block: fix initialization in bdrv_io_limits_enable()

bdrv_io_limits_enable() starts a new slice, but does not set io_base
correctly for that slice.

Here is how io_base is used:

    bytes_base  = bs->nr_bytes[is_write] - bs->io_base.bytes[is_write];
    bytes_res   = (unsigned) nb_sectors * BDRV_SECTOR_SIZE;

    if (bytes_base + bytes_res <= bytes_limit) {
        /* no wait */
    } else {
        /* operation needs to be throttled */
    }

As a result, any I/O operations that are triggered between now and
bs->slice_end are incorrectly limited.  If 10 MB of data has been
written since the VM was started, QEMU thinks that 10 MB of data has
been written in this slice. This leads to a I/O lockup in the guest.

We fix this by delaying the start of a new slice to the next
call of bdrv_exceed_io_limits().

Signed-off-by: Peter Lieven <pl@kamp.de>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

diff --git a/block.c b/block.c
index b5e64ecf1118dfce190ad9157d6256613bad93d2..4a90dd1a78175d5612a24fc3dada5e002fe18971 100644 (file)
--- a/block.c
+++ b/block.c
@@ -155,10 +155,6 @@ void bdrv_io_limits_enable(BlockDriverState *bs)
 {
     qemu_co_queue_init(&bs->throttled_reqs);
     bs->block_timer = qemu_new_timer_ns(vm_clock, bdrv_block_timer, bs);
-    bs->slice_time  = 5 * BLOCK_IO_SLICE_TIME;
-    bs->slice_start = qemu_get_clock_ns(vm_clock);
-    bs->slice_end   = bs->slice_start + bs->slice_time;
-    memset(&bs->io_base, 0, sizeof(bs->io_base));
     bs->io_limits_enabled = true;
 }