Merge remote-tracking branch 'remotes/juanquintela/tags/migration/20150930' into staging

migration/next for 20150930

# gpg: Signature made Wed 30 Sep 2015 09:24:02 BST using RSA key ID 5872D723
# gpg: Good signature from "Juan Quintela <quintela@redhat.com>"
# gpg:                 aka "Juan Quintela <quintela@trasno.org>"

* remotes/juanquintela/tags/migration/20150930:
  migration: Disambiguate MAX_THROTTLE
  qmp/hmp: Add throttle ratio to query-migrate and info migrate
  migration: Dynamic cpu throttling for auto-converge
  migration: Parameters for auto-converge cpu throttling
  cpu: Provide vcpu throttling interface
  migration: yet more possible state transitions

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

2 files changed, 85 insertions, 61 deletions

diff --git a/migration/migration.c b/migration/migration.c
index e48dd13720..b7de9b7b3f 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -29,8 +29,9 @@
 #include "trace.h"
 #include "qapi/util.h"
 #include "qapi-event.h"
+#include "qom/cpu.h"
 
-#define MAX_THROTTLE  (32 << 20)      /* Migration speed throttling */
+#define MAX_THROTTLE  (32 << 20)      /* Migration transfer speed throttling */
 
 /* Amount of time to allocate to each "chunk" of bandwidth-throttled
  * data. */
@@ -44,6 +45,9 @@
 #define DEFAULT_MIGRATE_DECOMPRESS_THREAD_COUNT 2
 /*0: means nocompress, 1: best speed, ... 9: best compress ratio */
 #define DEFAULT_MIGRATE_COMPRESS_LEVEL 1
+/* Define default autoconverge cpu throttle migration parameters */
+#define DEFAULT_MIGRATE_X_CPU_THROTTLE_INITIAL 20
+#define DEFAULT_MIGRATE_X_CPU_THROTTLE_INCREMENT 10
 
 /* Migration XBZRLE default cache size */
 #define DEFAULT_MIGRATE_CACHE_SIZE (64 * 1024 * 1024)
@@ -71,6 +75,10 @@ MigrationState *migrate_get_current(void)
                 DEFAULT_MIGRATE_COMPRESS_THREAD_COUNT,
         .parameters[MIGRATION_PARAMETER_DECOMPRESS_THREADS] =
                 DEFAULT_MIGRATE_DECOMPRESS_THREAD_COUNT,
+        .parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INITIAL] =
+                DEFAULT_MIGRATE_X_CPU_THROTTLE_INITIAL,
+        .parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INCREMENT] =
+                DEFAULT_MIGRATE_X_CPU_THROTTLE_INCREMENT,
     };
 
     return &current_migration;
@@ -372,6 +380,10 @@ MigrationParameters *qmp_query_migrate_parameters(Error **errp)
             s->parameters[MIGRATION_PARAMETER_COMPRESS_THREADS];
     params->decompress_threads =
             s->parameters[MIGRATION_PARAMETER_DECOMPRESS_THREADS];
+    params->x_cpu_throttle_initial =
+            s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INITIAL];
+    params->x_cpu_throttle_increment =
+            s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INCREMENT];
 
     return params;
 }
@@ -435,6 +447,11 @@ MigrationInfo *qmp_query_migrate(Error **errp)
             info->disk->total = blk_mig_bytes_total();
         }
 
+        if (cpu_throttle_active()) {
+            info->has_x_cpu_throttle_percentage = true;
+            info->x_cpu_throttle_percentage = cpu_throttle_get_percentage();
+        }
+
         get_xbzrle_cache_stats(info);
         break;
     case MIGRATION_STATUS_COMPLETED:
@@ -494,7 +511,11 @@ void qmp_migrate_set_parameters(bool has_compress_level,
                                 bool has_compress_threads,
                                 int64_t compress_threads,
                                 bool has_decompress_threads,
-                                int64_t decompress_threads, Error **errp)
+                                int64_t decompress_threads,
+                                bool has_x_cpu_throttle_initial,
+                                int64_t x_cpu_throttle_initial,
+                                bool has_x_cpu_throttle_increment,
+                                int64_t x_cpu_throttle_increment, Error **errp)
 {
     MigrationState *s = migrate_get_current();
 
@@ -517,6 +538,18 @@ void qmp_migrate_set_parameters(bool has_compress_level,
                    "is invalid, it should be in the range of 1 to 255");
         return;
     }
+    if (has_x_cpu_throttle_initial &&
+            (x_cpu_throttle_initial < 1 || x_cpu_throttle_initial > 99)) {
+        error_setg(errp, QERR_INVALID_PARAMETER_VALUE,
+                   "x_cpu_throttle_initial",
+                   "an integer in the range of 1 to 99");
+    }
+    if (has_x_cpu_throttle_increment &&
+            (x_cpu_throttle_increment < 1 || x_cpu_throttle_increment > 99)) {
+        error_setg(errp, QERR_INVALID_PARAMETER_VALUE,
+                   "x_cpu_throttle_increment",
+                   "an integer in the range of 1 to 99");
+    }
 
     if (has_compress_level) {
         s->parameters[MIGRATION_PARAMETER_COMPRESS_LEVEL] = compress_level;
@@ -528,6 +561,15 @@ void qmp_migrate_set_parameters(bool has_compress_level,
         s->parameters[MIGRATION_PARAMETER_DECOMPRESS_THREADS] =
                                                     decompress_threads;
     }
+    if (has_x_cpu_throttle_initial) {
+        s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INITIAL] =
+                                                    x_cpu_throttle_initial;
+    }
+
+    if (has_x_cpu_throttle_increment) {
+        s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INCREMENT] =
+                                                    x_cpu_throttle_increment;
+    }
 }
 
 /* shared migration helpers */
@@ -643,6 +685,10 @@ static MigrationState *migrate_init(const MigrationParams *params)
             s->parameters[MIGRATION_PARAMETER_COMPRESS_THREADS];
     int decompress_thread_count =
             s->parameters[MIGRATION_PARAMETER_DECOMPRESS_THREADS];
+    int x_cpu_throttle_initial =
+            s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INITIAL];
+    int x_cpu_throttle_increment =
+            s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INCREMENT];
 
     memcpy(enabled_capabilities, s->enabled_capabilities,
            sizeof(enabled_capabilities));
@@ -658,6 +704,10 @@ static MigrationState *migrate_init(const MigrationParams *params)
                compress_thread_count;
     s->parameters[MIGRATION_PARAMETER_DECOMPRESS_THREADS] =
                decompress_thread_count;
+    s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INITIAL] =
+                x_cpu_throttle_initial;
+    s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INCREMENT] =
+                x_cpu_throttle_increment;
     s->bandwidth_limit = bandwidth_limit;
     migrate_set_state(s, MIGRATION_STATUS_NONE, MIGRATION_STATUS_SETUP);
 
@@ -1026,6 +1076,9 @@ static void *migration_thread(void *opaque)
         }
     }
 
+    /* If we enabled cpu throttling for auto-converge, turn it off. */
+    cpu_throttle_stop();
+
     qemu_mutex_lock_iothread();
     if (s->state == MIGRATION_STATUS_COMPLETED) {
         int64_t end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
diff --git a/migration/ram.c b/migration/ram.c
index 5187637d45..2d1d0b99e4 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -47,9 +47,7 @@
     do { } while (0)
 #endif
 
-static bool mig_throttle_on;
 static int dirty_rate_high_cnt;
-static void check_guest_throttling(void);
 
 static uint64_t bitmap_sync_count;
 
@@ -407,6 +405,29 @@ static size_t save_page_header(QEMUFile *f, RAMBlock *block, ram_addr_t offset)
     return size;
 }
 
+/* Reduce amount of guest cpu execution to hopefully slow down memory writes.
+ * If guest dirty memory rate is reduced below the rate at which we can
+ * transfer pages to the destination then we should be able to complete
+ * migration. Some workloads dirty memory way too fast and will not effectively
+ * converge, even with auto-converge.
+ */
+static void mig_throttle_guest_down(void)
+{
+    MigrationState *s = migrate_get_current();
+    uint64_t pct_initial =
+            s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INITIAL];
+    uint64_t pct_icrement =
+            s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INCREMENT];
+
+    /* We have not started throttling yet. Let's start it. */
+    if (!cpu_throttle_active()) {
+        cpu_throttle_set(pct_initial);
+    } else {
+        /* Throttling already on, just increase the rate */
+        cpu_throttle_set(cpu_throttle_get_percentage() + pct_icrement);
+    }
+}
+
 /* Update the xbzrle cache to reflect a page that's been sent as all 0.
  * The important thing is that a stale (not-yet-0'd) page be replaced
  * by the new data.
@@ -599,21 +620,21 @@ static void migration_bitmap_sync(void)
             /* The following detection logic can be refined later. For now:
                Check to see if the dirtied bytes is 50% more than the approx.
                amount of bytes that just got transferred since the last time we
-               were in this routine. If that happens >N times (for now N==4)
-               we turn on the throttle down logic */
+               were in this routine. If that happens twice, start or increase
+               throttling */
             bytes_xfer_now = ram_bytes_transferred();
+
             if (s->dirty_pages_rate &&
                (num_dirty_pages_period * TARGET_PAGE_SIZE >
                    (bytes_xfer_now - bytes_xfer_prev)/2) &&
-               (dirty_rate_high_cnt++ > 4)) {
+               (dirty_rate_high_cnt++ >= 2)) {
                     trace_migration_throttle();
-                    mig_throttle_on = true;
                     dirty_rate_high_cnt = 0;
+                    mig_throttle_guest_down();
              }
              bytes_xfer_prev = bytes_xfer_now;
-        } else {
-             mig_throttle_on = false;
         }
+
         if (migrate_use_xbzrle()) {
             if (iterations_prev != acct_info.iterations) {
                 acct_info.xbzrle_cache_miss_rate =
@@ -1146,7 +1167,6 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
     RAMBlock *block;
     int64_t ram_bitmap_pages; /* Size of bitmap in pages, including gaps */
 
-    mig_throttle_on = false;
     dirty_rate_high_cnt = 0;
     bitmap_sync_count = 0;
     migration_bitmap_sync_init();
@@ -1251,7 +1271,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
         }
         pages_sent += pages;
         acct_info.iterations++;
-        check_guest_throttling();
+
         /* we want to check in the 1st loop, just in case it was the 1st time
            and we had to sync the dirty bitmap.
            qemu_get_clock_ns() is a bit expensive, so we only check each some
@@ -1664,52 +1684,3 @@ void ram_mig_init(void)
     qemu_mutex_init(&XBZRLE.lock);
     register_savevm_live(NULL, "ram", 0, 4, &savevm_ram_handlers, NULL);
 }
-/* Stub function that's gets run on the vcpu when its brought out of the
-   VM to run inside qemu via async_run_on_cpu()*/
-
-static void mig_sleep_cpu(void *opq)
-{
-    qemu_mutex_unlock_iothread();
-    g_usleep(30*1000);
-    qemu_mutex_lock_iothread();
-}
-
-/* To reduce the dirty rate explicitly disallow the VCPUs from spending
-   much time in the VM. The migration thread will try to catchup.
-   Workload will experience a performance drop.
-*/
-static void mig_throttle_guest_down(void)
-{
-    CPUState *cpu;
-
-    qemu_mutex_lock_iothread();
-    CPU_FOREACH(cpu) {
-        async_run_on_cpu(cpu, mig_sleep_cpu, NULL);
-    }
-    qemu_mutex_unlock_iothread();
-}
-
-static void check_guest_throttling(void)
-{
-    static int64_t t0;
-    int64_t        t1;
-
-    if (!mig_throttle_on) {
-        return;
-    }
-
-    if (!t0)  {
-        t0 = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
-        return;
-    }
-
-    t1 = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
-
-    /* If it has been more than 40 ms since the last time the guest
-     * was throttled then do it again.
-     */
-    if (40 < (t1-t0)/1000000) {
-        mig_throttle_guest_down();
-        t0 = t1;
-    }
-}