static void blk_handle_requests(struct XenBlkDev *blkdev)
{
RING_IDX rc, rp;
struct ioreq *ioreq;
blkdev->more_work = 0;
rc = blkdev->rings.common.req_cons;
rp = blkdev->rings.common.sring->req_prod;
xen_rmb(); /* Ensure we see queued requests up to 'rp'. */
blk_send_response_all(blkdev);
while (rc != rp) {
/* pull request from ring */
if (RING_REQUEST_CONS_OVERFLOW(&blkdev->rings.common, rc)) {
break;
}
ioreq = ioreq_start(blkdev);
if (ioreq == NULL) {
blkdev->more_work++;
break;
}
blk_get_request(blkdev, ioreq, rc);
blkdev->rings.common.req_cons = ++rc;
/* parse them */
if (ioreq_parse(ioreq) != 0) {
switch (ioreq->req.operation) {
case BLKIF_OP_READ:
block_acct_invalid(blk_get_stats(blkdev->blk),
BLOCK_ACCT_READ);
break;
case BLKIF_OP_WRITE:
block_acct_invalid(blk_get_stats(blkdev->blk),
BLOCK_ACCT_WRITE);
break;
case BLKIF_OP_FLUSH_DISKCACHE:
block_acct_invalid(blk_get_stats(blkdev->blk),
BLOCK_ACCT_FLUSH);
default:
break;
};
if (blk_send_response_one(ioreq)) {
xen_pv_send_notify(&blkdev->xendev);
}
ioreq_release(ioreq, false);
continue;
}
ioreq_runio_qemu_aio(ioreq);
}
if (blkdev->more_work && blkdev->requests_inflight < blkdev->max_requests) {
qemu_bh_schedule(blkdev->bh);
}
}
static void virtio_blk_rw_complete(void *opaque, int ret)
{
VirtIOBlockReq *next = opaque;
while (next) {
VirtIOBlockReq *req = next;
next = req->mr_next;
trace_virtio_blk_rw_complete(req, ret);
if (req->qiov.nalloc != -1) {
/* If nalloc is != 1 req->qiov is a local copy of the original
* external iovec. It was allocated in submit_merged_requests
* to be able to merge requests. */
qemu_iovec_destroy(&req->qiov);
}
if (ret) {
int p = virtio_ldl_p(VIRTIO_DEVICE(req->dev), &req->out.type);
bool is_read = !(p & VIRTIO_BLK_T_OUT);
if (virtio_blk_handle_rw_error(req, -ret, is_read)) {
continue;
}
}
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
block_acct_done(blk_get_stats(req->dev->blk), &req->acct);
virtio_blk_free_request(req);
}
}
static void virtio_blk_handle_flush(VirtIOBlockReq *req, MultiReqBuffer *mrb)
{
block_acct_start(blk_get_stats(req->dev->blk), &req->acct, 0,
BLOCK_ACCT_FLUSH);
/*
* Make sure all outstanding writes are posted to the backing device.
*/
if (mrb->is_write && mrb->num_reqs > 0) {
virtio_blk_submit_multireq(req->dev->blk, mrb);
}
blk_aio_flush(req->dev->blk, virtio_blk_flush_complete, req);
}
static void virtio_blk_flush_complete(void *opaque, int ret)
{
VirtIOBlockReq *req = opaque;
if (ret) {
if (virtio_blk_handle_rw_error(req, -ret, 0)) {
return;
}
}
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
block_acct_done(blk_get_stats(req->dev->blk), &req->acct);
virtio_blk_free_request(req);
}
static inline void submit_requests(BlockBackend *blk, MultiReqBuffer *mrb,
int start, int num_reqs, int niov)
{
QEMUIOVector *qiov = &mrb->reqs[start]->qiov;
int64_t sector_num = mrb->reqs[start]->sector_num;
int nb_sectors = mrb->reqs[start]->qiov.size / BDRV_SECTOR_SIZE;
bool is_write = mrb->is_write;
if (num_reqs > 1) {
int i;
struct iovec *tmp_iov = qiov->iov;
int tmp_niov = qiov->niov;
/* mrb->reqs[start]->qiov was initialized from external so we can't
* modifiy it here. We need to initialize it locally and then add the
* external iovecs. */
qemu_iovec_init(qiov, niov);
for (i = 0; i < tmp_niov; i++) {
qemu_iovec_add(qiov, tmp_iov[i].iov_base, tmp_iov[i].iov_len);
}
for (i = start + 1; i < start + num_reqs; i++) {
qemu_iovec_concat(qiov, &mrb->reqs[i]->qiov, 0,
mrb->reqs[i]->qiov.size);
mrb->reqs[i - 1]->mr_next = mrb->reqs[i];
nb_sectors += mrb->reqs[i]->qiov.size / BDRV_SECTOR_SIZE;
}
assert(nb_sectors == qiov->size / BDRV_SECTOR_SIZE);
trace_virtio_blk_submit_multireq(mrb, start, num_reqs, sector_num,
nb_sectors, is_write);
block_acct_merge_done(blk_get_stats(blk),
is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ,
num_reqs - 1);
}
if (is_write) {
blk_aio_writev(blk, sector_num, qiov, nb_sectors,
virtio_blk_rw_complete, mrb->reqs[start]);
} else {
blk_aio_readv(blk, sector_num, qiov, nb_sectors,
virtio_blk_rw_complete, mrb->reqs[start]);
}
}
static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error,
bool is_read)
{
BlockErrorAction action = blk_get_error_action(req->dev->blk,
is_read, error);
VirtIOBlock *s = req->dev;
if (action == BLOCK_ERROR_ACTION_STOP) {
req->next = s->rq;
s->rq = req;
} else if (action == BLOCK_ERROR_ACTION_REPORT) {
virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
block_acct_done(blk_get_stats(s->blk), &req->acct);
virtio_blk_free_request(req);
}
blk_error_action(s->blk, action, is_read, error);
return action != BLOCK_ERROR_ACTION_IGNORE;
}
static void virtio_blk_flush_complete(void *opaque, int ret)
{
VirtIOBlockReq *req = opaque;
VirtIOBlock *s = req->dev;
aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
if (ret) {
if (virtio_blk_handle_rw_error(req, -ret, 0)) {
goto out;
}
}
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
block_acct_done(blk_get_stats(req->dev->blk), &req->acct);
virtio_blk_free_request(req);
out:
aio_context_release(blk_get_aio_context(s->conf.conf.blk));
}
static void virtio_blk_rw_complete(void *opaque, int ret)
{
VirtIOBlockReq *next = opaque;
while (next) {
VirtIOBlockReq *req = next;
next = req->mr_next;
trace_virtio_blk_rw_complete(req, ret);
if (req->qiov.nalloc != -1) {
/* If nalloc is != 1 req->qiov is a local copy of the original
* external iovec. It was allocated in submit_merged_requests
* to be able to merge requests. */
qemu_iovec_destroy(&req->qiov);
}
if (ret) {
int p = virtio_ldl_p(VIRTIO_DEVICE(req->dev), &req->out.type);
bool is_read = !(p & VIRTIO_BLK_T_OUT);
/* Note that memory may be dirtied on read failure. If the
* virtio request is not completed here, as is the case for
* BLOCK_ERROR_ACTION_STOP, the memory may not be copied
* correctly during live migration. While this is ugly,
* it is acceptable because the device is free to write to
* the memory until the request is completed (which will
* happen on the other side of the migration).
*/
if (virtio_blk_handle_rw_error(req, -ret, is_read)) {
/* Break the link in case the next request is added to the
* restart queue and is going to be parsed from the ring again.
*/
req->mr_next = NULL;
continue;
}
}
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
block_acct_done(blk_get_stats(req->dev->blk), &req->acct);
virtio_blk_free_request(req);
}
}
static void virtio_blk_rw_complete(void *opaque, int ret)
{
VirtIOBlockReq *next = opaque;
VirtIOBlock *s = next->dev;
VirtIODevice *vdev = VIRTIO_DEVICE(s);
aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
while (next) {
VirtIOBlockReq *req = next;
next = req->mr_next;
trace_virtio_blk_rw_complete(vdev, req, ret);
if (req->qiov.nalloc != -1) {
/* If nalloc is != -1 req->qiov is a local copy of the original
* external iovec. It was allocated in submit_requests to be
* able to merge requests. */
qemu_iovec_destroy(&req->qiov);
}
if (ret) {
int p = virtio_ldl_p(VIRTIO_DEVICE(req->dev), &req->out.type);
bool is_read = !(p & VIRTIO_BLK_T_OUT);
/* Note that memory may be dirtied on read failure. If the
* virtio request is not completed here, as is the case for
* BLOCK_ERROR_ACTION_STOP, the memory may not be copied
* correctly during live migration. While this is ugly,
* it is acceptable because the device is free to write to
* the memory until the request is completed (which will
* happen on the other side of the migration).
*/
if (virtio_blk_handle_rw_error(req, -ret, is_read, true)) {
continue;
}
}
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
block_acct_done(blk_get_stats(req->dev->blk), &req->acct);
virtio_blk_free_request(req);
}
aio_context_release(blk_get_aio_context(s->conf.conf.blk));
}
static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error,
bool is_read)
{
VirtIOBlock *s = req->dev;
BlockErrorAction action = blk_get_error_action(s->blk, is_read, error);
if (action == BLOCK_ERROR_ACTION_STOP) {
/* Break the link as the next request is going to be parsed from the
* ring again. Otherwise we may end up doing a double completion! */
req->mr_next = NULL;
req->next = s->rq;
s->rq = req;
} else if (action == BLOCK_ERROR_ACTION_REPORT) {
virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
block_acct_failed(blk_get_stats(s->blk), &req->acct);
virtio_blk_free_request(req);
}
blk_error_action(s->blk, action, is_read, error);
return action != BLOCK_ERROR_ACTION_IGNORE;
}
static void virtio_blk_discard_write_zeroes_complete(void *opaque, int ret)
{
VirtIOBlockReq *req = opaque;
VirtIOBlock *s = req->dev;
bool is_write_zeroes = (virtio_ldl_p(VIRTIO_DEVICE(s), &req->out.type) &
~VIRTIO_BLK_T_BARRIER) == VIRTIO_BLK_T_WRITE_ZEROES;
aio_context_acquire(blk_get_aio_context(s->conf.conf.blk));
if (ret) {
if (virtio_blk_handle_rw_error(req, -ret, false, is_write_zeroes)) {
goto out;
}
}
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
if (is_write_zeroes) {
block_acct_done(blk_get_stats(s->blk), &req->acct);
}
virtio_blk_free_request(req);
out:
aio_context_release(blk_get_aio_context(s->conf.conf.blk));
}
static void xen_block_handle_requests(XenBlockDataPlane *dataplane)
{
RING_IDX rc, rp;
XenBlockRequest *request;
int inflight_atstart = dataplane->requests_inflight;
int batched = 0;
dataplane->more_work = 0;
rc = dataplane->rings.common.req_cons;
rp = dataplane->rings.common.sring->req_prod;
xen_rmb(); /* Ensure we see queued requests up to 'rp'. */
/*
* If there was more than IO_PLUG_THRESHOLD requests in flight
* when we got here, this is an indication that there the bottleneck
* is below us, so it's worth beginning to batch up I/O requests
* rather than submitting them immediately. The maximum number
* of requests we're willing to batch is the number already in
* flight, so it can grow up to max_requests when the bottleneck
* is below us.
*/
if (inflight_atstart > IO_PLUG_THRESHOLD) {
blk_io_plug(dataplane->blk);
}
while (rc != rp) {
/* pull request from ring */
if (RING_REQUEST_CONS_OVERFLOW(&dataplane->rings.common, rc)) {
break;
}
request = xen_block_start_request(dataplane);
if (request == NULL) {
dataplane->more_work++;
break;
}
xen_block_get_request(dataplane, request, rc);
dataplane->rings.common.req_cons = ++rc;
/* parse them */
if (xen_block_parse_request(request) != 0) {
switch (request->req.operation) {
case BLKIF_OP_READ:
block_acct_invalid(blk_get_stats(dataplane->blk),
BLOCK_ACCT_READ);
break;
case BLKIF_OP_WRITE:
block_acct_invalid(blk_get_stats(dataplane->blk),
BLOCK_ACCT_WRITE);
break;
case BLKIF_OP_FLUSH_DISKCACHE:
block_acct_invalid(blk_get_stats(dataplane->blk),
BLOCK_ACCT_FLUSH);
default:
break;
};
if (xen_block_send_response(request)) {
Error *local_err = NULL;
xen_device_notify_event_channel(dataplane->xendev,
dataplane->event_channel,
&local_err);
if (local_err) {
error_report_err(local_err);
}
}
xen_block_release_request(request);
continue;
}
if (inflight_atstart > IO_PLUG_THRESHOLD &&
batched >= inflight_atstart) {
blk_io_unplug(dataplane->blk);
}
xen_block_do_aio(request);
if (inflight_atstart > IO_PLUG_THRESHOLD) {
if (batched >= inflight_atstart) {
blk_io_plug(dataplane->blk);
batched = 0;
} else {
batched++;
}
}
}
if (inflight_atstart > IO_PLUG_THRESHOLD) {
blk_io_unplug(dataplane->blk);
}
if (dataplane->more_work &&
dataplane->requests_inflight < dataplane->max_requests) {
qemu_bh_schedule(dataplane->bh);
}
}
static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
{
BlockAcctStats *stats = blk_get_stats(blk);
BlockAcctTimedStats *ts = NULL;
ds->rd_bytes = stats->nr_bytes[BLOCK_ACCT_READ];
ds->wr_bytes = stats->nr_bytes[BLOCK_ACCT_WRITE];
ds->rd_operations = stats->nr_ops[BLOCK_ACCT_READ];
ds->wr_operations = stats->nr_ops[BLOCK_ACCT_WRITE];
ds->failed_rd_operations = stats->failed_ops[BLOCK_ACCT_READ];
ds->failed_wr_operations = stats->failed_ops[BLOCK_ACCT_WRITE];
ds->failed_flush_operations = stats->failed_ops[BLOCK_ACCT_FLUSH];
ds->invalid_rd_operations = stats->invalid_ops[BLOCK_ACCT_READ];
ds->invalid_wr_operations = stats->invalid_ops[BLOCK_ACCT_WRITE];
ds->invalid_flush_operations =
stats->invalid_ops[BLOCK_ACCT_FLUSH];
ds->rd_merged = stats->merged[BLOCK_ACCT_READ];
ds->wr_merged = stats->merged[BLOCK_ACCT_WRITE];
ds->flush_operations = stats->nr_ops[BLOCK_ACCT_FLUSH];
ds->wr_total_time_ns = stats->total_time_ns[BLOCK_ACCT_WRITE];
ds->rd_total_time_ns = stats->total_time_ns[BLOCK_ACCT_READ];
ds->flush_total_time_ns = stats->total_time_ns[BLOCK_ACCT_FLUSH];
ds->has_idle_time_ns = stats->last_access_time_ns > 0;
if (ds->has_idle_time_ns) {
ds->idle_time_ns = block_acct_idle_time_ns(stats);
}
ds->account_invalid = stats->account_invalid;
ds->account_failed = stats->account_failed;
while ((ts = block_acct_interval_next(stats, ts))) {
BlockDeviceTimedStatsList *timed_stats =
g_malloc0(sizeof(*timed_stats));
BlockDeviceTimedStats *dev_stats = g_malloc0(sizeof(*dev_stats));
timed_stats->next = ds->timed_stats;
timed_stats->value = dev_stats;
ds->timed_stats = timed_stats;
TimedAverage *rd = &ts->latency[BLOCK_ACCT_READ];
TimedAverage *wr = &ts->latency[BLOCK_ACCT_WRITE];
TimedAverage *fl = &ts->latency[BLOCK_ACCT_FLUSH];
dev_stats->interval_length = ts->interval_length;
dev_stats->min_rd_latency_ns = timed_average_min(rd);
dev_stats->max_rd_latency_ns = timed_average_max(rd);
dev_stats->avg_rd_latency_ns = timed_average_avg(rd);
dev_stats->min_wr_latency_ns = timed_average_min(wr);
dev_stats->max_wr_latency_ns = timed_average_max(wr);
dev_stats->avg_wr_latency_ns = timed_average_avg(wr);
dev_stats->min_flush_latency_ns = timed_average_min(fl);
dev_stats->max_flush_latency_ns = timed_average_max(fl);
dev_stats->avg_flush_latency_ns = timed_average_avg(fl);
dev_stats->avg_rd_queue_depth =
block_acct_queue_depth(ts, BLOCK_ACCT_READ);
dev_stats->avg_wr_queue_depth =
block_acct_queue_depth(ts, BLOCK_ACCT_WRITE);
}
}
void dma_acct_start(BlockBackend *blk, BlockAcctCookie *cookie,
QEMUSGList *sg, enum BlockAcctType type)
{
block_acct_start(blk_get_stats(blk), cookie, sg->size, type);
}
static int xen_block_do_aio(XenBlockRequest *request)
{
XenBlockDataPlane *dataplane = request->dataplane;
if (request->req.nr_segments &&
(request->req.operation == BLKIF_OP_WRITE ||
request->req.operation == BLKIF_OP_FLUSH_DISKCACHE) &&
xen_block_copy_request(request)) {
goto err;
}
request->aio_inflight++;
if (request->presync) {
blk_aio_flush(request->dataplane->blk, xen_block_complete_aio,
request);
return 0;
}
switch (request->req.operation) {
case BLKIF_OP_READ:
qemu_iovec_add(&request->v, request->buf, request->size);
block_acct_start(blk_get_stats(dataplane->blk), &request->acct,
request->v.size, BLOCK_ACCT_READ);
request->aio_inflight++;
blk_aio_preadv(dataplane->blk, request->start, &request->v, 0,
xen_block_complete_aio, request);
break;
case BLKIF_OP_WRITE:
case BLKIF_OP_FLUSH_DISKCACHE:
if (!request->req.nr_segments) {
break;
}
qemu_iovec_add(&request->v, request->buf, request->size);
block_acct_start(blk_get_stats(dataplane->blk), &request->acct,
request->v.size,
request->req.operation == BLKIF_OP_WRITE ?
BLOCK_ACCT_WRITE : BLOCK_ACCT_FLUSH);
request->aio_inflight++;
blk_aio_pwritev(dataplane->blk, request->start, &request->v, 0,
xen_block_complete_aio, request);
break;
case BLKIF_OP_DISCARD:
{
struct blkif_request_discard *req = (void *)&request->req;
if (!xen_block_split_discard(request, req->sector_number,
req->nr_sectors)) {
goto err;
}
break;
}
default:
/* unknown operation (shouldn't happen -- parse catches this) */
goto err;
}
xen_block_complete_aio(request, 0);
return 0;
err:
xen_block_finish_request(request);
request->status = BLKIF_RSP_ERROR;
return -1;
}
static int ioreq_runio_qemu_aio(struct ioreq *ioreq)
{
struct XenBlkDev *blkdev = ioreq->blkdev;
ioreq->buf = qemu_memalign(XC_PAGE_SIZE, ioreq->size);
if (ioreq->req.nr_segments &&
(ioreq->req.operation == BLKIF_OP_WRITE ||
ioreq->req.operation == BLKIF_OP_FLUSH_DISKCACHE) &&
ioreq_grant_copy(ioreq)) {
qemu_vfree(ioreq->buf);
goto err;
}
ioreq->aio_inflight++;
if (ioreq->presync) {
blk_aio_flush(ioreq->blkdev->blk, qemu_aio_complete, ioreq);
return 0;
}
switch (ioreq->req.operation) {
case BLKIF_OP_READ:
qemu_iovec_add(&ioreq->v, ioreq->buf, ioreq->size);
block_acct_start(blk_get_stats(blkdev->blk), &ioreq->acct,
ioreq->v.size, BLOCK_ACCT_READ);
ioreq->aio_inflight++;
blk_aio_preadv(blkdev->blk, ioreq->start, &ioreq->v, 0,
qemu_aio_complete, ioreq);
break;
case BLKIF_OP_WRITE:
case BLKIF_OP_FLUSH_DISKCACHE:
if (!ioreq->req.nr_segments) {
break;
}
qemu_iovec_add(&ioreq->v, ioreq->buf, ioreq->size);
block_acct_start(blk_get_stats(blkdev->blk), &ioreq->acct,
ioreq->v.size,
ioreq->req.operation == BLKIF_OP_WRITE ?
BLOCK_ACCT_WRITE : BLOCK_ACCT_FLUSH);
ioreq->aio_inflight++;
blk_aio_pwritev(blkdev->blk, ioreq->start, &ioreq->v, 0,
qemu_aio_complete, ioreq);
break;
case BLKIF_OP_DISCARD:
{
struct blkif_request_discard *req = (void *)&ioreq->req;
if (!blk_split_discard(ioreq, req->sector_number, req->nr_sectors)) {
goto err;
}
break;
}
default:
/* unknown operation (shouldn't happen -- parse catches this) */
goto err;
}
qemu_aio_complete(ioreq, 0);
return 0;
err:
ioreq_finish(ioreq);
ioreq->status = BLKIF_RSP_ERROR;
return -1;
}
static void qemu_aio_complete(void *opaque, int ret)
{
struct ioreq *ioreq = opaque;
struct XenBlkDev *blkdev = ioreq->blkdev;
struct XenDevice *xendev = &blkdev->xendev;
aio_context_acquire(blkdev->ctx);
if (ret != 0) {
xen_pv_printf(xendev, 0, "%s I/O error\n",
ioreq->req.operation == BLKIF_OP_READ ? "read" : "write");
ioreq->aio_errors++;
}
ioreq->aio_inflight--;
if (ioreq->presync) {
ioreq->presync = 0;
ioreq_runio_qemu_aio(ioreq);
goto done;
}
if (ioreq->aio_inflight > 0) {
goto done;
}
switch (ioreq->req.operation) {
case BLKIF_OP_READ:
/* in case of failure ioreq->aio_errors is increased */
if (ret == 0) {
ioreq_grant_copy(ioreq);
}
qemu_vfree(ioreq->buf);
break;
case BLKIF_OP_WRITE:
case BLKIF_OP_FLUSH_DISKCACHE:
if (!ioreq->req.nr_segments) {
break;
}
qemu_vfree(ioreq->buf);
break;
default:
break;
}
ioreq->status = ioreq->aio_errors ? BLKIF_RSP_ERROR : BLKIF_RSP_OKAY;
ioreq_finish(ioreq);
switch (ioreq->req.operation) {
case BLKIF_OP_WRITE:
case BLKIF_OP_FLUSH_DISKCACHE:
if (!ioreq->req.nr_segments) {
break;
}
case BLKIF_OP_READ:
if (ioreq->status == BLKIF_RSP_OKAY) {
block_acct_done(blk_get_stats(blkdev->blk), &ioreq->acct);
} else {
block_acct_failed(blk_get_stats(blkdev->blk), &ioreq->acct);
}
break;
case BLKIF_OP_DISCARD:
default:
break;
}
qemu_bh_schedule(blkdev->bh);
done:
aio_context_release(blkdev->ctx);
}
static BlockStats *bdrv_query_stats(const BlockDriverState *bs,
bool query_backing)
{
BlockStats *s;
s = g_malloc0(sizeof(*s));
if (bdrv_get_device_name(bs)[0]) {
s->has_device = true;
s->device = g_strdup(bdrv_get_device_name(bs));
}
if (bdrv_get_node_name(bs)[0]) {
s->has_node_name = true;
s->node_name = g_strdup(bdrv_get_node_name(bs));
}
s->stats = g_malloc0(sizeof(*s->stats));
if (bs->blk) {
BlockAcctStats *stats = blk_get_stats(bs->blk);
BlockAcctTimedStats *ts = NULL;
s->stats->rd_bytes = stats->nr_bytes[BLOCK_ACCT_READ];
s->stats->wr_bytes = stats->nr_bytes[BLOCK_ACCT_WRITE];
s->stats->rd_operations = stats->nr_ops[BLOCK_ACCT_READ];
s->stats->wr_operations = stats->nr_ops[BLOCK_ACCT_WRITE];
s->stats->failed_rd_operations = stats->failed_ops[BLOCK_ACCT_READ];
s->stats->failed_wr_operations = stats->failed_ops[BLOCK_ACCT_WRITE];
s->stats->failed_flush_operations = stats->failed_ops[BLOCK_ACCT_FLUSH];
s->stats->invalid_rd_operations = stats->invalid_ops[BLOCK_ACCT_READ];
s->stats->invalid_wr_operations = stats->invalid_ops[BLOCK_ACCT_WRITE];
s->stats->invalid_flush_operations =
stats->invalid_ops[BLOCK_ACCT_FLUSH];
s->stats->rd_merged = stats->merged[BLOCK_ACCT_READ];
s->stats->wr_merged = stats->merged[BLOCK_ACCT_WRITE];
s->stats->flush_operations = stats->nr_ops[BLOCK_ACCT_FLUSH];
s->stats->wr_total_time_ns = stats->total_time_ns[BLOCK_ACCT_WRITE];
s->stats->rd_total_time_ns = stats->total_time_ns[BLOCK_ACCT_READ];
s->stats->flush_total_time_ns = stats->total_time_ns[BLOCK_ACCT_FLUSH];
s->stats->has_idle_time_ns = stats->last_access_time_ns > 0;
if (s->stats->has_idle_time_ns) {
s->stats->idle_time_ns = block_acct_idle_time_ns(stats);
}
s->stats->account_invalid = stats->account_invalid;
s->stats->account_failed = stats->account_failed;
while ((ts = block_acct_interval_next(stats, ts))) {
BlockDeviceTimedStatsList *timed_stats =
g_malloc0(sizeof(*timed_stats));
BlockDeviceTimedStats *dev_stats = g_malloc0(sizeof(*dev_stats));
timed_stats->next = s->stats->timed_stats;
timed_stats->value = dev_stats;
s->stats->timed_stats = timed_stats;
TimedAverage *rd = &ts->latency[BLOCK_ACCT_READ];
TimedAverage *wr = &ts->latency[BLOCK_ACCT_WRITE];
TimedAverage *fl = &ts->latency[BLOCK_ACCT_FLUSH];
dev_stats->interval_length = ts->interval_length;
dev_stats->min_rd_latency_ns = timed_average_min(rd);
dev_stats->max_rd_latency_ns = timed_average_max(rd);
dev_stats->avg_rd_latency_ns = timed_average_avg(rd);
dev_stats->min_wr_latency_ns = timed_average_min(wr);
dev_stats->max_wr_latency_ns = timed_average_max(wr);
dev_stats->avg_wr_latency_ns = timed_average_avg(wr);
dev_stats->min_flush_latency_ns = timed_average_min(fl);
dev_stats->max_flush_latency_ns = timed_average_max(fl);
dev_stats->avg_flush_latency_ns = timed_average_avg(fl);
dev_stats->avg_rd_queue_depth =
block_acct_queue_depth(ts, BLOCK_ACCT_READ);
dev_stats->avg_wr_queue_depth =
block_acct_queue_depth(ts, BLOCK_ACCT_WRITE);
}
}
s->stats->wr_highest_offset = bs->wr_highest_offset;
if (bs->file) {
s->has_parent = true;
s->parent = bdrv_query_stats(bs->file->bs, query_backing);
}
if (query_backing && bs->backing) {
s->has_backing = true;
s->backing = bdrv_query_stats(bs->backing->bs, query_backing);
}
return s;
}
static void xen_block_complete_aio(void *opaque, int ret)
{
XenBlockRequest *request = opaque;
XenBlockDataPlane *dataplane = request->dataplane;
aio_context_acquire(dataplane->ctx);
if (ret != 0) {
error_report("%s I/O error",
request->req.operation == BLKIF_OP_READ ?
"read" : "write");
request->aio_errors++;
}
request->aio_inflight--;
if (request->presync) {
request->presync = 0;
xen_block_do_aio(request);
goto done;
}
if (request->aio_inflight > 0) {
goto done;
}
switch (request->req.operation) {
case BLKIF_OP_READ:
/* in case of failure request->aio_errors is increased */
if (ret == 0) {
xen_block_copy_request(request);
}
break;
case BLKIF_OP_WRITE:
case BLKIF_OP_FLUSH_DISKCACHE:
default:
break;
}
request->status = request->aio_errors ? BLKIF_RSP_ERROR : BLKIF_RSP_OKAY;
xen_block_finish_request(request);
switch (request->req.operation) {
case BLKIF_OP_WRITE:
case BLKIF_OP_FLUSH_DISKCACHE:
if (!request->req.nr_segments) {
break;
}
/* fall through */
case BLKIF_OP_READ:
if (request->status == BLKIF_RSP_OKAY) {
block_acct_done(blk_get_stats(dataplane->blk), &request->acct);
} else {
block_acct_failed(blk_get_stats(dataplane->blk), &request->acct);
}
break;
case BLKIF_OP_DISCARD:
default:
break;
}
if (xen_block_send_response(request)) {
Error *local_err = NULL;
xen_device_notify_event_channel(dataplane->xendev,
dataplane->event_channel,
&local_err);
if (local_err) {
error_report_err(local_err);
}
}
xen_block_release_request(request);
qemu_bh_schedule(dataplane->bh);
done:
aio_context_release(dataplane->ctx);
}
