Patchwork [v11,1/4] block: add the blockio limits command line support

login
register
mail settings
Submitter Zhi Yong Wu
Date Nov. 2, 2011, 6:01 a.m.
Message ID <1320213705-8097-2-git-send-email-wuzhy@linux.vnet.ibm.com>
Download mbox | patch
Permalink /patch/123223/
State New
Headers show

Comments

Zhi Yong Wu - Nov. 2, 2011, 6:01 a.m.
Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
---
 block.c         |   40 ++++++++++++++++++++++++++++++++++++++++
 block.h         |    4 ++++
 block_int.h     |   29 +++++++++++++++++++++++++++++
 blockdev.c      |   44 ++++++++++++++++++++++++++++++++++++++++++++
 qemu-config.c   |   24 ++++++++++++++++++++++++
 qemu-options.hx |    1 +
 6 files changed, 142 insertions(+), 0 deletions(-)
Kevin Wolf - Nov. 2, 2011, 11:32 a.m.
Am 02.11.2011 07:01, schrieb Zhi Yong Wu:
> Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
> Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
> ---
>  block.c         |   40 ++++++++++++++++++++++++++++++++++++++++
>  block.h         |    4 ++++
>  block_int.h     |   29 +++++++++++++++++++++++++++++
>  blockdev.c      |   44 ++++++++++++++++++++++++++++++++++++++++++++
>  qemu-config.c   |   24 ++++++++++++++++++++++++
>  qemu-options.hx |    1 +
>  6 files changed, 142 insertions(+), 0 deletions(-)
> 
> diff --git a/block.c b/block.c
> index 9bb236c..c70f86d 100644
> --- a/block.c
> +++ b/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 +106,37 @@ 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);
> +}

This runs only one request, whereas in previous versions all queued
requests were resubmitted. Is this change intentional?

> diff --git a/block_int.h b/block_int.h
> index f4547f6..0abe843 100644
> --- a/block_int.h
> +++ b/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 BlockIODisp {
> +    uint64_t bytes[2];
> +    uint64_t ios[2];
> +} BlockIODisp;

I would prefer a different name. Something like BlockIOBaseValue maybe
(no, I don't really like this either, I'm open for suggestions)

Kevin
Zhiyong Wu - Nov. 3, 2011, 3:11 a.m.
On Wed, Nov 2, 2011 at 7:32 PM, Kevin Wolf <kwolf@redhat.com> wrote:
> Am 02.11.2011 07:01, schrieb Zhi Yong Wu:
>> Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
>> Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
>> ---
>>  block.c         |   40 ++++++++++++++++++++++++++++++++++++++++
>>  block.h         |    4 ++++
>>  block_int.h     |   29 +++++++++++++++++++++++++++++
>>  blockdev.c      |   44 ++++++++++++++++++++++++++++++++++++++++++++
>>  qemu-config.c   |   24 ++++++++++++++++++++++++
>>  qemu-options.hx |    1 +
>>  6 files changed, 142 insertions(+), 0 deletions(-)
>>
>> diff --git a/block.c b/block.c
>> index 9bb236c..c70f86d 100644
>> --- a/block.c
>> +++ b/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 +106,37 @@ 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);
>> +}
>
> This runs only one request, whereas in previous versions all queued
> requests were resubmitted. Is this change intentional?
Yeah, This timer function is only the trigger for the head request
from throttled_req to be reactivated. If the head request is allowed
to be serviced, the next request which follows it will be reactivated
too.

>
>> diff --git a/block_int.h b/block_int.h
>> index f4547f6..0abe843 100644
>> --- a/block_int.h
>> +++ b/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 BlockIODisp {
>> +    uint64_t bytes[2];
>> +    uint64_t ios[2];
>> +} BlockIODisp;
>
> I would prefer a different name. Something like BlockIOBaseValue maybe
> (no, I don't really like this either, I'm open for suggestions)
OK.

>
> Kevin
>

Patch

diff --git a/block.c b/block.c
index 9bb236c..c70f86d 100644
--- a/block.c
+++ b/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 +106,37 @@  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)
+{
+    bs->io_limits_enabled = true;
+    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_disps, 0, sizeof(bs->io_disps));
+}
+
+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)
 {
@@ -1519,6 +1551,14 @@  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.h b/block.h
index 38cd748..bc8315d 100644
--- a/block.h
+++ b/block.h
@@ -89,6 +89,10 @@  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);
diff --git a/block_int.h b/block_int.h
index f4547f6..0abe843 100644
--- a/block_int.h
+++ b/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 BlockIODisp {
+    uint64_t bytes[2];
+    uint64_t ios[2];
+} BlockIODisp;
+
 struct BlockDriver {
     const char *format_name;
     int instance_size;
@@ -184,6 +200,16 @@  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;
+    BlockIODisp  io_disps;
+    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];
@@ -227,6 +253,9 @@  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
diff --git a/blockdev.c b/blockdev.c
index 0827bf7..651828c 100644
--- a/blockdev.c
+++ b/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:
diff --git a/qemu-config.c b/qemu-config.c
index 597d7e1..1aa080f 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 681eaf1..25a7be7 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}[,...]]]