[Qemu-devel] [PATCH v5 2/3] linux-aio: handling -EAGAIN for !s->io_q.plugged case

[Ming Lei]

Previously -EAGAIN is simply ignored for !s->io_q.plugged case,
and sometimes it is easy to cause -EIO to VM, such as NVME device.

This patch handles -EAGAIN by io queue for !s->io_q.plugged case,
and it will be retried in following aio completion cb.

Suggested-by: Paolo Bonzini <address@hidden>
Signed-off-by: Ming Lei <address@hidden>
---
 block/linux-aio.c |   28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/block/linux-aio.c b/block/linux-aio.c
index 70312a4..0cb098d 100644
--- a/block/linux-aio.c
+++ b/block/linux-aio.c
@@ -282,12 +282,17 @@ static int ioq_enqueue(struct qemu_laio_state *s, struct 
iocb *iocb)
     s->io_q.iocbs[idx++] = iocb;
     s->io_q.idx = idx;
 
-    /* submit immediately if queue depth is above 2/3 */
-    if (idx > s->io_q.size * 2 / 3) {
-        return ioq_submit(s);
+    /*
+     * This is reached in two cases: queue not plugged but io_submit
+     * returned -EAGAIN, or queue plugged.  In the latter case, start
+     * submitting some I/O if the queue is getting too full.  In the
+     * former case, instead, wait until an I/O operation is completed.
+     */
+    if (!s->io_q.plugged || likely(idx < s->io_q.size * 2 / 3)) {
+        return 0;
     }
 
-    return 0;
+    return ioq_submit(s);
 }
 
 void laio_io_plug(BlockDriverState *bs, void *aio_ctx)
@@ -348,15 +353,18 @@ BlockAIOCB *laio_submit(BlockDriverState *bs, void 
*aio_ctx, int fd,
     }
     io_set_eventfd(&laiocb->iocb, event_notifier_get_fd(&s->e));
 
-    if (!s->io_q.plugged) {
-        if (io_submit(s->ctx, 1, &iocbs) < 0) {
-            goto out_free_aiocb;
-        }
-    } else {
-        if (ioq_enqueue(s, iocbs) < 0) {
+    /* Switch to queue mode until -EAGAIN is handled */
+    if (!s->io_q.plugged && !s->io_q.idx) {
+        int ret = io_submit(s->ctx, 1, &iocbs);
+        if (ret >= 0) {
+            return &laiocb->common;
+        } else if (ret != -EAGAIN) {
             goto out_free_aiocb;
         }
     }
+    if (ioq_enqueue(s, iocbs) < 0) {
+        goto out_free_aiocb;
+    }
     return &laiocb->common;
 
 out_free_aiocb:
-- 
1.7.9.5