qcow2: Order concurrent AIO requests on the same unallocated cluster

When two AIO requests write to the same cluster, and this cluster is
unallocated, currently both requests allocate a new cluster and the second one
merges the first one when it is completed. This means an cluster allocation, a
read and a cluster deallocation which cause some overhead. If we simply let the
second request wait until the first one is done, we improve overall performance
with AIO requests (specifially, qcow2/virtio combinations).

This patch maintains a list of in-flight requests that have allocated new
clusters. A second request touching the same cluster is limited so that it
either doesn't touch the allocation of the first request (so it can have a
non-overlapping allocation) or it waits for the first request to complete.

Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

1 files changed, 7 insertions, 0 deletions

diff --git a/block/qcow2.h b/block/qcow2.h
index c99b374bd0..965a2f45c1 100644
--- a/block/qcow2.h
+++ b/block/qcow2.h
@@ -98,6 +98,7 @@ typedef struct BDRVQcowState {
     uint8_t *cluster_cache;
     uint8_t *cluster_data;
     uint64_t cluster_cache_offset;
+    LIST_HEAD(QCowClusterAlloc, QCowL2Meta) cluster_allocs;
 
     uint64_t *refcount_table;
     uint64_t refcount_table_offset;
@@ -128,6 +129,8 @@ typedef struct QCowCreateState {
     int64_t refcount_block_offset;
 } QCowCreateState;
 
+struct QCowAIOCB;
+
 /* XXX This could be private for qcow2-cluster.c */
 typedef struct QCowL2Meta
 {
@@ -135,6 +138,10 @@ typedef struct QCowL2Meta
     int n_start;
     int nb_available;
     int nb_clusters;
+    struct QCowL2Meta *depends_on;
+    LIST_HEAD(QCowAioDependencies, QCowAIOCB) dependent_requests;
+
+    LIST_ENTRY(QCowL2Meta) next_in_flight;
 } QCowL2Meta;
 
 static inline int size_to_clusters(BDRVQcowState *s, int64_t size)