coroutine: try harder not to delete coroutines

Placing coroutines on the global pool should be preferrable, because it
can help all threads.  But if the global pool is full, we can still
try to save some allocations by stashing completed coroutines on the
local pool.  This is quite cheap too, because it does not require
atomic operations, and provides a gain of 15% in the best case.

Signed-off-by: Peter Lieven <pl@kamp.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Message-id: 1417518350-6167-8-git-send-email-pbonzini@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

qemu-coroutine.c

@@ -27,6 +27,7 @@ enum {
 static QSLIST_HEAD(, Coroutine) release_pool = QSLIST_HEAD_INITIALIZER(pool);
 static unsigned int release_pool_size;
 static __thread QSLIST_HEAD(, Coroutine) alloc_pool = QSLIST_HEAD_INITIALIZER(pool);
+static __thread unsigned int alloc_pool_size;
 static __thread Notifier coroutine_pool_cleanup_notifier;
 
 static void coroutine_pool_cleanup(Notifier *n, void *value)
@@ -58,13 +59,14 @@ Coroutine *qemu_coroutine_create(CoroutineEntry *entry)
                  * release_pool_size and the actual size of release_pool.  But
                  * it is just a heuristic, it does not need to be perfect.
                  */
-                release_pool_size = 0;
+                alloc_pool_size = atomic_xchg(&release_pool_size, 0);
                 QSLIST_MOVE_ATOMIC(&alloc_pool, &release_pool);
                 co = QSLIST_FIRST(&alloc_pool);
             }
         }
         if (co) {
             QSLIST_REMOVE_HEAD(&alloc_pool, pool_next);
+            alloc_pool_size--;
         }
     }
 
@@ -87,6 +89,11 @@ static void coroutine_delete(Coroutine *co)
             atomic_inc(&release_pool_size);
             return;
         }
+        if (alloc_pool_size < POOL_BATCH_SIZE) {
+            QSLIST_INSERT_HEAD(&alloc_pool, co, pool_next);
+            alloc_pool_size++;
+            return;
+        }
     }
 
     qemu_coroutine_delete(co);