softmmu/dirtylimit: Implement virtual CPU throttle

Setup a negative feedback system when vCPU thread
handling KVM_EXIT_DIRTY_RING_FULL exit by introducing
throttle_us_per_full field in struct CPUState. Sleep
throttle_us_per_full microseconds to throttle vCPU
if dirtylimit is in service.

Signed-off-by: Hyman Huang(黄勇) <huangy81@chinatelecom.cn>
Reviewed-by: Peter Xu <peterx@redhat.com>
Message-Id: <977e808e03a1cef5151cae75984658b6821be618.1656177590.git.huangy81@chinatelecom.cn>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

2 files changed, 298 insertions, 0 deletions

diff --git a/softmmu/dirtylimit.c b/softmmu/dirtylimit.c
index ebdc064c9d..e5a4f970bd 100644
--- a/softmmu/dirtylimit.c
+++ b/softmmu/dirtylimit.c
@@ -18,6 +18,26 @@
 #include "sysemu/dirtylimit.h"
 #include "exec/memory.h"
 #include "hw/boards.h"
+#include "sysemu/kvm.h"
+#include "trace.h"
+
+/*
+ * Dirtylimit stop working if dirty page rate error
+ * value less than DIRTYLIMIT_TOLERANCE_RANGE
+ */
+#define DIRTYLIMIT_TOLERANCE_RANGE  25  /* MB/s */
+/*
+ * Plus or minus vcpu sleep time linearly if dirty
+ * page rate error value percentage over
+ * DIRTYLIMIT_LINEAR_ADJUSTMENT_PCT.
+ * Otherwise, plus or minus a fixed vcpu sleep time.
+ */
+#define DIRTYLIMIT_LINEAR_ADJUSTMENT_PCT     50
+/*
+ * Max vcpu sleep time percentage during a cycle
+ * composed of dirty ring full and sleep time.
+ */
+#define DIRTYLIMIT_THROTTLE_PCT_MAX 99
 
 struct {
     VcpuStat stat;
@@ -25,6 +45,30 @@ struct {
     QemuThread thread;
 } *vcpu_dirty_rate_stat;
 
+typedef struct VcpuDirtyLimitState {
+    int cpu_index;
+    bool enabled;
+    /*
+     * Quota dirty page rate, unit is MB/s
+     * zero if not enabled.
+     */
+    uint64_t quota;
+} VcpuDirtyLimitState;
+
+struct {
+    VcpuDirtyLimitState *states;
+    /* Max cpus number configured by user */
+    int max_cpus;
+    /* Number of vcpu under dirtylimit */
+    int limited_nvcpu;
+} *dirtylimit_state;
+
+/* protect dirtylimit_state */
+static QemuMutex dirtylimit_mutex;
+
+/* dirtylimit thread quit if dirtylimit_quit is true */
+static bool dirtylimit_quit;
+
 static void vcpu_dirty_rate_stat_collect(void)
 {
     VcpuStat stat;
@@ -54,6 +98,9 @@ static void *vcpu_dirty_rate_stat_thread(void *opaque)
 
     while (qatomic_read(&vcpu_dirty_rate_stat->running)) {
         vcpu_dirty_rate_stat_collect();
+        if (dirtylimit_in_service()) {
+            dirtylimit_process();
+        }
     }
 
     /* stop log sync */
@@ -86,9 +133,11 @@ void vcpu_dirty_rate_stat_start(void)
 void vcpu_dirty_rate_stat_stop(void)
 {
     qatomic_set(&vcpu_dirty_rate_stat->running, 0);
+    dirtylimit_state_unlock();
     qemu_mutex_unlock_iothread();
     qemu_thread_join(&vcpu_dirty_rate_stat->thread);
     qemu_mutex_lock_iothread();
+    dirtylimit_state_lock();
 }
 
 void vcpu_dirty_rate_stat_initialize(void)
@@ -114,3 +163,245 @@ void vcpu_dirty_rate_stat_finalize(void)
     free(vcpu_dirty_rate_stat);
     vcpu_dirty_rate_stat = NULL;
 }
+
+void dirtylimit_state_lock(void)
+{
+    qemu_mutex_lock(&dirtylimit_mutex);
+}
+
+void dirtylimit_state_unlock(void)
+{
+    qemu_mutex_unlock(&dirtylimit_mutex);
+}
+
+static void
+__attribute__((__constructor__)) dirtylimit_mutex_init(void)
+{
+    qemu_mutex_init(&dirtylimit_mutex);
+}
+
+static inline VcpuDirtyLimitState *dirtylimit_vcpu_get_state(int cpu_index)
+{
+    return &dirtylimit_state->states[cpu_index];
+}
+
+void dirtylimit_state_initialize(void)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+    int max_cpus = ms->smp.max_cpus;
+    int i;
+
+    dirtylimit_state = g_malloc0(sizeof(*dirtylimit_state));
+
+    dirtylimit_state->states =
+            g_malloc0(sizeof(VcpuDirtyLimitState) * max_cpus);
+
+    for (i = 0; i < max_cpus; i++) {
+        dirtylimit_state->states[i].cpu_index = i;
+    }
+
+    dirtylimit_state->max_cpus = max_cpus;
+    trace_dirtylimit_state_initialize(max_cpus);
+}
+
+void dirtylimit_state_finalize(void)
+{
+    free(dirtylimit_state->states);
+    dirtylimit_state->states = NULL;
+
+    free(dirtylimit_state);
+    dirtylimit_state = NULL;
+
+    trace_dirtylimit_state_finalize();
+}
+
+bool dirtylimit_in_service(void)
+{
+    return !!dirtylimit_state;
+}
+
+bool dirtylimit_vcpu_index_valid(int cpu_index)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+
+    return !(cpu_index < 0 ||
+             cpu_index >= ms->smp.max_cpus);
+}
+
+static inline int64_t dirtylimit_dirty_ring_full_time(uint64_t dirtyrate)
+{
+    static uint64_t max_dirtyrate;
+    uint32_t dirty_ring_size = kvm_dirty_ring_size();
+    uint64_t dirty_ring_size_meory_MB =
+        dirty_ring_size * TARGET_PAGE_SIZE >> 20;
+
+    if (max_dirtyrate < dirtyrate) {
+        max_dirtyrate = dirtyrate;
+    }
+
+    return dirty_ring_size_meory_MB * 1000000 / max_dirtyrate;
+}
+
+static inline bool dirtylimit_done(uint64_t quota,
+                                   uint64_t current)
+{
+    uint64_t min, max;
+
+    min = MIN(quota, current);
+    max = MAX(quota, current);
+
+    return ((max - min) <= DIRTYLIMIT_TOLERANCE_RANGE) ? true : false;
+}
+
+static inline bool
+dirtylimit_need_linear_adjustment(uint64_t quota,
+                                  uint64_t current)
+{
+    uint64_t min, max;
+
+    min = MIN(quota, current);
+    max = MAX(quota, current);
+
+    return ((max - min) * 100 / max) > DIRTYLIMIT_LINEAR_ADJUSTMENT_PCT;
+}
+
+static void dirtylimit_set_throttle(CPUState *cpu,
+                                    uint64_t quota,
+                                    uint64_t current)
+{
+    int64_t ring_full_time_us = 0;
+    uint64_t sleep_pct = 0;
+    uint64_t throttle_us = 0;
+
+    if (current == 0) {
+        cpu->throttle_us_per_full = 0;
+        return;
+    }
+
+    ring_full_time_us = dirtylimit_dirty_ring_full_time(current);
+
+    if (dirtylimit_need_linear_adjustment(quota, current)) {
+        if (quota < current) {
+            sleep_pct = (current - quota) * 100 / current;
+            throttle_us =
+                ring_full_time_us * sleep_pct / (double)(100 - sleep_pct);
+            cpu->throttle_us_per_full += throttle_us;
+        } else {
+            sleep_pct = (quota - current) * 100 / quota;
+            throttle_us =
+                ring_full_time_us * sleep_pct / (double)(100 - sleep_pct);
+            cpu->throttle_us_per_full -= throttle_us;
+        }
+
+        trace_dirtylimit_throttle_pct(cpu->cpu_index,
+                                      sleep_pct,
+                                      throttle_us);
+    } else {
+        if (quota < current) {
+            cpu->throttle_us_per_full += ring_full_time_us / 10;
+        } else {
+            cpu->throttle_us_per_full -= ring_full_time_us / 10;
+        }
+    }
+
+    /*
+     * TODO: in the big kvm_dirty_ring_size case (eg: 65536, or other scenario),
+     *       current dirty page rate may never reach the quota, we should stop
+     *       increasing sleep time?
+     */
+    cpu->throttle_us_per_full = MIN(cpu->throttle_us_per_full,
+        ring_full_time_us * DIRTYLIMIT_THROTTLE_PCT_MAX);
+
+    cpu->throttle_us_per_full = MAX(cpu->throttle_us_per_full, 0);
+}
+
+static void dirtylimit_adjust_throttle(CPUState *cpu)
+{
+    uint64_t quota = 0;
+    uint64_t current = 0;
+    int cpu_index = cpu->cpu_index;
+
+    quota = dirtylimit_vcpu_get_state(cpu_index)->quota;
+    current = vcpu_dirty_rate_get(cpu_index);
+
+    if (!dirtylimit_done(quota, current)) {
+        dirtylimit_set_throttle(cpu, quota, current);
+    }
+
+    return;
+}
+
+void dirtylimit_process(void)
+{
+    CPUState *cpu;
+
+    if (!qatomic_read(&dirtylimit_quit)) {
+        dirtylimit_state_lock();
+
+        if (!dirtylimit_in_service()) {
+            dirtylimit_state_unlock();
+            return;
+        }
+
+        CPU_FOREACH(cpu) {
+            if (!dirtylimit_vcpu_get_state(cpu->cpu_index)->enabled) {
+                continue;
+            }
+            dirtylimit_adjust_throttle(cpu);
+        }
+        dirtylimit_state_unlock();
+    }
+}
+
+void dirtylimit_change(bool start)
+{
+    if (start) {
+        qatomic_set(&dirtylimit_quit, 0);
+    } else {
+        qatomic_set(&dirtylimit_quit, 1);
+    }
+}
+
+void dirtylimit_set_vcpu(int cpu_index,
+                         uint64_t quota,
+                         bool enable)
+{
+    trace_dirtylimit_set_vcpu(cpu_index, quota);
+
+    if (enable) {
+        dirtylimit_state->states[cpu_index].quota = quota;
+        if (!dirtylimit_vcpu_get_state(cpu_index)->enabled) {
+            dirtylimit_state->limited_nvcpu++;
+        }
+    } else {
+        dirtylimit_state->states[cpu_index].quota = 0;
+        if (dirtylimit_state->states[cpu_index].enabled) {
+            dirtylimit_state->limited_nvcpu--;
+        }
+    }
+
+    dirtylimit_state->states[cpu_index].enabled = enable;
+}
+
+void dirtylimit_set_all(uint64_t quota,
+                        bool enable)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+    int max_cpus = ms->smp.max_cpus;
+    int i;
+
+    for (i = 0; i < max_cpus; i++) {
+        dirtylimit_set_vcpu(i, quota, enable);
+    }
+}
+
+void dirtylimit_vcpu_execute(CPUState *cpu)
+{
+    if (dirtylimit_in_service() &&
+        dirtylimit_vcpu_get_state(cpu->cpu_index)->enabled &&
+        cpu->throttle_us_per_full) {
+        trace_dirtylimit_vcpu_execute(cpu->cpu_index,
+                cpu->throttle_us_per_full);
+        usleep(cpu->throttle_us_per_full);
+    }
+}
diff --git a/softmmu/trace-events b/softmmu/trace-events
index 9c88887b3c..22606dc27b 100644
--- a/softmmu/trace-events
+++ b/softmmu/trace-events
@@ -31,3 +31,10 @@ runstate_set(int current_state, const char *current_state_str, int new_state, co
 system_wakeup_request(int reason) "reason=%d"
 qemu_system_shutdown_request(int reason) "reason=%d"
 qemu_system_powerdown_request(void) ""
+
+#dirtylimit.c
+dirtylimit_state_initialize(int max_cpus) "dirtylimit state initialize: max cpus %d"
+dirtylimit_state_finalize(void)
+dirtylimit_throttle_pct(int cpu_index, uint64_t pct, int64_t time_us) "CPU[%d] throttle percent: %" PRIu64 ", throttle adjust time %"PRIi64 " us"
+dirtylimit_set_vcpu(int cpu_index, uint64_t quota) "CPU[%d] set dirty page rate limit %"PRIu64
+dirtylimit_vcpu_execute(int cpu_index, int64_t sleep_time_us) "CPU[%d] sleep %"PRIi64 " us"