diff options
author | Alexander Motin <mav@FreeBSD.org> | 2010-09-13 07:25:35 +0000 |
---|---|---|
committer | Alexander Motin <mav@FreeBSD.org> | 2010-09-13 07:25:35 +0000 |
commit | a157e42516dcee534177e5e0dc59815c3334d647 (patch) | |
tree | b0666da99693a46e1663a3a882abfdee5e324830 /sys/pc98 | |
parent | 3c7f49dcf28dcb78fd219f420504e50518ccea48 (diff) | |
download | src-a157e42516dcee534177e5e0dc59815c3334d647.tar.gz src-a157e42516dcee534177e5e0dc59815c3334d647.zip |
Refactor timer management code with priority to one-shot operation mode.
The main goal of this is to generate timer interrupts only when there is
some work to do. When CPU is busy interrupts are generating at full rate
of hz + stathz to fullfill scheduler and timekeeping requirements. But
when CPU is idle, only minimum set of interrupts (down to 8 interrupts per
second per CPU now), needed to handle scheduled callouts is executed.
This allows significantly increase idle CPU sleep time, increasing effect
of static power-saving technologies. Also it should reduce host CPU load
on virtualized systems, when guest system is idle.
There is set of tunables, also available as writable sysctls, allowing to
control wanted event timer subsystem behavior:
kern.eventtimer.timer - allows to choose event timer hardware to use.
On x86 there is up to 4 different kinds of timers. Depending on whether
chosen timer is per-CPU, behavior of other options slightly differs.
kern.eventtimer.periodic - allows to choose periodic and one-shot
operation mode. In periodic mode, current timer hardware taken as the only
source of time for time events. This mode is quite alike to previous kernel
behavior. One-shot mode instead uses currently selected time counter
hardware to schedule all needed events one by one and program timer to
generate interrupt exactly in specified time. Default value depends of
chosen timer capabilities, but one-shot mode is preferred, until other is
forced by user or hardware.
kern.eventtimer.singlemul - in periodic mode specifies how much times
higher timer frequency should be, to not strictly alias hardclock() and
statclock() events. Default values are 2 and 4, but could be reduced to 1
if extra interrupts are unwanted.
kern.eventtimer.idletick - makes each CPU to receive every timer interrupt
independently of whether they busy or not. By default this options is
disabled. If chosen timer is per-CPU and runs in periodic mode, this option
has no effect - all interrupts are generating.
As soon as this patch modifies cpu_idle() on some platforms, I have also
refactored one on x86. Now it makes use of MONITOR/MWAIT instrunctions
(if supported) under high sleep/wakeup rate, as fast alternative to other
methods. It allows SMP scheduler to wake up sleeping CPUs much faster
without using IPI, significantly increasing performance on some highly
task-switching loads.
Tested by: many (on i386, amd64, sparc64 and powerc)
H/W donated by: Gheorghe Ardelean
Sponsored by: iXsystems, Inc.
Notes
Notes:
svn path=/head/; revision=212541
Diffstat (limited to 'sys/pc98')
-rw-r--r-- | sys/pc98/pc98/machdep.c | 141 |
1 files changed, 82 insertions, 59 deletions
diff --git a/sys/pc98/pc98/machdep.c b/sys/pc98/pc98/machdep.c index 671ce5b3cf37..22dc8f0c5e00 100644 --- a/sys/pc98/pc98/machdep.c +++ b/sys/pc98/pc98/machdep.c @@ -1120,40 +1120,36 @@ cpu_halt(void) __asm__ ("hlt"); } +static int idle_mwait = 1; /* Use MONITOR/MWAIT for short idle. */ +TUNABLE_INT("machdep.idle_mwait", &idle_mwait); +SYSCTL_INT(_machdep, OID_AUTO, idle_mwait, CTLFLAG_RW, &idle_mwait, + 0, "Use MONITOR/MWAIT for short idle"); + +#define STATE_RUNNING 0x0 +#define STATE_MWAIT 0x1 +#define STATE_SLEEPING 0x2 + static void cpu_idle_hlt(int busy) { + int *state; + + state = (int *)PCPU_PTR(monitorbuf); + *state = STATE_SLEEPING; /* - * we must absolutely guarentee that hlt is the next instruction + * We must absolutely guarentee that hlt is the next instruction * after sti or we introduce a timing window. */ disable_intr(); - if (sched_runnable()) + if (sched_runnable()) enable_intr(); else __asm __volatile("sti; hlt"); -} - -static void -cpu_idle_spin(int busy) -{ - return; -} - -void (*cpu_idle_fn)(int) = cpu_idle_hlt; - -void -cpu_idle(int busy) -{ -#if defined(SMP) - if (mp_grab_cpu_hlt()) - return; -#endif - cpu_idle_fn(busy); + *state = STATE_RUNNING; } /* - * mwait cpu power states. Lower 4 bits are sub-states. + * MWAIT cpu power states. Lower 4 bits are sub-states. */ #define MWAIT_C0 0xf0 #define MWAIT_C1 0x00 @@ -1161,63 +1157,91 @@ cpu_idle(int busy) #define MWAIT_C3 0x20 #define MWAIT_C4 0x30 -#define MWAIT_DISABLED 0x0 -#define MWAIT_WOKEN 0x1 -#define MWAIT_WAITING 0x2 - static void cpu_idle_mwait(int busy) { - int *mwait; - - mwait = (int *)PCPU_PTR(monitorbuf); - *mwait = MWAIT_WAITING; - if (sched_runnable()) - return; - cpu_monitor(mwait, 0, 0); - if (*mwait == MWAIT_WAITING) - cpu_mwait(0, MWAIT_C1); + int *state; + + state = (int *)PCPU_PTR(monitorbuf); + *state = STATE_MWAIT; + if (!sched_runnable()) { + cpu_monitor(state, 0, 0); + if (*state == STATE_MWAIT) + cpu_mwait(0, MWAIT_C1); + } + *state = STATE_RUNNING; } static void -cpu_idle_mwait_hlt(int busy) +cpu_idle_spin(int busy) { - int *mwait; + int *state; + int i; - mwait = (int *)PCPU_PTR(monitorbuf); - if (busy == 0) { - *mwait = MWAIT_DISABLED; - cpu_idle_hlt(busy); - return; + state = (int *)PCPU_PTR(monitorbuf); + *state = STATE_RUNNING; + for (i = 0; i < 1000; i++) { + if (sched_runnable()) + return; + cpu_spinwait(); } - *mwait = MWAIT_WAITING; - if (sched_runnable()) +} + +void (*cpu_idle_fn)(int) = cpu_idle_hlt; + +void +cpu_idle(int busy) +{ + + CTR2(KTR_SPARE2, "cpu_idle(%d) at %d", + busy, curcpu); +#ifdef SMP + if (mp_grab_cpu_hlt()) return; - cpu_monitor(mwait, 0, 0); - if (*mwait == MWAIT_WAITING) - cpu_mwait(0, MWAIT_C1); +#endif + /* If we are busy - try to use fast methods. */ + if (busy) { + if ((cpu_feature2 & CPUID2_MON) && idle_mwait) { + cpu_idle_mwait(busy); + goto out; + } + } + + /* If we have time - switch timers into idle mode. */ + if (!busy) { + critical_enter(); + cpu_idleclock(); + } + + /* Call main idle method. */ + cpu_idle_fn(busy); + + /* Switch timers mack into active mode. */ + if (!busy) { + cpu_activeclock(); + critical_exit(); + } +out: + CTR2(KTR_SPARE2, "cpu_idle(%d) at %d done", + busy, curcpu); } int cpu_idle_wakeup(int cpu) { struct pcpu *pcpu; - int *mwait; + int *state; - if (cpu_idle_fn == cpu_idle_spin) - return (1); - if (cpu_idle_fn != cpu_idle_mwait && cpu_idle_fn != cpu_idle_mwait_hlt) - return (0); pcpu = pcpu_find(cpu); - mwait = (int *)pcpu->pc_monitorbuf; + state = (int *)pcpu->pc_monitorbuf; /* * This doesn't need to be atomic since missing the race will * simply result in unnecessary IPIs. */ - if (cpu_idle_fn == cpu_idle_mwait_hlt && *mwait == MWAIT_DISABLED) + if (*state == STATE_SLEEPING) return (0); - *mwait = MWAIT_WOKEN; - + if (*state == STATE_MWAIT) + *state = STATE_RUNNING; return (1); } @@ -1230,7 +1254,6 @@ struct { } idle_tbl[] = { { cpu_idle_spin, "spin" }, { cpu_idle_mwait, "mwait" }, - { cpu_idle_mwait_hlt, "mwait_hlt" }, { cpu_idle_hlt, "hlt" }, { NULL, NULL } }; @@ -1255,6 +1278,9 @@ idle_sysctl_available(SYSCTL_HANDLER_ARGS) return (error); } +SYSCTL_PROC(_machdep, OID_AUTO, idle_available, CTLTYPE_STRING | CTLFLAG_RD, + 0, 0, idle_sysctl_available, "A", "list of available idle functions"); + static int idle_sysctl(SYSCTL_HANDLER_ARGS) { @@ -1286,9 +1312,6 @@ idle_sysctl(SYSCTL_HANDLER_ARGS) return (EINVAL); } -SYSCTL_PROC(_machdep, OID_AUTO, idle_available, CTLTYPE_STRING | CTLFLAG_RD, - 0, 0, idle_sysctl_available, "A", "list of available idle functions"); - SYSCTL_PROC(_machdep, OID_AUTO, idle, CTLTYPE_STRING | CTLFLAG_RW, 0, 0, idle_sysctl, "A", "currently selected idle function"); |