block: explicit I/O accounting

Decouple the I/O accounting from bdrv_aio_readv/writev/flush and
make the hardware models call directly into the accounting helpers.

This means:
 - we do not count internal requests from image formats in addition
   to guest originating I/O
 - we do not double count I/O ops if the device model handles it
   chunk wise
 - we only account I/O once it actuall is done
 - can extent I/O accounting to synchronous or coroutine I/O easily
 - implement I/O latency tracking easily (see the next patch)

I've conveted the existing device model callers to the new model,
device models that are using synchronous I/O and weren't accounted
before haven't been updated yet.  Also scsi hasn't been converted
to the end-to-end accounting as I want to defer that after the pending
scsi layer overhaul.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

1 files changed, 5 insertions, 0 deletions

diff --git a/hw/xen_disk.c b/hw/xen_disk.c
index 31f91514f2..bd5c66916b 100644
--- a/hw/xen_disk.c
+++ b/hw/xen_disk.c
@@ -79,6 +79,7 @@ struct ioreq {
 
     struct XenBlkDev    *blkdev;
     QLIST_ENTRY(ioreq)   list;
+    BlockAcctCookie     acct;
 };
 
 struct XenBlkDev {
@@ -401,6 +402,7 @@ static void qemu_aio_complete(void *opaque, int ret)
     ioreq->status = ioreq->aio_errors ? BLKIF_RSP_ERROR : BLKIF_RSP_OKAY;
     ioreq_unmap(ioreq);
     ioreq_finish(ioreq);
+    bdrv_acct_done(ioreq->blkdev->bs, &ioreq->acct);
     qemu_bh_schedule(ioreq->blkdev->bh);
 }
 
@@ -419,6 +421,7 @@ static int ioreq_runio_qemu_aio(struct ioreq *ioreq)
 
     switch (ioreq->req.operation) {
     case BLKIF_OP_READ:
+        bdrv_acct_start(blkdev->bs, &ioreq->acct, ioreq->v.size, BDRV_ACCT_READ);
         ioreq->aio_inflight++;
         bdrv_aio_readv(blkdev->bs, ioreq->start / BLOCK_SIZE,
                        &ioreq->v, ioreq->v.size / BLOCK_SIZE,
@@ -429,6 +432,8 @@ static int ioreq_runio_qemu_aio(struct ioreq *ioreq)
         if (!ioreq->req.nr_segments) {
             break;
         }
+
+        bdrv_acct_start(blkdev->bs, &ioreq->acct, ioreq->v.size, BDRV_ACCT_WRITE);
         ioreq->aio_inflight++;
         bdrv_aio_writev(blkdev->bs, ioreq->start / BLOCK_SIZE,
                         &ioreq->v, ioreq->v.size / BLOCK_SIZE,