[Qemu-devel] [PATCH v7 0/4] The intro of QEMU block I/O throttling

[Qemu-devel] [PATCH v7 0/4] The intro of QEMU block I/O throttling

[Zhi Yong Wu]

The main goal of the patch is to effectively cap the disk I/O speed or counts of one single VM.It is only one draft, so it unavoidably has some drawbacks, if you catch them, please let me know.

The patch will mainly introduce one block I/O throttling algorithm, one timer and one block queue for each I/O limits enabled drive.

When a block request is coming in, the throttling algorithm will check if its I/O rate or counts exceed the limits; if yes, then it will enqueue to the block queue; The timer will handle the I/O requests in it.

Some available features follow as below:
(1) global bps limit.
   -drive bps=xxx            in bytes/s
(2) only read bps limit
   -drive bps_rd=xxx         in bytes/s
(3) only write bps limit
   -drive bps_wr=xxx         in bytes/s
(4) global iops limit
   -drive iops=xxx           in ios/s
(5) only read iops limit
   -drive iops_rd=xxx        in ios/s
(6) only write iops limit
   -drive iops_wr=xxx        in ios/s
(7) the combination of some limits.
   -drive bps=xxx,iops=xxx

Known Limitations:
(1) #1 can not coexist with #2, #3
(2) #4 can not coexist with #5, #6
(3) When bps/iops limits are specified to a small value such as 511 bytes/s, this VM will hang up. We are considering how to handle this senario.

Changes since code V6:
  Mainly simply the block queue.
  Adjust codes based on stefan's comments.

Zhi Yong Wu (4):
  block: add the command line support
  block: add the block queue support
  block: add block timer and throttling algorithm
  qmp/hmp: add block_set_io_throttle

 v6: Mainly fix the aio callback issue for block queue.
     Adjust codes based on Ram Pai's comments.

 v5: add qmp/hmp support.
     Adjust the codes based on stefan's comments
     qmp/hmp: add block_set_io_throttle

 v4: fix memory leaking based on ryan's feedback.

 v3: Added the code for extending slice time, and modified the method to compute wait time for the timer.

 v2: The codes V2 for QEMU disk I/O limits.
     Modified the codes mainly based on stefan's comments.

 v1: Submit the codes for QEMU disk I/O limits.
     Only a code draft.

 Makefile.objs     |    2 +-
 block.c           |  331 +++++++++++++++++++++++++++++++++++++++++++++++++++--
 block.h           |    6 +-
 block/blk-queue.c |  184 +++++++++++++++++++++++++++++
 block/blk-queue.h |   59 ++++++++++
 block_int.h       |   30 +++++
 blockdev.c        |   98 ++++++++++++++++
 blockdev.h        |    2 +
 hmp-commands.hx   |   15 +++
 qemu-config.c     |   24 ++++
 qemu-options.hx   |    1 +
 qerror.c          |    4 +
 qerror.h          |    3 +
 qmp-commands.hx   |   52 ++++++++-
 14 files changed, 796 insertions(+), 15 deletions(-)
 create mode 100644 block/blk-queue.c
 create mode 100644 block/blk-queue.h

-- 
1.7.6

[Qemu-devel] [PATCH v7 1/4] block: add the command line support

[Zhi Yong Wu]

Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
---
 block.c         |    8 ++++++++
 block_int.h     |   30 ++++++++++++++++++++++++++++++
 blockdev.c      |   29 +++++++++++++++++++++++++++++
 blockdev.h      |    2 ++
 qemu-config.c   |   24 ++++++++++++++++++++++++
 qemu-options.hx |    1 +
 6 files changed, 94 insertions(+), 0 deletions(-)

diff --git a/block.c b/block.c
index 03a21d8..17ee3df 100644
--- a/block.c
+++ b/block.c
@@ -1453,6 +1453,14 @@ void bdrv_get_geometry_hint(BlockDriverState *bs,
     *psecs = bs->secs;
 }
 
+/* throttling disk io limits */
+void bdrv_set_io_limits(BlockDriverState *bs,
+                            BlockIOLimit *io_limits)
+{
+    bs->io_limits = *io_limits;
+    bs->io_limits_enabled = bdrv_io_limits_enabled(bs);
+}
+
 /* Recognize floppy formats */
 typedef struct FDFormat {
     FDriveType drive;
diff --git a/block_int.h b/block_int.h
index 8a72b80..368c776 100644
--- a/block_int.h
+++ b/block_int.h
@@ -29,10 +29,18 @@
 #include "qemu-queue.h"
 #include "qemu-coroutine.h"
 #include "qemu-timer.h"
+#include "block/blk-queue.h"
 
 #define BLOCK_FLAG_ENCRYPT	1
 #define BLOCK_FLAG_COMPAT6	4
 
+#define BLOCK_IO_LIMIT_READ     0
+#define BLOCK_IO_LIMIT_WRITE    1
+#define BLOCK_IO_LIMIT_TOTAL    2
+
+#define BLOCK_IO_SLICE_TIME     100000000
+#define NANOSECONDS_PER_SECOND  1000000000.0
+
 #define BLOCK_OPT_SIZE          "size"
 #define BLOCK_OPT_ENCRYPT       "encryption"
 #define BLOCK_OPT_COMPAT6       "compat6"
@@ -49,6 +57,16 @@ typedef struct AIOPool {
     BlockDriverAIOCB *free_aiocb;
 } AIOPool;
 
+typedef struct BlockIOLimit {
+    uint64_t bps[3];
+    uint64_t iops[3];
+} BlockIOLimit;
+
+typedef struct BlockIODisp {
+    uint64_t bytes[2];
+    uint64_t ios[2];
+} BlockIODisp;
+
 struct BlockDriver {
     const char *format_name;
     int instance_size;
@@ -184,6 +202,15 @@ struct BlockDriverState {
 
     void *sync_aiocb;
 
+    /* the time for latest disk I/O */
+    int64_t slice_start;
+    int64_t slice_end;
+    BlockIOLimit io_limits;
+    BlockIODisp  io_disps;
+    BlockQueue   *block_queue;
+    QEMUTimer    *block_timer;
+    bool         io_limits_enabled;
+
     /* I/O stats (display with "info blockstats"). */
     uint64_t nr_bytes[BDRV_MAX_IOTYPE];
     uint64_t nr_ops[BDRV_MAX_IOTYPE];
@@ -230,6 +257,9 @@ void qemu_aio_release(void *p);
 
 void *qemu_blockalign(BlockDriverState *bs, size_t size);
 
+void bdrv_set_io_limits(BlockDriverState *bs,
+                            BlockIOLimit *io_limits);
+
 #ifdef _WIN32
 int is_windows_drive(const char *filename);
 #endif
diff --git a/blockdev.c b/blockdev.c
index 2602591..619ae9f 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -236,6 +236,7 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
     int on_read_error, on_write_error;
     const char *devaddr;
     DriveInfo *dinfo;
+    BlockIOLimit io_limits;
     int snapshot = 0;
     int ret;
 
@@ -354,6 +355,31 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
         }
     }
 
+    /* disk I/O throttling */
+    io_limits.bps[BLOCK_IO_LIMIT_TOTAL]  =
+                           qemu_opt_get_number(opts, "bps", 0);
+    io_limits.bps[BLOCK_IO_LIMIT_READ]   =
+                           qemu_opt_get_number(opts, "bps_rd", 0);
+    io_limits.bps[BLOCK_IO_LIMIT_WRITE]  =
+                           qemu_opt_get_number(opts, "bps_wr", 0);
+    io_limits.iops[BLOCK_IO_LIMIT_TOTAL] =
+                           qemu_opt_get_number(opts, "iops", 0);
+    io_limits.iops[BLOCK_IO_LIMIT_READ]  =
+                           qemu_opt_get_number(opts, "iops_rd", 0);
+    io_limits.iops[BLOCK_IO_LIMIT_WRITE] =
+                           qemu_opt_get_number(opts, "iops_wr", 0);
+
+    if (((io_limits.bps[BLOCK_IO_LIMIT_TOTAL] != 0)
+            && ((io_limits.bps[BLOCK_IO_LIMIT_READ] != 0)
+            || (io_limits.bps[BLOCK_IO_LIMIT_WRITE] != 0)))
+            || ((io_limits.iops[BLOCK_IO_LIMIT_TOTAL] != 0)
+            && ((io_limits.iops[BLOCK_IO_LIMIT_READ] != 0)
+            || (io_limits.iops[BLOCK_IO_LIMIT_WRITE] != 0)))) {
+        error_report("bps(iops) and bps_rd/bps_wr(iops_rd/iops_wr)"
+                     "cannot be used at the same time");
+        return NULL;
+    }
+
     on_write_error = BLOCK_ERR_STOP_ENOSPC;
     if ((buf = qemu_opt_get(opts, "werror")) != NULL) {
         if (type != IF_IDE && type != IF_SCSI && type != IF_VIRTIO && type != IF_NONE) {
@@ -461,6 +487,9 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 
     bdrv_set_on_error(dinfo->bdrv, on_read_error, on_write_error);
 
+    /* disk I/O throttling */
+    bdrv_set_io_limits(dinfo->bdrv, &io_limits);
+
     switch(type) {
     case IF_IDE:
     case IF_SCSI:
diff --git a/blockdev.h b/blockdev.h
index 3587786..c2f44c6 100644
--- a/blockdev.h
+++ b/blockdev.h
@@ -63,6 +63,8 @@ int do_block_set_passwd(Monitor *mon, const QDict *qdict, QObject **ret_data);
 int do_change_block(Monitor *mon, const char *device,
                     const char *filename, const char *fmt);
 int do_drive_del(Monitor *mon, const QDict *qdict, QObject **ret_data);
+int do_block_set_io_throttle(Monitor *mon,
+                    const QDict *qdict, QObject **ret_data);
 int do_snapshot_blkdev(Monitor *mon, const QDict *qdict, QObject **ret_data);
 int do_block_resize(Monitor *mon, const QDict *qdict, QObject **ret_data);
 
diff --git a/qemu-config.c b/qemu-config.c
index 139e077..abcf476 100644
--- a/qemu-config.c
+++ b/qemu-config.c
@@ -85,6 +85,30 @@ static QemuOptsList qemu_drive_opts = {
             .name = "readonly",
             .type = QEMU_OPT_BOOL,
             .help = "open drive file as read-only",
+        },{
+            .name = "iops",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit total I/O operations per second",
+        },{
+            .name = "iops_rd",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit read operations per second",
+        },{
+            .name = "iops_wr",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit write operations per second",
+        },{
+            .name = "bps",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit total bytes per second",
+        },{
+            .name = "bps_rd",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit read bytes per second",
+        },{
+            .name = "bps_wr",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit write bytes per second",
         },
         { /* end of list */ }
     },
diff --git a/qemu-options.hx b/qemu-options.hx
index 35d95d1..bbd15dd 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -136,6 +136,7 @@ DEF("drive", HAS_ARG, QEMU_OPTION_drive,
     "       [,cache=writethrough|writeback|none|directsync|unsafe][,format=f]\n"
     "       [,serial=s][,addr=A][,id=name][,aio=threads|native]\n"
     "       [,readonly=on|off]\n"
+    "       [[,bps=b]|[[,bps_rd=r][,bps_wr=w]]][[,iops=i]|[[,iops_rd=r][,iops_wr=w]]\n"
     "                use 'file' as a drive image\n", QEMU_ARCH_ALL)
 STEXI
 @item -drive @var{option}[,@var{option}[,@var{option}[,...]]]
-- 
1.7.6

[Qemu-devel] [PATCH v7 2/4] block: add the block queue support

[Zhi Yong Wu]

Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
---
 Makefile.objs     |    2 +-
 block/blk-queue.c |  184 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 block/blk-queue.h |   59 +++++++++++++++++
 3 files changed, 244 insertions(+), 1 deletions(-)
 create mode 100644 block/blk-queue.c
 create mode 100644 block/blk-queue.h

diff --git a/Makefile.objs b/Makefile.objs
index d1f3e5d..96a7323 100644
--- a/Makefile.objs
+++ b/Makefile.objs
@@ -33,7 +33,7 @@ block-nested-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vv
 block-nested-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
 block-nested-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
 block-nested-y += qed-check.o
-block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o
+block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o blk-queue.o
 block-nested-$(CONFIG_WIN32) += raw-win32.o
 block-nested-$(CONFIG_POSIX) += raw-posix.o
 block-nested-$(CONFIG_CURL) += curl.o
diff --git a/block/blk-queue.c b/block/blk-queue.c
new file mode 100644
index 0000000..da01fcb
--- /dev/null
+++ b/block/blk-queue.c
@@ -0,0 +1,184 @@
+/*
+ * QEMU System Emulator queue definition for block layer
+ *
+ * Copyright (c) IBM, Corp. 2011
+ *
+ * Authors:
+ *  Zhi Yong Wu  <wuzhy@linux.vnet.ibm.com>
+ *  Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "block_int.h"
+#include "block/blk-queue.h"
+#include "qemu-common.h"
+
+/* The APIs for block request queue on qemu block layer.
+ */
+
+struct BlockQueueAIOCB {
+    BlockDriverAIOCB common;
+    QTAILQ_ENTRY(BlockQueueAIOCB) entry;
+    BlockRequestHandler *handler;
+    BlockDriverAIOCB *real_acb;
+
+    int64_t sector_num;
+    QEMUIOVector *qiov;
+    int nb_sectors;
+};
+
+typedef struct BlockQueueAIOCB BlockQueueAIOCB;
+
+struct BlockQueue {
+    QTAILQ_HEAD(requests, BlockQueueAIOCB) requests;
+    bool flushing;
+};
+
+static void qemu_block_queue_dequeue(BlockQueue *queue,
+                                     BlockQueueAIOCB *request)
+{
+    BlockQueueAIOCB *req;
+
+    assert(queue);
+    while (!QTAILQ_EMPTY(&queue->requests)) {
+        req = QTAILQ_FIRST(&queue->requests);
+        if (req == request) {
+            QTAILQ_REMOVE(&queue->requests, req, entry);
+            break;
+        }
+    }
+}
+
+static void qemu_block_queue_cancel(BlockDriverAIOCB *acb)
+{
+    BlockQueueAIOCB *request = container_of(acb, BlockQueueAIOCB, common);
+    if (request->real_acb) {
+        bdrv_aio_cancel(request->real_acb);
+    } else {
+        assert(request->common.bs->block_queue);
+        qemu_block_queue_dequeue(request->common.bs->block_queue,
+                                 request);
+    }
+
+    qemu_aio_release(request);
+}
+
+static AIOPool block_queue_pool = {
+    .aiocb_size         = sizeof(struct BlockQueueAIOCB),
+    .cancel             = qemu_block_queue_cancel,
+};
+
+BlockQueue *qemu_new_block_queue(void)
+{
+    BlockQueue *queue;
+
+    queue = g_malloc0(sizeof(BlockQueue));
+
+    QTAILQ_INIT(&queue->requests);
+
+    queue->flushing = false;
+
+    return queue;
+}
+
+void qemu_del_block_queue(BlockQueue *queue)
+{
+    BlockQueueAIOCB *request, *next;
+
+    QTAILQ_FOREACH_SAFE(request, &queue->requests, entry, next) {
+        QTAILQ_REMOVE(&queue->requests, request, entry);
+        qemu_aio_release(request);
+    }
+
+    g_free(queue);
+}
+
+BlockDriverAIOCB *qemu_block_queue_enqueue(BlockQueue *queue,
+                        BlockDriverState *bs,
+                        BlockRequestHandler *handler,
+                        int64_t sector_num,
+                        QEMUIOVector *qiov,
+                        int nb_sectors,
+                        BlockDriverCompletionFunc *cb,
+                        void *opaque)
+{
+    BlockDriverAIOCB *acb;
+    BlockQueueAIOCB *request;
+
+    if (queue->flushing) {
+        return NULL;
+    } else {
+        acb = qemu_aio_get(&block_queue_pool, bs,
+                           cb, opaque);
+        request = container_of(acb, BlockQueueAIOCB, common);
+        request->handler       = handler;
+        request->sector_num    = sector_num;
+        request->qiov          = qiov;
+        request->nb_sectors    = nb_sectors;
+        request->real_acb      = NULL;
+        QTAILQ_INSERT_TAIL(&queue->requests, request, entry);
+    }
+
+    return acb;
+}
+
+static int qemu_block_queue_handler(BlockQueueAIOCB *request)
+{
+    int ret;
+    BlockDriverAIOCB *res;
+
+    res = request->handler(request->common.bs, request->sector_num,
+                           request->qiov, request->nb_sectors,
+                           request->common.cb, request->common.opaque);
+    if (res) {
+        request->real_acb = res;
+    }
+
+    ret = (res == NULL) ? 0 : 1;
+
+    return ret;
+}
+
+void qemu_block_queue_flush(BlockQueue *queue)
+{
+    queue->flushing = true;
+    while (!QTAILQ_EMPTY(&queue->requests)) {
+        BlockQueueAIOCB *request = NULL;
+        int ret = 0;
+
+        request = QTAILQ_FIRST(&queue->requests);
+        QTAILQ_REMOVE(&queue->requests, request, entry);
+
+        ret = qemu_block_queue_handler(request);
+        if (ret == 0) {
+            QTAILQ_INSERT_HEAD(&queue->requests, request, entry);
+            break;
+        }
+
+        qemu_aio_release(request);
+    }
+
+    queue->flushing = false;
+}
+
+bool qemu_block_queue_has_pending(BlockQueue *queue)
+{
+    return !queue->flushing && !QTAILQ_EMPTY(&queue->requests);
+}
diff --git a/block/blk-queue.h b/block/blk-queue.h
new file mode 100644
index 0000000..c1529f7
--- /dev/null
+++ b/block/blk-queue.h
@@ -0,0 +1,59 @@
+/*
+ * QEMU System Emulator queue declaration for block layer
+ *
+ * Copyright (c) IBM, Corp. 2011
+ *
+ * Authors:
+ *  Zhi Yong Wu  <wuzhy@linux.vnet.ibm.com>
+ *  Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#ifndef QEMU_BLOCK_QUEUE_H
+#define QEMU_BLOCK_QUEUE_H
+
+#include "block.h"
+#include "qemu-queue.h"
+
+typedef BlockDriverAIOCB* (BlockRequestHandler) (BlockDriverState *bs,
+                                int64_t sector_num, QEMUIOVector *qiov,
+                                int nb_sectors, BlockDriverCompletionFunc *cb,
+                                void *opaque);
+
+typedef struct BlockQueue BlockQueue;
+
+BlockQueue *qemu_new_block_queue(void);
+
+void qemu_del_block_queue(BlockQueue *queue);
+
+BlockDriverAIOCB *qemu_block_queue_enqueue(BlockQueue *queue,
+                        BlockDriverState *bs,
+                        BlockRequestHandler *handler,
+                        int64_t sector_num,
+                        QEMUIOVector *qiov,
+                        int nb_sectors,
+                        BlockDriverCompletionFunc *cb,
+                        void *opaque);
+
+void qemu_block_queue_flush(BlockQueue *queue);
+
+bool qemu_block_queue_has_pending(BlockQueue *queue);
+
+#endif /* QEMU_BLOCK_QUEUE_H */
-- 
1.7.6

[Qemu-devel] [PATCH v7 3/4] block: add block timer and throttling algorithm

[Zhi Yong Wu]

Note:
     1.) When bps/iops limits are specified to a small value such as 511 bytes/s, this VM will hang up. We are considering how to handle this senario.
     2.) When "dd" command is issued in guest, if its option bs is set to a large value such as "bs=1024K", the result speed will slightly bigger than the limits.

For these problems, if you have nice thought, pls let us know.:)

Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
---
 block.c    |  297 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++--
 block.h    |    6 +-
 blockdev.c |   69 ++++++++++++++
 3 files changed, 361 insertions(+), 11 deletions(-)

diff --git a/block.c b/block.c
index 17ee3df..1f6f188 100644
--- a/block.c
+++ b/block.c
@@ -30,6 +30,9 @@
 #include "qemu-objects.h"
 #include "qemu-coroutine.h"
 
+#include "qemu-timer.h"
+#include "block/blk-queue.h"
+
 #ifdef CONFIG_BSD
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -72,6 +75,13 @@ static int coroutine_fn bdrv_co_writev_em(BlockDriverState *bs,
                                          QEMUIOVector *iov);
 static int coroutine_fn bdrv_co_flush_em(BlockDriverState *bs);
 
+static bool bdrv_exceed_bps_limits(BlockDriverState *bs, int nb_sectors,
+        bool is_write, double elapsed_time, uint64_t *wait);
+static bool bdrv_exceed_iops_limits(BlockDriverState *bs, bool is_write,
+        double elapsed_time, uint64_t *wait);
+static bool bdrv_exceed_io_limits(BlockDriverState *bs, int nb_sectors,
+        bool is_write, int64_t *wait);
+
 static QTAILQ_HEAD(, BlockDriverState) bdrv_states =
     QTAILQ_HEAD_INITIALIZER(bdrv_states);
 
@@ -104,6 +114,57 @@ int is_windows_drive(const char *filename)
 }
 #endif
 
+/* throttling disk I/O limits */
+void bdrv_io_limits_disable(BlockDriverState *bs)
+{
+    bs->io_limits_enabled = false;
+
+    if (bs->block_queue) {
+        qemu_block_queue_flush(bs->block_queue);
+        qemu_del_block_queue(bs->block_queue);
+        bs->block_queue = NULL;
+    }
+
+    if (bs->block_timer) {
+        qemu_del_timer(bs->block_timer);
+        qemu_free_timer(bs->block_timer);
+        bs->block_timer     = NULL;
+    }
+
+    bs->slice_start = 0;
+
+    bs->slice_end   = 0;
+}
+
+static void bdrv_block_timer(void *opaque)
+{
+    BlockDriverState *bs = opaque;
+    BlockQueue *queue    = bs->block_queue;
+
+    qemu_block_queue_flush(queue);
+}
+
+void bdrv_io_limits_enable(BlockDriverState *bs)
+{
+    bs->block_queue = qemu_new_block_queue();
+    bs->block_timer = qemu_new_timer_ns(vm_clock, bdrv_block_timer, bs);
+
+    bs->slice_start = qemu_get_clock_ns(vm_clock);
+
+    bs->slice_end   = bs->slice_start + BLOCK_IO_SLICE_TIME;
+}
+
+bool bdrv_io_limits_enabled(BlockDriverState *bs)
+{
+    BlockIOLimit *io_limits = &bs->io_limits;
+    return io_limits->bps[BLOCK_IO_LIMIT_READ]
+         || io_limits->bps[BLOCK_IO_LIMIT_WRITE]
+         || io_limits->bps[BLOCK_IO_LIMIT_TOTAL]
+         || io_limits->iops[BLOCK_IO_LIMIT_READ]
+         || io_limits->iops[BLOCK_IO_LIMIT_WRITE]
+         || io_limits->iops[BLOCK_IO_LIMIT_TOTAL];
+}
+
 /* check if the path starts with "<protocol>:" */
 static int path_has_protocol(const char *path)
 {
@@ -694,6 +755,11 @@ int bdrv_open(BlockDriverState *bs, const char *filename, int flags,
             bs->change_cb(bs->change_opaque, CHANGE_MEDIA);
     }
 
+    /* throttling disk I/O limits */
+    if (bs->io_limits_enabled) {
+        bdrv_io_limits_enable(bs);
+    }
+
     return 0;
 
 unlink_and_fail:
@@ -732,6 +798,18 @@ void bdrv_close(BlockDriverState *bs)
         if (bs->change_cb)
             bs->change_cb(bs->change_opaque, CHANGE_MEDIA);
     }
+
+    /* throttling disk I/O limits */
+    if (bs->block_queue) {
+        qemu_del_block_queue(bs->block_queue);
+        bs->block_queue = NULL;
+    }
+
+    if (bs->block_timer) {
+        qemu_del_timer(bs->block_timer);
+        qemu_free_timer(bs->block_timer);
+        bs->block_timer = NULL;
+    }
 }
 
 void bdrv_close_all(void)
@@ -2290,16 +2368,40 @@ BlockDriverAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num,
                                  BlockDriverCompletionFunc *cb, void *opaque)
 {
     BlockDriver *drv = bs->drv;
+    BlockDriverAIOCB *ret;
+    int64_t wait_time = -1;
 
     trace_bdrv_aio_readv(bs, sector_num, nb_sectors, opaque);
 
-    if (!drv)
-        return NULL;
-    if (bdrv_check_request(bs, sector_num, nb_sectors))
+    if (!drv || bdrv_check_request(bs, sector_num, nb_sectors)) {
         return NULL;
+    }
 
-    return drv->bdrv_aio_readv(bs, sector_num, qiov, nb_sectors,
+    /* throttling disk read I/O */
+    if (bs->io_limits_enabled) {
+        if (bdrv_exceed_io_limits(bs, nb_sectors, false, &wait_time)) {
+            ret = qemu_block_queue_enqueue(bs->block_queue, bs, bdrv_aio_readv,
+                           sector_num, qiov, nb_sectors, cb, opaque);
+            if (wait_time != -1) {
+                qemu_mod_timer(bs->block_timer,
+                               wait_time + qemu_get_clock_ns(vm_clock));
+            }
+
+            return ret;
+        }
+    }
+
+    ret =  drv->bdrv_aio_readv(bs, sector_num, qiov, nb_sectors,
                                cb, opaque);
+    if (ret) {
+        if (bs->io_limits_enabled) {
+            bs->io_disps.bytes[BLOCK_IO_LIMIT_READ] +=
+                              (unsigned) nb_sectors * BDRV_SECTOR_SIZE;
+            bs->io_disps.ios[BLOCK_IO_LIMIT_READ]++;
+        }
+    }
+
+    return ret;
 }
 
 typedef struct BlockCompleteData {
@@ -2345,15 +2447,14 @@ BlockDriverAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num,
     BlockDriver *drv = bs->drv;
     BlockDriverAIOCB *ret;
     BlockCompleteData *blk_cb_data;
+    int64_t wait_time = -1;
 
     trace_bdrv_aio_writev(bs, sector_num, nb_sectors, opaque);
 
-    if (!drv)
-        return NULL;
-    if (bs->read_only)
-        return NULL;
-    if (bdrv_check_request(bs, sector_num, nb_sectors))
+    if (!drv || bs->read_only
+        || bdrv_check_request(bs, sector_num, nb_sectors)) {
         return NULL;
+    }
 
     if (bs->dirty_bitmap) {
         blk_cb_data = blk_dirty_cb_alloc(bs, sector_num, nb_sectors, cb,
@@ -2362,13 +2463,32 @@ BlockDriverAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num,
         opaque = blk_cb_data;
     }
 
+    /* throttling disk write I/O */
+    if (bs->io_limits_enabled) {
+        if (bdrv_exceed_io_limits(bs, nb_sectors, true, &wait_time)) {
+            ret = qemu_block_queue_enqueue(bs->block_queue, bs, bdrv_aio_writev,
+                                  sector_num, qiov, nb_sectors, cb, opaque);
+            if (wait_time != -1) {
+                qemu_mod_timer(bs->block_timer,
+                               wait_time + qemu_get_clock_ns(vm_clock));
+            }
+
+            return ret;
+        }
+    }
+
     ret = drv->bdrv_aio_writev(bs, sector_num, qiov, nb_sectors,
                                cb, opaque);
-
     if (ret) {
         if (bs->wr_highest_sector < sector_num + nb_sectors - 1) {
             bs->wr_highest_sector = sector_num + nb_sectors - 1;
         }
+
+        if (bs->io_limits_enabled) {
+            bs->io_disps.bytes[BLOCK_IO_LIMIT_WRITE] +=
+                               (unsigned) nb_sectors * BDRV_SECTOR_SIZE;
+            bs->io_disps.ios[BLOCK_IO_LIMIT_WRITE]++;
+        }
     }
 
     return ret;
@@ -2633,6 +2753,163 @@ void bdrv_aio_cancel(BlockDriverAIOCB *acb)
     acb->pool->cancel(acb);
 }
 
+static bool bdrv_exceed_bps_limits(BlockDriverState *bs, int nb_sectors,
+                 bool is_write, double elapsed_time, uint64_t *wait) {
+    uint64_t bps_limit = 0;
+    double   bytes_limit, bytes_disp, bytes_res;
+    double   slice_time, wait_time;
+
+    if (bs->io_limits.bps[BLOCK_IO_LIMIT_TOTAL]) {
+        bps_limit = bs->io_limits.bps[BLOCK_IO_LIMIT_TOTAL];
+    } else if (bs->io_limits.bps[is_write]) {
+        bps_limit = bs->io_limits.bps[is_write];
+    } else {
+        if (wait) {
+            *wait = 0;
+        }
+
+        return false;
+    }
+
+    slice_time = bs->slice_end - bs->slice_start;
+    slice_time /= (NANOSECONDS_PER_SECOND);
+    bytes_limit = bps_limit * slice_time;
+    bytes_disp  = bs->io_disps.bytes[is_write];
+    if (bs->io_limits.bps[BLOCK_IO_LIMIT_TOTAL]) {
+        bytes_disp += bs->io_disps.bytes[!is_write];
+    }
+
+    bytes_res   = (unsigned) nb_sectors * BDRV_SECTOR_SIZE;
+
+    if (bytes_disp + bytes_res <= bytes_limit) {
+        if (wait) {
+            *wait = 0;
+        }
+
+        return false;
+    }
+
+    /* Calc approx time to dispatch */
+    wait_time = (bytes_disp + bytes_res) / bps_limit - elapsed_time;
+
+    if (wait) {
+        *wait = wait_time * BLOCK_IO_SLICE_TIME * 10;
+    }
+
+    return true;
+}
+
+static bool bdrv_exceed_iops_limits(BlockDriverState *bs, bool is_write,
+                             double elapsed_time, uint64_t *wait) {
+    uint64_t iops_limit = 0;
+    double   ios_limit, ios_disp;
+    double   slice_time, wait_time;
+
+    if (bs->io_limits.iops[BLOCK_IO_LIMIT_TOTAL]) {
+        iops_limit = bs->io_limits.iops[BLOCK_IO_LIMIT_TOTAL];
+    } else if (bs->io_limits.iops[is_write]) {
+        iops_limit = bs->io_limits.iops[is_write];
+    } else {
+        if (wait) {
+            *wait = 0;
+        }
+
+        return false;
+    }
+
+    slice_time = bs->slice_end - bs->slice_start;
+    slice_time /= (NANOSECONDS_PER_SECOND);
+    ios_limit  = iops_limit * slice_time;
+    ios_disp   = bs->io_disps.ios[is_write];
+    if (bs->io_limits.iops[BLOCK_IO_LIMIT_TOTAL]) {
+        ios_disp += bs->io_disps.ios[!is_write];
+    }
+
+    if (ios_disp + 1 <= ios_limit) {
+        if (wait) {
+            *wait = 0;
+        }
+
+        return false;
+    }
+
+    /* Calc approx time to dispatch */
+    wait_time = (ios_disp + 1) / iops_limit;
+    if (wait_time > elapsed_time) {
+        wait_time = wait_time - elapsed_time;
+    } else {
+        wait_time = 0;
+    }
+
+    if (wait) {
+        *wait = wait_time * BLOCK_IO_SLICE_TIME * 10;
+    }
+
+    return true;
+}
+
+static bool bdrv_exceed_io_limits(BlockDriverState *bs, int nb_sectors,
+                           bool is_write, int64_t *wait) {
+    int64_t  now, max_wait;
+    uint64_t bps_wait = 0, iops_wait = 0;
+    double   elapsed_time;
+    int      bps_ret, iops_ret;
+
+    now = qemu_get_clock_ns(vm_clock);
+    if ((bs->slice_start < now)
+        && (bs->slice_end > now)) {
+        bs->slice_end = now + BLOCK_IO_SLICE_TIME;
+    } else {
+        bs->slice_start = now;
+        bs->slice_end   = now + BLOCK_IO_SLICE_TIME;
+
+        bs->io_disps.bytes[is_write]  = 0;
+        bs->io_disps.bytes[!is_write] = 0;
+
+        bs->io_disps.ios[is_write]    = 0;
+        bs->io_disps.ios[!is_write]   = 0;
+    }
+
+    /* If a limit was exceeded, immediately queue this request */
+    if (qemu_block_queue_has_pending(bs->block_queue)) {
+        if (bs->io_limits.bps[BLOCK_IO_LIMIT_TOTAL]
+            || bs->io_limits.bps[is_write] || bs->io_limits.iops[is_write]
+            || bs->io_limits.iops[BLOCK_IO_LIMIT_TOTAL]) {
+            if (wait) {
+                *wait = -1;
+            }
+
+            return true;
+        }
+    }
+
+    elapsed_time  = now - bs->slice_start;
+    elapsed_time  /= (NANOSECONDS_PER_SECOND);
+
+    bps_ret  = bdrv_exceed_bps_limits(bs, nb_sectors,
+                                      is_write, elapsed_time, &bps_wait);
+    iops_ret = bdrv_exceed_iops_limits(bs, is_write,
+                                      elapsed_time, &iops_wait);
+    if (bps_ret || iops_ret) {
+        max_wait = bps_wait > iops_wait ? bps_wait : iops_wait;
+        if (wait) {
+            *wait = max_wait;
+        }
+
+        now = qemu_get_clock_ns(vm_clock);
+        if (bs->slice_end < now + max_wait) {
+            bs->slice_end = now + max_wait;
+        }
+
+        return true;
+    }
+
+    if (wait) {
+        *wait = 0;
+    }
+
+    return false;
+}
 
 /**************************************************************/
 /* async block device emulation */
diff --git a/block.h b/block.h
index 3ac0b94..10d2828 100644
--- a/block.h
+++ b/block.h
@@ -58,6 +58,11 @@ void bdrv_info(Monitor *mon, QObject **ret_data);
 void bdrv_stats_print(Monitor *mon, const QObject *data);
 void bdrv_info_stats(Monitor *mon, QObject **ret_data);
 
+/* disk I/O throttling */
+void bdrv_io_limits_enable(BlockDriverState *bs);
+void bdrv_io_limits_disable(BlockDriverState *bs);
+bool bdrv_io_limits_enabled(BlockDriverState *bs);
+
 void bdrv_init(void);
 void bdrv_init_with_whitelist(void);
 BlockDriver *bdrv_find_protocol(const char *filename);
@@ -102,7 +107,6 @@ int bdrv_change_backing_file(BlockDriverState *bs,
     const char *backing_file, const char *backing_fmt);
 void bdrv_register(BlockDriver *bdrv);
 
-
 typedef struct BdrvCheckResult {
     int corruptions;
     int leaks;
diff --git a/blockdev.c b/blockdev.c
index 619ae9f..7f5c4df 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -747,6 +747,75 @@ int do_change_block(Monitor *mon, const char *device,
     return monitor_read_bdrv_key_start(mon, bs, NULL, NULL);
 }
 
+/* throttling disk I/O limits */
+int do_block_set_io_throttle(Monitor *mon,
+                       const QDict *qdict, QObject **ret_data)
+{
+    const char *devname = qdict_get_str(qdict, "device");
+    uint64_t bps        = qdict_get_try_int(qdict, "bps", -1);
+    uint64_t bps_rd     = qdict_get_try_int(qdict, "bps_rd", -1);
+    uint64_t bps_wr     = qdict_get_try_int(qdict, "bps_wr", -1);
+    uint64_t iops       = qdict_get_try_int(qdict, "iops", -1);
+    uint64_t iops_rd    = qdict_get_try_int(qdict, "iops_rd", -1);
+    uint64_t iops_wr    = qdict_get_try_int(qdict, "iops_wr", -1);
+    BlockDriverState *bs;
+
+    bs = bdrv_find(devname);
+    if (!bs) {
+        qerror_report(QERR_DEVICE_NOT_FOUND, devname);
+        return -1;
+    }
+
+    if ((bps == -1) && (bps_rd == -1) && (bps_wr == -1)
+        && (iops == -1) && (iops_rd == -1) && (iops_wr == -1)) {
+        qerror_report(QERR_MISSING_PARAMETER,
+                      "bps/bps_rd/bps_wr/iops/iops_rd/iops_wr");
+        return -1;
+    }
+
+    if (((bps != -1) && ((bps_rd != -1) || (bps_wr != -1)))
+        || ((iops != -1) && ((iops_rd != -1) || (iops_wr != -1)))) {
+        qerror_report(QERR_INVALID_PARAMETER_COMBINATION);
+        return -1;
+    }
+
+    if (bps != -1) {
+        bs->io_limits.bps[BLOCK_IO_LIMIT_TOTAL] = bps;
+        bs->io_limits.bps[BLOCK_IO_LIMIT_READ]  = 0;
+        bs->io_limits.bps[BLOCK_IO_LIMIT_WRITE] = 0;
+    }
+
+    if ((bps_rd != -1) || (bps_wr != -1)) {
+        bs->io_limits.bps[BLOCK_IO_LIMIT_READ]   =
+           (bps_rd == -1) ? bs->io_limits.bps[BLOCK_IO_LIMIT_READ] : bps_rd;
+        bs->io_limits.bps[BLOCK_IO_LIMIT_WRITE]  =
+           (bps_wr == -1) ? bs->io_limits.bps[BLOCK_IO_LIMIT_WRITE] : bps_wr;
+        bs->io_limits.bps[BLOCK_IO_LIMIT_TOTAL]  = 0;
+    }
+
+    if (iops != -1) {
+        bs->io_limits.iops[BLOCK_IO_LIMIT_TOTAL] = iops;
+        bs->io_limits.iops[BLOCK_IO_LIMIT_READ]  = 0;
+        bs->io_limits.iops[BLOCK_IO_LIMIT_WRITE] = 0;
+    }
+
+    if ((iops_rd != -1) || (iops_wr != -1)) {
+        bs->io_limits.iops[BLOCK_IO_LIMIT_READ]  =
+           (iops_rd == -1) ? bs->io_limits.iops[BLOCK_IO_LIMIT_READ] : iops_rd;
+        bs->io_limits.iops[BLOCK_IO_LIMIT_WRITE] =
+           (iops_wr == -1) ? bs->io_limits.iops[BLOCK_IO_LIMIT_WRITE] : iops_wr;
+        bs->io_limits.iops[BLOCK_IO_LIMIT_TOTAL] = 0;
+    }
+
+    if (!bs->io_limits_enabled && bdrv_io_limits_enabled(bs)) {
+        bdrv_io_limits_enable(bs);
+    } else if (bs->io_limits_enabled && !bdrv_io_limits_enabled(bs)) {
+        bdrv_io_limits_disable(bs);
+    }
+
+    return 0;
+}
+
 int do_drive_del(Monitor *mon, const QDict *qdict, QObject **ret_data)
 {
     const char *id = qdict_get_str(qdict, "id");
-- 
1.7.6

[Qemu-devel] [PATCH v7 4/4] qmp/hmp: add block_set_io_throttle

[Zhi Yong Wu]

The patch introduce one new command block_set_io_throttle; For its usage syntax, if you have better idea, pls let me know.

Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
---
 block.c         |   26 ++++++++++++++++++++++++--
 hmp-commands.hx |   15 +++++++++++++++
 qerror.c        |    4 ++++
 qerror.h        |    3 +++
 qmp-commands.hx |   52 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 5 files changed, 97 insertions(+), 3 deletions(-)

diff --git a/block.c b/block.c
index 1f6f188..dfa5567 100644
--- a/block.c
+++ b/block.c
@@ -1938,6 +1938,16 @@ static void bdrv_print_dict(QObject *obj, void *opaque)
                             qdict_get_bool(qdict, "ro"),
                             qdict_get_str(qdict, "drv"),
                             qdict_get_bool(qdict, "encrypted"));
+
+        monitor_printf(mon, " bps=%" PRId64 " bps_rd=%" PRId64
+                            " bps_wr=%" PRId64 " iops=%" PRId64
+                            " iops_rd=%" PRId64 " iops_wr=%" PRId64,
+                            qdict_get_int(qdict, "bps"),
+                            qdict_get_int(qdict, "bps_rd"),
+                            qdict_get_int(qdict, "bps_wr"),
+                            qdict_get_int(qdict, "iops"),
+                            qdict_get_int(qdict, "iops_rd"),
+                            qdict_get_int(qdict, "iops_wr"));
     } else {
         monitor_printf(mon, " [not inserted]");
     }
@@ -1970,10 +1980,22 @@ void bdrv_info(Monitor *mon, QObject **ret_data)
             QDict *bs_dict = qobject_to_qdict(bs_obj);
 
             obj = qobject_from_jsonf("{ 'file': %s, 'ro': %i, 'drv': %s, "
-                                     "'encrypted': %i }",
+                                     "'encrypted': %i, "
+                                     "'bps': %" PRId64 ","
+                                     "'bps_rd': %" PRId64 ","
+                                     "'bps_wr': %" PRId64 ","
+                                     "'iops': %" PRId64 ","
+                                     "'iops_rd': %" PRId64 ","
+                                     "'iops_wr': %" PRId64 "}",
                                      bs->filename, bs->read_only,
                                      bs->drv->format_name,
-                                     bdrv_is_encrypted(bs));
+                                     bdrv_is_encrypted(bs),
+                                     bs->io_limits.bps[BLOCK_IO_LIMIT_TOTAL],
+                                     bs->io_limits.bps[BLOCK_IO_LIMIT_READ],
+                                     bs->io_limits.bps[BLOCK_IO_LIMIT_WRITE],
+                                     bs->io_limits.iops[BLOCK_IO_LIMIT_TOTAL],
+                                     bs->io_limits.iops[BLOCK_IO_LIMIT_READ],
+                                     bs->io_limits.iops[BLOCK_IO_LIMIT_WRITE]);
             if (bs->backing_file[0] != '\0') {
                 QDict *qdict = qobject_to_qdict(obj);
                 qdict_put(qdict, "backing_file",
diff --git a/hmp-commands.hx b/hmp-commands.hx
index 0ccfb28..147f9cf 100644
--- a/hmp-commands.hx
+++ b/hmp-commands.hx
@@ -1210,6 +1210,21 @@ ETEXI
     },
 
 STEXI
+@item block_set_io_throttle @var{device} @var{bps} @var{bps_rd} @var{bps_wr} @var{iops} @var{iops_rd} @var{iops_wr}
+@findex block_set_io_throttle
+Change I/O throttle limits for a block drive to @var{bps} @var{bps_rd} @var{bps_wr} @var{iops} @var{iops_rd} @var{iops_wr}
+ETEXI
+
+    {
+        .name       = "block_set_io_throttle",
+        .args_type  = "device:B,bps:i?,bps_rd:i?,bps_wr:i?,iops:i?,iops_rd:i?,iops_wr:i?",
+        .params     = "device [bps] [bps_rd] [bps_wr] [iops] [iops_rd] [iops_wr]",
+        .help       = "change I/O throttle limits for a block drive",
+        .user_print = monitor_user_noop,
+        .mhandler.cmd_new = do_block_set_io_throttle,
+    },
+
+STEXI
 @item block_passwd @var{device} @var{password}
 @findex block_passwd
 Set the encrypted device @var{device} password to @var{password}
diff --git a/qerror.c b/qerror.c
index 3d64b80..33f9fdd 100644
--- a/qerror.c
+++ b/qerror.c
@@ -230,6 +230,10 @@ static const QErrorStringTable qerror_table[] = {
         .error_fmt = QERR_QGA_COMMAND_FAILED,
         .desc      = "Guest agent command failed, error was '%(message)'",
     },
+    {
+        .error_fmt = QERR_INVALID_PARAMETER_COMBINATION,
+        .desc      = "Invalid paramter combination",
+    },
     {}
 };
 
diff --git a/qerror.h b/qerror.h
index 8058456..62c1df2 100644
--- a/qerror.h
+++ b/qerror.h
@@ -193,4 +193,7 @@ QError *qobject_to_qerror(const QObject *obj);
 #define QERR_QGA_COMMAND_FAILED \
     "{ 'class': 'QgaCommandFailed', 'data': { 'message': %s } }"
 
+#define QERR_INVALID_PARAMETER_COMBINATION \
+    "{ 'class': 'InvalidParameterCombination', 'data': {} }"
+
 #endif /* QERROR_H */
diff --git a/qmp-commands.hx b/qmp-commands.hx
index 27cc66e..e848969 100644
--- a/qmp-commands.hx
+++ b/qmp-commands.hx
@@ -862,6 +862,44 @@ Example:
 EQMP
 
     {
+        .name       = "block_set_io_throttle",
+        .args_type  = "device:B,bps:i?,bps_rd:i?,bps_wr:i?,iops:i?,iops_rd:i?,iops_wr:i?",
+        .params     = "device [bps] [bps_rd] [bps_wr] [iops] [iops_rd] [iops_wr]",
+        .help       = "change I/O throttle limits for a block drive",
+        .user_print = monitor_user_noop,
+        .mhandler.cmd_new = do_block_set_io_throttle,
+    },
+
+SQMP
+block_set_io_throttle
+------------
+
+Change I/O throttle limits for a block drive.
+
+Arguments:
+
+- "device": device name (json-string)
+- "bps":  total throughput limit in bytes per second(json-int, optional)
+- "bps_rd":  read throughput limit in bytes per second(json-int, optional)
+- "bps_wr":  read throughput limit in bytes per second(json-int, optional)
+- "iops":  total I/O operations per second(json-int, optional)
+- "iops_rd":  read I/O operations per second(json-int, optional)
+- "iops_wr":  write I/O operations per second(json-int, optional)
+
+Example:
+
+-> { "execute": "block_set_io_throttle", "arguments": { "device": "virtio0",
+                                               "bps": "1000000",
+                                               "bps_rd": "0",
+                                               "bps_wr": "0",
+                                               "iops": "0",
+                                               "iops_rd": "0",
+                                               "iops_wr": "0" } }
+<- { "return": {} }
+
+EQMP
+
+    {
         .name       = "set_password",
         .args_type  = "protocol:s,password:s,connected:s?",
         .params     = "protocol password action-if-connected",
@@ -1143,6 +1181,12 @@ Each json-object contain the following:
                                 "tftp", "vdi", "vmdk", "vpc", "vvfat"
          - "backing_file": backing file name (json-string, optional)
          - "encrypted": true if encrypted, false otherwise (json-bool)
+         - "bps": limit total bytes per second (json-int)
+         - "bps_rd": limit read bytes per second (json-int)
+         - "bps_wr": limit write bytes per second (json-int)
+         - "iops": limit total I/O operations per second (json-int)
+         - "iops_rd": limit read operations per second (json-int)
+         - "iops_wr": limit write operations per second (json-int)
 
 Example:
 
@@ -1157,7 +1201,13 @@ Example:
                "ro":false,
                "drv":"qcow2",
                "encrypted":false,
-               "file":"disks/test.img"
+               "file":"disks/vm.img",
+               "bps":1000000,
+               "bps_rd":0,
+               "bps_wr":0,
+               "iops":1000000,
+               "iops_rd":0,
+               "iops_wr":0,
             },
             "type":"unknown"
          },
-- 
1.7.6

Re: [Qemu-devel] [PATCH v7 1/4] block: add the command line support

[Stefan Hajnoczi]

On Tue, Sep 6, 2011 at 11:48 AM, Zhi Yong Wu <wuzhy@linux.vnet.ibm.com> wrote:
> Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
> ---
>  block.c         |    8 ++++++++
>  block_int.h     |   30 ++++++++++++++++++++++++++++++
>  blockdev.c      |   29 +++++++++++++++++++++++++++++
>  blockdev.h      |    2 ++
>  qemu-config.c   |   24 ++++++++++++++++++++++++
>  qemu-options.hx |    1 +
>  6 files changed, 94 insertions(+), 0 deletions(-)
[...]
> +#include "block/blk-queue.h"

This patch fails to build.  blk-queue.h does not exist yet.  Please
order changes so that each patch builds.

Stefan