This patch adds the necessary KVM specific code to allow KVM to
support the CPU halting and kicking operations needed by the queue
spinlock PV code.
Two KVM guests of 20 CPU cores (2 nodes) were created for performance
testing in one of the following three configurations:
1) Only 1 VM is active
2) Both VMs are active and they share the same 20 physical CPUs
(200% overcommit)
3) Both VMs are active and they shares 30 physical CPUs (10 delicated
and 10 shared - 133% overcommit)
The tests run included the disk workload of the AIM7 benchmark on both
ext4 and xfs RAM disks at 3000 users on a 3.15-rc1 based kernel. The
"ebizzy -m" test was was also run and its performance data were
recorded. With two VMs running, the "idle=poll" kernel option was
added to simulate a busy guest. The entry "unfair + PV qspinlock"
below means that both the unfair lock and PV spinlock configuration
options were turned on.
AIM7 XFS Disk Test (no overcommit)
kernel JPM Real Time Sys Time Usr Time
----- --- --------- -------- --------
PV ticketlock 2489626 7.23 101.08 5.30
qspinlock 2531646 7.11 100.75 5.43
PV qspinlock 2500000 7.20 101.94 5.40
unfair qspinlock 2549575 7.06 99.81 5.35
unfair + PV qspinlock 2486188 7.24 101.55 5.51
AIM7 XFS Disk Test (133% overcommit)
kernel JPM Real Time Sys Time Usr Time
----- --- --------- -------- --------
PV ticketlock 1114551 16.15 220.17 10.75
qspinlock 1159047 15.53 216.60 10.24
PV qspinlock 1170351 15.38 216.16 11.03
unfair qspinlock 1188119 15.15 209.37 10.82
unfair + PV qspinlock 1178782 15.27 211.37 11.25
AIM7 XFS Disk Test (200% overcommit)
kernel JPM Real Time Sys Time Usr Time
----- --- --------- -------- --------
PV ticketlock 587467 30.64 444.95 11.92
qspinlock 593276 30.34 439.39 14.59
PV qspinlock 601403 29.93 426.04 14.49
unfair qspinlock 654070 27.52 400.82 10.86
unfair + PV qspinlock 614334 29.30 393.38 28.56
AIM7 EXT4 Disk Test (no overcommit)
kernel JPM Real Time Sys Time Usr Time
----- --- --------- -------- --------
PV ticketlock 2002225 9.07 105.62 5.43
qspinlock 2006689 8.97 105.65 5.26
PV qspinlock 2002225 8.99 103.19 5.19
unfair qspinlock 1988950 9.05 103.81 5.03
unfair + PV qspinlock 1993355 9.03 107.99 5.68
AIM7 EXT4 Disk Test (133% overcommit)
kernel JPM Real Time Sys Time Usr Time
----- --- --------- -------- --------
PV ticketlock 987383 18.23 221.63 8.89
qspinlock 1050788 17.13 206.87 8.35
PV qspinlock 1058823 17.00 205.22 9.18
unfair qspinlock 1161290 15.50 184.22 8.84
unfair + PV qspinlock 1122894 16.03 195.86 9.34
AIM7 EXT4 Disk Test (200% overcommit)
kernel JPM Real Time Sys Time Usr Time
----- --- --------- -------- --------
PV ticketlock 420757 42.78 565.96 5.84
qspinlock 427452 42.11 543.08 11.12
PV qspinlock 420659 42.79 548.30 10.56
unfair qspinlock 504909 35.65 466.71 5.38
unfair + PV qspinlock 500974 35.93 469.02 6.77
EBIZZY-M Test (no overcommit)
kernel Rec/s Real Time Sys Time Usr Time
----- ----- --------- -------- --------
PV ticketlock 1230 10.00 88.34 1.42
qspinlock 1212 10.00 68.25 1.47
PV qspinlock 1265 10.00 91.50 1.41
unfair qspinlock 1304 10.00 77.94 1.49
unfair + PV qspinlock 1445 10.00 75.45 1.68
EBIZZY-M Test (133% overcommit)
kernel Rec/s Real Time Sys Time Usr Time
----- ----- --------- -------- --------
PV ticketlock 467 10.00 88.16 0.73
qspinlock 463 10.00 89.44 0.78
PV qspinlock 441 10.00 95.10 0.74
unfair qspinlock 1233 10.00 35.76 1.76
unfair + PV qspinlock 1555 10.00 32.12 1.96
EBIZZY-M Test (200% overcommit)
kernel Rec/s Real Time Sys Time Usr Time
----- ----- --------- -------- --------
PV ticketlock 263 10.00 84.48 4.27
qspinlock 226 10.00 87.74 2.02
PV qspinlock 253 10.00 98.28 2.63
unfair qspinlock 338 10.00 61.15 1.68
unfair + PV qspinlock 346 10.00 60.47 3.31
Raghavendra KT had done some performance testing on this patch with
the following results:
Overall we are seeing good improvement for pv-unfair version.
System: 32 cpu sandybridge with HT on (4 node with 32 GB each)
Guest : 8GB with 16 vcpu/VM.
Average was taken over 8-10 data points.
Base = 3.15-rc2 with PRAVIRT_SPINLOCK = y
A = 3.15-rc2 + qspinlock v9 patch with QUEUE_SPINLOCK = y
PRAVIRT_SPINLOCK = y PARAVIRT_UNFAIR_LOCKS = y (unfair lock)
B = 3.15-rc2 + qspinlock v9 patch with QUEUE_SPINLOCK = y
PRAVIRT_SPINLOCK = n PARAVIRT_UNFAIR_LOCKS = n
(queue spinlock without paravirt)
C = 3.15-rc2 + qspinlock v9 patch with QUEUE_SPINLOCK = y
PRAVIRT_SPINLOCK = y PARAVIRT_UNFAIR_LOCKS = n
(queue spinlock with paravirt)
Ebizzy %improvements
====================
overcommit A B C
0.5x 4.4265 2.0611 1.5824
1.0x 0.9015 -7.7828 4.5443
1.5x 46.1162 -2.9845 -3.5046
2.0x 99.8150 -2.7116 4.7461
Dbench %improvements
====================
overcommit A B C
0.5x 3.2617 3.5436 2.5676
1.0x 0.6302 2.2342 5.2201
1.5x 5.0027 4.8275 3.8375
2.0x 23.8242 4.5782 12.6067
Absolute values of base results: (overcommit, value, stdev)
Ebizzy ( records / sec with 120 sec run)
0.5x 20941.8750 (2%)
1.0x 17623.8750 (5%)
1.5x 5874.7778 (15%)
2.0x 3581.8750 (7%)
Dbench (throughput in MB/sec)
0.5x 10009.6610 (5%)
1.0x 6583.0538 (1%)
1.5x 3991.9622 (4%)
2.0x 2527.0613 (2.5%)
Signed-off-by: Waiman Long <Waiman.Long@xxxxxx>
Tested-by: Raghavendra K T <raghavendra.kt@xxxxxxxxxxxxxxxxxx>
---
arch/x86/kernel/kvm.c | 135 +++++++++++++++++++++++++++++++++++++++++++++++++
kernel/Kconfig.locks | 2 +-
2 files changed, 136 insertions(+), 1 deletions(-)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 7ab8ab3..eef427b 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -567,6 +567,7 @@ static void kvm_kick_cpu(int cpu)
kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid);
}
+#ifndef CONFIG_QUEUE_SPINLOCK
enum kvm_contention_stat {
TAKEN_SLOW,
TAKEN_SLOW_PICKUP,
@@ -794,6 +795,134 @@ static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket)
}
}
}
+#else /* !CONFIG_QUEUE_SPINLOCK */
+
+#ifdef CONFIG_KVM_DEBUG_FS
+static struct dentry *d_spin_debug;
+static struct dentry *d_kvm_debug;
+static u32 kick_nohlt_stats; /* Kick but not halt count */
+static u32 halt_qhead_stats; /* Queue head halting count */
+static u32 halt_qnode_stats; /* Queue node halting count */
+static u32 halt_abort_stats; /* Halting abort count */
+static u32 wake_kick_stats; /* Wakeup by kicking count */
+static u32 wake_spur_stats; /* Spurious wakeup count */
+static u64 time_blocked; /* Total blocking time */
+
+static int __init kvm_spinlock_debugfs(void)
+{
+ d_kvm_debug = debugfs_create_dir("kvm-guest", NULL);
+ if (!d_kvm_debug) {
+ printk(KERN_WARNING
+ "Could not create 'kvm' debugfs directory\n");
+ return -ENOMEM;
+ }
+ d_spin_debug = debugfs_create_dir("spinlocks", d_kvm_debug);
+
+ debugfs_create_u32("kick_nohlt_stats",
+ 0644, d_spin_debug, &kick_nohlt_stats);
+ debugfs_create_u32("halt_qhead_stats",
+ 0644, d_spin_debug, &halt_qhead_stats);
+ debugfs_create_u32("halt_qnode_stats",
+ 0644, d_spin_debug, &halt_qnode_stats);
+ debugfs_create_u32("halt_abort_stats",
+ 0644, d_spin_debug, &halt_abort_stats);
+ debugfs_create_u32("wake_kick_stats",
+ 0644, d_spin_debug, &wake_kick_stats);
+ debugfs_create_u32("wake_spur_stats",
+ 0644, d_spin_debug, &wake_spur_stats);
+ debugfs_create_u64("time_blocked",
+ 0644, d_spin_debug, &time_blocked);
+ return 0;
+}
+
+static inline void kvm_halt_stats(enum pv_lock_stats type)
+{
+ if (type == PV_HALT_QHEAD)
+ add_smp(&halt_qhead_stats, 1);
+ else if (type == PV_HALT_QNODE)
+ add_smp(&halt_qnode_stats, 1);
+ else /* type == PV_HALT_ABORT */
+ add_smp(&halt_abort_stats, 1);
+}
+
+static inline void kvm_lock_stats(enum pv_lock_stats type)
+{
+ if (type == PV_WAKE_KICKED)
+ add_smp(&wake_kick_stats, 1);
+ else if (type == PV_WAKE_SPURIOUS)
+ add_smp(&wake_spur_stats, 1);
+ else /* type == PV_KICK_NOHALT */
+ add_smp(&kick_nohlt_stats, 1);
+}
+
+static inline u64 spin_time_start(void)
+{
+ return sched_clock();
+}
+
+static inline void spin_time_accum_blocked(u64 start)
+{
+ u64 delta;
+
+ delta = sched_clock() - start;
+ add_smp(&time_blocked, delta);
+}
+
+fs_initcall(kvm_spinlock_debugfs);
+
+#else /* CONFIG_KVM_DEBUG_FS */
+static inline void kvm_halt_stats(enum pv_lock_stats type)
+{
+}
+
+static inline void kvm_lock_stats(enum pv_lock_stats type)
+{
+}
+
+static inline u64 spin_time_start(void)
+{
+ return 0;
+}
+
+static inline void spin_time_accum_blocked(u64 start)
+{
+}
+#endif /* CONFIG_KVM_DEBUG_FS */
+
+/*
+ * Halt the current CPU & release it back to the host
+ */
+static void kvm_halt_cpu(enum pv_lock_stats type, s8 *state, s8 sval)
+{
+ unsigned long flags;
+ u64 start;
+
+ if (in_nmi())
+ return;
+
+ /*
+ * Make sure an interrupt handler can't upset things in a
+ * partially setup state.
+ */
+ local_irq_save(flags);
+ /*
+ * Don't halt if the CPU state has been changed.
+ */
+ if (ACCESS_ONCE(*state) != sval) {
+ kvm_halt_stats(PV_HALT_ABORT);
+ goto out;
+ }
+ start = spin_time_start();
+ kvm_halt_stats(type);
+ if (arch_irqs_disabled_flags(flags))
+ halt();
+ else
+ safe_halt();
+ spin_time_accum_blocked(start);
+out:
+ local_irq_restore(flags);
+}
+#endif /* !CONFIG_QUEUE_SPINLOCK */
/*
* Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
@@ -806,8 +935,14 @@ void __init kvm_spinlock_init(void)
if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
return;
+#ifdef CONFIG_QUEUE_SPINLOCK
+ pv_lock_ops.kick_cpu = kvm_kick_cpu;
+ pv_lock_ops.halt_cpu = kvm_halt_cpu;
+ pv_lock_ops.lockstat = kvm_lock_stats;
+#else
pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
pv_lock_ops.unlock_kick = kvm_unlock_kick;
+#endif
}
static __init int kvm_spinlock_init_jump(void)
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index f185584..a70fdeb 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -229,4 +229,4 @@ config ARCH_USE_QUEUE_SPINLOCK
config QUEUE_SPINLOCK
def_bool y if ARCH_USE_QUEUE_SPINLOCK
- depends on SMP && !PARAVIRT_SPINLOCKS
+ depends on SMP && (!PARAVIRT_SPINLOCKS || !XEN)
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
