提交 f7819512 编写于 作者: P Paolo Bonzini

kvm: add halt_poll_ns module parameter

This patch introduces a new module parameter for the KVM module; when it
is present, KVM attempts a bit of polling on every HLT before scheduling
itself out via kvm_vcpu_block.

This parameter helps a lot for latency-bound workloads---in particular
I tested it with O_DSYNC writes with a battery-backed disk in the host.
In this case, writes are fast (because the data doesn't have to go all
the way to the platters) but they cannot be merged by either the host or
the guest.  KVM's performance here is usually around 30% of bare metal,
or 50% if you use cache=directsync or cache=writethrough (these
parameters avoid that the guest sends pointless flush requests, and
at the same time they are not slow because of the battery-backed cache).
The bad performance happens because on every halt the host CPU decides
to halt itself too.  When the interrupt comes, the vCPU thread is then
migrated to a new physical CPU, and in general the latency is horrible
because the vCPU thread has to be scheduled back in.

With this patch performance reaches 60-65% of bare metal and, more
important, 99% of what you get if you use idle=poll in the guest.  This
means that the tunable gets rid of this particular bottleneck, and more
work can be done to improve performance in the kernel or QEMU.

Of course there is some price to pay; every time an otherwise idle vCPUs
is interrupted by an interrupt, it will poll unnecessarily and thus
impose a little load on the host.  The above results were obtained with
a mostly random value of the parameter (500000), and the load was around
1.5-2.5% CPU usage on one of the host's core for each idle guest vCPU.

The patch also adds a new stat, /sys/kernel/debug/kvm/halt_successful_poll,
that can be used to tune the parameter.  It counts how many HLT
instructions received an interrupt during the polling period; each
successful poll avoids that Linux schedules the VCPU thread out and back
in, and may also avoid a likely trip to C1 and back for the physical CPU.

While the VM is idle, a Linux 4 VCPU VM halts around 10 times per second.
Of these halts, almost all are failed polls.  During the benchmark,
instead, basically all halts end within the polling period, except a more
or less constant stream of 50 per second coming from vCPUs that are not
running the benchmark.  The wasted time is thus very low.  Things may
be slightly different for Windows VMs, which have a ~10 ms timer tick.

The effect is also visible on Marcelo's recently-introduced latency
test for the TSC deadline timer.  Though of course a non-RT kernel has
awful latency bounds, the latency of the timer is around 8000-10000 clock
cycles compared to 20000-120000 without setting halt_poll_ns.  For the TSC
deadline timer, thus, the effect is both a smaller average latency and
a smaller variance.
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
上级 1c2b364b
......@@ -148,6 +148,7 @@ struct kvm_vm_stat {
};
struct kvm_vcpu_stat {
u32 halt_successful_poll;
u32 halt_wakeup;
};
......
......@@ -165,6 +165,7 @@ struct kvm_vm_stat {
};
struct kvm_vcpu_stat {
u32 halt_successful_poll;
u32 halt_wakeup;
};
......
......@@ -120,6 +120,7 @@ struct kvm_vcpu_stat {
u32 resvd_inst_exits;
u32 break_inst_exits;
u32 flush_dcache_exits;
u32 halt_successful_poll;
u32 halt_wakeup;
};
......
......@@ -49,6 +49,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "resvd_inst", VCPU_STAT(resvd_inst_exits), KVM_STAT_VCPU },
{ "break_inst", VCPU_STAT(break_inst_exits), KVM_STAT_VCPU },
{ "flush_dcache", VCPU_STAT(flush_dcache_exits), KVM_STAT_VCPU },
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll), KVM_STAT_VCPU },
{ "halt_wakeup", VCPU_STAT(halt_wakeup), KVM_STAT_VCPU },
{NULL}
};
......
......@@ -107,6 +107,7 @@ struct kvm_vcpu_stat {
u32 emulated_inst_exits;
u32 dec_exits;
u32 ext_intr_exits;
u32 halt_successful_poll;
u32 halt_wakeup;
u32 dbell_exits;
u32 gdbell_exits;
......
......@@ -52,6 +52,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "dec", VCPU_STAT(dec_exits) },
{ "ext_intr", VCPU_STAT(ext_intr_exits) },
{ "queue_intr", VCPU_STAT(queue_intr) },
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll), },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
{ "pf_storage", VCPU_STAT(pf_storage) },
{ "sp_storage", VCPU_STAT(sp_storage) },
......
......@@ -62,6 +62,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "inst_emu", VCPU_STAT(emulated_inst_exits) },
{ "dec", VCPU_STAT(dec_exits) },
{ "ext_intr", VCPU_STAT(ext_intr_exits) },
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
{ "doorbell", VCPU_STAT(dbell_exits) },
{ "guest doorbell", VCPU_STAT(gdbell_exits) },
......
......@@ -196,6 +196,7 @@ struct kvm_vcpu_stat {
u32 exit_stop_request;
u32 exit_validity;
u32 exit_instruction;
u32 halt_successful_poll;
u32 halt_wakeup;
u32 instruction_lctl;
u32 instruction_lctlg;
......
......@@ -51,6 +51,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "exit_instruction", VCPU_STAT(exit_instruction) },
{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
......
......@@ -655,6 +655,7 @@ struct kvm_vcpu_stat {
u32 irq_window_exits;
u32 nmi_window_exits;
u32 halt_exits;
u32 halt_successful_poll;
u32 halt_wakeup;
u32 request_irq_exits;
u32 irq_exits;
......
......@@ -145,6 +145,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "irq_window", VCPU_STAT(irq_window_exits) },
{ "nmi_window", VCPU_STAT(nmi_window_exits) },
{ "halt_exits", VCPU_STAT(halt_exits) },
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
{ "hypercalls", VCPU_STAT(hypercalls) },
{ "request_irq", VCPU_STAT(request_irq_exits) },
......
......@@ -37,6 +37,25 @@ TRACE_EVENT(kvm_userspace_exit,
__entry->errno < 0 ? -__entry->errno : __entry->reason)
);
TRACE_EVENT(kvm_vcpu_wakeup,
TP_PROTO(__u64 ns, bool waited),
TP_ARGS(ns, waited),
TP_STRUCT__entry(
__field( __u64, ns )
__field( bool, waited )
),
TP_fast_assign(
__entry->ns = ns;
__entry->waited = waited;
),
TP_printk("%s time %lld ns",
__entry->waited ? "wait" : "poll",
__entry->ns)
);
#if defined(CONFIG_HAVE_KVM_IRQFD)
TRACE_EVENT(kvm_set_irq,
TP_PROTO(unsigned int gsi, int level, int irq_source_id),
......
......@@ -66,6 +66,9 @@
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
unsigned int halt_poll_ns = 0;
module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR);
/*
* Ordering of locks:
*
......@@ -1813,29 +1816,60 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
}
EXPORT_SYMBOL_GPL(mark_page_dirty);
static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu)
{
if (kvm_arch_vcpu_runnable(vcpu)) {
kvm_make_request(KVM_REQ_UNHALT, vcpu);
return -EINTR;
}
if (kvm_cpu_has_pending_timer(vcpu))
return -EINTR;
if (signal_pending(current))
return -EINTR;
return 0;
}
/*
* The vCPU has executed a HLT instruction with in-kernel mode enabled.
*/
void kvm_vcpu_block(struct kvm_vcpu *vcpu)
{
ktime_t start, cur;
DEFINE_WAIT(wait);
bool waited = false;
start = cur = ktime_get();
if (halt_poll_ns) {
ktime_t stop = ktime_add_ns(ktime_get(), halt_poll_ns);
do {
/*
* This sets KVM_REQ_UNHALT if an interrupt
* arrives.
*/
if (kvm_vcpu_check_block(vcpu) < 0) {
++vcpu->stat.halt_successful_poll;
goto out;
}
cur = ktime_get();
} while (single_task_running() && ktime_before(cur, stop));
}
for (;;) {
prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
if (kvm_arch_vcpu_runnable(vcpu)) {
kvm_make_request(KVM_REQ_UNHALT, vcpu);
break;
}
if (kvm_cpu_has_pending_timer(vcpu))
break;
if (signal_pending(current))
if (kvm_vcpu_check_block(vcpu) < 0)
break;
waited = true;
schedule();
}
finish_wait(&vcpu->wq, &wait);
cur = ktime_get();
out:
trace_kvm_vcpu_wakeup(ktime_to_ns(cur) - ktime_to_ns(start), waited);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_block);
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册