[v5,07/10] Reset the auto-converge counter at every checkpoint.

Commit Message

Rao, Lei April 1, 2021, 7:47 a.m. UTC

From: "Rao, Lei" <[e-mail]>

if we don't reset the auto-converge counter,
it will continue to run with COLO running,
and eventually the system will hang due to the
CPU throttle reaching DEFAULT_MIGRATE_MAX_CPU_THROTTLE.

Signed-off-by: Lei Rao <[e-mail]>
Reviewed-by: Dr. David Alan Gilbert <[e-mail]>
---
 migration/colo.c | 4 ++++
 migration/ram.c  | 9 +++++++++
 migration/ram.h  | 1 +
 3 files changed, 14 insertions(+)

Patch

diff --git a/migration/colo.c b/migration/colo.c
index 1aaf316..723ffb8 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -459,6 +459,10 @@  static int colo_do_checkpoint_transaction(MigrationState *s,
     if (ret < 0) {
         goto out;
     }
+
+    if (migrate_auto_converge()) {
+        mig_throttle_counter_reset();
+    }
     /*
      * Only save VM's live state, which not including device state.
      * TODO: We may need a timeout mechanism to prevent COLO process
diff --git a/migration/ram.c b/migration/ram.c
index 40e7895..c69a8e0 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -652,6 +652,15 @@  static void mig_throttle_guest_down(uint64_t bytes_dirty_period,
     }
 }
 
+void mig_throttle_counter_reset(void)
+{
+    RAMState *rs = ram_state;
+
+    rs->time_last_bitmap_sync = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+    rs->num_dirty_pages_period = 0;
+    rs->bytes_xfer_prev = ram_counters.transferred;
+}
+
 /**
  * xbzrle_cache_zero_page: insert a zero page in the XBZRLE cache
  *
diff --git a/migration/ram.h b/migration/ram.h
index 6378bb3..3f78175 100644
--- a/migration/ram.h
+++ b/migration/ram.h
@@ -50,6 +50,7 @@  bool ramblock_is_ignored(RAMBlock *block);
 int xbzrle_cache_resize(uint64_t new_size, Error **errp);
 uint64_t ram_bytes_remaining(void);
 uint64_t ram_bytes_total(void);
+void mig_throttle_counter_reset(void);
 
 uint64_t ram_pagesize_summary(void);
 int ram_save_queue_pages(const char *rbname, ram_addr_t start, ram_addr_t len);