* [Qemu-devel] [PATCH v4 1/5] block: add accounting for merged requests
2015-02-02 13:52 [Qemu-devel] [PATCH v4 0/5] this series adds the long missing multiread support to virtio-blk Peter Lieven
@ 2015-02-02 13:52 ` Peter Lieven
2015-02-02 13:52 ` [Qemu-devel] [PATCH v4 2/5] hw/virtio-blk: add a constant for max number of " Peter Lieven
` (4 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: Peter Lieven @ 2015-02-02 13:52 UTC (permalink / raw)
To: qemu-devel
Cc: kwolf, famz, benoit, ming.lei, Peter Lieven, armbru, mreitz,
stefanha, pbonzini
Signed-off-by: Peter Lieven <pl@kamp.de>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
---
block.c | 2 ++
block/accounting.c | 7 +++++++
block/qapi.c | 2 ++
hmp.c | 6 +++++-
include/block/accounting.h | 3 +++
qapi/block-core.json | 9 ++++++++-
qmp-commands.hx | 22 ++++++++++++++++++----
7 files changed, 45 insertions(+), 6 deletions(-)
diff --git a/block.c b/block.c
index d45e4dd..61412e9 100644
--- a/block.c
+++ b/block.c
@@ -4562,6 +4562,8 @@ static int multiwrite_merge(BlockDriverState *bs, BlockRequest *reqs,
}
}
+ block_acct_merge_done(&bs->stats, BLOCK_ACCT_WRITE, num_reqs - outidx - 1);
+
return outidx + 1;
}
diff --git a/block/accounting.c b/block/accounting.c
index 18102f0..01d594f 100644
--- a/block/accounting.c
+++ b/block/accounting.c
@@ -54,3 +54,10 @@ void block_acct_highest_sector(BlockAcctStats *stats, int64_t sector_num,
stats->wr_highest_sector = sector_num + nb_sectors - 1;
}
}
+
+void block_acct_merge_done(BlockAcctStats *stats, enum BlockAcctType type,
+ int num_requests)
+{
+ assert(type < BLOCK_MAX_IOTYPE);
+ stats->merged[type] += num_requests;
+}
diff --git a/block/qapi.c b/block/qapi.c
index 75c388e..d1a8917 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -335,6 +335,8 @@ static BlockStats *bdrv_query_stats(const BlockDriverState *bs,
s->stats->wr_bytes = bs->stats.nr_bytes[BLOCK_ACCT_WRITE];
s->stats->rd_operations = bs->stats.nr_ops[BLOCK_ACCT_READ];
s->stats->wr_operations = bs->stats.nr_ops[BLOCK_ACCT_WRITE];
+ s->stats->rd_merged = bs->stats.merged[BLOCK_ACCT_READ];
+ s->stats->wr_merged = bs->stats.merged[BLOCK_ACCT_WRITE];
s->stats->wr_highest_offset =
bs->stats.wr_highest_sector * BDRV_SECTOR_SIZE;
s->stats->flush_operations = bs->stats.nr_ops[BLOCK_ACCT_FLUSH];
diff --git a/hmp.c b/hmp.c
index 481be80..5a10154 100644
--- a/hmp.c
+++ b/hmp.c
@@ -474,6 +474,8 @@ void hmp_info_blockstats(Monitor *mon, const QDict *qdict)
" wr_total_time_ns=%" PRId64
" rd_total_time_ns=%" PRId64
" flush_total_time_ns=%" PRId64
+ " rd_merged=%" PRId64
+ " wr_merged=%" PRId64
"\n",
stats->value->stats->rd_bytes,
stats->value->stats->wr_bytes,
@@ -482,7 +484,9 @@ void hmp_info_blockstats(Monitor *mon, const QDict *qdict)
stats->value->stats->flush_operations,
stats->value->stats->wr_total_time_ns,
stats->value->stats->rd_total_time_ns,
- stats->value->stats->flush_total_time_ns);
+ stats->value->stats->flush_total_time_ns,
+ stats->value->stats->rd_merged,
+ stats->value->stats->wr_merged);
}
qapi_free_BlockStatsList(stats_list);
diff --git a/include/block/accounting.h b/include/block/accounting.h
index 50b42b3..4c406cf 100644
--- a/include/block/accounting.h
+++ b/include/block/accounting.h
@@ -39,6 +39,7 @@ typedef struct BlockAcctStats {
uint64_t nr_bytes[BLOCK_MAX_IOTYPE];
uint64_t nr_ops[BLOCK_MAX_IOTYPE];
uint64_t total_time_ns[BLOCK_MAX_IOTYPE];
+ uint64_t merged[BLOCK_MAX_IOTYPE];
uint64_t wr_highest_sector;
} BlockAcctStats;
@@ -53,5 +54,7 @@ void block_acct_start(BlockAcctStats *stats, BlockAcctCookie *cookie,
void block_acct_done(BlockAcctStats *stats, BlockAcctCookie *cookie);
void block_acct_highest_sector(BlockAcctStats *stats, int64_t sector_num,
unsigned int nb_sectors);
+void block_acct_merge_done(BlockAcctStats *stats, enum BlockAcctType type,
+ int num_requests);
#endif
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 80984d1..b7d9772 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -407,13 +407,20 @@
# growable sparse files (like qcow2) that are used on top
# of a physical device.
#
+# @rd_merged: Number of read requests that have been merged into another
+# request (Since 2.3).
+#
+# @wr_merged: Number of write requests that have been merged into another
+# request (Since 2.3).
+#
# Since: 0.14.0
##
{ 'type': 'BlockDeviceStats',
'data': {'rd_bytes': 'int', 'wr_bytes': 'int', 'rd_operations': 'int',
'wr_operations': 'int', 'flush_operations': 'int',
'flush_total_time_ns': 'int', 'wr_total_time_ns': 'int',
- 'rd_total_time_ns': 'int', 'wr_highest_offset': 'int' } }
+ 'rd_total_time_ns': 'int', 'wr_highest_offset': 'int',
+ 'rd_merged': 'int', 'wr_merged': 'int' } }
##
# @BlockStats:
diff --git a/qmp-commands.hx b/qmp-commands.hx
index c5f16dd..af3fd19 100644
--- a/qmp-commands.hx
+++ b/qmp-commands.hx
@@ -2303,6 +2303,10 @@ Each json-object contain the following:
- "flush_total_time_ns": total time spend on cache flushes in nano-seconds (json-int)
- "wr_highest_offset": Highest offset of a sector written since the
BlockDriverState has been opened (json-int)
+ - "rd_merged": number of read requests that have been merged into
+ another request (json-int)
+ - "wr_merged": number of write requests that have been merged into
+ another request (json-int)
- "parent": Contains recursively the statistics of the underlying
protocol (e.g. the host file for a qcow2 image). If there is
no underlying protocol, this field is omitted
@@ -2326,6 +2330,8 @@ Example:
"rd_total_times_ns":3465673657
"flush_total_times_ns":49653
"flush_operations":61,
+ "rd_merged":0,
+ "wr_merged":0
}
},
"stats":{
@@ -2337,7 +2343,9 @@ Example:
"flush_operations":51,
"wr_total_times_ns":313253456
"rd_total_times_ns":3465673657
- "flush_total_times_ns":49653
+ "flush_total_times_ns":49653,
+ "rd_merged":0,
+ "wr_merged":0
}
},
{
@@ -2351,7 +2359,9 @@ Example:
"flush_operations":0,
"wr_total_times_ns":0
"rd_total_times_ns":0
- "flush_total_times_ns":0
+ "flush_total_times_ns":0,
+ "rd_merged":0,
+ "wr_merged":0
}
},
{
@@ -2365,7 +2375,9 @@ Example:
"flush_operations":0,
"wr_total_times_ns":0
"rd_total_times_ns":0
- "flush_total_times_ns":0
+ "flush_total_times_ns":0,
+ "rd_merged":0,
+ "wr_merged":0
}
},
{
@@ -2379,7 +2391,9 @@ Example:
"flush_operations":0,
"wr_total_times_ns":0
"rd_total_times_ns":0
- "flush_total_times_ns":0
+ "flush_total_times_ns":0,
+ "rd_merged":0,
+ "wr_merged":0
}
}
]
--
1.9.1
^ permalink raw reply related [flat|nested] 7+ messages in thread* [Qemu-devel] [PATCH v4 4/5] virtio-blk: introduce multiread
2015-02-02 13:52 [Qemu-devel] [PATCH v4 0/5] this series adds the long missing multiread support to virtio-blk Peter Lieven
` (2 preceding siblings ...)
2015-02-02 13:52 ` [Qemu-devel] [PATCH v4 3/5] block-backend: expose bs->bl.max_transfer_length Peter Lieven
@ 2015-02-02 13:52 ` Peter Lieven
2015-02-02 13:52 ` [Qemu-devel] [PATCH v4 5/5] virtio-blk: add a knob to disable request merging Peter Lieven
2015-02-02 16:09 ` [Qemu-devel] [PATCH v4 0/5] this series adds the long missing multiread support to virtio-blk Kevin Wolf
5 siblings, 0 replies; 7+ messages in thread
From: Peter Lieven @ 2015-02-02 13:52 UTC (permalink / raw)
To: qemu-devel
Cc: kwolf, famz, benoit, ming.lei, Peter Lieven, armbru, mreitz,
stefanha, pbonzini
this patch finally introduces multiread support to virtio-blk. While
multiwrite support was there for a long time, read support was missing.
The complete merge logic is moved into virtio-blk.c which has
been the only user of request merging ever since. This is required
to be able to merge chunks of requests and immediately invoke callbacks
for those requests. Secondly, this is required to switch to
direct invocation of coroutines which is planned at a later stage.
The following benchmarks show the performance of running fio with
4 worker threads on a local ram disk. The numbers show the average
of 10 test runs after 1 run as warmup phase.
| 4k | 64k | 4k
MB/s | rd seq | rd rand | rd seq | rd rand | wr seq | wr rand
--------------+--------+---------+--------+---------+--------+--------
master | 1221 | 1187 | 4178 | 4114 | 1745 | 1213
multiread | 1829 | 1189 | 4639 | 4110 | 1894 | 1216
Signed-off-by: Peter Lieven <pl@kamp.de>
---
hw/block/dataplane/virtio-blk.c | 8 +-
hw/block/virtio-blk.c | 296 +++++++++++++++++++++++++++-------------
include/hw/virtio/virtio-blk.h | 19 +--
trace-events | 1 +
4 files changed, 218 insertions(+), 106 deletions(-)
diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
index 39c5d71..be957d1 100644
--- a/hw/block/dataplane/virtio-blk.c
+++ b/hw/block/dataplane/virtio-blk.c
@@ -96,9 +96,7 @@ static void handle_notify(EventNotifier *e)
event_notifier_test_and_clear(&s->host_notifier);
blk_io_plug(s->conf->conf.blk);
for (;;) {
- MultiReqBuffer mrb = {
- .num_writes = 0,
- };
+ MultiReqBuffer mrb = {};
int ret;
/* Disable guest->host notifies to avoid unnecessary vmexits */
@@ -120,7 +118,9 @@ static void handle_notify(EventNotifier *e)
virtio_blk_handle_request(req, &mrb);
}
- virtio_submit_multiwrite(s->conf->conf.blk, &mrb);
+ if (mrb.num_reqs) {
+ virtio_blk_submit_multireq(s->conf->conf.blk, &mrb);
+ }
if (likely(ret == -EAGAIN)) { /* vring emptied */
/* Re-enable guest->host notifies and stop processing the vring.
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index e04adb8..d0a01a8 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -34,6 +34,7 @@ VirtIOBlockReq *virtio_blk_alloc_request(VirtIOBlock *s)
req->dev = s;
req->qiov.size = 0;
req->next = NULL;
+ req->mr_next = NULL;
return req;
}
@@ -84,20 +85,32 @@ static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error,
static void virtio_blk_rw_complete(void *opaque, int ret)
{
- VirtIOBlockReq *req = opaque;
+ VirtIOBlockReq *next = opaque;
- trace_virtio_blk_rw_complete(req, ret);
+ while (next) {
+ VirtIOBlockReq *req = next;
+ next = req->mr_next;
+ trace_virtio_blk_rw_complete(req, ret);
- 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))
- return;
- }
+ 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);
+ }
- 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);
+ 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_flush_complete(void *opaque, int ret)
@@ -291,24 +304,127 @@ static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
}
}
-void virtio_submit_multiwrite(BlockBackend *blk, MultiReqBuffer *mrb)
+static inline void submit_requests(BlockBackend *blk, MultiReqBuffer *mrb,
+ int start, int num_reqs, int niov)
{
- int i, ret;
+ 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);
+ }
- if (!mrb->num_writes) {
+ 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 multireq_compare(const void *a, const void *b)
+{
+ const VirtIOBlockReq *req1 = *(VirtIOBlockReq **)a,
+ *req2 = *(VirtIOBlockReq **)b;
+
+ /*
+ * Note that we can't simply subtract sector_num1 from sector_num2
+ * here as that could overflow the return value.
+ */
+ if (req1->sector_num > req2->sector_num) {
+ return 1;
+ } else if (req1->sector_num < req2->sector_num) {
+ return -1;
+ } else {
+ return 0;
+ }
+}
+
+void virtio_blk_submit_multireq(BlockBackend *blk, MultiReqBuffer *mrb)
+{
+ int i = 0, start = 0, num_reqs = 0, niov = 0, nb_sectors = 0;
+ int max_xfer_len = 0;
+ int64_t sector_num = 0;
+
+ if (mrb->num_reqs == 1) {
+ submit_requests(blk, mrb, 0, 1, -1);
+ mrb->num_reqs = 0;
return;
}
- ret = blk_aio_multiwrite(blk, mrb->blkreq, mrb->num_writes);
- if (ret != 0) {
- for (i = 0; i < mrb->num_writes; i++) {
- if (mrb->blkreq[i].error) {
- virtio_blk_rw_complete(mrb->blkreq[i].opaque, -EIO);
+ max_xfer_len = blk_get_max_transfer_length(mrb->reqs[0]->dev->blk);
+ max_xfer_len = MIN_NON_ZERO(max_xfer_len, INT_MAX);
+
+ qsort(mrb->reqs, mrb->num_reqs, sizeof(*mrb->reqs),
+ &multireq_compare);
+
+ for (i = 0; i < mrb->num_reqs; i++) {
+ VirtIOBlockReq *req = mrb->reqs[i];
+ if (num_reqs > 0) {
+ bool merge = true;
+
+ /* merge would exceed maximum number of IOVs */
+ if (niov + req->qiov.niov > IOV_MAX) {
+ merge = false;
+ }
+
+ /* merge would exceed maximum transfer length of backend device */
+ if (req->qiov.size / BDRV_SECTOR_SIZE + nb_sectors > max_xfer_len) {
+ merge = false;
+ }
+
+ /* requests are not sequential */
+ if (sector_num + nb_sectors != req->sector_num) {
+ merge = false;
+ }
+
+ if (!merge) {
+ submit_requests(blk, mrb, start, num_reqs, niov);
+ num_reqs = 0;
}
}
+
+ if (num_reqs == 0) {
+ sector_num = req->sector_num;
+ nb_sectors = niov = 0;
+ start = i;
+ }
+
+ nb_sectors += req->qiov.size / BDRV_SECTOR_SIZE;
+ niov += req->qiov.niov;
+ num_reqs++;
}
- mrb->num_writes = 0;
+ submit_requests(blk, mrb, start, num_reqs, niov);
+ mrb->num_reqs = 0;
}
static void virtio_blk_handle_flush(VirtIOBlockReq *req, MultiReqBuffer *mrb)
@@ -319,7 +435,9 @@ static void virtio_blk_handle_flush(VirtIOBlockReq *req, MultiReqBuffer *mrb)
/*
* Make sure all outstanding writes are posted to the backing device.
*/
- virtio_submit_multiwrite(req->dev->blk, mrb);
+ 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);
}
@@ -329,6 +447,9 @@ static bool virtio_blk_sect_range_ok(VirtIOBlock *dev,
uint64_t nb_sectors = size >> BDRV_SECTOR_BITS;
uint64_t total_sectors;
+ if (nb_sectors > INT_MAX) {
+ return false;
+ }
if (sector & dev->sector_mask) {
return false;
}
@@ -342,60 +463,6 @@ static bool virtio_blk_sect_range_ok(VirtIOBlock *dev,
return true;
}
-static void virtio_blk_handle_write(VirtIOBlockReq *req, MultiReqBuffer *mrb)
-{
- BlockRequest *blkreq;
- uint64_t sector;
-
- sector = virtio_ldq_p(VIRTIO_DEVICE(req->dev), &req->out.sector);
-
- trace_virtio_blk_handle_write(req, sector, req->qiov.size / 512);
-
- if (!virtio_blk_sect_range_ok(req->dev, sector, req->qiov.size)) {
- virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
- virtio_blk_free_request(req);
- return;
- }
-
- block_acct_start(blk_get_stats(req->dev->blk), &req->acct, req->qiov.size,
- BLOCK_ACCT_WRITE);
-
- if (mrb->num_writes == VIRTIO_BLK_MAX_MERGE_REQS) {
- virtio_submit_multiwrite(req->dev->blk, mrb);
- }
-
- blkreq = &mrb->blkreq[mrb->num_writes];
- blkreq->sector = sector;
- blkreq->nb_sectors = req->qiov.size / BDRV_SECTOR_SIZE;
- blkreq->qiov = &req->qiov;
- blkreq->cb = virtio_blk_rw_complete;
- blkreq->opaque = req;
- blkreq->error = 0;
-
- mrb->num_writes++;
-}
-
-static void virtio_blk_handle_read(VirtIOBlockReq *req)
-{
- uint64_t sector;
-
- sector = virtio_ldq_p(VIRTIO_DEVICE(req->dev), &req->out.sector);
-
- trace_virtio_blk_handle_read(req, sector, req->qiov.size / 512);
-
- if (!virtio_blk_sect_range_ok(req->dev, sector, req->qiov.size)) {
- virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
- virtio_blk_free_request(req);
- return;
- }
-
- block_acct_start(blk_get_stats(req->dev->blk), &req->acct, req->qiov.size,
- BLOCK_ACCT_READ);
- blk_aio_readv(req->dev->blk, sector, &req->qiov,
- req->qiov.size / BDRV_SECTOR_SIZE,
- virtio_blk_rw_complete, req);
-}
-
void virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
{
uint32_t type;
@@ -430,11 +497,57 @@ void virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
type = virtio_ldl_p(VIRTIO_DEVICE(req->dev), &req->out.type);
- if (type & VIRTIO_BLK_T_FLUSH) {
+ /* VIRTIO_BLK_T_OUT defines the command direction. VIRTIO_BLK_T_BARRIER
+ * is an optional flag. Altough a guest should not send this flag if
+ * not negotiated we ignored it in the past. So keep ignoring it. */
+ switch (type & ~(VIRTIO_BLK_T_OUT | VIRTIO_BLK_T_BARRIER)) {
+ case VIRTIO_BLK_T_IN:
+ {
+ bool is_write = type & VIRTIO_BLK_T_OUT;
+ req->sector_num = virtio_ldq_p(VIRTIO_DEVICE(req->dev),
+ &req->out.sector);
+
+ if (is_write) {
+ qemu_iovec_init_external(&req->qiov, iov, out_num);
+ trace_virtio_blk_handle_write(req, req->sector_num,
+ req->qiov.size / BDRV_SECTOR_SIZE);
+ } else {
+ qemu_iovec_init_external(&req->qiov, in_iov, in_num);
+ trace_virtio_blk_handle_read(req, req->sector_num,
+ req->qiov.size / BDRV_SECTOR_SIZE);
+ }
+
+ if (!virtio_blk_sect_range_ok(req->dev, req->sector_num,
+ req->qiov.size)) {
+ virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
+ virtio_blk_free_request(req);
+ return;
+ }
+
+ block_acct_start(blk_get_stats(req->dev->blk),
+ &req->acct, req->qiov.size,
+ is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
+
+ /* merge would exceed maximum number of requests or IO direction
+ * changes */
+ if (mrb->num_reqs > 0 && (mrb->num_reqs == VIRTIO_BLK_MAX_MERGE_REQS ||
+ is_write != mrb->is_write)) {
+ virtio_blk_submit_multireq(req->dev->blk, mrb);
+ }
+
+ assert(mrb->num_reqs < VIRTIO_BLK_MAX_MERGE_REQS);
+ mrb->reqs[mrb->num_reqs++] = req;
+ mrb->is_write = is_write;
+ break;
+ }
+ case VIRTIO_BLK_T_FLUSH:
virtio_blk_handle_flush(req, mrb);
- } else if (type & VIRTIO_BLK_T_SCSI_CMD) {
+ break;
+ case VIRTIO_BLK_T_SCSI_CMD:
virtio_blk_handle_scsi(req);
- } else if (type & VIRTIO_BLK_T_GET_ID) {
+ break;
+ case VIRTIO_BLK_T_GET_ID:
+ {
VirtIOBlock *s = req->dev;
/*
@@ -448,14 +561,9 @@ void virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
iov_from_buf(in_iov, in_num, 0, serial, size);
virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
virtio_blk_free_request(req);
- } else if (type & VIRTIO_BLK_T_OUT) {
- qemu_iovec_init_external(&req->qiov, iov, out_num);
- virtio_blk_handle_write(req, mrb);
- } else if (type == VIRTIO_BLK_T_IN || type == VIRTIO_BLK_T_BARRIER) {
- /* VIRTIO_BLK_T_IN is 0, so we can't just & it. */
- qemu_iovec_init_external(&req->qiov, in_iov, in_num);
- virtio_blk_handle_read(req);
- } else {
+ break;
+ }
+ default:
virtio_blk_req_complete(req, VIRTIO_BLK_S_UNSUPP);
virtio_blk_free_request(req);
}
@@ -465,9 +573,7 @@ static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIOBlock *s = VIRTIO_BLK(vdev);
VirtIOBlockReq *req;
- MultiReqBuffer mrb = {
- .num_writes = 0,
- };
+ MultiReqBuffer mrb = {};
/* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start
* dataplane here instead of waiting for .set_status().
@@ -481,7 +587,9 @@ static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
virtio_blk_handle_request(req, &mrb);
}
- virtio_submit_multiwrite(s->blk, &mrb);
+ if (mrb.num_reqs) {
+ virtio_blk_submit_multireq(s->blk, &mrb);
+ }
/*
* FIXME: Want to check for completions before returning to guest mode,
@@ -494,9 +602,7 @@ static void virtio_blk_dma_restart_bh(void *opaque)
{
VirtIOBlock *s = opaque;
VirtIOBlockReq *req = s->rq;
- MultiReqBuffer mrb = {
- .num_writes = 0,
- };
+ MultiReqBuffer mrb = {};
qemu_bh_delete(s->bh);
s->bh = NULL;
@@ -509,7 +615,9 @@ static void virtio_blk_dma_restart_bh(void *opaque)
req = next;
}
- virtio_submit_multiwrite(s->blk, &mrb);
+ if (mrb.num_reqs) {
+ virtio_blk_submit_multireq(s->blk, &mrb);
+ }
}
static void virtio_blk_dma_restart_cb(void *opaque, int running,
diff --git a/include/hw/virtio/virtio-blk.h b/include/hw/virtio/virtio-blk.h
index 6ef3fa5..2027a64 100644
--- a/include/hw/virtio/virtio-blk.h
+++ b/include/hw/virtio/virtio-blk.h
@@ -134,29 +134,32 @@ typedef struct VirtIOBlock {
struct VirtIOBlockDataPlane *dataplane;
} VirtIOBlock;
-#define VIRTIO_BLK_MAX_MERGE_REQS 32
-
-typedef struct MultiReqBuffer {
- BlockRequest blkreq[VIRTIO_BLK_MAX_MERGE_REQS];
- unsigned int num_writes;
-} MultiReqBuffer;
-
typedef struct VirtIOBlockReq {
+ int64_t sector_num;
VirtIOBlock *dev;
VirtQueueElement elem;
struct virtio_blk_inhdr *in;
struct virtio_blk_outhdr out;
QEMUIOVector qiov;
struct VirtIOBlockReq *next;
+ struct VirtIOBlockReq *mr_next;
BlockAcctCookie acct;
} VirtIOBlockReq;
+#define VIRTIO_BLK_MAX_MERGE_REQS 32
+
+typedef struct MultiReqBuffer {
+ VirtIOBlockReq *reqs[VIRTIO_BLK_MAX_MERGE_REQS];
+ unsigned int num_reqs;
+ bool is_write;
+} MultiReqBuffer;
+
VirtIOBlockReq *virtio_blk_alloc_request(VirtIOBlock *s);
void virtio_blk_free_request(VirtIOBlockReq *req);
void virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb);
-void virtio_submit_multiwrite(BlockBackend *blk, MultiReqBuffer *mrb);
+void virtio_blk_submit_multireq(BlockBackend *blk, MultiReqBuffer *mrb);
#endif
diff --git a/trace-events b/trace-events
index 04f5df2..9e8ad8a 100644
--- a/trace-events
+++ b/trace-events
@@ -116,6 +116,7 @@ virtio_blk_req_complete(void *req, int status) "req %p status %d"
virtio_blk_rw_complete(void *req, int ret) "req %p ret %d"
virtio_blk_handle_write(void *req, uint64_t sector, size_t nsectors) "req %p sector %"PRIu64" nsectors %zu"
virtio_blk_handle_read(void *req, uint64_t sector, size_t nsectors) "req %p sector %"PRIu64" nsectors %zu"
+virtio_blk_submit_multireq(void *mrb, int start, int num_reqs, uint64_t sector, size_t nsectors, bool is_write) "mrb %p start %d num_reqs %d sector %"PRIu64" nsectors %zu is_write %d"
# hw/block/dataplane/virtio-blk.c
virtio_blk_data_plane_start(void *s) "dataplane %p"
--
1.9.1
^ permalink raw reply related [flat|nested] 7+ messages in thread