savevm: New save live migration method: pending

Code just now does (simplified for clarity)

    if (qemu_savevm_state_iterate(s->file) == 1) {
       vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
       qemu_savevm_state_complete(s->file);
    }

Problem here is that qemu_savevm_state_iterate() returns 1 when it
knows that remaining memory to sent takes less than max downtime.

But this means that we could end spending 2x max_downtime, one
downtime in qemu_savevm_iterate, and the other in
qemu_savevm_state_complete.

Changed code to:

    pending_size = qemu_savevm_state_pending(s->file, max_size);
    DPRINTF("pending size %lu max %lu\n", pending_size, max_size);
    if (pending_size >= max_size) {
        ret = qemu_savevm_state_iterate(s->file);
     } else {
        vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
        qemu_savevm_state_complete(s->file);
     }

So what we do is: at current network speed, we calculate the maximum
number of bytes we can sent: max_size.

Then we ask every save_live section how much they have pending.  If
they are less than max_size, we move to complete phase, otherwise we
do an iterate one.

This makes things much simpler, because now individual sections don't
have to caluclate the bandwidth (it was implossible to do right from
there).

Signed-off-by: Juan Quintela <quintela@redhat.com>

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 10 insertions, 39 deletions

diff --git a/block-migration.c b/block-migration.c
index ca4ba3fffb..6acf3e1682 100644
--- a/block-migration.c
+++ b/block-migration.c
@@ -77,9 +77,7 @@ typedef struct BlkMigState {
     int64_t total_sector_sum;
     int prev_progress;
     int bulk_completed;
-    long double total_time;
     long double prev_time_offset;
-    int reads;
 } BlkMigState;
 
 static BlkMigState block_mig_state;
@@ -132,12 +130,6 @@ uint64_t blk_mig_bytes_total(void)
     return sum << BDRV_SECTOR_BITS;
 }
 
-static inline long double compute_read_bwidth(void)
-{
-    assert(block_mig_state.total_time != 0);
-    return (block_mig_state.reads / block_mig_state.total_time) * BLOCK_SIZE;
-}
-
 static int bmds_aio_inflight(BlkMigDevState *bmds, int64_t sector)
 {
     int64_t chunk = sector / (int64_t)BDRV_SECTORS_PER_DIRTY_CHUNK;
@@ -191,8 +183,6 @@ static void blk_mig_read_cb(void *opaque, int ret)
 
     blk->ret = ret;
 
-    block_mig_state.reads++;
-    block_mig_state.total_time += (curr_time - block_mig_state.prev_time_offset);
     block_mig_state.prev_time_offset = curr_time;
 
     QSIMPLEQ_INSERT_TAIL(&block_mig_state.blk_list, blk, entry);
@@ -310,8 +300,6 @@ static void init_blk_migration(QEMUFile *f)
     block_mig_state.total_sector_sum = 0;
     block_mig_state.prev_progress = -1;
     block_mig_state.bulk_completed = 0;
-    block_mig_state.total_time = 0;
-    block_mig_state.reads = 0;
 
     bdrv_iterate(init_blk_migration_it, NULL);
 }
@@ -493,32 +481,6 @@ static int64_t get_remaining_dirty(void)
     return dirty * BLOCK_SIZE;
 }
 
-static int is_stage2_completed(void)
-{
-    int64_t remaining_dirty;
-    long double bwidth;
-
-    if (block_mig_state.bulk_completed == 1) {
-
-        remaining_dirty = get_remaining_dirty();
-        if (remaining_dirty == 0) {
-            return 1;
-        }
-
-        bwidth = compute_read_bwidth();
-
-        if ((remaining_dirty / bwidth) <=
-            migrate_max_downtime()) {
-            /* finish stage2 because we think that we can finish remaining work
-               below max_downtime */
-
-            return 1;
-        }
-    }
-
-    return 0;
-}
-
 static void blk_mig_cleanup(void)
 {
     BlkMigDevState *bmds;
@@ -619,7 +581,7 @@ static int block_save_iterate(QEMUFile *f, void *opaque)
 
     qemu_put_be64(f, BLK_MIG_FLAG_EOS);
 
-    return is_stage2_completed();
+    return 0;
 }
 
 static int block_save_complete(QEMUFile *f, void *opaque)
@@ -659,6 +621,14 @@ static int block_save_complete(QEMUFile *f, void *opaque)
     return 0;
 }
 
+static uint64_t block_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)
+{
+
+    DPRINTF("Enter save live pending  %ld\n", get_remaining_dirty());
+
+    return get_remaining_dirty();
+}
+
 static int block_load(QEMUFile *f, void *opaque, int version_id)
 {
     static int banner_printed;
@@ -755,6 +725,7 @@ SaveVMHandlers savevm_block_handlers = {
     .save_live_setup = block_save_setup,
     .save_live_iterate = block_save_iterate,
     .save_live_complete = block_save_complete,
+    .save_live_pending = block_save_pending,
     .load_state = block_load,
     .cancel = block_migration_cancel,
     .is_active = block_is_active,