block: add the blockio limits command line support

Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

block.c

@@ -30,6 +30,7 @@
 #include "qjson.h"
 #include "qemu-coroutine.h"
 #include "qmp-commands.h"
+#include "qemu-timer.h"
 
 #ifdef CONFIG_BSD
 #include <sys/types.h>
@@ -105,6 +106,36 @@ int is_windows_drive(const char *filename)
 }
 #endif
 
+/* throttling disk I/O limits */
+static void bdrv_block_timer(void *opaque)
+{
+    BlockDriverState *bs = opaque;
+
+    qemu_co_queue_next(&bs->throttled_reqs);
+}
+
+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;
+}
+
+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)
 {
@@ -1526,6 +1557,14 @@ 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;

block.h

@@ -98,6 +98,10 @@ 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);
+bool bdrv_io_limits_enabled(BlockDriverState *bs);
+
 void bdrv_init(void);
 void bdrv_init_with_whitelist(void);
 BlockDriver *bdrv_find_protocol(const char *filename);

block_int.h

@@ -34,6 +34,12 @@
 #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 BLOCK_OPT_SIZE          "size"
 #define BLOCK_OPT_ENCRYPT       "encryption"
 #define BLOCK_OPT_COMPAT6       "compat6"
@@ -50,6 +56,16 @@ typedef struct AIOPool {
     BlockDriverAIOCB *free_aiocb;
 } AIOPool;
 
+typedef struct BlockIOLimit {
+    int64_t bps[3];
+    int64_t iops[3];
+} BlockIOLimit;
+
+typedef struct BlockIOBaseValue {
+    uint64_t bytes[2];
+    uint64_t ios[2];
+} BlockIOBaseValue;
+
 struct BlockDriver {
     const char *format_name;
     int instance_size;
@@ -201,6 +217,16 @@ struct BlockDriverState {
 
     void *sync_aiocb;
 
+    /* the time for latest disk I/O */
+    int64_t slice_time;
+    int64_t slice_start;
+    int64_t slice_end;
+    BlockIOLimit io_limits;
+    BlockIOBaseValue  io_base;
+    CoQueue      throttled_reqs;
+    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];
@@ -244,6 +270,9 @@ void *qemu_aio_get(AIOPool *pool, BlockDriverState *bs,
                    BlockDriverCompletionFunc *cb, void *opaque);
 void qemu_aio_release(void *p);
 
+void bdrv_set_io_limits(BlockDriverState *bs,
+                        BlockIOLimit *io_limits);
+
 #ifdef _WIN32
 int is_windows_drive(const char *filename);
 #endif

blockdev.c

@@ -216,6 +216,26 @@ static int parse_block_error_action(const char *buf, int is_read)
     }
 }
 
+static bool do_check_io_limits(BlockIOLimit *io_limits)
+{
+    bool bps_flag;
+    bool iops_flag;
+
+    assert(io_limits);
+
+    bps_flag  = (io_limits->bps[BLOCK_IO_LIMIT_TOTAL] != 0)
+                 && ((io_limits->bps[BLOCK_IO_LIMIT_READ] != 0)
+                 || (io_limits->bps[BLOCK_IO_LIMIT_WRITE] != 0));
+    iops_flag = (io_limits->iops[BLOCK_IO_LIMIT_TOTAL] != 0)
+                 && ((io_limits->iops[BLOCK_IO_LIMIT_READ] != 0)
+                 || (io_limits->iops[BLOCK_IO_LIMIT_WRITE] != 0));
+    if (bps_flag || iops_flag) {
+        return false;
+    }
+
+    return true;
+}
+
 DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 {
     const char *buf;
@@ -235,6 +255,7 @@ 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;
 
@@ -353,6 +374,26 @@ 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 (!do_check_io_limits(&io_limits)) {
+        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) {
@@ -460,6 +501,9 @@ 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:

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 */ }
     },

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}[,...]]]