[PULL 09/30] migration: Rate limit inside host pages

[Juan Quintela]

From: "Dr. David Alan Gilbert" <address@hidden>

When using hugepages, rate limiting is necessary within each huge
page, since a 1G huge page can take a significant time to send, so
you end up with bursty behaviour.

Fixes: 4c011c37ecb3 ("postcopy: Send whole huge pages")
Reported-by: Lin Ma <address@hidden>
Signed-off-by: Dr. David Alan Gilbert <address@hidden>
Reviewed-by: Juan Quintela <address@hidden>
Reviewed-by: Peter Xu <address@hidden>
Signed-off-by: Juan Quintela <address@hidden>
---
 migration/migration.c  | 57 ++++++++++++++++++++++++------------------
 migration/migration.h  |  1 +
 migration/ram.c        |  2 ++
 migration/trace-events |  4 +--
 4 files changed, 37 insertions(+), 27 deletions(-)

diff --git a/migration/migration.c b/migration/migration.c
index 354ad072fa..27500d09a9 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -3224,6 +3224,37 @@ void migration_consume_urgent_request(void)
     qemu_sem_wait(&migrate_get_current()->rate_limit_sem);
 }
 
+/* Returns true if the rate limiting was broken by an urgent request */
+bool migration_rate_limit(void)
+{
+    int64_t now = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+    MigrationState *s = migrate_get_current();
+
+    bool urgent = false;
+    migration_update_counters(s, now);
+    if (qemu_file_rate_limit(s->to_dst_file)) {
+        /*
+         * Wait for a delay to do rate limiting OR
+         * something urgent to post the semaphore.
+         */
+        int ms = s->iteration_start_time + BUFFER_DELAY - now;
+        trace_migration_rate_limit_pre(ms);
+        if (qemu_sem_timedwait(&s->rate_limit_sem, ms) == 0) {
+            /*
+             * We were woken by one or more urgent things but
+             * the timedwait will have consumed one of them.
+             * The service routine for the urgent wake will dec
+             * the semaphore itself for each item it consumes,
+             * so add this one we just eat back.
+             */
+            qemu_sem_post(&s->rate_limit_sem);
+            urgent = true;
+        }
+        trace_migration_rate_limit_post(urgent);
+    }
+    return urgent;
+}
+
 /*
  * Master migration thread on the source VM.
  * It drives the migration and pumps the data down the outgoing channel.
@@ -3290,8 +3321,6 @@ static void *migration_thread(void *opaque)
     trace_migration_thread_setup_complete();
 
     while (migration_is_active(s)) {
-        int64_t current_time;
-
         if (urgent || !qemu_file_rate_limit(s->to_dst_file)) {
             MigIterateState iter_state = migration_iteration_run(s);
             if (iter_state == MIG_ITERATE_SKIP) {
@@ -3318,29 +3347,7 @@ static void *migration_thread(void *opaque)
             update_iteration_initial_status(s);
         }
 
-        current_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
-
-        migration_update_counters(s, current_time);
-
-        urgent = false;
-        if (qemu_file_rate_limit(s->to_dst_file)) {
-            /* Wait for a delay to do rate limiting OR
-             * something urgent to post the semaphore.
-             */
-            int ms = s->iteration_start_time + BUFFER_DELAY - current_time;
-            trace_migration_thread_ratelimit_pre(ms);
-            if (qemu_sem_timedwait(&s->rate_limit_sem, ms) == 0) {
-                /* We were worken by one or more urgent things but
-                 * the timedwait will have consumed one of them.
-                 * The service routine for the urgent wake will dec
-                 * the semaphore itself for each item it consumes,
-                 * so add this one we just eat back.
-                 */
-                qemu_sem_post(&s->rate_limit_sem);
-                urgent = true;
-            }
-            trace_migration_thread_ratelimit_post(urgent);
-        }
+        urgent = migration_rate_limit();
     }
 
     trace_migration_thread_after_loop();
diff --git a/migration/migration.h b/migration/migration.h
index 79b3dda146..aa9ff6f27b 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -341,5 +341,6 @@ int foreach_not_ignored_block(RAMBlockIterFunc func, void 
*opaque);
 
 void migration_make_urgent_request(void);
 void migration_consume_urgent_request(void);
+bool migration_rate_limit(void);
 
 #endif
diff --git a/migration/ram.c b/migration/ram.c
index 825f47f517..aa6cc7d47a 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -2639,6 +2639,8 @@ static int ram_save_host_page(RAMState *rs, 
PageSearchStatus *pss,
 
         pages += tmppages;
         pss->page++;
+        /* Allow rate limiting to happen in the middle of huge pages */
+        migration_rate_limit();
     } while ((pss->page & (pagesize_bits - 1)) &&
              offset_in_ramblock(pss->block, pss->page << TARGET_PAGE_BITS));
 
diff --git a/migration/trace-events b/migration/trace-events
index 6dee7b5389..2f9129e213 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -138,12 +138,12 @@ migrate_send_rp_recv_bitmap(char *name, int64_t size) 
"block '%s' size 0x%"PRIi6
 migration_completion_file_err(void) ""
 migration_completion_postcopy_end(void) ""
 migration_completion_postcopy_end_after_complete(void) ""
+migration_rate_limit_pre(int ms) "%d ms"
+migration_rate_limit_post(int urgent) "urgent: %d"
 migration_return_path_end_before(void) ""
 migration_return_path_end_after(int rp_error) "%d"
 migration_thread_after_loop(void) ""
 migration_thread_file_err(void) ""
-migration_thread_ratelimit_pre(int ms) "%d ms"
-migration_thread_ratelimit_post(int urgent) "urgent: %d"
 migration_thread_setup_complete(void) ""
 open_return_path_on_source(void) ""
 open_return_path_on_source_continue(void) ""
-- 
2.24.1