linux-aio: add `dev_max_batch` parameter to laio_co_submit()

This new parameter can be used by block devices to limit the
Linux AIO batch size more than the limit set by the AIO context.

file-posix backend supports this, passing its `aio-max-batch` option
previously added.

Add an helper function to calculate the maximum batch size.

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20211026162346.253081-3-sgarzare@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

block/file-posix.c

@@ -2066,7 +2066,8 @@ static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset,
     } else if (s->use_linux_aio) {
         LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs));
         assert(qiov->size == bytes);
-        return laio_co_submit(bs, aio, s->fd, offset, qiov, type);
+        return laio_co_submit(bs, aio, s->fd, offset, qiov, type,
+                              s->aio_max_batch);
 #endif
     }
 

block/linux-aio.c

@@ -334,6 +334,23 @@ static void ioq_submit(LinuxAioState *s)
     }
 }
 
+static uint64_t laio_max_batch(LinuxAioState *s, uint64_t dev_max_batch)
+{
+    uint64_t max_batch = s->aio_context->aio_max_batch ?: DEFAULT_MAX_BATCH;
+
+    /*
+     * AIO context can be shared between multiple block devices, so
+     * `dev_max_batch` allows reducing the batch size for latency-sensitive
+     * devices.
+     */
+    max_batch = MIN_NON_ZERO(dev_max_batch, max_batch);
+
+    /* limit the batch with the number of available events */
+    max_batch = MIN_NON_ZERO(MAX_EVENTS - s->io_q.in_flight, max_batch);
+
+    return max_batch;
+}
+
 void laio_io_plug(BlockDriverState *bs, LinuxAioState *s)
 {
     s->io_q.plugged++;
@@ -349,15 +366,11 @@ void laio_io_unplug(BlockDriverState *bs, LinuxAioState *s)
 }
 
 static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset,
-                          int type)
+                          int type, uint64_t dev_max_batch)
 {
     LinuxAioState *s = laiocb->ctx;
     struct iocb *iocbs = &laiocb->iocb;
     QEMUIOVector *qiov = laiocb->qiov;
-    int64_t max_batch = s->aio_context->aio_max_batch ?: DEFAULT_MAX_BATCH;
-
-    /* limit the batch with the number of available events */
-    max_batch = MIN_NON_ZERO(MAX_EVENTS - s->io_q.in_flight, max_batch);
 
     switch (type) {
     case QEMU_AIO_WRITE:
@@ -378,7 +391,7 @@ static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset,
     s->io_q.in_queue++;
     if (!s->io_q.blocked &&
         (!s->io_q.plugged ||
-         s->io_q.in_queue >= max_batch)) {
+         s->io_q.in_queue >= laio_max_batch(s, dev_max_batch))) {
         ioq_submit(s);
     }
 
@@ -386,7 +399,8 @@ static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset,
 }
 
 int coroutine_fn laio_co_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
-                                uint64_t offset, QEMUIOVector *qiov, int type)
+                                uint64_t offset, QEMUIOVector *qiov, int type,
+                                uint64_t dev_max_batch)
 {
     int ret;
     struct qemu_laiocb laiocb = {
@@ -398,7 +412,7 @@ int coroutine_fn laio_co_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
         .qiov       = qiov,
     };
 
-    ret = laio_do_submit(fd, &laiocb, offset, type);
+    ret = laio_do_submit(fd, &laiocb, offset, type, dev_max_batch);
     if (ret < 0) {
         return ret;
     }

include/block/raw-aio.h

@@ -51,7 +51,8 @@ typedef struct LinuxAioState LinuxAioState;
 LinuxAioState *laio_init(Error **errp);
 void laio_cleanup(LinuxAioState *s);
 int coroutine_fn laio_co_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
-                                uint64_t offset, QEMUIOVector *qiov, int type);
+                                uint64_t offset, QEMUIOVector *qiov, int type,
+                                uint64_t dev_max_batch);
 void laio_detach_aio_context(LinuxAioState *s, AioContext *old_context);
 void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context);
 void laio_io_plug(BlockDriverState *bs, LinuxAioState *s);