched_fork_exit() are introduced to allow the schedulers to fix-up locking at these points. - Add some minor infrastructure for optionally exporting scheduler statistics that were invaluable in solving performance problems with this patch. Generally these statistics allow you to differentiate between different causes of context switches. Tested by: kris, current@ Tested on: i386, amd64, ULE, 4BSD, libthr, libkse, PREEMPTION, etc. Discussed with: kris, attilio, kmacy, jhb, julian, bde (small parts each)
2007-06-04 23:50:30 +00:00
int error;
int val;
- Use DPCPU for SCHED_STATS. This is somewhat awkward because the offset of the stat is not known until link time so we must emit a function to call SYSCTL_ADD_PROC rather than using SYSCTL_PROC directly. - Eliminate the atomic from SCHED_STAT_INC now that it's using per-cpu variables. Sched stats are always incremented while we're holding a spinlock so no further protection is required. Reviewed by: sam
2009-06-25 01:33:51 +00:00
int i;
Commit 1/14 of sched_lock decomposition. - Move all scheduler locking into the schedulers utilizing a technique similar to solaris's container locking. - A per-process spinlock is now used to protect the queue of threads, thread count, suspension count, p_sflags, and other process related scheduling fields. - The new thread lock is actually a pointer to a spinlock for the container that the thread is currently owned by. The container may be a turnstile, sleepqueue, or run queue. - thread_lock() is now used to protect access to thread related scheduling fields. thread_unlock() unlocks the lock and thread_set_lock() implements the transition from one lock to another. - A new "blocked_lock" is used in cases where it is not safe to hold the actual thread's lock yet we must prevent access to the thread. - sched_throw() and sched_fork_exit() are introduced to allow the schedulers to fix-up locking at these points. - Add some minor infrastructure for optionally exporting scheduler statistics that were invaluable in solving performance problems with this patch. Generally these statistics allow you to differentiate between different causes of context switches. Tested by: kris, current@ Tested on: i386, amd64, ULE, 4BSD, libthr, libkse, PREEMPTION, etc. Discussed with: kris, attilio, kmacy, jhb, julian, bde (small parts each)
2007-06-04 23:50:30 +00:00
val = 0;
error = sysctl_handle_int(oidp, &val, 0, req);
if (error != 0 || req->newptr == NULL)
return (error);
if (val == 0)
return (0);
- Make SCHED_STATS more generic by adding a wrapper to create the variables and sysctl nodes. - In reset walk the children of kern_sched_stats and reset the counters via the oid_arg1 pointer. This allows us to add arbitrary counters to the tree and still reset them properly. - Define a set of switch types to be passed with flags to mi_switch(). These types are named SWT_*. These types correspond to SCHED_STATS counters and are automatically handled in this way. - Make the new SWT_ types more specific than the older switch stats. There are now stats for idle switches, remote idle wakeups, remote preemption ithreads idling, etc. - Add switch statistics for ULE's pickcpu algorithm. These stats include how much migration there is, how often affinity was successful, how often threads were migrated to the local cpu on wakeup, etc. Sponsored by: Nokia
2008-04-17 04:20:10 +00:00
/*
* Traverse the list of children of _kern_sched_stats and reset each
* to 0. Skip the reset entry.
*/
SLIST_FOREACH(p, oidp->oid_parent, oid_link) {
if (p == oidp || p->oid_arg1 == NULL)
continue;
- Use DPCPU for SCHED_STATS. This is somewhat awkward because the offset of the stat is not known until link time so we must emit a function to call SYSCTL_ADD_PROC rather than using SYSCTL_PROC directly. - Eliminate the atomic from SCHED_STAT_INC now that it's using per-cpu variables. Sched stats are always incremented while we're holding a spinlock so no further protection is required. Reviewed by: sam
2009-06-25 01:33:51 +00:00
counter = (uintptr_t)p->oid_arg1;
Update several places that iterate over CPUs to use CPU_FOREACH().
2010-06-11 18:46:34 +00:00
CPU_FOREACH(i) {
- Use DPCPU for SCHED_STATS. This is somewhat awkward because the offset of the stat is not known until link time so we must emit a function to call SYSCTL_ADD_PROC rather than using SYSCTL_PROC directly. - Eliminate the atomic from SCHED_STAT_INC now that it's using per-cpu variables. Sched stats are always incremented while we're holding a spinlock so no further protection is required. Reviewed by: sam
2009-06-25 01:33:51 +00:00
*(long *)(dpcpu_off[i] + counter) = 0;
}
- Make SCHED_STATS more generic by adding a wrapper to create the variables and sysctl nodes. - In reset walk the children of kern_sched_stats and reset the counters via the oid_arg1 pointer. This allows us to add arbitrary counters to the tree and still reset them properly. - Define a set of switch types to be passed with flags to mi_switch(). These types are named SWT_*. These types correspond to SCHED_STATS counters and are automatically handled in this way. - Make the new SWT_ types more specific than the older switch stats. There are now stats for idle switches, remote idle wakeups, remote preemption ithreads idling, etc. - Add switch statistics for ULE's pickcpu algorithm. These stats include how much migration there is, how often affinity was successful, how often threads were migrated to the local cpu on wakeup, etc. Sponsored by: Nokia
2008-04-17 04:20:10 +00:00
}
Commit 1/14 of sched_lock decomposition. - Move all scheduler locking into the schedulers utilizing a technique similar to solaris's container locking. - A per-process spinlock is now used to protect the queue of threads, thread count, suspension count, p_sflags, and other process related scheduling fields. - The new thread lock is actually a pointer to a spinlock for the container that the thread is currently owned by. The container may be a turnstile, sleepqueue, or run queue. - thread_lock() is now used to protect access to thread related scheduling fields. thread_unlock() unlocks the lock and thread_set_lock() implements the transition from one lock to another. - A new "blocked_lock" is used in cases where it is not safe to hold the actual thread's lock yet we must prevent access to the thread. - sched_throw() and sched_fork_exit() are introduced to allow the schedulers to fix-up locking at these points. - Add some minor infrastructure for optionally exporting scheduler statistics that were invaluable in solving performance problems with this patch. Generally these statistics allow you to differentiate between different causes of context switches. Tested by: kris, current@ Tested on: i386, amd64, ULE, 4BSD, libthr, libkse, PREEMPTION, etc. Discussed with: kris, attilio, kmacy, jhb, julian, bde (small parts each)
2007-06-04 23:50:30 +00:00
return (0);
}
SYSCTL_PROC(_kern_sched_stats, OID_AUTO, reset, CTLTYPE_INT | CTLFLAG_WR, NULL,
0, sysctl_stats_reset, "I", "Reset scheduler statistics");
#endif
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
/************************************************************************
* Functions that manipulate runnability from a thread perspective. *
************************************************************************/
Make KSE a kernel option, turned on by default in all GENERIC kernel configs except sun4v (which doesn't process signals properly with KSE). Reviewed by: davidxu@
2006-10-26 21:42:22 +00:00
/*
* Select the thread that will be run next.
*/
KSE Milestone 2 Note ALL MODULES MUST BE RECOMPILED make the kernel aware that there are smaller units of scheduling than the process. (but only allow one thread per process at this time). This is functionally equivalent to teh previousl -current except that there is a thread associated with each process. Sorry john! (your next MFC will be a doosie!) Reviewed by: peter@freebsd.org, dillon@freebsd.org X-MFC after: ha ha ha ha
2001-09-12 08:38:13 +00:00
struct thread *
choosethread(void)
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
{
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
struct thread *td;
Allow alphas to do crashdumps: Refuse to run anything in choosethread() after a panic which is not an interrupt thread, or the thread which caused the panic. Also, remove panicstr checks from msleep() and from cv_wait() in order to allow threads to go to sleep and yeild the cpu to the panicing thread, or to an interrupt thread which might be doing the crashdump. Reviewed by: jhb (and it was mostly his idea too)
2002-07-17 02:23:44 +00:00
retry:
- Remove setrunqueue and replace it with direct calls to sched_add(). setrunqueue() was mostly empty. The few asserts and thread state setting were moved to the individual schedulers. sched_add() was chosen to displace it for naming consistency reasons. - Remove adjustrunqueue, it was 4 lines of code that was ifdef'd to be different on all three schedulers where it was only called in one place each. - Remove the long ifdef'd out remrunqueue code. - Remove the now redundant ts_state. Inspect the thread state directly. - Don't set TSF_* flags from kern_switch.c, we were only doing this to support a feature in one scheduler. - Change sched_choose() to return a thread rather than a td_sched. Also, rely on the schedulers to return the idlethread. This simplifies the logic in choosethread(). Aside from the run queue links kern_switch.c mostly does not care about the contents of td_sched. Discussed with: julian - Move the idle thread loop into the per scheduler area. ULE wants to do something different from the other schedulers. Suggested by: jhb Tested on: x86/amd64 sched_{4BSD, ULE, CORE}.
2007-01-23 08:46:51 +00:00
td = sched_choose();
Add code to ddb to allow backtracing an arbitrary thread. (show thread {address}) Remove the IDLE kse state and replace it with a change in the way threads sahre KSEs. Every KSE now has a thread, which is considered its "owner" however a KSE may also be lent to other threads in the same group to allow completion of in-kernel work. n this case the owner remains the same and the KSE will revert to the owner when the other work has been completed. All creations of upcalls etc. is now done from kse_reassign() which in turn is called from mi_switch or thread_exit(). This means that special code can be removed from msleep() and cv_wait(). kse_release() does not leave a KSE with no thread any more but converts the existing thread into teh KSE's owner, and sets it up for doing an upcall. It is just inhibitted from being scheduled until there is some reason to do an upcall. Remove all trace of the kse_idle queue since it is no-longer needed. "Idle" KSEs are now on the loanable queue.
2002-12-28 01:23:07 +00:00
/*
When we are spilling threads out of the run queue during panic, make sure we keep the thread state variable consistent with its real state. i.e. Don't say it's on the run queue when it isn't. Also clarify the associated comment. Turns a double panic back to a single panic :-/ Approved by: re@ (jhb)
2003-05-21 18:53:25 +00:00
* If we are in panic, only allow system threads,
* plus the one we are running in, to be run.
Add code to ddb to allow backtracing an arbitrary thread. (show thread {address}) Remove the IDLE kse state and replace it with a change in the way threads sahre KSEs. Every KSE now has a thread, which is considered its "owner" however a KSE may also be lent to other threads in the same group to allow completion of in-kernel work. n this case the owner remains the same and the KSE will revert to the owner when the other work has been completed. All creations of upcalls etc. is now done from kse_reassign() which in turn is called from mi_switch or thread_exit(). This means that special code can be removed from msleep() and cv_wait(). kse_release() does not leave a KSE with no thread any more but converts the existing thread into teh KSE's owner, and sets it up for doing an upcall. It is just inhibitted from being scheduled until there is some reason to do an upcall. Remove all trace of the kse_idle queue since it is no-longer needed. "Idle" KSEs are now on the loanable queue.
2002-12-28 01:23:07 +00:00
*/
Allow alphas to do crashdumps: Refuse to run anything in choosethread() after a panic which is not an interrupt thread, or the thread which caused the panic. Also, remove panicstr checks from msleep() and from cv_wait() in order to allow threads to go to sleep and yeild the cpu to the panicing thread, or to an interrupt thread which might be doing the crashdump. Reviewed by: jhb (and it was mostly his idea too)
2002-07-17 02:23:44 +00:00
if (panicstr && ((td->td_proc->p_flag & P_SYSTEM) == 0 &&
When we are spilling threads out of the run queue during panic, make sure we keep the thread state variable consistent with its real state. i.e. Don't say it's on the run queue when it isn't. Also clarify the associated comment. Turns a double panic back to a single panic :-/ Approved by: re@ (jhb)
2003-05-21 18:53:25 +00:00
(td->td_flags & TDF_INPANIC) == 0)) {
/* note that it is no longer on the run queue */
TD_SET_CAN_RUN(td);
Allow alphas to do crashdumps: Refuse to run anything in choosethread() after a panic which is not an interrupt thread, or the thread which caused the panic. Also, remove panicstr checks from msleep() and from cv_wait() in order to allow threads to go to sleep and yeild the cpu to the panicing thread, or to an interrupt thread which might be doing the crashdump. Reviewed by: jhb (and it was mostly his idea too)
2002-07-17 02:23:44 +00:00
goto retry;
When we are spilling threads out of the run queue during panic, make sure we keep the thread state variable consistent with its real state. i.e. Don't say it's on the run queue when it isn't. Also clarify the associated comment. Turns a double panic back to a single panic :-/ Approved by: re@ (jhb)
2003-05-21 18:53:25 +00:00
}
Add code to ddb to allow backtracing an arbitrary thread. (show thread {address}) Remove the IDLE kse state and replace it with a change in the way threads sahre KSEs. Every KSE now has a thread, which is considered its "owner" however a KSE may also be lent to other threads in the same group to allow completion of in-kernel work. n this case the owner remains the same and the KSE will revert to the owner when the other work has been completed. All creations of upcalls etc. is now done from kse_reassign() which in turn is called from mi_switch or thread_exit(). This means that special code can be removed from msleep() and cv_wait(). kse_release() does not leave a KSE with no thread any more but converts the existing thread into teh KSE's owner, and sets it up for doing an upcall. It is just inhibitted from being scheduled until there is some reason to do an upcall. Remove all trace of the kse_idle queue since it is no-longer needed. "Idle" KSEs are now on the loanable queue.
2002-12-28 01:23:07 +00:00
Completely redo thread states. Reviewed by: davidxu@freebsd.org
2002-09-11 08:13:56 +00:00
TD_SET_RUNNING(td);
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
return (td);
}
Implement preemption of kernel threads natively in the scheduler rather than as one-off hacks in various other parts of the kernel: - Add a function maybe_preempt() that is called from sched_add() to determine if a thread about to be added to a run queue should be preempted to directly. If it is not safe to preempt or if the new thread does not have a high enough priority, then the function returns false and sched_add() adds the thread to the run queue. If the thread should be preempted to but the current thread is in a nested critical section, then the flag TDF_OWEPREEMPT is set and the thread is added to the run queue. Otherwise, mi_switch() is called immediately and the thread is never added to the run queue since it is switch to directly. When exiting an outermost critical section, if TDF_OWEPREEMPT is set, then clear it and call mi_switch() to perform the deferred preemption. - Remove explicit preemption from ithread_schedule() as calling setrunqueue() now does all the correct work. This also removes the do_switch argument from ithread_schedule(). - Do not use the manual preemption code in mtx_unlock if the architecture supports native preemption. - Don't call mi_switch() in a loop during shutdown to give ithreads a chance to run if the architecture supports native preemption since the ithreads will just preempt DELAY(). - Don't call mi_switch() from the page zeroing idle thread for architectures that support native preemption as it is unnecessary. - Native preemption is enabled on the same archs that supported ithread preemption, namely alpha, i386, and amd64. This change should largely be a NOP for the default case as committed except that we will do fewer context switches in a few cases and will avoid the run queues completely when preempting. Approved by: scottl (with his re@ hat)
2004-07-02 20:21:44 +00:00
/*
* Kernel thread preemption implementation. Critical sections mark
* regions of code in which preemptions are not allowed.
Add a comment on why inlining critical_enter() may not be a good idea for the general case. Reviewed by: bde MFC after: 1 week
2012-12-09 04:54:22 +00:00
*
* It might seem a good idea to inline critical_enter() but, in order
* to prevent instructions reordering by the compiler, a __compiler_membar()
* would have to be used here (the same as sched_pin()). The performance
* penalty imposed by the membar could, then, produce slower code than
* the function call itself, for most cases.
Implement preemption of kernel threads natively in the scheduler rather than as one-off hacks in various other parts of the kernel: - Add a function maybe_preempt() that is called from sched_add() to determine if a thread about to be added to a run queue should be preempted to directly. If it is not safe to preempt or if the new thread does not have a high enough priority, then the function returns false and sched_add() adds the thread to the run queue. If the thread should be preempted to but the current thread is in a nested critical section, then the flag TDF_OWEPREEMPT is set and the thread is added to the run queue. Otherwise, mi_switch() is called immediately and the thread is never added to the run queue since it is switch to directly. When exiting an outermost critical section, if TDF_OWEPREEMPT is set, then clear it and call mi_switch() to perform the deferred preemption. - Remove explicit preemption from ithread_schedule() as calling setrunqueue() now does all the correct work. This also removes the do_switch argument from ithread_schedule(). - Do not use the manual preemption code in mtx_unlock if the architecture supports native preemption. - Don't call mi_switch() in a loop during shutdown to give ithreads a chance to run if the architecture supports native preemption since the ithreads will just preempt DELAY(). - Don't call mi_switch() from the page zeroing idle thread for architectures that support native preemption as it is unnecessary. - Native preemption is enabled on the same archs that supported ithread preemption, namely alpha, i386, and amd64. This change should largely be a NOP for the default case as committed except that we will do fewer context switches in a few cases and will avoid the run queues completely when preempting. Approved by: scottl (with his re@ hat)
2004-07-02 20:21:44 +00:00
*/
Modify the critical section API as follows: - The MD functions critical_enter/exit are renamed to start with a cpu_ prefix. - MI wrapper functions critical_enter/exit maintain a per-thread nesting count and a per-thread critical section saved state set when entering a critical section while at nesting level 0 and restored when exiting to nesting level 0. This moves the saved state out of spin mutexes so that interlocking spin mutexes works properly. - Most low-level MD code that used critical_enter/exit now use cpu_critical_enter/exit. MI code such as device drivers and spin mutexes use the MI wrappers. Note that since the MI wrappers store the state in the current thread, they do not have any return values or arguments. - mtx_intr_enable() is replaced with a constant CRITICAL_FORK which is assigned to curthread->td_savecrit during fork_exit(). Tested on: i386, alpha
2001-12-18 00:27:18 +00:00
void
critical_enter(void)
{
struct thread *td;
td = curthread;
td->td_critnest++;
Restore KTR_CRITICAL but conditionally compile it in as KTR_SCHED. Requested by: scottl, jhb
2005-12-18 18:10:57 +00:00
CTR4(KTR_CRITICAL, "critical_enter by thread %p (%ld, %s) to %d", td,
generally we are interested in what thread did something as opposed to what process. Since threads by default have teh name of the process unless over-written with more useful information, just print the thread name instead.
2007-11-14 06:21:24 +00:00
(long)td->td_proc->p_pid, td->td_name, td->td_critnest);
Modify the critical section API as follows: - The MD functions critical_enter/exit are renamed to start with a cpu_ prefix. - MI wrapper functions critical_enter/exit maintain a per-thread nesting count and a per-thread critical section saved state set when entering a critical section while at nesting level 0 and restored when exiting to nesting level 0. This moves the saved state out of spin mutexes so that interlocking spin mutexes works properly. - Most low-level MD code that used critical_enter/exit now use cpu_critical_enter/exit. MI code such as device drivers and spin mutexes use the MI wrappers. Note that since the MI wrappers store the state in the current thread, they do not have any return values or arguments. - mtx_intr_enable() is replaced with a constant CRITICAL_FORK which is assigned to curthread->td_savecrit during fork_exit(). Tested on: i386, alpha
2001-12-18 00:27:18 +00:00
}
void
critical_exit(void)
{
struct thread *td;
- Make SCHED_STATS more generic by adding a wrapper to create the variables and sysctl nodes. - In reset walk the children of kern_sched_stats and reset the counters via the oid_arg1 pointer. This allows us to add arbitrary counters to the tree and still reset them properly. - Define a set of switch types to be passed with flags to mi_switch(). These types are named SWT_*. These types correspond to SCHED_STATS counters and are automatically handled in this way. - Make the new SWT_ types more specific than the older switch stats. There are now stats for idle switches, remote idle wakeups, remote preemption ithreads idling, etc. - Add switch statistics for ULE's pickcpu algorithm. These stats include how much migration there is, how often affinity was successful, how often threads were migrated to the local cpu on wakeup, etc. Sponsored by: Nokia
2008-04-17 04:20:10 +00:00
int flags;
Modify the critical section API as follows: - The MD functions critical_enter/exit are renamed to start with a cpu_ prefix. - MI wrapper functions critical_enter/exit maintain a per-thread nesting count and a per-thread critical section saved state set when entering a critical section while at nesting level 0 and restored when exiting to nesting level 0. This moves the saved state out of spin mutexes so that interlocking spin mutexes works properly. - Most low-level MD code that used critical_enter/exit now use cpu_critical_enter/exit. MI code such as device drivers and spin mutexes use the MI wrappers. Note that since the MI wrappers store the state in the current thread, they do not have any return values or arguments. - mtx_intr_enable() is replaced with a constant CRITICAL_FORK which is assigned to curthread->td_savecrit during fork_exit(). Tested on: i386, alpha
2001-12-18 00:27:18 +00:00
td = curthread;
- style fixes to the critical_exit() KASSERT(). Submitted by: bde
2004-02-02 08:13:27 +00:00
KASSERT(td->td_critnest != 0,
("critical_exit: td_critnest == 0"));
- Fix ULE in kernels without PREEMPTION compiled in by always enabling the critical_exit() owepreempt check. ULE will always use owepreempt to preempt the idle thread. This change does not effect 4BSD since it will never set owepreempt without PREEMPTION enabled. - Remove some unused code from choosethread(). Discussed with: jhb Approved by: re
2007-10-08 23:37:28 +00:00
Modify the critical section API as follows: - The MD functions critical_enter/exit are renamed to start with a cpu_ prefix. - MI wrapper functions critical_enter/exit maintain a per-thread nesting count and a per-thread critical section saved state set when entering a critical section while at nesting level 0 and restored when exiting to nesting level 0. This moves the saved state out of spin mutexes so that interlocking spin mutexes works properly. - Most low-level MD code that used critical_enter/exit now use cpu_critical_enter/exit. MI code such as device drivers and spin mutexes use the MI wrappers. Note that since the MI wrappers store the state in the current thread, they do not have any return values or arguments. - mtx_intr_enable() is replaced with a constant CRITICAL_FORK which is assigned to curthread->td_savecrit during fork_exit(). Tested on: i386, alpha
2001-12-18 00:27:18 +00:00
if (td->td_critnest == 1) {
Sprinkle some volatile magic and rearrange things a bit to avoid race conditions in critical_exit now that it no longer blocks interrupts. Reviewed by: jhb
2005-04-08 03:37:53 +00:00
td->td_critnest = 0;
critical_exit: ignore td_owepreempt if kdb_active is set calling mi_switch in such a context results in a recursion via kdb_switch Suggested by: jhb Reviewed by: jhb MFC after: 5 weeks
2011-12-04 21:27:41 +00:00
if (td->td_owepreempt && !kdb_active) {
Sprinkle some volatile magic and rearrange things a bit to avoid race conditions in critical_exit now that it no longer blocks interrupts. Reviewed by: jhb
2005-04-08 03:37:53 +00:00
td->td_critnest = 1;
Commit 1/14 of sched_lock decomposition. - Move all scheduler locking into the schedulers utilizing a technique similar to solaris's container locking. - A per-process spinlock is now used to protect the queue of threads, thread count, suspension count, p_sflags, and other process related scheduling fields. - The new thread lock is actually a pointer to a spinlock for the container that the thread is currently owned by. The container may be a turnstile, sleepqueue, or run queue. - thread_lock() is now used to protect access to thread related scheduling fields. thread_unlock() unlocks the lock and thread_set_lock() implements the transition from one lock to another. - A new "blocked_lock" is used in cases where it is not safe to hold the actual thread's lock yet we must prevent access to the thread. - sched_throw() and sched_fork_exit() are introduced to allow the schedulers to fix-up locking at these points. - Add some minor infrastructure for optionally exporting scheduler statistics that were invaluable in solving performance problems with this patch. Generally these statistics allow you to differentiate between different causes of context switches. Tested by: kris, current@ Tested on: i386, amd64, ULE, 4BSD, libthr, libkse, PREEMPTION, etc. Discussed with: kris, attilio, kmacy, jhb, julian, bde (small parts each)
2007-06-04 23:50:30 +00:00
thread_lock(td);
Sprinkle some volatile magic and rearrange things a bit to avoid race conditions in critical_exit now that it no longer blocks interrupts. Reviewed by: jhb
2005-04-08 03:37:53 +00:00
td->td_critnest--;
- Make SCHED_STATS more generic by adding a wrapper to create the variables and sysctl nodes. - In reset walk the children of kern_sched_stats and reset the counters via the oid_arg1 pointer. This allows us to add arbitrary counters to the tree and still reset them properly. - Define a set of switch types to be passed with flags to mi_switch(). These types are named SWT_*. These types correspond to SCHED_STATS counters and are automatically handled in this way. - Make the new SWT_ types more specific than the older switch stats. There are now stats for idle switches, remote idle wakeups, remote preemption ithreads idling, etc. - Add switch statistics for ULE's pickcpu algorithm. These stats include how much migration there is, how often affinity was successful, how often threads were migrated to the local cpu on wakeup, etc. Sponsored by: Nokia
2008-04-17 04:20:10 +00:00
flags = SW_INVOL | SW_PREEMPT;
if (TD_IS_IDLETHREAD(td))
flags |= SWT_IDLE;
else
flags |= SWT_OWEPREEMPT;
mi_switch(flags, NULL);
Commit 1/14 of sched_lock decomposition. - Move all scheduler locking into the schedulers utilizing a technique similar to solaris's container locking. - A per-process spinlock is now used to protect the queue of threads, thread count, suspension count, p_sflags, and other process related scheduling fields. - The new thread lock is actually a pointer to a spinlock for the container that the thread is currently owned by. The container may be a turnstile, sleepqueue, or run queue. - thread_lock() is now used to protect access to thread related scheduling fields. thread_unlock() unlocks the lock and thread_set_lock() implements the transition from one lock to another. - A new "blocked_lock" is used in cases where it is not safe to hold the actual thread's lock yet we must prevent access to the thread. - sched_throw() and sched_fork_exit() are introduced to allow the schedulers to fix-up locking at these points. - Add some minor infrastructure for optionally exporting scheduler statistics that were invaluable in solving performance problems with this patch. Generally these statistics allow you to differentiate between different causes of context switches. Tested by: kris, current@ Tested on: i386, amd64, ULE, 4BSD, libthr, libkse, PREEMPTION, etc. Discussed with: kris, attilio, kmacy, jhb, julian, bde (small parts each)
2007-06-04 23:50:30 +00:00
thread_unlock(td);
Implement preemption of kernel threads natively in the scheduler rather than as one-off hacks in various other parts of the kernel: - Add a function maybe_preempt() that is called from sched_add() to determine if a thread about to be added to a run queue should be preempted to directly. If it is not safe to preempt or if the new thread does not have a high enough priority, then the function returns false and sched_add() adds the thread to the run queue. If the thread should be preempted to but the current thread is in a nested critical section, then the flag TDF_OWEPREEMPT is set and the thread is added to the run queue. Otherwise, mi_switch() is called immediately and the thread is never added to the run queue since it is switch to directly. When exiting an outermost critical section, if TDF_OWEPREEMPT is set, then clear it and call mi_switch() to perform the deferred preemption. - Remove explicit preemption from ithread_schedule() as calling setrunqueue() now does all the correct work. This also removes the do_switch argument from ithread_schedule(). - Do not use the manual preemption code in mtx_unlock if the architecture supports native preemption. - Don't call mi_switch() in a loop during shutdown to give ithreads a chance to run if the architecture supports native preemption since the ithreads will just preempt DELAY(). - Don't call mi_switch() from the page zeroing idle thread for architectures that support native preemption as it is unnecessary. - Native preemption is enabled on the same archs that supported ithread preemption, namely alpha, i386, and amd64. This change should largely be a NOP for the default case as committed except that we will do fewer context switches in a few cases and will avoid the run queues completely when preempting. Approved by: scottl (with his re@ hat)
2004-07-02 20:21:44 +00:00
}
Trim trailing whitespace.
2005-12-28 17:13:31 +00:00
} else
Modify the critical section API as follows: - The MD functions critical_enter/exit are renamed to start with a cpu_ prefix. - MI wrapper functions critical_enter/exit maintain a per-thread nesting count and a per-thread critical section saved state set when entering a critical section while at nesting level 0 and restored when exiting to nesting level 0. This moves the saved state out of spin mutexes so that interlocking spin mutexes works properly. - Most low-level MD code that used critical_enter/exit now use cpu_critical_enter/exit. MI code such as device drivers and spin mutexes use the MI wrappers. Note that since the MI wrappers store the state in the current thread, they do not have any return values or arguments. - mtx_intr_enable() is replaced with a constant CRITICAL_FORK which is assigned to curthread->td_savecrit during fork_exit(). Tested on: i386, alpha
2001-12-18 00:27:18 +00:00
td->td_critnest--;
Trim trailing whitespace.
2005-12-28 17:13:31 +00:00
Restore KTR_CRITICAL but conditionally compile it in as KTR_SCHED. Requested by: scottl, jhb
2005-12-18 18:10:57 +00:00
CTR4(KTR_CRITICAL, "critical_exit by thread %p (%ld, %s) to %d", td,
generally we are interested in what thread did something as opposed to what process. Since threads by default have teh name of the process unless over-written with more useful information, just print the thread name instead.
2007-11-14 06:21:24 +00:00
(long)td->td_proc->p_pid, td->td_name, td->td_critnest);
Modify the critical section API as follows: - The MD functions critical_enter/exit are renamed to start with a cpu_ prefix. - MI wrapper functions critical_enter/exit maintain a per-thread nesting count and a per-thread critical section saved state set when entering a critical section while at nesting level 0 and restored when exiting to nesting level 0. This moves the saved state out of spin mutexes so that interlocking spin mutexes works properly. - Most low-level MD code that used critical_enter/exit now use cpu_critical_enter/exit. MI code such as device drivers and spin mutexes use the MI wrappers. Note that since the MI wrappers store the state in the current thread, they do not have any return values or arguments. - mtx_intr_enable() is replaced with a constant CRITICAL_FORK which is assigned to curthread->td_savecrit during fork_exit(). Tested on: i386, alpha
2001-12-18 00:27:18 +00:00
}
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
/************************************************************************
* SYSTEM RUN QUEUE manipulations and tests *
************************************************************************/
/*
* Initialize a run structure.
*/
void
runq_init(struct runq *rq)
{
int i;
bzero(rq, sizeof *rq);
for (i = 0; i < RQ_NQS; i++)
TAILQ_INIT(&rq->rq_queues[i]);
}
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
/*
* Clear the status bit of the queue corresponding to priority level pri,
* indicating that it is empty.
*/
static __inline void
runq_clrbit(struct runq *rq, int pri)
{
struct rqbits *rqb;
Major update to the way synchronization is done in the kernel. Highlights include: * Mutual exclusion is used instead of spl*(). See mutex(9). (Note: The alpha port is still in transition and currently uses both.) * Per-CPU idle processes. * Interrupts are run in their own separate kernel threads and can be preempted (i386 only). Partially contributed by: BSDi (BSD/OS) Submissions by (at least): cp, dfr, dillon, grog, jake, jhb, sheldonh
2000-09-07 01:33:02 +00:00
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
rqb = &rq->rq_status;
CTR4(KTR_RUNQ, "runq_clrbit: bits=%#x %#x bit=%#x word=%d",
rqb->rqb_bits[RQB_WORD(pri)],
rqb->rqb_bits[RQB_WORD(pri)] & ~RQB_BIT(pri),
RQB_BIT(pri), RQB_WORD(pri));
rqb->rqb_bits[RQB_WORD(pri)] &= ~RQB_BIT(pri);
}
/*
* Find the index of the first non-empty run queue. This is done by
* scanning the status bits, a set bit indicates a non-empty queue.
*/
static __inline int
runq_findbit(struct runq *rq)
{
struct rqbits *rqb;
int pri;
int i;
rqb = &rq->rq_status;
for (i = 0; i < RQB_LEN; i++)
if (rqb->rqb_bits[i]) {
Move the "- 1" into the RQB_FFS(mask) macro itself so that implementations can provide a base zero ffs function if they wish. This changes #define RQB_FFS(mask) (ffs64(mask)) foo = RQB_FFS(mask) - 1; to #define RQB_FFS(mask) (ffs64(mask) - 1) foo = RQB_FFS(mask); On some platforms we can get the "- 1" for free, eg: those that use the C code for ffs64(). Reviewed by: jake (in principle)
2002-06-20 06:21:20 +00:00
pri = RQB_FFS(rqb->rqb_bits[i]) + (i << RQB_L2BPW);
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
CTR3(KTR_RUNQ, "runq_findbit: bits=%#x i=%d pri=%d",
rqb->rqb_bits[i], i, pri);
return (pri);
}
return (-1);
}
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
static __inline int
- Improve runq_findbit_from() which is used by ULE's circular queue. Mask of the bits we want to ignore on the first pass rather than doing a linear scan. This puts us within a few instructions of the cost of runq_findbit() and removes this function from the top of profiling output for context switch heavy workloads. Approved by: re
2007-08-20 06:36:12 +00:00
runq_findbit_from(struct runq *rq, u_char pri)
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
{
struct rqbits *rqb;
- Improve runq_findbit_from() which is used by ULE's circular queue. Mask of the bits we want to ignore on the first pass rather than doing a linear scan. This puts us within a few instructions of the cost of runq_findbit() and removes this function from the top of profiling output for context switch heavy workloads. Approved by: re
2007-08-20 06:36:12 +00:00
rqb_word_t mask;
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
int i;
- Improve runq_findbit_from() which is used by ULE's circular queue. Mask of the bits we want to ignore on the first pass rather than doing a linear scan. This puts us within a few instructions of the cost of runq_findbit() and removes this function from the top of profiling output for context switch heavy workloads. Approved by: re
2007-08-20 06:36:12 +00:00
/*
* Set the mask for the first word so we ignore priorities before 'pri'.
*/
mask = (rqb_word_t)-1 << (pri & (RQB_BPW - 1));
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
rqb = &rq->rq_status;
again:
- Improve runq_findbit_from() which is used by ULE's circular queue. Mask of the bits we want to ignore on the first pass rather than doing a linear scan. This puts us within a few instructions of the cost of runq_findbit() and removes this function from the top of profiling output for context switch heavy workloads. Approved by: re
2007-08-20 06:36:12 +00:00
for (i = RQB_WORD(pri); i < RQB_LEN; mask = -1, i++) {
mask = rqb->rqb_bits[i] & mask;
if (mask == 0)
continue;
pri = RQB_FFS(mask) + (i << RQB_L2BPW);
CTR3(KTR_RUNQ, "runq_findbit_from: bits=%#x i=%d pri=%d",
mask, i, pri);
return (pri);
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
}
- Improve runq_findbit_from() which is used by ULE's circular queue. Mask of the bits we want to ignore on the first pass rather than doing a linear scan. This puts us within a few instructions of the cost of runq_findbit() and removes this function from the top of profiling output for context switch heavy workloads. Approved by: re
2007-08-20 06:36:12 +00:00
if (pri == 0)
return (-1);
/*
* Wrap back around to the beginning of the list just once so we
* scan the whole thing.
*/
pri = 0;
goto again;
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
}
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
/*
* Set the status bit of the queue corresponding to priority level pri,
* indicating that it is non-empty.
*/
static __inline void
runq_setbit(struct runq *rq, int pri)
{
struct rqbits *rqb;
rqb = &rq->rq_status;
CTR4(KTR_RUNQ, "runq_setbit: bits=%#x %#x bit=%#x word=%d",
rqb->rqb_bits[RQB_WORD(pri)],
rqb->rqb_bits[RQB_WORD(pri)] | RQB_BIT(pri),
RQB_BIT(pri), RQB_WORD(pri));
rqb->rqb_bits[RQB_WORD(pri)] |= RQB_BIT(pri);
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
}
/*
Threading cleanup.. part 2 of several. Make part of John Birrell's KSE patch permanent.. Specifically, remove: Any reference of the ksegrp structure. This feature was never fully utilised and made things overly complicated. All code in the scheduler that tried to make threaded programs fair to unthreaded programs. Libpthread processes will already do this to some extent and libthr processes already disable it. Also: Since this makes such a big change to the scheduler(s), take the opportunity to rename some structures and elements that had to be moved anyhow. This makes the code a lot more readable. The ULE scheduler compiles again but I have no idea if it works. The 4bsd scheduler still reqires a little cleaning and some functions that now do ALMOST nothing will go away, but I thought I'd do that as a separate commit. Tested by David Xu, and Dan Eischen using libthr and libpthread.
2006-12-06 06:34:57 +00:00
* Add the thread to the queue specified by its priority, and set the
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
* corresponding status bit.
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
*/
void
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
runq_add(struct runq *rq, struct thread *td, int flags)
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
{
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
struct rqhead *rqh;
int pri;
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
pri = td->td_priority / RQ_PPQ;
td->td_rqindex = pri;
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
runq_setbit(rq, pri);
rqh = &rq->rq_queues[pri];
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
CTR4(KTR_RUNQ, "runq_add: td=%p pri=%d %d rqh=%p",
td, td->td_priority, pri, rqh);
When preempting a thread, put it back on the HEAD of its run queue. (Only really implemented in 4bsd) MFC after: 4 days
2004-10-05 22:03:10 +00:00
if (flags & SRQ_PREEMPTED) {
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
TAILQ_INSERT_HEAD(rqh, td, td_runq);
When preempting a thread, put it back on the HEAD of its run queue. (Only really implemented in 4bsd) MFC after: 4 days
2004-10-05 22:03:10 +00:00
} else {
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
TAILQ_INSERT_TAIL(rqh, td, td_runq);
When preempting a thread, put it back on the HEAD of its run queue. (Only really implemented in 4bsd) MFC after: 4 days
2004-10-05 22:03:10 +00:00
}
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
}
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
void
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
runq_add_pri(struct runq *rq, struct thread *td, u_char pri, int flags)
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
{
struct rqhead *rqh;
KASSERT(pri < RQ_NQS, ("runq_add_pri: %d out of range", pri));
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
td->td_rqindex = pri;
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
runq_setbit(rq, pri);
rqh = &rq->rq_queues[pri];
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
CTR4(KTR_RUNQ, "runq_add_pri: td=%p pri=%d idx=%d rqh=%p",
td, td->td_priority, pri, rqh);
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
if (flags & SRQ_PREEMPTED) {
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
TAILQ_INSERT_HEAD(rqh, td, td_runq);
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
} else {
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
TAILQ_INSERT_TAIL(rqh, td, td_runq);
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
}
}
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
/*
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
* Return true if there are runnable processes of any priority on the run
* queue, false otherwise. Has no side effects, does not modify the run
* queue structure.
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
*/
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
int
runq_check(struct runq *rq)
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
{
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
struct rqbits *rqb;
int i;
rqb = &rq->rq_status;
for (i = 0; i < RQB_LEN; i++)
if (rqb->rqb_bits[i]) {
CTR2(KTR_RUNQ, "runq_check: bits=%#x i=%d",
rqb->rqb_bits[i], i);
return (1);
}
CTR0(KTR_RUNQ, "runq_check: empty");
return (0);
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
}
/*
- Create a new scheduler api that is defined in sys/sched.h - Begin moving scheduler specific functionality into sched_4bsd.c - Replace direct manipulation of scheduler data with hooks provided by the new api. - Remove KSE specific state modifications and single runq assumptions from kern_switch.c Reviewed by: -arch
2002-10-12 05:32:24 +00:00
* Find the highest priority process on the run queue.
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
*/
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
struct thread *
- Move maybe_preempt() from kern_switch.c to sched_4bsd.c. This is function is only used by 4bsd. - Create a new runq_choose_fuzz() function rather than polluting runq_choose() with 4BSD specific code. - Move the fuzz sysctl into sched_4bsd.c - Remove some dead code from kern_switch.c
2008-03-20 02:14:02 +00:00
runq_choose_fuzz(struct runq *rq, int fuzz)
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
{
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
struct rqhead *rqh;
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
struct thread *td;
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
int pri;
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
while ((pri = runq_findbit(rq)) != -1) {
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
rqh = &rq->rq_queues[pri];
Give the 4bsd scheduler the ability to wake up idle processors when there is new work to be done. MFC after: 5 days
2004-09-01 06:42:02 +00:00
/* fuzz == 1 is normal.. 0 or less are ignored */
- Move maybe_preempt() from kern_switch.c to sched_4bsd.c. This is function is only used by 4bsd. - Create a new runq_choose_fuzz() function rather than polluting runq_choose() with 4BSD specific code. - Move the fuzz sysctl into sched_4bsd.c - Remove some dead code from kern_switch.c
2008-03-20 02:14:02 +00:00
if (fuzz > 1) {
Give the 4bsd scheduler the ability to wake up idle processors when there is new work to be done. MFC after: 5 days
2004-09-01 06:42:02 +00:00
/*
* In the first couple of entries, check if
* there is one for our CPU as a preference.
*/
- Move maybe_preempt() from kern_switch.c to sched_4bsd.c. This is function is only used by 4bsd. - Create a new runq_choose_fuzz() function rather than polluting runq_choose() with 4BSD specific code. - Move the fuzz sysctl into sched_4bsd.c - Remove some dead code from kern_switch.c
2008-03-20 02:14:02 +00:00
int count = fuzz;
Give the 4bsd scheduler the ability to wake up idle processors when there is new work to be done. MFC after: 5 days
2004-09-01 06:42:02 +00:00
int cpu = PCPU_GET(cpuid);
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
struct thread *td2;
td2 = td = TAILQ_FIRST(rqh);
Give the 4bsd scheduler the ability to wake up idle processors when there is new work to be done. MFC after: 5 days
2004-09-01 06:42:02 +00:00
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
while (count-- && td2) {
fix typo in runz_fuzz noticed by:Elijah Buck
2008-05-12 06:42:06 +00:00
if (td2->td_lastcpu == cpu) {
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
td = td2;
Give the 4bsd scheduler the ability to wake up idle processors when there is new work to be done. MFC after: 5 days
2004-09-01 06:42:02 +00:00
break;
}
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
td2 = TAILQ_NEXT(td2, td_runq);
Give the 4bsd scheduler the ability to wake up idle processors when there is new work to be done. MFC after: 5 days
2004-09-01 06:42:02 +00:00
}
Trim trailing whitespace.
2005-12-28 17:13:31 +00:00
} else
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
td = TAILQ_FIRST(rqh);
KASSERT(td != NULL, ("runq_choose_fuzz: no proc on busy queue"));
- Move maybe_preempt() from kern_switch.c to sched_4bsd.c. This is function is only used by 4bsd. - Create a new runq_choose_fuzz() function rather than polluting runq_choose() with 4BSD specific code. - Move the fuzz sysctl into sched_4bsd.c - Remove some dead code from kern_switch.c
2008-03-20 02:14:02 +00:00
CTR3(KTR_RUNQ,
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
"runq_choose_fuzz: pri=%d thread=%p rqh=%p", pri, td, rqh);
return (td);
- Move maybe_preempt() from kern_switch.c to sched_4bsd.c. This is function is only used by 4bsd. - Create a new runq_choose_fuzz() function rather than polluting runq_choose() with 4BSD specific code. - Move the fuzz sysctl into sched_4bsd.c - Remove some dead code from kern_switch.c
2008-03-20 02:14:02 +00:00
}
CTR1(KTR_RUNQ, "runq_choose_fuzz: idleproc pri=%d", pri);
return (NULL);
}
/*
* Find the highest priority process on the run queue.
*/
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
struct thread *
- Move maybe_preempt() from kern_switch.c to sched_4bsd.c. This is function is only used by 4bsd. - Create a new runq_choose_fuzz() function rather than polluting runq_choose() with 4BSD specific code. - Move the fuzz sysctl into sched_4bsd.c - Remove some dead code from kern_switch.c
2008-03-20 02:14:02 +00:00
runq_choose(struct runq *rq)
{
struct rqhead *rqh;
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
struct thread *td;
- Move maybe_preempt() from kern_switch.c to sched_4bsd.c. This is function is only used by 4bsd. - Create a new runq_choose_fuzz() function rather than polluting runq_choose() with 4BSD specific code. - Move the fuzz sysctl into sched_4bsd.c - Remove some dead code from kern_switch.c
2008-03-20 02:14:02 +00:00
int pri;
while ((pri = runq_findbit(rq)) != -1) {
rqh = &rq->rq_queues[pri];
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
td = TAILQ_FIRST(rqh);
KASSERT(td != NULL, ("runq_choose: no thread on busy queue"));
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
CTR3(KTR_RUNQ,
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
"runq_choose: pri=%d thread=%p rqh=%p", pri, td, rqh);
return (td);
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
}
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
CTR1(KTR_RUNQ, "runq_choose: idlethread pri=%d", pri);
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
return (NULL);
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
}
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
struct thread *
- Change types for necent runq additions to u_char rather than int. - Fix these types in ULE as well. This fixes bugs in priority index calculations in certain edge cases. (int)-1 % 64 != (uint)-1 % 64. Reported by: kkenn using pho's stress2.
2007-02-08 01:52:25 +00:00
runq_choose_from(struct runq *rq, u_char idx)
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
{
struct rqhead *rqh;
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
struct thread *td;
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
int pri;
- Don't pass a pointer into runq_choose_from(). The caller can adjust the index if it chooses to.
2007-01-04 12:10:58 +00:00
if ((pri = runq_findbit_from(rq, idx)) != -1) {
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
rqh = &rq->rq_queues[pri];
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
td = TAILQ_FIRST(rqh);
KASSERT(td != NULL, ("runq_choose: no thread on busy queue"));
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
CTR4(KTR_RUNQ,
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
"runq_choose_from: pri=%d thread=%p idx=%d rqh=%p",
pri, td, td->td_rqindex, rqh);
return (td);
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
}
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
CTR1(KTR_RUNQ, "runq_choose_from: idlethread pri=%d", pri);
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
return (NULL);
}
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
/*
Threading cleanup.. part 2 of several. Make part of John Birrell's KSE patch permanent.. Specifically, remove: Any reference of the ksegrp structure. This feature was never fully utilised and made things overly complicated. All code in the scheduler that tried to make threaded programs fair to unthreaded programs. Libpthread processes will already do this to some extent and libthr processes already disable it. Also: Since this makes such a big change to the scheduler(s), take the opportunity to rename some structures and elements that had to be moved anyhow. This makes the code a lot more readable. The ULE scheduler compiles again but I have no idea if it works. The 4bsd scheduler still reqires a little cleaning and some functions that now do ALMOST nothing will go away, but I thought I'd do that as a separate commit. Tested by David Xu, and Dan Eischen using libthr and libpthread.
2006-12-06 06:34:57 +00:00
* Remove the thread from the queue specified by its priority, and clear the
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
* corresponding status bit if the queue becomes empty.
- Remove setrunqueue and replace it with direct calls to sched_add(). setrunqueue() was mostly empty. The few asserts and thread state setting were moved to the individual schedulers. sched_add() was chosen to displace it for naming consistency reasons. - Remove adjustrunqueue, it was 4 lines of code that was ifdef'd to be different on all three schedulers where it was only called in one place each. - Remove the long ifdef'd out remrunqueue code. - Remove the now redundant ts_state. Inspect the thread state directly. - Don't set TSF_* flags from kern_switch.c, we were only doing this to support a feature in one scheduler. - Change sched_choose() to return a thread rather than a td_sched. Also, rely on the schedulers to return the idlethread. This simplifies the logic in choosethread(). Aside from the run queue links kern_switch.c mostly does not care about the contents of td_sched. Discussed with: julian - Move the idle thread loop into the per scheduler area. ULE wants to do something different from the other schedulers. Suggested by: jhb Tested on: x86/amd64 sched_{4BSD, ULE, CORE}.
2007-01-23 08:46:51 +00:00
* Caller must set state afterwards.
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
*/
void
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
runq_remove(struct runq *rq, struct thread *td)
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
{
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
runq_remove_idx(rq, td, NULL);
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
}
void
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
runq_remove_idx(struct runq *rq, struct thread *td, u_char *idx)
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
{
struct rqhead *rqh;
- Change types for necent runq additions to u_char rather than int. - Fix these types in ULE as well. This fixes bugs in priority index calculations in certain edge cases. (int)-1 % 64 != (uint)-1 % 64. Reported by: kkenn using pho's stress2.
2007-02-08 01:52:25 +00:00
u_char pri;
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
KASSERT(td->td_flags & TDF_INMEM,
- Move all of the PS_ flags into either p_flag or td_flags. - p_sflag was mostly protected by PROC_LOCK rather than the PROC_SLOCK or previously the sched_lock. These bugs have existed for some time. - Allow swapout to try each thread in a process individually and then swapin the whole process if any of these fail. This allows us to move most scheduler related swap flags into td_flags. - Keep ki_sflag for backwards compat but change all in source tools to use the new and more correct location of P_INMEM. Reported by: pho Reviewed by: attilio, kib Approved by: re (kensmith)
2007-09-17 05:31:39 +00:00
("runq_remove_idx: thread swapped out"));
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
pri = td->td_rqindex;
Commit 1/14 of sched_lock decomposition. - Move all scheduler locking into the schedulers utilizing a technique similar to solaris's container locking. - A per-process spinlock is now used to protect the queue of threads, thread count, suspension count, p_sflags, and other process related scheduling fields. - The new thread lock is actually a pointer to a spinlock for the container that the thread is currently owned by. The container may be a turnstile, sleepqueue, or run queue. - thread_lock() is now used to protect access to thread related scheduling fields. thread_unlock() unlocks the lock and thread_set_lock() implements the transition from one lock to another. - A new "blocked_lock" is used in cases where it is not safe to hold the actual thread's lock yet we must prevent access to the thread. - sched_throw() and sched_fork_exit() are introduced to allow the schedulers to fix-up locking at these points. - Add some minor infrastructure for optionally exporting scheduler statistics that were invaluable in solving performance problems with this patch. Generally these statistics allow you to differentiate between different causes of context switches. Tested by: kris, current@ Tested on: i386, amd64, ULE, 4BSD, libthr, libkse, PREEMPTION, etc. Discussed with: kris, attilio, kmacy, jhb, julian, bde (small parts each)
2007-06-04 23:50:30 +00:00
KASSERT(pri < RQ_NQS, ("runq_remove_idx: Invalid index %d\n", pri));
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
rqh = &rq->rq_queues[pri];
- Restore runq to manipulating threads directly by putting runq links and rqindex back in struct thread. - Compile kern_switch.c independently again and stop #include'ing it from schedulers. - Remove the ts_thread backpointers and convert most code to go from struct thread to struct td_sched. - Cleanup the ts_flags #define garbage that was causing us to sometimes do things that expanded to td->td_sched->ts_thread->td_flags in 4BSD. - Export the kern.sched sysctl node in sysctl.h
2008-03-20 05:51:16 +00:00
CTR4(KTR_RUNQ, "runq_remove_idx: td=%p, pri=%d %d rqh=%p",
td, td->td_priority, pri, rqh);
TAILQ_REMOVE(rqh, td, td_runq);
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
if (TAILQ_EMPTY(rqh)) {
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
CTR0(KTR_RUNQ, "runq_remove_idx: empty");
Implement a unified run queue and adjust priority levels accordingly. - All processes go into the same array of queues, with different scheduling classes using different portions of the array. This allows user processes to have their priorities propogated up into interrupt thread range if need be. - I chose 64 run queues as an arbitrary number that is greater than 32. We used to have 4 separate arrays of 32 queues each, so this may not be optimal. The new run queue code was written with this in mind; changing the number of run queues only requires changing constants in runq.h and adjusting the priority levels. - The new run queue code takes the run queue as a parameter. This is intended to be used to create per-cpu run queues. Implement wrappers for compatibility with the old interface which pass in the global run queue structure. - Group the priority level, user priority, native priority (before propogation) and the scheduling class into a struct priority. - Change any hard coded priority levels that I found to use symbolic constants (TTIPRI and TTOPRI). - Remove the curpriority global variable and use that of curproc. This was used to detect when a process' priority had lowered and it should yield. We now effectively yield on every interrupt. - Activate propogate_priority(). It should now have the desired effect without needing to also propogate the scheduling class. - Temporarily comment out the call to vm_page_zero_idle() in the idle loop. It interfered with propogate_priority() because the idle process needed to do a non-blocking acquire of Giant and then other processes would try to propogate their priority onto it. The idle process should not do anything except idle. vm_page_zero_idle() will return in the form of an idle priority kernel thread which is woken up at apprioriate times by the vm system. - Update struct kinfo_proc to the new priority interface. Deliberately change its size by adjusting the spare fields. It remained the same size, but the layout has changed, so userland processes that use it would parse the data incorrectly. The size constraint should really be changed to an arbitrary version number. Also add a debug.sizeof sysctl node for struct kinfo_proc.
2001-02-12 00:20:08 +00:00
runq_clrbit(rq, pri);
- Add three new functions to support circular run queues. - runq_add_pri allows the caller to position the thread at any rqindex regardless of priority. - runq_choose_from() chooses the lowest priority thread starting from a given index. The index is updated with the rqindex of the chosen thread. This routine is used to pick the lowest priority relative to a given index. - runq_remove_idx() updates the index if the run queue that held the removed thread is now empty.
2007-01-04 08:39:58 +00:00
if (idx != NULL && *idx == pri)
*idx = (pri + 1) % RQ_NQS;
Extract the next runnable process selection out of cpu_switch() into a fairly machine independent C routine. gcc actually does a pretty good job of this. Reviewed by: msmith (in principle)
1999-08-19 00:06:53 +00:00
}
Part 1 of KSE-III The ability to schedule multiple threads per process (one one cpu) by making ALL system calls optionally asynchronous. to come: ia64 and power-pc patches, patches for gdb, test program (in tools) Reviewed by: Almost everyone who counts (at various times, peter, jhb, matt, alfred, mini, bernd, and a cast of thousands) NOTE: this is still Beta code, and contains lots of debugging stuff. expect slight instability in signals..
2002-06-29 17:26:22 +00:00
}
Reference in New Issue Copy Permalink