[Qemu-devel] [PATCH 03/11] Improve accuracy of block migration bandwidth calculation

[Kevin Wolf <kwolf@redhat.com>]

From: Avishay Traeger <AVISHAY@il.ibm.com>

block_mig_state.total_time is currently the sum of the read request
latencies.  This is not very accurate because block migration uses aio and
so several requests can be submitted at once.  Bandwidth should be computed
with wall-clock time, not by adding the latencies.  In this case,
"total_time" has a higher value than it should, and so the computed
bandwidth is lower than it is in reality.  This means that migration can
take longer than it needs to.
However, we don't want to use pure wall-clock time here.  We are computing
bandwidth in the asynchronous phase, where the migration repeatedly wakes
up and sends some aio requests.  The computed bandwidth will be used for
synchronous transfer.

Signed-off-by: Avishay Traeger <avishay@il.ibm.com>
Reviewed-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 block-migration.c |   23 +++++++++++------------
 1 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/block-migration.c b/block-migration.c
index 576e55a..8d06a23 100644
--- a/block-migration.c
+++ b/block-migration.c
@@ -62,7 +62,6 @@ typedef struct BlkMigBlock {
     QEMUIOVector qiov;
     BlockDriverAIOCB *aiocb;
     int ret;
-    int64_t time;
     QSIMPLEQ_ENTRY(BlkMigBlock) entry;
 } BlkMigBlock;
 
@@ -78,6 +77,7 @@ typedef struct BlkMigState {
     int prev_progress;
     int bulk_completed;
     long double total_time;
+    long double prev_time_offset;
     int reads;
 } BlkMigState;
 
@@ -131,12 +131,6 @@ uint64_t blk_mig_bytes_total(void)
     return sum << BDRV_SECTOR_BITS;
 }
 
-static inline void add_avg_read_time(int64_t time)
-{
-    block_mig_state.reads++;
-    block_mig_state.total_time += time;
-}
-
 static inline long double compute_read_bwidth(void)
 {
     assert(block_mig_state.total_time != 0);
@@ -191,13 +185,14 @@ static void alloc_aio_bitmap(BlkMigDevState *bmds)
 
 static void blk_mig_read_cb(void *opaque, int ret)
 {
+    long double curr_time = qemu_get_clock_ns(rt_clock);
     BlkMigBlock *blk = opaque;
 
     blk->ret = ret;
 
-    blk->time = qemu_get_clock_ns(rt_clock) - blk->time;
-
-    add_avg_read_time(blk->time);
+    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);
     bmds_set_aio_inflight(blk->bmds, blk->sector, blk->nr_sectors, 0);
@@ -250,7 +245,9 @@ static int mig_save_device_bulk(Monitor *mon, QEMUFile *f,
     blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE;
     qemu_iovec_init_external(&blk->qiov, &blk->iov, 1);
 
-    blk->time = qemu_get_clock_ns(rt_clock);
+    if (block_mig_state.submitted == 0) {
+        block_mig_state.prev_time_offset = qemu_get_clock_ns(rt_clock);
+    }
 
     blk->aiocb = bdrv_aio_readv(bs, cur_sector, &blk->qiov,
                                 nr_sectors, blk_mig_read_cb, blk);
@@ -409,7 +406,9 @@ static int mig_save_device_dirty(Monitor *mon, QEMUFile *f,
                 blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE;
                 qemu_iovec_init_external(&blk->qiov, &blk->iov, 1);
 
-                blk->time = qemu_get_clock_ns(rt_clock);
+                if (block_mig_state.submitted == 0) {
+                    block_mig_state.prev_time_offset = qemu_get_clock_ns(rt_clock);
+                }
 
                 blk->aiocb = bdrv_aio_readv(bmds->bs, sector, &blk->qiov,
                                             nr_sectors, blk_mig_read_cb, blk);
-- 
1.7.2.3