Merge remote-tracking branch 'remotes/kevin/tags/for-upstream' into staging

Block layer patches

# gpg: Signature made Mon 22 Feb 2016 15:59:25 GMT using RSA key ID C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"

* remotes/kevin/tags/for-upstream: (34 commits)
  qemu-iotests: 140: make description slightly more verbose
  qemu-iotests: 140: don't use IDE device
  qemu-iotests: 067: ignore QMP events
  blockdev: unset inappropriate flags when changing medium
  MAINTAINERS: Add myself as maintainer of the throttling code
  docs: Document the throttling infrastructure
  qapi: Correct the name of the iops_rd parameter
  qemu-iotests: Extend iotest 093 to test bursts
  throttle: Test throttle_compute_wait() during bursts
  throttle: Check that burst_level leaks correctly
  qapi: Add burst length fields to BlockDeviceInfo
  qapi: Add burst length parameters to block_set_io_throttle
  throttle: Add command-line settings to define the burst periods
  throttle: Add support for burst periods
  throttle: Use throttle_config_init() to initialize ThrottleConfig
  throttle: Merge all functions that check the configuration into one
  throttle: Set always an average value when setting a maximum value
  throttle: Make throttle_is_valid() set errp
  throttle: Make throttle_max_is_missing_limit() set errp
  throttle: Make throttle_conflicting() set errp
  ...
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

MAINTAINERS

@@ -1283,6 +1283,15 @@ S: Maintained
 F: include/qemu/sockets.h
 F: util/qemu-sockets.c
 
+Throttling infrastructure
+M: Alberto Garcia <berto@igalia.com>
+S: Supported
+F: block/throttle-groups.c
+F: include/block/throttle-groups.h
+F: include/qemu/throttle.h
+F: util/throttle.c
+L: qemu-block@nongnu.org
+
 Usermode Emulation
 ------------------
 Overall

block.c

@@ -1191,10 +1191,6 @@ static int bdrv_fill_options(QDict **options, const char *filename,
         }
     }
 
-    if (runstate_check(RUN_STATE_INMIGRATE)) {
-        *flags |= BDRV_O_INACTIVE;
-    }
-
     return 0;
 }
 

block/qapi.c

@@ -92,6 +92,26 @@ BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs, Error **errp)
         info->has_iops_wr_max = cfg.buckets[THROTTLE_OPS_WRITE].max;
         info->iops_wr_max     = cfg.buckets[THROTTLE_OPS_WRITE].max;
 
+        info->has_bps_max_length     = info->has_bps_max;
+        info->bps_max_length         =
+            cfg.buckets[THROTTLE_BPS_TOTAL].burst_length;
+        info->has_bps_rd_max_length  = info->has_bps_rd_max;
+        info->bps_rd_max_length      =
+            cfg.buckets[THROTTLE_BPS_READ].burst_length;
+        info->has_bps_wr_max_length  = info->has_bps_wr_max;
+        info->bps_wr_max_length      =
+            cfg.buckets[THROTTLE_BPS_WRITE].burst_length;
+
+        info->has_iops_max_length    = info->has_iops_max;
+        info->iops_max_length        =
+            cfg.buckets[THROTTLE_OPS_TOTAL].burst_length;
+        info->has_iops_rd_max_length = info->has_iops_rd_max;
+        info->iops_rd_max_length     =
+            cfg.buckets[THROTTLE_OPS_READ].burst_length;
+        info->has_iops_wr_max_length = info->has_iops_wr_max;
+        info->iops_wr_max_length     =
+            cfg.buckets[THROTTLE_OPS_WRITE].burst_length;
+
         info->has_iops_size = cfg.op_size;
         info->iops_size = cfg.op_size;
 

block/quorum.c

@@ -286,7 +286,8 @@ static void quorum_aio_cb(void *opaque, int ret)
 
     if (acb->is_read && s->read_pattern == QUORUM_READ_PATTERN_FIFO) {
         /* We try to read next child in FIFO order if we fail to read */
-        if (ret < 0 && ++acb->child_iter < s->num_children) {
+        if (ret < 0 && (acb->child_iter + 1) < s->num_children) {
+            acb->child_iter++;
             read_fifo_child(acb);
             return;
         }

blockdev.c

@@ -343,29 +343,6 @@ static bool parse_stats_intervals(BlockAcctStats *stats, QList *intervals,
     return true;
 }
 
-static bool check_throttle_config(ThrottleConfig *cfg, Error **errp)
-{
-    if (throttle_conflicting(cfg)) {
-        error_setg(errp, "bps/iops/max total values and read/write values"
-                         " cannot be used at the same time");
-        return false;
-    }
-
-    if (!throttle_is_valid(cfg)) {
-        error_setg(errp, "bps/iops/max values must be within [0, %lld]",
-                   THROTTLE_VALUE_MAX);
-        return false;
-    }
-
-    if (throttle_max_is_missing_limit(cfg)) {
-        error_setg(errp, "bps_max/iops_max require corresponding"
-                         " bps/iops values");
-        return false;
-    }
-
-    return true;
-}
-
 typedef enum { MEDIA_DISK, MEDIA_CDROM } DriveMediaType;
 
 /* All parameters but @opts are optional and may be set to NULL. */
@@ -410,7 +387,7 @@ static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags,
     }
 
     if (throttle_cfg) {
-        memset(throttle_cfg, 0, sizeof(*throttle_cfg));
+        throttle_config_init(throttle_cfg);
         throttle_cfg->buckets[THROTTLE_BPS_TOTAL].avg =
             qemu_opt_get_number(opts, "throttling.bps-total", 0);
         throttle_cfg->buckets[THROTTLE_BPS_READ].avg  =
@@ -437,10 +414,23 @@ static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags,
         throttle_cfg->buckets[THROTTLE_OPS_WRITE].max =
             qemu_opt_get_number(opts, "throttling.iops-write-max", 0);
 
+        throttle_cfg->buckets[THROTTLE_BPS_TOTAL].burst_length =
+            qemu_opt_get_number(opts, "throttling.bps-total-max-length", 1);
+        throttle_cfg->buckets[THROTTLE_BPS_READ].burst_length  =
+            qemu_opt_get_number(opts, "throttling.bps-read-max-length", 1);
+        throttle_cfg->buckets[THROTTLE_BPS_WRITE].burst_length =
+            qemu_opt_get_number(opts, "throttling.bps-write-max-length", 1);
+        throttle_cfg->buckets[THROTTLE_OPS_TOTAL].burst_length =
+            qemu_opt_get_number(opts, "throttling.iops-total-max-length", 1);
+        throttle_cfg->buckets[THROTTLE_OPS_READ].burst_length =
+            qemu_opt_get_number(opts, "throttling.iops-read-max-length", 1);
+        throttle_cfg->buckets[THROTTLE_OPS_WRITE].burst_length =
+            qemu_opt_get_number(opts, "throttling.iops-write-max-length", 1);
+
         throttle_cfg->op_size =
             qemu_opt_get_number(opts, "throttling.iops-size", 0);
 
-        if (!check_throttle_config(throttle_cfg, errp)) {
+        if (!throttle_is_valid(throttle_cfg, errp)) {
             return;
         }
     }
@@ -610,6 +600,10 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
             qdict_put(bs_opts, BDRV_OPT_CACHE_NO_FLUSH, qstring_from_str("on"));
         }
 
+        if (runstate_check(RUN_STATE_INMIGRATE)) {
+            bdrv_flags |= BDRV_O_INACTIVE;
+        }
+
         blk = blk_new_open(qemu_opts_id(opts), file, NULL, bs_opts, bdrv_flags,
                            errp);
         if (!blk) {
@@ -688,6 +682,10 @@ static BlockDriverState *bds_tree_init(QDict *bs_opts, Error **errp)
         goto fail;
     }
 
+    if (runstate_check(RUN_STATE_INMIGRATE)) {
+        bdrv_flags |= BDRV_O_INACTIVE;
+    }
+
     bs = NULL;
     ret = bdrv_open(&bs, NULL, NULL, bs_opts, bdrv_flags, errp);
     if (ret < 0) {
@@ -2515,6 +2513,8 @@ void qmp_blockdev_change_medium(const char *device, const char *filename,
     }
 
     bdrv_flags = blk_get_open_flags_from_root_state(blk);
+    bdrv_flags &= ~(BDRV_O_TEMPORARY | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING |
+        BDRV_O_PROTOCOL);
 
     if (!has_read_only) {
         read_only = BLOCKDEV_CHANGE_READ_ONLY_MODE_RETAIN;
@@ -2600,6 +2600,18 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
                                int64_t iops_rd_max,
                                bool has_iops_wr_max,
                                int64_t iops_wr_max,
+                               bool has_bps_max_length,
+                               int64_t bps_max_length,
+                               bool has_bps_rd_max_length,
+                               int64_t bps_rd_max_length,
+                               bool has_bps_wr_max_length,
+                               int64_t bps_wr_max_length,
+                               bool has_iops_max_length,
+                               int64_t iops_max_length,
+                               bool has_iops_rd_max_length,
+                               int64_t iops_rd_max_length,
+                               bool has_iops_wr_max_length,
+                               int64_t iops_wr_max_length,
                                bool has_iops_size,
                                int64_t iops_size,
                                bool has_group,
@@ -2626,7 +2638,7 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
         goto out;
     }
 
-    memset(&cfg, 0, sizeof(cfg));
+    throttle_config_init(&cfg);
     cfg.buckets[THROTTLE_BPS_TOTAL].avg = bps;
     cfg.buckets[THROTTLE_BPS_READ].avg  = bps_rd;
     cfg.buckets[THROTTLE_BPS_WRITE].avg = bps_wr;
@@ -2654,11 +2666,30 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
         cfg.buckets[THROTTLE_OPS_WRITE].max = iops_wr_max;
     }
 
+    if (has_bps_max_length) {
+        cfg.buckets[THROTTLE_BPS_TOTAL].burst_length = bps_max_length;
+    }
+    if (has_bps_rd_max_length) {
+        cfg.buckets[THROTTLE_BPS_READ].burst_length = bps_rd_max_length;
+    }
+    if (has_bps_wr_max_length) {
+        cfg.buckets[THROTTLE_BPS_WRITE].burst_length = bps_wr_max_length;
+    }
+    if (has_iops_max_length) {
+        cfg.buckets[THROTTLE_OPS_TOTAL].burst_length = iops_max_length;
+    }
+    if (has_iops_rd_max_length) {
+        cfg.buckets[THROTTLE_OPS_READ].burst_length = iops_rd_max_length;
+    }
+    if (has_iops_wr_max_length) {
+        cfg.buckets[THROTTLE_OPS_WRITE].burst_length = iops_wr_max_length;
+    }
+
     if (has_iops_size) {
         cfg.op_size = iops_size;
     }
 
-    if (!check_throttle_config(&cfg, errp)) {
+    if (!throttle_is_valid(&cfg, errp)) {
         goto out;
     }
 
@@ -4086,6 +4117,30 @@ QemuOptsList qemu_common_drive_opts = {
             .name = "throttling.bps-write-max",
             .type = QEMU_OPT_NUMBER,
             .help = "total bytes write burst",
+        },{
+            .name = "throttling.iops-total-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the iops-total-max burst period, in seconds",
+        },{
+            .name = "throttling.iops-read-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the iops-read-max burst period, in seconds",
+        },{
+            .name = "throttling.iops-write-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the iops-write-max burst period, in seconds",
+        },{
+            .name = "throttling.bps-total-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the bps-total-max burst period, in seconds",
+        },{
+            .name = "throttling.bps-read-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the bps-read-max burst period, in seconds",
+        },{
+            .name = "throttling.bps-write-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the bps-write-max burst period, in seconds",
         },{
             .name = "throttling.iops-size",
             .type = QEMU_OPT_NUMBER,

docs/specs/qcow2.txt

@@ -103,7 +103,18 @@ in the description of a field.
                     write to an image with unknown auto-clear features if it
                     clears the respective bits from this field first.
 
-                    Bits 0-63:  Reserved (set to 0)
+                    Bit 0:      Bitmaps extension bit
+                                This bit indicates consistency for the bitmaps
+                                extension data.
+
+                                It is an error if this bit is set without the
+                                bitmaps extension present.
+
+                                If the bitmaps extension is present but this
+                                bit is unset, the bitmaps extension data must be
+                                considered inconsistent.
+
+                    Bits 1-63:  Reserved (set to 0)
 
          96 -  99:  refcount_order
                     Describes the width of a reference count block entry (width
@@ -123,6 +134,7 @@ be stored. Each extension has a structure like the following:
                         0x00000000 - End of the header extension area
                         0xE2792ACA - Backing file format name
                         0x6803f857 - Feature name table
+                        0x23852875 - Bitmaps extension
                         other      - Unknown header extension, can be safely
                                      ignored
 
@@ -166,6 +178,36 @@ the header extension data. Each entry look like this:
                     terminated if it has full length)
 
 
+== Bitmaps extension ==
+
+The bitmaps extension is an optional header extension. It provides the ability
+to store bitmaps related to a virtual disk. For now, there is only one bitmap
+type: the dirty tracking bitmap, which tracks virtual disk changes from some
+point in time.
+
+The data of the extension should be considered consistent only if the
+corresponding auto-clear feature bit is set, see autoclear_features above.
+
+The fields of the bitmaps extension are:
+
+    Byte  0 -  3:  nb_bitmaps
+                   The number of bitmaps contained in the image. Must be
+                   greater than or equal to 1.
+
+                   Note: Qemu currently only supports up to 65535 bitmaps per
+                   image.
+
+          4 -  7:  Reserved, must be zero.
+
+          8 - 15:  bitmap_directory_size
+                   Size of the bitmap directory in bytes. It is the cumulative
+                   size of all (nb_bitmaps) bitmap headers.
+
+         16 - 23:  bitmap_directory_offset
+                   Offset into the image file at which the bitmap directory
+                   starts. Must be aligned to a cluster boundary.
+
+
 == Host cluster management ==
 
 qcow2 manages the allocation of host clusters by maintaining a reference count
@@ -360,3 +402,180 @@ Snapshot table entry:
 
         variable:   Padding to round up the snapshot table entry size to the
                     next multiple of 8.
+
+
+== Bitmaps ==
+
+As mentioned above, the bitmaps extension provides the ability to store bitmaps
+related to a virtual disk. This section describes how these bitmaps are stored.
+
+All stored bitmaps are related to the virtual disk stored in the same image, so
+each bitmap size is equal to the virtual disk size.
+
+Each bit of the bitmap is responsible for strictly defined range of the virtual
+disk. For bit number bit_nr the corresponding range (in bytes) will be:
+
+    [bit_nr * bitmap_granularity .. (bit_nr + 1) * bitmap_granularity - 1]
+
+Granularity is a property of the concrete bitmap, see below.
+
+
+=== Bitmap directory ===
+
+Each bitmap saved in the image is described in a bitmap directory entry. The
+bitmap directory is a contiguous area in the image file, whose starting offset
+and length are given by the header extension fields bitmap_directory_offset and
+bitmap_directory_size. The entries of the bitmap directory have variable
+length, depending on the lengths of the bitmap name and extra data. These
+entries are also called bitmap headers.
+
+Structure of a bitmap directory entry:
+
+    Byte 0 -  7:    bitmap_table_offset
+                    Offset into the image file at which the bitmap table
+                    (described below) for the bitmap starts. Must be aligned to
+                    a cluster boundary.
+
+         8 - 11:    bitmap_table_size
+                    Number of entries in the bitmap table of the bitmap.
+
+        12 - 15:    flags
+                    Bit
+                      0: in_use
+                         The bitmap was not saved correctly and may be
+                         inconsistent.
+
+                      1: auto
+                         The bitmap must reflect all changes of the virtual
+                         disk by any application that would write to this qcow2
+                         file (including writes, snapshot switching, etc.). The
+                         type of this bitmap must be 'dirty tracking bitmap'.
+
+                      2: extra_data_compatible
+                         This flags is meaningful when the extra data is
+                         unknown to the software (currently any extra data is
+                         unknown to Qemu).
+                         If it is set, the bitmap may be used as expected, extra
+                         data must be left as is.
+                         If it is not set, the bitmap must not be used, but
+                         both it and its extra data be left as is.
+
+                    Bits 3 - 31 are reserved and must be 0.
+
+             16:    type
+                    This field describes the sort of the bitmap.
+                    Values:
+                      1: Dirty tracking bitmap
+
+                    Values 0, 2 - 255 are reserved.
+
+             17:    granularity_bits
+                    Granularity bits. Valid values: 0 - 63.
+
+                    Note: Qemu currently doesn't support granularity_bits
+                    greater than 31.
+
+                    Granularity is calculated as
+                        granularity = 1 << granularity_bits
+
+                    A bitmap's granularity is how many bytes of the image
+                    accounts for one bit of the bitmap.
+
+        18 - 19:    name_size
+                    Size of the bitmap name. Must be non-zero.
+
+                    Note: Qemu currently doesn't support values greater than
+                    1023.
+
+        20 - 23:    extra_data_size
+                    Size of type-specific extra data.
+
+                    For now, as no extra data is defined, extra_data_size is
+                    reserved and should be zero. If it is non-zero the
+                    behavior is defined by extra_data_compatible flag.
+
+        variable:   extra_data
+                    Extra data for the bitmap, occupying extra_data_size bytes.
+                    Extra data must never contain references to clusters or in
+                    some other way allocate additional clusters.
+
+        variable:   name
+                    The name of the bitmap (not null terminated), occupying
+                    name_size bytes. Must be unique among all bitmap names
+                    within the bitmaps extension.
+
+        variable:   Padding to round up the bitmap directory entry size to the
+                    next multiple of 8. All bytes of the padding must be zero.
+
+
+=== Bitmap table ===
+
+Each bitmap is stored using a one-level structure (as opposed to two-level
+structures like for refcounts and guest clusters mapping) for the mapping of
+bitmap data to host clusters. This structure is called the bitmap table.
+
+Each bitmap table has a variable size (stored in the bitmap directory entry)
+and may use multiple clusters, however, it must be contiguous in the image
+file.
+
+Structure of a bitmap table entry:
+
+    Bit       0:    Reserved and must be zero if bits 9 - 55 are non-zero.
+                    If bits 9 - 55 are zero:
+                      0: Cluster should be read as all zeros.
+                      1: Cluster should be read as all ones.
+
+         1 -  8:    Reserved and must be zero.
+
+         9 - 55:    Bits 9 - 55 of the host cluster offset. Must be aligned to
+                    a cluster boundary. If the offset is 0, the cluster is
+                    unallocated; in that case, bit 0 determines how this
+                    cluster should be treated during reads.
+
+        56 - 63:    Reserved and must be zero.
+
+
+=== Bitmap data ===
+
+As noted above, bitmap data is stored in separate clusters, described by the
+bitmap table. Given an offset (in bytes) into the bitmap data, the offset into
+the image file can be obtained as follows:
+
+    image_offset(bitmap_data_offset) =
+        bitmap_table[bitmap_data_offset / cluster_size] +
+            (bitmap_data_offset % cluster_size)
+
+This offset is not defined if bits 9 - 55 of bitmap table entry are zero (see
+above).
+
+Given an offset byte_nr into the virtual disk and the bitmap's granularity, the
+bit offset into the image file to the corresponding bit of the bitmap can be
+calculated like this:
+
+    bit_offset(byte_nr) =
+        image_offset(byte_nr / granularity / 8) * 8 +
+            (byte_nr / granularity) % 8
+
+If the size of the bitmap data is not a multiple of the cluster size then the
+last cluster of the bitmap data contains some unused tail bits. These bits must
+be zero.
+
+
+=== Dirty tracking bitmaps ===
+
+Bitmaps with 'type' field equal to one are dirty tracking bitmaps.
+
+When the virtual disk is in use dirty tracking bitmap may be 'enabled' or
+'disabled'. While the bitmap is 'enabled', all writes to the virtual disk
+should be reflected in the bitmap. A set bit in the bitmap means that the
+corresponding range of the virtual disk (see above) was written to while the
+bitmap was 'enabled'. An unset bit means that this range was not written to.
+
+The software doesn't have to sync the bitmap in the image file with its
+representation in RAM after each write. Flag 'in_use' should be set while the
+bitmap is not synced.
+
+In the image file the 'enabled' state is reflected by the 'auto' flag. If this
+flag is set, the software must consider the bitmap as 'enabled' and start
+tracking virtual disk changes to this bitmap from the first write to the
+virtual disk. If this flag is not set then the bitmap is disabled.

docs/throttle.txt

+The QEMU throttling infrastructure
+==================================
+Copyright (C) 2016 Igalia, S.L.
+Author: Alberto Garcia <berto@igalia.com>
+
+This work is licensed under the terms of the GNU GPL, version 2 or
+later. See the COPYING file in the top-level directory.
+
+Introduction
+------------
+QEMU includes a throttling module that can be used to set limits to
+I/O operations. The code itself is generic and independent of the I/O
+units, but it is currenly used to limit the number of bytes per second
+and operations per second (IOPS) when performing disk I/O.
+
+This document explains how to use the throttling code in QEMU, and how
+it works internally. The implementation is in throttle.c.
+
+
+Using throttling to limit disk I/O
+----------------------------------
+Two aspects of the disk I/O can be limited: the number of bytes per
+second and the number of operations per second (IOPS). For each one of
+them the user can set a global limit or separate limits for read and
+write operations. This gives us a total of six different parameters.
+
+I/O limits can be set using the throttling.* parameters of -drive, or
+using the QMP 'block_set_io_throttle' command. These are the names of
+the parameters for both cases:
+
+|-----------------------+-----------------------|
+| -drive                | block_set_io_throttle |
+|-----------------------+-----------------------|
+| throttling.iops-total | iops                  |
+| throttling.iops-read  | iops_rd               |
+| throttling.iops-write | iops_wr               |
+| throttling.bps-total  | bps                   |
+| throttling.bps-read   | bps_rd                |
+| throttling.bps-write  | bps_wr                |
+|-----------------------+-----------------------|
+
+It is possible to set limits for both IOPS and bps and the same time,
+and for each case we can decide whether to have separate read and
+write limits or not, but note that if iops-total is set then neither
+iops-read nor iops-write can be set. The same applies to bps-total and
+bps-read/write.
+
+The default value of these parameters is 0, and it means 'unlimited'.
+
+In its most basic usage, the user can add a drive to QEMU with a limit
+of 100 IOPS with the following -drive line:
+
+   -drive file=hd0.qcow2,throttling.iops-total=100
+
+We can do the same using QMP. In this case all these parameters are
+mandatory, so we must set to 0 the ones that we don't want to limit:
+
+   { "execute": "block_set_io_throttle",
+     "arguments": {
+        "device": "virtio0",
+        "iops": 100,
+        "iops_rd": 0,
+        "iops_wr": 0,
+        "bps": 0,
+        "bps_rd": 0,
+        "bps_wr": 0
+     }
+   }
+
+
+I/O bursts
+----------
+In addition to the basic limits we have just seen, QEMU allows the
+user to do bursts of I/O for a configurable amount of time. A burst is
+an amount of I/O that can exceed the basic limit. Bursts are useful to
+allow better performance when there are peaks of activity (the OS
+boots, a service needs to be restarted) while keeping the average
+limits lower the rest of the time.
+
+Two parameters control bursts: their length and the maximum amount of
+I/O they allow. These two can be configured separately for each one of
+the six basic parameters described in the previous section, but in
+this section we'll use 'iops-total' as an example.
+
+The I/O limit during bursts is set using 'iops-total-max', and the
+maximum length (in seconds) is set with 'iops-total-max-length'. So if
+we want to configure a drive with a basic limit of 100 IOPS and allow
+bursts of 2000 IOPS for 60 seconds, we would do it like this (the line
+is split for clarity):
+
+   -drive file=hd0.qcow2,
+          throttling.iops-total=100,
+          throttling.iops-total-max=2000,
+          throttling.iops-total-max-length=60
+
+Or, with QMP:
+
+   { "execute": "block_set_io_throttle",
+     "arguments": {
+        "device": "virtio0",
+        "iops": 100,
+        "iops_rd": 0,
+        "iops_wr": 0,
+        "bps": 0,
+        "bps_rd": 0,
+        "bps_wr": 0,
+        "iops_max": 2000,
+        "iops_max_length": 60,
+     }
+   }
+
+With this, the user can perform I/O on hd0.qcow2 at a rate of 2000
+IOPS for 1 minute before it's throttled down to 100 IOPS.
+
+The user will be able to do bursts again if there's a sufficiently
+long period of time with unused I/O (see below for details).
+
+The default value for 'iops-total-max' is 0 and it means that bursts
+are not allowed. 'iops-total-max-length' can only be set if
+'iops-total-max' is set as well, and its default value is 1 second.
+
+Here's the complete list of parameters for configuring bursts:
+
+|----------------------------------+-----------------------|
+| -drive                           | block_set_io_throttle |
+|----------------------------------+-----------------------|
+| throttling.iops-total-max        | iops_max              |
+| throttling.iops-total-max-length | iops_max_length       |
+| throttling.iops-read-max         | iops_rd_max           |
+| throttling.iops-read-max-length  | iops_rd_max_length    |
+| throttling.iops-write-max        | iops_wr_max           |
+| throttling.iops-write-max-length | iops_wr_max_length    |
+| throttling.bps-total-max         | bps_max               |
+| throttling.bps-total-max-length  | bps_max_length        |
+| throttling.bps-read-max          | bps_rd_max            |
+| throttling.bps-read-max-length   | bps_rd_max_length     |
+| throttling.bps-write-max         | bps_wr_max            |
+| throttling.bps-write-max-length  | bps_wr_max_length     |
+|----------------------------------+-----------------------|
+
+
+Controlling the size of I/O operations
+--------------------------------------
+When applying IOPS limits all I/O operations are treated equally
+regardless of their size. This means that the user can take advantage
+of this in order to circumvent the limits and submit one huge I/O
+request instead of several smaller ones.
+
+QEMU provides a setting called throttling.iops-size to prevent this
+from happening. This setting specifies the size (in bytes) of an I/O
+request for accounting purposes. Larger requests will be counted
+proportionally to this size.
+
+For example, if iops-size is set to 4096 then an 8KB request will be
+counted as two, and a 6KB request will be counted as one and a
+half. This only applies to requests larger than iops-size: smaller
+requests will be always counted as one, no matter their size.
+
+The default value of iops-size is 0 and it means that the size of the
+requests is never taken into account when applying IOPS limits.
+
+
+Applying I/O limits to groups of disks
+--------------------------------------
+In all the examples so far we have seen how to apply limits to the I/O
+performed on individual drives, but QEMU allows grouping drives so
+they all share the same limits.
+
+The way it works is that each drive with I/O limits is assigned to a
+group named using the throttling.group parameter. If this parameter is
+not specified, then the device name (i.e. 'virtio0', 'ide0-hd0') will
+be used as the group name.
+
+Limits set using the throttling.* parameters discussed earlier in this
+document apply to the combined I/O of all members of a group.
+
+Consider this example:
+
+   -drive file=hd1.qcow2,throttling.iops-total=6000,throttling.group=foo
+   -drive file=hd2.qcow2,throttling.iops-total=6000,throttling.group=foo
+   -drive file=hd3.qcow2,throttling.iops-total=3000,throttling.group=bar
+   -drive file=hd4.qcow2,throttling.iops-total=6000,throttling.group=foo
+   -drive file=hd5.qcow2,throttling.iops-total=3000,throttling.group=bar
+   -drive file=hd6.qcow2,throttling.iops-total=5000
+
+Here hd1, hd2 and hd4 are all members of a group named 'foo' with a
+combined IOPS limit of 6000, and hd3 and hd5 are members of 'bar'. hd6
+is left alone (technically it is part of a 1-member group).
+
+Limits are applied in a round-robin fashion so if there are concurrent
+I/O requests on several drives of the same group they will be
+distributed evenly.
+
+When I/O limits are applied to an existing drive using the QMP command
+'block_set_io_throttle', the following things need to be taken into
+account:
+
+   - I/O limits are shared within the same group, so new values will
+     affect all members and overwrite the previous settings. In other
+     words: if different limits are applied to members of the same
+     group, the last one wins.
+
+   - If 'group' is unset it is assumed to be the current group of that
+     drive. If the drive is not in a group yet, it will be added to a
+     group named after the device name.
+
+   - If 'group' is set then the drive will be moved to that group if
+     it was member of a different one. In this case the limits
+     specified in the parameters will be applied to the new group
+     only.
+
+   - I/O limits can be disabled by setting all of them to 0. In this
+     case the device will be removed from its group and the rest of
+     its members will not be affected. The 'group' parameter is
+     ignored.
+
+
+The Leaky Bucket algorithm
+--------------------------
+I/O limits in QEMU are implemented using the leaky bucket algorithm
+(specifically the "Leaky bucket as a meter" variant).
+
+This algorithm uses the analogy of a bucket that leaks water
+constantly. The water that gets into the bucket represents the I/O
+that has been performed, and no more I/O is allowed once the bucket is
+full.
+
+To see the way this corresponds to the throttling parameters in QEMU,
+consider the following values:
+
+  iops-total=100
+  iops-total-max=2000
+  iops-total-max-length=60
+
+  - Water leaks from the bucket at a rate of 100 IOPS.
+  - Water can be added to the bucket at a rate of 2000 IOPS.
+  - The size of the bucket is 2000 x 60 = 120000
+  - If 'iops-total-max-length' is unset then the bucket size is 100.
+
+The bucket is initially empty, therefore water can be added until it's
+full at a rate of 2000 IOPS (the burst rate). Once the bucket is full
+we can only add as much water as it leaks, therefore the I/O rate is
+reduced to 100 IOPS. If we add less water than it leaks then the
+bucket will start to empty, allowing for bursts again.
+
+Note that since water is leaking from the bucket even during bursts,
+it will take a bit more than 60 seconds at 2000 IOPS to fill it
+up. After those 60 seconds the bucket will have leaked 60 x 100 =
+6000, allowing for 3 more seconds of I/O at 2000 IOPS.
+
+Also, due to the way the algorithm works, longer burst can be done at
+a lower I/O rate, e.g. 1000 IOPS during 120 seconds.

hmp.c

@@ -1414,6 +1414,18 @@ void hmp_block_set_io_throttle(Monitor *mon, const QDict *qdict)
                               0,
                               false,
                               0,
+                              false, /* no burst length via HMP */
+                              0,
+                              false,
+                              0,
+                              false,
+                              0,
+                              false,
+                              0,
+                              false,
+                              0,
+                              false,
+                              0,
                               false, /* No default I/O size */
                               0,
                               false,

include/qemu/throttle.h

@@ -2,7 +2,7 @@
  * QEMU throttling infrastructure
  *
  * Copyright (C) Nodalink, EURL. 2013-2014
- * Copyright (C) Igalia, S.L. 2015
+ * Copyright (C) Igalia, S.L. 2015-2016
  *
  * Authors:
  *   Benoît Canet <benoit.canet@nodalink.com>
@@ -42,16 +42,47 @@ typedef enum {
 } BucketType;
 
 /*
- * The max parameter of the leaky bucket throttling algorithm can be used to
- * allow the guest to do bursts.
- * The max value is a pool of I/O that the guest can use without being throttled
- * at all. Throttling is triggered once this pool is empty.
+ * This module implements I/O limits using the leaky bucket
+ * algorithm. The code is independent of the I/O units, but it is
+ * currently used for bytes per second and operations per second.
+ *
+ * Three parameters can be set by the user:
+ *
+ * - avg: the desired I/O limits in units per second.
+ * - max: the limit during bursts, also in units per second.
+ * - burst_length: the maximum length of the burst period, in seconds.
+ *
+ * Here's how it works:
+ *
+ * - The bucket level (number of performed I/O units) is kept in
+ *   bkt.level and leaks at a rate of bkt.avg units per second.
+ *
+ * - The size of the bucket is bkt.max * bkt.burst_length. Once the
+ *   bucket is full no more I/O is performed until the bucket leaks
+ *   again. This is what makes the I/O rate bkt.avg.
+ *
+ * - The bkt.avg rate does not apply until the bucket is full,
+ *   allowing the user to do bursts until then. The I/O limit during
+ *   bursts is bkt.max. To enforce this limit we keep an additional
+ *   bucket in bkt.burst_length that leaks at a rate of bkt.max units
+ *   per second.
+ *
+ * - Because of all of the above, the user can perform I/O at a
+ *   maximum of bkt.max units per second for at most bkt.burst_length
+ *   seconds in a row. After that the bucket will be full and the I/O
+ *   rate will go down to bkt.avg.
+ *
+ * - Since the bucket always leaks at a rate of bkt.avg, this also
+ *   determines how much the user needs to wait before being able to
+ *   do bursts again.
  */
 
 typedef struct LeakyBucket {
     double  avg;              /* average goal in units per second */
     double  max;              /* leaky bucket max burst in units */
     double  level;            /* bucket level in units */
+    double  burst_level;      /* bucket level in units (for computing bursts) */
+    unsigned burst_length;    /* max length of the burst period, in seconds */
 } LeakyBucket;
 
 /* The following structure is used to configure a ThrottleState
@@ -84,12 +115,6 @@ void throttle_leak_bucket(LeakyBucket *bkt, int64_t delta);
 
 int64_t throttle_compute_wait(LeakyBucket *bkt);
 
-/* expose timer computation function for unit tests */
-bool throttle_compute_timer(ThrottleState *ts,
-                            bool is_write,
-                            int64_t now,
-                            int64_t *next_timestamp);
-
 /* init/destroy cycle */
 void throttle_init(ThrottleState *ts);
 
@@ -112,11 +137,7 @@ bool throttle_timers_are_initialized(ThrottleTimers *tt);
 /* configuration */
 bool throttle_enabled(ThrottleConfig *cfg);
 
-bool throttle_conflicting(ThrottleConfig *cfg);
-
-bool throttle_is_valid(ThrottleConfig *cfg);
-
-bool throttle_max_is_missing_limit(ThrottleConfig *cfg);
+bool throttle_is_valid(ThrottleConfig *cfg, Error **errp);
 
 void throttle_config(ThrottleState *ts,
                      ThrottleTimers *tt,
@@ -124,6 +145,8 @@ void throttle_config(ThrottleState *ts,
 
 void throttle_get_config(ThrottleState *ts, ThrottleConfig *cfg);
 
+void throttle_config_init(ThrottleConfig *cfg);
+
 /* usage */
 bool throttle_schedule_timer(ThrottleState *ts,
                              ThrottleTimers *tt,

migration/block.c

@@ -786,6 +786,7 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
     int64_t addr;
     BlockDriverState *bs, *bs_prev = NULL;
     BlockBackend *blk;
+    Error *local_err = NULL;
     uint8_t *buf;
     int64_t total_sectors = 0;
     int nr_sectors;
@@ -824,6 +825,12 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
                                  device_name);
                     return -EINVAL;
                 }
+
+                bdrv_invalidate_cache(bs, &local_err);
+                if (local_err) {
+                    error_report_err(local_err);
+                    return -EINVAL;
+                }
             }
 
             if (total_sectors - addr < BDRV_SECTORS_PER_DIRTY_CHUNK) {

qapi/block-core.json

@@ -273,17 +273,41 @@
 #
 # @image: the info of image used (since: 1.6)
 #
-# @bps_max: #optional total max in bytes (Since 1.7)
+# @bps_max: #optional total throughput limit during bursts,
+#                     in bytes (Since 1.7)
 #
-# @bps_rd_max: #optional read max in bytes (Since 1.7)
+# @bps_rd_max: #optional read throughput limit during bursts,
+#                        in bytes (Since 1.7)
 #
-# @bps_wr_max: #optional write max in bytes (Since 1.7)
+# @bps_wr_max: #optional write throughput limit during bursts,
+#                        in bytes (Since 1.7)
 #
-# @iops_max: #optional total I/O operations max (Since 1.7)
+# @iops_max: #optional total I/O operations per second during bursts,
+#                      in bytes (Since 1.7)
 #
-# @iops_rd_max: #optional read I/O operations max (Since 1.7)
+# @iops_rd_max: #optional read I/O operations per second during bursts,
+#                         in bytes (Since 1.7)
 #
-# @iops_wr_max: #optional write I/O operations max (Since 1.7)
+# @iops_wr_max: #optional write I/O operations per second during bursts,
+#                         in bytes (Since 1.7)
+#
+# @bps_max_length: #optional maximum length of the @bps_max burst
+#                            period, in seconds. (Since 2.6)
+#
+# @bps_rd_max_length: #optional maximum length of the @bps_rd_max
+#                               burst period, in seconds. (Since 2.6)
+#
+# @bps_wr_max_length: #optional maximum length of the @bps_wr_max
+#                               burst period, in seconds. (Since 2.6)
+#
+# @iops_max_length: #optional maximum length of the @iops burst
+#                             period, in seconds. (Since 2.6)
+#
+# @iops_rd_max_length: #optional maximum length of the @iops_rd_max
+#                                burst period, in seconds. (Since 2.6)
+#
+# @iops_wr_max_length: #optional maximum length of the @iops_wr_max
+#                                burst period, in seconds. (Since 2.6)
 #
 # @iops_size: #optional an I/O size in bytes (Since 1.7)
 #
@@ -308,6 +332,9 @@
             '*bps_max': 'int', '*bps_rd_max': 'int',
             '*bps_wr_max': 'int', '*iops_max': 'int',
             '*iops_rd_max': 'int', '*iops_wr_max': 'int',
+            '*bps_max_length': 'int', '*bps_rd_max_length': 'int',
+            '*bps_wr_max_length': 'int', '*iops_max_length': 'int',
+            '*iops_rd_max_length': 'int', '*iops_wr_max_length': 'int',
             '*iops_size': 'int', '*group': 'str', 'cache': 'BlockdevCacheInfo',
             'write_threshold': 'int' } }
 
@@ -1294,21 +1321,57 @@
 #
 # @iops: total I/O operations per second
 #
-# @ops_rd: read I/O operations per second
+# @iops_rd: read I/O operations per second
 #
 # @iops_wr: write I/O operations per second
 #
-# @bps_max: #optional total max in bytes (Since 1.7)
+# @bps_max: #optional total throughput limit during bursts,
+#                     in bytes (Since 1.7)
+#
+# @bps_rd_max: #optional read throughput limit during bursts,
+#                        in bytes (Since 1.7)
+#
+# @bps_wr_max: #optional write throughput limit during bursts,
+#                        in bytes (Since 1.7)
+#
+# @iops_max: #optional total I/O operations per second during bursts,
+#                      in bytes (Since 1.7)
+#
+# @iops_rd_max: #optional read I/O operations per second during bursts,
+#                         in bytes (Since 1.7)
+#
+# @iops_wr_max: #optional write I/O operations per second during bursts,
+#                         in bytes (Since 1.7)
+#
+# @bps_max_length: #optional maximum length of the @bps_max burst
+#                            period, in seconds. It must only
+#                            be set if @bps_max is set as well.
+#                            Defaults to 1. (Since 2.6)
 #
-# @bps_rd_max: #optional read max in bytes (Since 1.7)
+# @bps_rd_max_length: #optional maximum length of the @bps_rd_max
+#                               burst period, in seconds. It must only
+#                               be set if @bps_rd_max is set as well.
+#                               Defaults to 1. (Since 2.6)
 #
-# @bps_wr_max: #optional write max in bytes (Since 1.7)
+# @bps_wr_max_length: #optional maximum length of the @bps_wr_max
+#                               burst period, in seconds. It must only
+#                               be set if @bps_wr_max is set as well.
+#                               Defaults to 1. (Since 2.6)
 #
-# @iops_max: #optional total I/O operations max (Since 1.7)
+# @iops_max_length: #optional maximum length of the @iops burst
+#                             period, in seconds. It must only
+#                             be set if @iops_max is set as well.
+#                             Defaults to 1. (Since 2.6)
 #
-# @iops_rd_max: #optional read I/O operations max (Since 1.7)
+# @iops_rd_max_length: #optional maximum length of the @iops_rd_max
+#                                burst period, in seconds. It must only
+#                                be set if @iops_rd_max is set as well.
+#                                Defaults to 1. (Since 2.6)
 #
-# @iops_wr_max: #optional write I/O operations max (Since 1.7)
+# @iops_wr_max_length: #optional maximum length of the @iops_wr_max
+#                                burst period, in seconds. It must only
+#                                be set if @iops_wr_max is set as well.
+#                                Defaults to 1. (Since 2.6)
 #
 # @iops_size: #optional an I/O size in bytes (Since 1.7)
 #
@@ -1325,6 +1388,9 @@
             '*bps_max': 'int', '*bps_rd_max': 'int',
             '*bps_wr_max': 'int', '*iops_max': 'int',
             '*iops_rd_max': 'int', '*iops_wr_max': 'int',
+            '*bps_max_length': 'int', '*bps_rd_max_length': 'int',
+            '*bps_wr_max_length': 'int', '*iops_max_length': 'int',
+            '*iops_rd_max_length': 'int', '*iops_wr_max_length': 'int',
             '*iops_size': 'int', '*group': 'str' } }
 
 ##

qemu-img-cmds.hx

@@ -10,68 +10,68 @@ STEXI
 ETEXI
 
 DEF("check", img_check,
-    "check [-q] [-f fmt] [--output=ofmt] [-r [leaks | all]] [-T src_cache] filename")
+    "check [-q] [--object objectdef] [--image-opts] [-f fmt] [--output=ofmt] [-r [leaks | all]] [-T src_cache] filename")
 STEXI
-@item check [-q] [-f @var{fmt}] [--output=@var{ofmt}] [-r [leaks | all]] [-T @var{src_cache}] @var{filename}
+@item check [--object @var{objectdef}] [--image-opts] [-q] [-f @var{fmt}] [--output=@var{ofmt}] [-r [leaks | all]] [-T @var{src_cache}] @var{filename}
 ETEXI
 
 DEF("create", img_create,
-    "create [-q] [-f fmt] [-o options] filename [size]")
+    "create [-q] [--object objectdef] [--image-opts] [-f fmt] [-o options] filename [size]")
 STEXI
-@item create [-q] [-f @var{fmt}] [-o @var{options}] @var{filename} [@var{size}]
+@item create [--object @var{objectdef}] [--image-opts] [-q] [-f @var{fmt}] [-o @var{options}] @var{filename} [@var{size}]
 ETEXI
 
 DEF("commit", img_commit,
-    "commit [-q] [-f fmt] [-t cache] [-b base] [-d] [-p] filename")
+    "commit [-q] [--object objectdef] [--image-opts] [-f fmt] [-t cache] [-b base] [-d] [-p] filename")
 STEXI
-@item commit [-q] [-f @var{fmt}] [-t @var{cache}] [-b @var{base}] [-d] [-p] @var{filename}
+@item commit [--object @var{objectdef}] [--image-opts] [-q] [-f @var{fmt}] [-t @var{cache}] [-b @var{base}] [-d] [-p] @var{filename}
 ETEXI
 
 DEF("compare", img_compare,
-    "compare [-f fmt] [-F fmt] [-T src_cache] [-p] [-q] [-s] filename1 filename2")
+    "compare [--object objectdef] [--image-opts] [-f fmt] [-F fmt] [-T src_cache] [-p] [-q] [-s] filename1 filename2")
 STEXI
-@item compare [-f @var{fmt}] [-F @var{fmt}] [-T @var{src_cache}] [-p] [-q] [-s] @var{filename1} @var{filename2}
+@item compare [--object @var{objectdef}] [--image-opts] [-f @var{fmt}] [-F @var{fmt}] [-T @var{src_cache}] [-p] [-q] [-s] @var{filename1} @var{filename2}
 ETEXI
 
 DEF("convert", img_convert,
-    "convert [-c] [-p] [-q] [-n] [-f fmt] [-t cache] [-T src_cache] [-O output_fmt] [-o options] [-s snapshot_id_or_name] [-l snapshot_param] [-S sparse_size] filename [filename2 [...]] output_filename")
+    "convert [--object objectdef] [--image-opts] [-c] [-p] [-q] [-n] [-f fmt] [-t cache] [-T src_cache] [-O output_fmt] [-o options] [-s snapshot_id_or_name] [-l snapshot_param] [-S sparse_size] filename [filename2 [...]] output_filename")
 STEXI
-@item convert [-c] [-p] [-q] [-n] [-f @var{fmt}] [-t @var{cache}] [-T @var{src_cache}] [-O @var{output_fmt}] [-o @var{options}] [-s @var{snapshot_id_or_name}] [-l @var{snapshot_param}] [-S @var{sparse_size}] @var{filename} [@var{filename2} [...]] @var{output_filename}
+@item convert [--object @var{objectdef}] [--image-opts] [-c] [-p] [-q] [-n] [-f @var{fmt}] [-t @var{cache}] [-T @var{src_cache}] [-O @var{output_fmt}] [-o @var{options}] [-s @var{snapshot_id_or_name}] [-l @var{snapshot_param}] [-S @var{sparse_size}] @var{filename} [@var{filename2} [...]] @var{output_filename}
 ETEXI
 
 DEF("info", img_info,
-    "info [-f fmt] [--output=ofmt] [--backing-chain] filename")
+    "info [--object objectdef] [--image-opts] [-f fmt] [--output=ofmt] [--backing-chain] filename")
 STEXI
-@item info [-f @var{fmt}] [--output=@var{ofmt}] [--backing-chain] @var{filename}
+@item info [--object @var{objectdef}] [--image-opts] [-f @var{fmt}] [--output=@var{ofmt}] [--backing-chain] @var{filename}
 ETEXI
 
 DEF("map", img_map,
-    "map [-f fmt] [--output=ofmt] filename")
+    "map [--object objectdef] [--image-opts] [-f fmt] [--output=ofmt] filename")
 STEXI
-@item map [-f @var{fmt}] [--output=@var{ofmt}] @var{filename}
+@item map [--object @var{objectdef}] [--image-opts] [-f @var{fmt}] [--output=@var{ofmt}] @var{filename}
 ETEXI
 
 DEF("snapshot", img_snapshot,
-    "snapshot [-q] [-l | -a snapshot | -c snapshot | -d snapshot] filename")
+    "snapshot [--object objectdef] [--image-opts] [-q] [-l | -a snapshot | -c snapshot | -d snapshot] filename")
 STEXI
-@item snapshot [-q] [-l | -a @var{snapshot} | -c @var{snapshot} | -d @var{snapshot}] @var{filename}
+@item snapshot [--object @var{objectdef}] [--image-opts] [-q] [-l | -a @var{snapshot} | -c @var{snapshot} | -d @var{snapshot}] @var{filename}
 ETEXI
 
 DEF("rebase", img_rebase,
-    "rebase [-q] [-f fmt] [-t cache] [-T src_cache] [-p] [-u] -b backing_file [-F backing_fmt] filename")
+    "rebase [--object objectdef] [--image-opts] [-q] [-f fmt] [-t cache] [-T src_cache] [-p] [-u] -b backing_file [-F backing_fmt] filename")
 STEXI
-@item rebase [-q] [-f @var{fmt}] [-t @var{cache}] [-T @var{src_cache}] [-p] [-u] -b @var{backing_file} [-F @var{backing_fmt}] @var{filename}
+@item rebase [--object @var{objectdef}] [--image-opts] [-q] [-f @var{fmt}] [-t @var{cache}] [-T @var{src_cache}] [-p] [-u] -b @var{backing_file} [-F @var{backing_fmt}] @var{filename}
 ETEXI
 
 DEF("resize", img_resize,
-    "resize [-q] filename [+ | -]size")
+    "resize [--object objectdef] [--image-opts] [-q] filename [+ | -]size")
 STEXI
-@item resize [-q] @var{filename} [+ | -]@var{size}
+@item resize [--object @var{objectdef}] [--image-opts] [-q] @var{filename} [+ | -]@var{size}
 ETEXI
 
 DEF("amend", img_amend,
-    "amend [-p] [-q] [-f fmt] [-t cache] -o options filename")
+    "amend [--object objectdef] [--image-opts] [-p] [-q] [-f fmt] [-t cache] -o options filename")
 STEXI
-@item amend [-p] [-q] [-f @var{fmt}] [-t @var{cache}] -o @var{options} @var{filename}
+@item amend [--object @var{objectdef}] [--image-opts] [-p] [-q] [-f @var{fmt}] [-t @var{cache}] -o @var{options} @var{filename}
 @end table
 ETEXI

qemu-img.texi

@@ -24,6 +24,20 @@ Command parameters:
 @table @var
 @item filename
  is a disk image filename
+
+@item --object @var{objectdef}
+
+is a QEMU user creatable object definition. See the @code{qemu(1)} manual
+page for a description of the object properties. The most common object
+type is a @code{secret}, which is used to supply passwords and/or encryption
+keys.
+
+@item --image-opts
+
+Indicates that the @var{filename} parameter is to be interpreted as a
+full option string, not a plain filename. This parameter is mutually
+exclusive with the @var{-f} and @var{-F} parameters.
+
 @item fmt
 is the disk image format. It is guessed automatically in most cases. See below
 for a description of the supported disk formats.

qemu-io.c

@@ -18,6 +18,7 @@
 #include "qemu/config-file.h"
 #include "qemu/readline.h"
 #include "qapi/qmp/qstring.h"
+#include "qom/object_interfaces.h"
 #include "sysemu/block-backend.h"
 #include "block/block_int.h"
 #include "trace/control.h"
@@ -31,6 +32,7 @@ static BlockBackend *qemuio_blk;
 /* qemu-io commands passed using -c */
 static int ncmdline;
 static char **cmdline;
+static bool imageOpts;
 
 static ReadLineState *readline_state;
 
@@ -150,6 +152,10 @@ static int open_f(BlockBackend *blk, int argc, char **argv)
             readonly = 1;
             break;
         case 'o':
+            if (imageOpts) {
+                printf("--image-opts and 'open -o' are mutually exclusive\n");
+                return 0;
+            }
             if (!qemu_opts_parse_noisily(&empty_opts, optarg, false)) {
                 qemu_opts_reset(&empty_opts);
                 return 0;
@@ -165,6 +171,14 @@ static int open_f(BlockBackend *blk, int argc, char **argv)
         flags |= BDRV_O_RDWR;
     }
 
+    if (imageOpts && (optind == argc - 1)) {
+        if (!qemu_opts_parse_noisily(&empty_opts, argv[optind], false)) {
+            qemu_opts_reset(&empty_opts);
+            return 0;
+        }
+        optind++;
+    }
+
     qopts = qemu_opts_find(&empty_opts, NULL);
     opts = qopts ? qemu_opts_to_qdict(qopts, NULL) : NULL;
     qemu_opts_reset(&empty_opts);
@@ -200,6 +214,8 @@ static void usage(const char *name)
 "Usage: %s [-h] [-V] [-rsnm] [-f FMT] [-c STRING] ... [file]\n"
 "QEMU Disk exerciser\n"
 "\n"
+"  --object OBJECTDEF   define an object such as 'secret' for\n"
+"                       passwords and/or encryption keys\n"
 "  -c, --cmd STRING     execute command with its arguments\n"
 "                       from the given string\n"
 "  -f, --format FMT     specifies the block driver to use\n"
@@ -361,24 +377,51 @@ static void reenable_tty_echo(void)
     qemu_set_tty_echo(STDIN_FILENO, true);
 }
 
+enum {
+    OPTION_OBJECT = 256,
+    OPTION_IMAGE_OPTS = 257,
+};
+
+static QemuOptsList qemu_object_opts = {
+    .name = "object",
+    .implied_opt_name = "qom-type",
+    .head = QTAILQ_HEAD_INITIALIZER(qemu_object_opts.head),
+    .desc = {
+        { }
+    },
+};
+
+
+static QemuOptsList file_opts = {
+    .name = "file",
+    .implied_opt_name = "file",
+    .head = QTAILQ_HEAD_INITIALIZER(file_opts.head),
+    .desc = {
+        /* no elements => accept any params */
+        { /* end of list */ }
+    },
+};
+
 int main(int argc, char **argv)
 {
     int readonly = 0;
     const char *sopt = "hVc:d:f:rsnmgkt:T:";
     const struct option lopt[] = {
-        { "help", 0, NULL, 'h' },
-        { "version", 0, NULL, 'V' },
-        { "offset", 1, NULL, 'o' },
-        { "cmd", 1, NULL, 'c' },
-        { "format", 1, NULL, 'f' },
-        { "read-only", 0, NULL, 'r' },
-        { "snapshot", 0, NULL, 's' },
-        { "nocache", 0, NULL, 'n' },
-        { "misalign", 0, NULL, 'm' },
-        { "native-aio", 0, NULL, 'k' },
-        { "discard", 1, NULL, 'd' },
-        { "cache", 1, NULL, 't' },
-        { "trace", 1, NULL, 'T' },
+        { "help", no_argument, NULL, 'h' },
+        { "version", no_argument, NULL, 'V' },
+        { "offset", required_argument, NULL, 'o' },
+        { "cmd", required_argument, NULL, 'c' },
+        { "format", required_argument, NULL, 'f' },
+        { "read-only", no_argument, NULL, 'r' },
+        { "snapshot", no_argument, NULL, 's' },
+        { "nocache", no_argument, NULL, 'n' },
+        { "misalign", no_argument, NULL, 'm' },
+        { "native-aio", no_argument, NULL, 'k' },
+        { "discard", required_argument, NULL, 'd' },
+        { "cache", required_argument, NULL, 't' },
+        { "trace", required_argument, NULL, 'T' },
+        { "object", required_argument, NULL, OPTION_OBJECT },
+        { "image-opts", no_argument, NULL, OPTION_IMAGE_OPTS },
         { NULL, 0, NULL, 0 }
     };
     int c;
@@ -386,6 +429,7 @@ int main(int argc, char **argv)
     int flags = BDRV_O_UNMAP;
     Error *local_error = NULL;
     QDict *opts = NULL;
+    const char *format = NULL;
 
 #ifdef CONFIG_POSIX
     signal(SIGPIPE, SIG_IGN);
@@ -395,6 +439,7 @@ int main(int argc, char **argv)
     qemu_init_exec_dir(argv[0]);
 
     module_call_init(MODULE_INIT_QOM);
+    qemu_add_opts(&qemu_object_opts);
     bdrv_init();
 
     while ((c = getopt_long(argc, argv, sopt, lopt, &opt_index)) != -1) {
@@ -412,10 +457,7 @@ int main(int argc, char **argv)
             }
             break;
         case 'f':
-            if (!opts) {
-                opts = qdict_new();
-            }
-            qdict_put(opts, "driver", qstring_from_str(optarg));
+            format = optarg;
             break;
         case 'c':
             add_user_command(optarg);
@@ -446,6 +488,17 @@ int main(int argc, char **argv)
         case 'h':
             usage(progname);
             exit(0);
+        case OPTION_OBJECT: {
+            QemuOpts *qopts;
+            qopts = qemu_opts_parse_noisily(&qemu_object_opts,
+                                            optarg, true);
+            if (!qopts) {
+                exit(1);
+            }
+        }   break;
+        case OPTION_IMAGE_OPTS:
+            imageOpts = true;
+            break;
         default:
             usage(progname);
             exit(1);
@@ -457,11 +510,23 @@ int main(int argc, char **argv)
         exit(1);
     }
 
+    if (format && imageOpts) {
+        error_report("--image-opts and -f are mutually exclusive");
+        exit(1);
+    }
+
     if (qemu_init_main_loop(&local_error)) {
         error_report_err(local_error);
         exit(1);
     }
 
+    if (qemu_opts_foreach(&qemu_object_opts,
+                          user_creatable_add_opts_foreach,
+                          NULL, &local_error)) {
+        error_report_err(local_error);
+        exit(1);
+    }
+
     /* initialize commands */
     qemuio_add_command(&quit_cmd);
     qemuio_add_command(&open_cmd);
@@ -482,7 +547,21 @@ int main(int argc, char **argv)
     }
 
     if ((argc - optind) == 1) {
-        openfile(argv[optind], flags, opts);
+        if (imageOpts) {
+            QemuOpts *qopts = NULL;
+            qopts = qemu_opts_parse_noisily(&file_opts, argv[optind], false);
+            if (!qopts) {
+                exit(1);
+            }
+            opts = qemu_opts_to_qdict(qopts, NULL);
+            openfile(NULL, flags, opts);
+        } else {
+            if (format) {
+                opts = qdict_new();
+                qdict_put(opts, "driver", qstring_from_str(format));
+            }
+            openfile(argv[optind], flags, opts);
+        }
     }
     command_loop();
 

qemu-nbd.c

@@ -37,12 +37,13 @@
 #include <pthread.h>
 
 #define SOCKET_PATH                "/var/lock/qemu-nbd-%s"
-#define QEMU_NBD_OPT_CACHE         1
-#define QEMU_NBD_OPT_AIO           2
-#define QEMU_NBD_OPT_DISCARD       3
-#define QEMU_NBD_OPT_DETECT_ZEROES 4
-#define QEMU_NBD_OPT_OBJECT        5
-#define QEMU_NBD_OPT_TLSCREDS      6
+#define QEMU_NBD_OPT_CACHE         256
+#define QEMU_NBD_OPT_AIO           257
+#define QEMU_NBD_OPT_DISCARD       258
+#define QEMU_NBD_OPT_DETECT_ZEROES 259
+#define QEMU_NBD_OPT_OBJECT        260
+#define QEMU_NBD_OPT_TLSCREDS      261
+#define QEMU_NBD_OPT_IMAGE_OPTS    262
 
 static NBDExport *exp;
 static bool newproto;
@@ -105,6 +106,7 @@ static void usage(const char *name)
 "      --aio=MODE            set AIO mode (native or threads)\n"
 "      --discard=MODE        set discard mode (ignore, unmap)\n"
 "      --detect-zeroes=MODE  set detect-zeroes mode (off, on, unmap)\n"
+"      --image-opts          treat FILE as a full set of image options\n"
 "\n"
 "Report bugs to <qemu-devel@nongnu.org>\n"
     , name, NBD_DEFAULT_PORT, "DEVICE");
@@ -394,6 +396,16 @@ static SocketAddress *nbd_build_socket_address(const char *sockpath,
 }
 
 
+static QemuOptsList file_opts = {
+    .name = "file",
+    .implied_opt_name = "file",
+    .head = QTAILQ_HEAD_INITIALIZER(file_opts.head),
+    .desc = {
+        /* no elements => accept any params */
+        { /* end of list */ }
+    },
+};
+
 static QemuOptsList qemu_object_opts = {
     .name = "object",
     .implied_opt_name = "qom-type",
@@ -451,30 +463,32 @@ int main(int argc, char **argv)
     const char *sn_id_or_name = NULL;
     const char *sopt = "hVb:o:p:rsnP:c:dvk:e:f:tl:x:";
     struct option lopt[] = {
-        { "help", 0, NULL, 'h' },
-        { "version", 0, NULL, 'V' },
-        { "bind", 1, NULL, 'b' },
-        { "port", 1, NULL, 'p' },
-        { "socket", 1, NULL, 'k' },
-        { "offset", 1, NULL, 'o' },
-        { "read-only", 0, NULL, 'r' },
-        { "partition", 1, NULL, 'P' },
-        { "connect", 1, NULL, 'c' },
-        { "disconnect", 0, NULL, 'd' },
-        { "snapshot", 0, NULL, 's' },
-        { "load-snapshot", 1, NULL, 'l' },
-        { "nocache", 0, NULL, 'n' },
-        { "cache", 1, NULL, QEMU_NBD_OPT_CACHE },
-        { "aio", 1, NULL, QEMU_NBD_OPT_AIO },
-        { "discard", 1, NULL, QEMU_NBD_OPT_DISCARD },
-        { "detect-zeroes", 1, NULL, QEMU_NBD_OPT_DETECT_ZEROES },
-        { "shared", 1, NULL, 'e' },
-        { "format", 1, NULL, 'f' },
-        { "persistent", 0, NULL, 't' },
-        { "verbose", 0, NULL, 'v' },
-        { "object", 1, NULL, QEMU_NBD_OPT_OBJECT },
-        { "export-name", 1, NULL, 'x' },
-        { "tls-creds", 1, NULL, QEMU_NBD_OPT_TLSCREDS },
+        { "help", no_argument, NULL, 'h' },
+        { "version", no_argument, NULL, 'V' },
+        { "bind", required_argument, NULL, 'b' },
+        { "port", required_argument, NULL, 'p' },
+        { "socket", required_argument, NULL, 'k' },
+        { "offset", required_argument, NULL, 'o' },
+        { "read-only", no_argument, NULL, 'r' },
+        { "partition", required_argument, NULL, 'P' },
+        { "connect", required_argument, NULL, 'c' },
+        { "disconnect", no_argument, NULL, 'd' },
+        { "snapshot", no_argument, NULL, 's' },
+        { "load-snapshot", required_argument, NULL, 'l' },
+        { "nocache", no_argument, NULL, 'n' },
+        { "cache", required_argument, NULL, QEMU_NBD_OPT_CACHE },
+        { "aio", required_argument, NULL, QEMU_NBD_OPT_AIO },
+        { "discard", required_argument, NULL, QEMU_NBD_OPT_DISCARD },
+        { "detect-zeroes", required_argument, NULL,
+          QEMU_NBD_OPT_DETECT_ZEROES },
+        { "shared", required_argument, NULL, 'e' },
+        { "format", required_argument, NULL, 'f' },
+        { "persistent", no_argument, NULL, 't' },
+        { "verbose", no_argument, NULL, 'v' },
+        { "object", required_argument, NULL, QEMU_NBD_OPT_OBJECT },
+        { "export-name", required_argument, NULL, 'x' },
+        { "tls-creds", required_argument, NULL, QEMU_NBD_OPT_TLSCREDS },
+        { "image-opts", no_argument, NULL, QEMU_NBD_OPT_IMAGE_OPTS },
         { NULL, 0, NULL, 0 }
     };
     int ch;
@@ -493,6 +507,7 @@ int main(int argc, char **argv)
     QDict *options = NULL;
     const char *export_name = NULL;
     const char *tlscredsid = NULL;
+    bool imageOpts = false;
 
     /* The client thread uses SIGTERM to interrupt the server.  A signal
      * handler ensures that "qemu-nbd -v -c" exits with a nice status code.
@@ -672,6 +687,9 @@ int main(int argc, char **argv)
         case QEMU_NBD_OPT_TLSCREDS:
             tlscredsid = optarg;
             break;
+        case QEMU_NBD_OPT_IMAGE_OPTS:
+            imageOpts = true;
+            break;
         }
     }
 
@@ -800,13 +818,29 @@ int main(int argc, char **argv)
     bdrv_init();
     atexit(bdrv_close_all);
 
-    if (fmt) {
-        options = qdict_new();
-        qdict_put(options, "driver", qstring_from_str(fmt));
+    srcpath = argv[optind];
+    if (imageOpts) {
+        QemuOpts *opts;
+        if (fmt) {
+            error_report("--image-opts and -f are mutually exclusive");
+            exit(EXIT_FAILURE);
+        }
+        opts = qemu_opts_parse_noisily(&file_opts, srcpath, true);
+        if (!opts) {
+            qemu_opts_reset(&file_opts);
+            exit(EXIT_FAILURE);
+        }
+        options = qemu_opts_to_qdict(opts, NULL);
+        qemu_opts_reset(&file_opts);
+        blk = blk_new_open("hda", NULL, NULL, options, flags, &local_err);
+    } else {
+        if (fmt) {
+            options = qdict_new();
+            qdict_put(options, "driver", qstring_from_str(fmt));
+        }
+        blk = blk_new_open("hda", srcpath, NULL, options, flags, &local_err);
     }
 
-    srcpath = argv[optind];
-    blk = blk_new_open("hda", srcpath, NULL, options, flags, &local_err);
     if (!blk) {
         error_reportf_err(local_err, "Failed to blk_new_open '%s': ",
                           argv[optind]);

qemu-nbd.texi

@@ -13,7 +13,8 @@ Export a QEMU disk image using the NBD protocol.
 @c man end
 
 @c man begin OPTIONS
-@var{filename} is a disk image filename.
+@var{filename} is a disk image filename, or a set of block
+driver options if @var{--image-opts} is specified.
 
 @var{dev} is an NBD device.
 
@@ -33,6 +34,10 @@ The offset into the image
 The interface to bind to (default @samp{0.0.0.0})
 @item -k, --socket=@var{path}
 Use a unix socket with path @var{path}
+@item --image-opts
+Treat @var{filename} as a set of image options, instead of a plain
+filename. If this flag is specified, the @var{-f} flag should
+not be used, instead the '@code{format=}' option should be set.
 @item -f, --format=@var{fmt}
 Force the use of the block driver for format @var{fmt} instead of
 auto-detecting

qmp-commands.hx

@@ -2006,7 +2006,7 @@ EQMP
 
     {
         .name       = "block_set_io_throttle",
-        .args_type  = "device:B,bps:l,bps_rd:l,bps_wr:l,iops:l,iops_rd:l,iops_wr:l,bps_max:l?,bps_rd_max:l?,bps_wr_max:l?,iops_max:l?,iops_rd_max:l?,iops_wr_max:l?,iops_size:l?,group:s?",
+        .args_type  = "device:B,bps:l,bps_rd:l,bps_wr:l,iops:l,iops_rd:l,iops_wr:l,bps_max:l?,bps_rd_max:l?,bps_wr_max:l?,iops_max:l?,iops_rd_max:l?,iops_wr_max:l?,bps_max_length:l?,bps_rd_max_length:l?,bps_wr_max_length:l?,iops_max_length:l?,iops_rd_max_length:l?,iops_wr_max_length:l?,iops_size:l?,group:s?",
         .mhandler.cmd_new = qmp_marshal_block_set_io_throttle,
     },
 
@@ -2025,14 +2025,20 @@ Arguments:
 - "iops": total I/O operations per second (json-int)
 - "iops_rd": read I/O operations per second (json-int)
 - "iops_wr": write I/O operations per second (json-int)
-- "bps_max":  total max in bytes (json-int)
-- "bps_rd_max":  read max in bytes (json-int)
-- "bps_wr_max":  write max in bytes (json-int)
-- "iops_max":  total I/O operations max (json-int)
-- "iops_rd_max":  read I/O operations max (json-int)
-- "iops_wr_max":  write I/O operations max (json-int)
-- "iops_size":  I/O size in bytes when limiting (json-int)
-- "group": throttle group name (json-string)
+- "bps_max": total throughput limit during bursts, in bytes (json-int, optional)
+- "bps_rd_max": read throughput limit during bursts, in bytes (json-int, optional)
+- "bps_wr_max": write throughput limit during bursts, in bytes (json-int, optional)
+- "iops_max": total I/O operations per second during bursts (json-int, optional)
+- "iops_rd_max": read I/O operations per second during bursts (json-int, optional)
+- "iops_wr_max": write I/O operations per second during bursts (json-int, optional)
+- "bps_max_length": maximum length of the @bps_max burst period, in seconds (json-int, optional)
+- "bps_rd_max_length": maximum length of the @bps_rd_max burst period, in seconds (json-int, optional)
+- "bps_wr_max_length": maximum length of the @bps_wr_max burst period, in seconds (json-int, optional)
+- "iops_max_length": maximum length of the @iops_max burst period, in seconds (json-int, optional)
+- "iops_rd_max_length": maximum length of the @iops_rd_max burst period, in seconds (json-int, optional)
+- "iops_wr_max_length": maximum length of the @iops_wr_max burst period, in seconds (json-int, optional)
+- "iops_size":  I/O size in bytes when limiting (json-int, optional)
+- "group": throttle group name (json-string, optional)
 
 Example:
 
@@ -2049,6 +2055,7 @@ Example:
                                                "iops_max": 0,
                                                "iops_rd_max": 0,
                                                "iops_wr_max": 0,
+                                               "bps_max_length": 60,
                                                "iops_size": 0 } }
 <- { "return": {} }
 

tests/qemu-iotests/067

@@ -45,11 +45,20 @@ function do_run_qemu()
     echo
 }
 
+# Remove QMP events from (pretty-printed) output. Doesn't handle
+# nested dicts correctly, but we don't get any of those in this test.
+_filter_qmp_events()
+{
+    tr '\n' '\t' | sed -e \
+	's/{\s*"timestamp":\s*{[^}]*},\s*"event":[^,}]*\(,\s*"data":\s*{[^}]*}\)\?\s*}\s*//g' \
+	| tr '\t' '\n'
+}
+
 function run_qemu()
 {
     do_run_qemu "$@" 2>&1 | _filter_testdir | _filter_qmp | _filter_qemu \
                           | sed -e 's/\("actual-size":\s*\)[0-9]\+/\1SIZE/g' \
-                          | _filter_generated_node_ids
+                          | _filter_generated_node_ids | _filter_qmp_events
 }
 
 size=128M

tests/qemu-iotests/067.out

@@ -69,34 +69,6 @@ Testing: -drive file=TEST_DIR/t.qcow2,format=qcow2,if=none,id=disk -device virti
     "return": {
     }
 }
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "DEVICE_DELETED",
-    "data": {
-        "path": "/machine/peripheral/virtio0/virtio-backend"
-    }
-}
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "DEVICE_DELETED",
-    "data": {
-        "device": "virtio0",
-        "path": "/machine/peripheral/virtio0"
-    }
-}
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "RESET"
-}
 {
     "return": [
     ]
@@ -105,14 +77,6 @@ Testing: -drive file=TEST_DIR/t.qcow2,format=qcow2,if=none,id=disk -device virti
     "return": {
     }
 }
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "SHUTDOWN"
-}
-
 
 === -drive/device_add and device_del ===
 
@@ -185,34 +149,6 @@ Testing: -drive file=TEST_DIR/t.qcow2,format=qcow2,if=none,id=disk
     "return": {
     }
 }
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "DEVICE_DELETED",
-    "data": {
-        "path": "/machine/peripheral/virtio0/virtio-backend"
-    }
-}
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "DEVICE_DELETED",
-    "data": {
-        "device": "virtio0",
-        "path": "/machine/peripheral/virtio0"
-    }
-}
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "RESET"
-}
 {
     "return": [
     ]
@@ -221,14 +157,6 @@ Testing: -drive file=TEST_DIR/t.qcow2,format=qcow2,if=none,id=disk
     "return": {
     }
 }
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "SHUTDOWN"
-}
-
 
 === drive_add/device_add and device_del ===
 
@@ -304,34 +232,6 @@ Testing:
     "return": {
     }
 }
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "DEVICE_DELETED",
-    "data": {
-        "path": "/machine/peripheral/virtio0/virtio-backend"
-    }
-}
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "DEVICE_DELETED",
-    "data": {
-        "device": "virtio0",
-        "path": "/machine/peripheral/virtio0"
-    }
-}
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "RESET"
-}
 {
     "return": [
     ]
@@ -340,14 +240,6 @@ Testing:
     "return": {
     }
 }
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "SHUTDOWN"
-}
-
 
 === blockdev_add/device_add and device_del ===
 
@@ -424,34 +316,6 @@ Testing:
     "return": {
     }
 }
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "DEVICE_DELETED",
-    "data": {
-        "path": "/machine/peripheral/virtio0/virtio-backend"
-    }
-}
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "DEVICE_DELETED",
-    "data": {
-        "device": "virtio0",
-        "path": "/machine/peripheral/virtio0"
-    }
-}
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "RESET"
-}
 {
     "return": [
         {
@@ -506,12 +370,4 @@ Testing:
     "return": {
     }
 }
-{
-    "timestamp": {
-        "seconds":  TIMESTAMP,
-        "microseconds":  TIMESTAMP
-    },
-    "event": "SHUTDOWN"
-}
-
 *** done

tests/qemu-iotests/093

@@ -3,7 +3,7 @@
 # Tests for IO throttling
 #
 # Copyright (C) 2015 Red Hat, Inc.
-# Copyright (C) 2015 Igalia, S.L.
+# Copyright (C) 2015-2016 Igalia, S.L.
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -21,6 +21,8 @@
 
 import iotests
 
+nsec_per_sec = 1000000000
+
 class ThrottleTestCase(iotests.QMPTestCase):
     test_img = "null-aio://"
     max_drives = 3
@@ -42,16 +44,7 @@ class ThrottleTestCase(iotests.QMPTestCase):
     def tearDown(self):
         self.vm.shutdown()
 
-    def do_test_throttle(self, ndrives, seconds, params):
-        def check_limit(limit, num):
-            # IO throttling algorithm is discrete, allow 10% error so the test
-            # is more robust
-            return limit == 0 or \
-                   (num < seconds * limit * 1.1 / ndrives
-                   and num > seconds * limit * 0.9 / ndrives)
-
-        nsec_per_sec = 1000000000
-
+    def configure_throttle(self, ndrives, params):
         params['group'] = 'test'
 
         # Set the I/O throttling parameters to all drives
@@ -60,13 +53,21 @@ class ThrottleTestCase(iotests.QMPTestCase):
             result = self.vm.qmp("block_set_io_throttle", conv_keys=False, **params)
             self.assert_qmp(result, 'return', {})
 
+    def do_test_throttle(self, ndrives, seconds, params):
+        def check_limit(limit, num):
+            # IO throttling algorithm is discrete, allow 10% error so the test
+            # is more robust
+            return limit == 0 or \
+                   (num < seconds * limit * 1.1 / ndrives
+                   and num > seconds * limit * 0.9 / ndrives)
+
         # Set vm clock to a known value
         ns = seconds * nsec_per_sec
         self.vm.qtest("clock_step %d" % ns)
 
-        # Submit enough requests. They will drain bps_max and iops_max, but the
-        # rest requests won't get executed until we advance the virtual clock
-        # with qtest interface
+        # Submit enough requests so the throttling mechanism kicks
+        # in. The throttled requests won't be executed until we
+        # advance the virtual clock.
         rq_size = 512
         rd_nr = max(params['bps'] / rq_size / 2,
                     params['bps_rd'] / rq_size,
@@ -142,8 +143,44 @@ class ThrottleTestCase(iotests.QMPTestCase):
             for tk in params:
                 limits = dict([(k, 0) for k in params])
                 limits[tk] = params[tk] * ndrives
+                self.configure_throttle(ndrives, limits)
                 self.do_test_throttle(ndrives, 5, limits)
 
+    def test_burst(self):
+        params = {"bps": 4096,
+                  "bps_rd": 4096,
+                  "bps_wr": 4096,
+                  "iops": 10,
+                  "iops_rd": 10,
+                  "iops_wr": 10,
+                 }
+        ndrives = 1
+        # Pick each out of all possible params and test
+        for tk in params:
+            rate = params[tk] * ndrives
+            burst_rate = rate * 7
+            burst_length = 4
+
+            # Configure the throttling settings
+            settings = dict([(k, 0) for k in params])
+            settings[tk] = rate
+            settings['%s_max' % tk] = burst_rate
+            settings['%s_max_length' % tk] = burst_length
+            self.configure_throttle(ndrives, settings)
+
+            # Wait for the bucket to empty so we can do bursts
+            wait_ns = nsec_per_sec * burst_length * burst_rate / rate
+            self.vm.qtest("clock_step %d" % wait_ns)
+
+            # Test I/O at the max burst rate
+            limits = dict([(k, 0) for k in params])
+            limits[tk] = burst_rate
+            self.do_test_throttle(ndrives, burst_length, limits)
+
+            # Now test I/O at the normal rate
+            limits[tk] = rate
+            self.do_test_throttle(ndrives, 5, limits)
+
 class ThrottleTestCoroutine(ThrottleTestCase):
     test_img = "null-co://"
 

tests/qemu-iotests/093.out

-..
+....
 ----------------------------------------------------------------------
-Ran 2 tests
+Ran 4 tests
 
 OK

tests/qemu-iotests/140

 #!/bin/bash
 #
-# Test case for ejecting a BB with an NBD server attached to it
+# Test case for ejecting a BlockBackend with an NBD server attached to it
+#
+# Verify that the NBD server stops offering the drive when ejecting a
+# BlockDriverState tree from a BlockBackend (that is, a medium from a
+# drive) exposed via an NBD server.
 #
 # Copyright (C) 2016 Red Hat, Inc.
 #
@@ -49,7 +53,7 @@ _make_test_img 64k
 $QEMU_IO -c 'write -P 42 0 64k' "$TEST_IMG" | _filter_qemu_io
 
 keep_stderr=y \
-_launch_qemu -drive if=ide,media=cdrom,id=drv,file="$TEST_IMG",format=$IMGFMT \
+_launch_qemu -drive if=none,media=cdrom,id=drv,file="$TEST_IMG",format=$IMGFMT \
     2> >(_filter_nbd)
 
 _send_qemu_cmd $QEMU_HANDLE \

tests/qemu-iotests/140.out

@@ -7,7 +7,6 @@ wrote 65536/65536 bytes at offset 0
 {"return": {}}
 read 65536/65536 bytes at offset 0
 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "DEVICE_TRAY_MOVED", "data": {"device": "drv", "tray-open": true}}
 {"return": {}}
 can't open device nbd+unix:///drv?socket=TEST_DIR/nbd: No export with name 'drv' available
 no file open, try 'help open'

tests/qemu-iotests/145

+#!/bin/bash
+#
+# Test the combination of -incoming and snapshot=on
+#
+# Copyright (C) 2016 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
+
+# creator
+owner=kwolf@redhat.com
+
+seq=`basename $0`
+echo "QA output created by $seq"
+
+here=`pwd`
+tmp=/tmp/$$
+status=1	# failure is the default!
+
+_cleanup()
+{
+	_cleanup_test_img
+	true
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+. ./common.rc
+. ./common.filter
+
+_supported_fmt generic
+_supported_proto generic
+_supported_os Linux
+
+_make_test_img 1M
+echo quit | $QEMU -nographic -hda "$TEST_IMG" -incoming 'exec:true' -snapshot -serial none -monitor stdio | _filter_qemu
+
+# success, all done
+echo "*** done"
+rm -f $seq.full
+status=0

tests/qemu-iotests/145.out

+QA output created by 145
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576
+QEMU X.Y.Z monitor - type 'help' for more information
+(qemu) qququiquit
+*** done

tests/qemu-iotests/group

@@ -147,3 +147,4 @@
 142 auto
 143 auto quick
 144 rw auto quick
+145 auto quick

tests/test-throttle.c

@@ -35,6 +35,9 @@ static bool double_cmp(double x, double y)
 /* tests for single bucket operations */
 static void test_leak_bucket(void)
 {
+    throttle_config_init(&cfg);
+    bkt = cfg.buckets[THROTTLE_BPS_TOTAL];
+
     /* set initial value */
     bkt.avg = 150;
     bkt.max = 15;
@@ -57,13 +60,33 @@ static void test_leak_bucket(void)
     g_assert(bkt.avg == 150);
     g_assert(bkt.max == 15);
     g_assert(double_cmp(bkt.level, 0));
+
+    /* check that burst_level leaks correctly */
+    bkt.burst_level = 6;
+    bkt.max = 250;
+    bkt.burst_length = 2; /* otherwise burst_level will not leak */
+    throttle_leak_bucket(&bkt, NANOSECONDS_PER_SECOND / 100);
+    g_assert(double_cmp(bkt.burst_level, 3.5));
+
+    throttle_leak_bucket(&bkt, NANOSECONDS_PER_SECOND / 100);
+    g_assert(double_cmp(bkt.burst_level, 1));
+
+    throttle_leak_bucket(&bkt, NANOSECONDS_PER_SECOND / 100);
+    g_assert(double_cmp(bkt.burst_level, 0));
+
+    throttle_leak_bucket(&bkt, NANOSECONDS_PER_SECOND / 100);
+    g_assert(double_cmp(bkt.burst_level, 0));
 }
 
 static void test_compute_wait(void)
 {
+    unsigned i;
     int64_t wait;
     int64_t result;
 
+    throttle_config_init(&cfg);
+    bkt = cfg.buckets[THROTTLE_BPS_TOTAL];
+
     /* no operation limit set */
     bkt.avg = 0;
     bkt.max = 15;
@@ -93,6 +116,27 @@ static void test_compute_wait(void)
     /* time required to do half an operation */
     result = (int64_t)  NANOSECONDS_PER_SECOND / 150 / 2;
     g_assert(wait == result);
+
+    /* Perform I/O for 2.2 seconds at a rate of bkt.max */
+    bkt.burst_length = 2;
+    bkt.level = 0;
+    bkt.avg = 10;
+    bkt.max = 200;
+    for (i = 0; i < 22; i++) {
+        double units = bkt.max / 10;
+        bkt.level += units;
+        bkt.burst_level += units;
+        throttle_leak_bucket(&bkt, NANOSECONDS_PER_SECOND / 10);
+        wait = throttle_compute_wait(&bkt);
+        g_assert(double_cmp(bkt.burst_level, 0));
+        g_assert(double_cmp(bkt.level, (i + 1) * (bkt.max - bkt.avg) / 10));
+        /* We can do bursts for the 2 seconds we have configured in
+         * burst_length. We have 100 extra miliseconds of burst
+         * because bkt.level has been leaking during this time.
+         * After that, we have to wait. */
+        result = i < 21 ? 0 : 1.8 * NANOSECONDS_PER_SECOND;
+        g_assert(wait == result);
+    }
 }
 
 /* functions to test ThrottleState initialization/destroy methods */
@@ -222,6 +266,8 @@ static void set_cfg_value(bool is_max, int index, int value)
 {
     if (is_max) {
         cfg.buckets[index].max = value;
+        /* If max is set, avg should never be 0 */
+        cfg.buckets[index].avg = MAX(cfg.buckets[index].avg, 1);
     } else {
         cfg.buckets[index].avg = value;
     }
@@ -231,17 +277,17 @@ static void test_enabled(void)
 {
     int i;
 
-    memset(&cfg, 0, sizeof(cfg));
+    throttle_config_init(&cfg);
     g_assert(!throttle_enabled(&cfg));
 
     for (i = 0; i < BUCKETS_COUNT; i++) {
-        memset(&cfg, 0, sizeof(cfg));
+        throttle_config_init(&cfg);
         set_cfg_value(false, i, 150);
         g_assert(throttle_enabled(&cfg));
     }
 
     for (i = 0; i < BUCKETS_COUNT; i++) {
-        memset(&cfg, 0, sizeof(cfg));
+        throttle_config_init(&cfg);
         set_cfg_value(false, i, -150);
         g_assert(!throttle_enabled(&cfg));
     }
@@ -254,32 +300,32 @@ static void test_conflicts_for_one_set(bool is_max,
                                        int read,
                                        int write)
 {
-    memset(&cfg, 0, sizeof(cfg));
-    g_assert(!throttle_conflicting(&cfg));
+    throttle_config_init(&cfg);
+    g_assert(throttle_is_valid(&cfg, NULL));
 
     set_cfg_value(is_max, total, 1);
     set_cfg_value(is_max, read,  1);
-    g_assert(throttle_conflicting(&cfg));
+    g_assert(!throttle_is_valid(&cfg, NULL));
 
-    memset(&cfg, 0, sizeof(cfg));
+    throttle_config_init(&cfg);
     set_cfg_value(is_max, total, 1);
     set_cfg_value(is_max, write, 1);
-    g_assert(throttle_conflicting(&cfg));
+    g_assert(!throttle_is_valid(&cfg, NULL));
 
-    memset(&cfg, 0, sizeof(cfg));
+    throttle_config_init(&cfg);
     set_cfg_value(is_max, total, 1);
     set_cfg_value(is_max, read,  1);
     set_cfg_value(is_max, write, 1);
-    g_assert(throttle_conflicting(&cfg));
+    g_assert(!throttle_is_valid(&cfg, NULL));
 
-    memset(&cfg, 0, sizeof(cfg));
+    throttle_config_init(&cfg);
     set_cfg_value(is_max, total, 1);
-    g_assert(!throttle_conflicting(&cfg));
+    g_assert(throttle_is_valid(&cfg, NULL));
 
-    memset(&cfg, 0, sizeof(cfg));
+    throttle_config_init(&cfg);
     set_cfg_value(is_max, read,  1);
     set_cfg_value(is_max, write, 1);
-    g_assert(!throttle_conflicting(&cfg));
+    g_assert(throttle_is_valid(&cfg, NULL));
 }
 
 static void test_conflicting_config(void)
@@ -313,9 +359,9 @@ static void test_is_valid_for_value(int value, bool should_be_valid)
     int is_max, index;
     for (is_max = 0; is_max < 2; is_max++) {
         for (index = 0; index < BUCKETS_COUNT; index++) {
-            memset(&cfg, 0, sizeof(cfg));
+            throttle_config_init(&cfg);
             set_cfg_value(is_max, index, value);
-            g_assert(throttle_is_valid(&cfg) == should_be_valid);
+            g_assert(throttle_is_valid(&cfg, NULL) == should_be_valid);
         }
     }
 }
@@ -335,18 +381,18 @@ static void test_max_is_missing_limit(void)
     int i;
 
     for (i = 0; i < BUCKETS_COUNT; i++) {
-        memset(&cfg, 0, sizeof(cfg));
+        throttle_config_init(&cfg);
         cfg.buckets[i].max = 100;
         cfg.buckets[i].avg = 0;
-        g_assert(throttle_max_is_missing_limit(&cfg));
+        g_assert(!throttle_is_valid(&cfg, NULL));
 
         cfg.buckets[i].max = 0;
         cfg.buckets[i].avg = 0;
-        g_assert(!throttle_max_is_missing_limit(&cfg));
+        g_assert(throttle_is_valid(&cfg, NULL));
 
         cfg.buckets[i].max = 0;
         cfg.buckets[i].avg = 100;
-        g_assert(!throttle_max_is_missing_limit(&cfg));
+        g_assert(throttle_is_valid(&cfg, NULL));
     }
 }
 
@@ -550,7 +596,7 @@ static void test_groups(void)
     g_assert(bdrv1->throttle_state == bdrv3->throttle_state);
 
     /* Setting the config of a group member affects the whole group */
-    memset(&cfg1, 0, sizeof(cfg1));
+    throttle_config_init(&cfg1);
     cfg1.buckets[THROTTLE_BPS_READ].avg  = 500000;
     cfg1.buckets[THROTTLE_BPS_WRITE].avg = 285000;
     cfg1.buckets[THROTTLE_OPS_READ].avg  = 20000;

util/throttle.c

@@ -41,6 +41,14 @@ void throttle_leak_bucket(LeakyBucket *bkt, int64_t delta_ns)
 
     /* make the bucket leak */
     bkt->level = MAX(bkt->level - leak, 0);
+
+    /* if we allow bursts for more than one second we also need to
+     * keep track of bkt->burst_level so the bkt->max goal per second
+     * is attained */
+    if (bkt->burst_length > 1) {
+        leak = (bkt->max * (double) delta_ns) / NANOSECONDS_PER_SECOND;
+        bkt->burst_level = MAX(bkt->burst_level - leak, 0);
+    }
 }
 
 /* Calculate the time delta since last leak and make proportionals leaks
@@ -91,13 +99,24 @@ int64_t throttle_compute_wait(LeakyBucket *bkt)
         return 0;
     }
 
-    extra = bkt->level - bkt->max;
+    /* If the bucket is full then we have to wait */
+    extra = bkt->level - bkt->max * bkt->burst_length;
+    if (extra > 0) {
+        return throttle_do_compute_wait(bkt->avg, extra);
+    }
 
-    if (extra <= 0) {
-        return 0;
+    /* If the bucket is not full yet we have to make sure that we
+     * fulfill the goal of bkt->max units per second. */
+    if (bkt->burst_length > 1) {
+        /* We use 1/10 of the max value to smooth the throttling.
+         * See throttle_fix_bucket() for more details. */
+        extra = bkt->burst_level - bkt->max / 10;
+        if (extra > 0) {
+            return throttle_do_compute_wait(bkt->max, extra);
+        }
     }
 
-    return throttle_do_compute_wait(bkt->avg, extra);
+    return 0;
 }
 
 /* This function compute the time that must be waited while this IO
@@ -137,10 +156,10 @@ static int64_t throttle_compute_wait_for(ThrottleState *ts,
  * @next_timestamp: the resulting timer
  * @ret:        true if a timer must be set
  */
-bool throttle_compute_timer(ThrottleState *ts,
-                            bool is_write,
-                            int64_t now,
-                            int64_t *next_timestamp)
+static bool throttle_compute_timer(ThrottleState *ts,
+                                   bool is_write,
+                                   int64_t now,
+                                   int64_t *next_timestamp)
 {
     int64_t wait;
 
@@ -171,10 +190,24 @@ void throttle_timers_attach_aio_context(ThrottleTimers *tt,
                                   tt->write_timer_cb, tt->timer_opaque);
 }
 
+/*
+ * Initialize the ThrottleConfig structure to a valid state
+ * @cfg: the config to initialize
+ */
+void throttle_config_init(ThrottleConfig *cfg)
+{
+    unsigned i;
+    memset(cfg, 0, sizeof(*cfg));
+    for (i = 0; i < BUCKETS_COUNT; i++) {
+        cfg->buckets[i].burst_length = 1;
+    }
+}
+
 /* To be called first on the ThrottleState */
 void throttle_init(ThrottleState *ts)
 {
     memset(ts, 0, sizeof(ThrottleState));
+    throttle_config_init(&ts->cfg);
 }
 
 /* To be called first on the ThrottleTimers */
@@ -248,13 +281,14 @@ bool throttle_enabled(ThrottleConfig *cfg)
     return false;
 }
 
-/* return true if any two throttling parameters conflicts
- *
+/* check if a throttling configuration is valid
  * @cfg: the throttling configuration to inspect
- * @ret: true if any conflict detected else false
+ * @ret: true if valid else false
+ * @errp: error object
  */
-bool throttle_conflicting(ThrottleConfig *cfg)
+bool throttle_is_valid(ThrottleConfig *cfg, Error **errp)
 {
+    int i;
     bool bps_flag, ops_flag;
     bool bps_max_flag, ops_max_flag;
 
@@ -274,42 +308,40 @@ bool throttle_conflicting(ThrottleConfig *cfg)
                    (cfg->buckets[THROTTLE_OPS_READ].max ||
                    cfg->buckets[THROTTLE_OPS_WRITE].max);
 
-    return bps_flag || ops_flag || bps_max_flag || ops_max_flag;
-}
-
-/* check if a throttling configuration is valid
- * @cfg: the throttling configuration to inspect
- * @ret: true if valid else false
- */
-bool throttle_is_valid(ThrottleConfig *cfg)
-{
-    int i;
+    if (bps_flag || ops_flag || bps_max_flag || ops_max_flag) {
+        error_setg(errp, "bps/iops/max total values and read/write values"
+                   " cannot be used at the same time");
+        return false;
+    }
 
     for (i = 0; i < BUCKETS_COUNT; i++) {
         if (cfg->buckets[i].avg < 0 ||
             cfg->buckets[i].max < 0 ||
             cfg->buckets[i].avg > THROTTLE_VALUE_MAX ||
             cfg->buckets[i].max > THROTTLE_VALUE_MAX) {
+            error_setg(errp, "bps/iops/max values must be within [0, %lld]",
+                       THROTTLE_VALUE_MAX);
             return false;
         }
-    }
 
-    return true;
-}
+        if (!cfg->buckets[i].burst_length) {
+            error_setg(errp, "the burst length cannot be 0");
+            return false;
+        }
 
-/* check if bps_max/iops_max is used without bps/iops
- * @cfg: the throttling configuration to inspect
- */
-bool throttle_max_is_missing_limit(ThrottleConfig *cfg)
-{
-    int i;
+        if (cfg->buckets[i].burst_length > 1 && !cfg->buckets[i].max) {
+            error_setg(errp, "burst length set without burst rate");
+            return false;
+        }
 
-    for (i = 0; i < BUCKETS_COUNT; i++) {
         if (cfg->buckets[i].max && !cfg->buckets[i].avg) {
-            return true;
+            error_setg(errp, "bps_max/iops_max require corresponding"
+                       " bps/iops values");
+            return false;
         }
     }
-    return false;
+
+    return true;
 }
 
 /* fix bucket parameters */
@@ -318,7 +350,7 @@ static void throttle_fix_bucket(LeakyBucket *bkt)
     double min;
 
     /* zero bucket level */
-    bkt->level = 0;
+    bkt->level = bkt->burst_level = 0;
 
     /* The following is done to cope with the Linux CFQ block scheduler
      * which regroup reads and writes by block of 100ms in the guest.
@@ -421,22 +453,36 @@ bool throttle_schedule_timer(ThrottleState *ts,
  */
 void throttle_account(ThrottleState *ts, bool is_write, uint64_t size)
 {
+    const BucketType bucket_types_size[2][2] = {
+        { THROTTLE_BPS_TOTAL, THROTTLE_BPS_READ },
+        { THROTTLE_BPS_TOTAL, THROTTLE_BPS_WRITE }
+    };
+    const BucketType bucket_types_units[2][2] = {
+        { THROTTLE_OPS_TOTAL, THROTTLE_OPS_READ },
+        { THROTTLE_OPS_TOTAL, THROTTLE_OPS_WRITE }
+    };
     double units = 1.0;
+    unsigned i;
 
     /* if cfg.op_size is defined and smaller than size we compute unit count */
     if (ts->cfg.op_size && size > ts->cfg.op_size) {
         units = (double) size / ts->cfg.op_size;
     }
 
-    ts->cfg.buckets[THROTTLE_BPS_TOTAL].level += size;
-    ts->cfg.buckets[THROTTLE_OPS_TOTAL].level += units;
+    for (i = 0; i < 2; i++) {
+        LeakyBucket *bkt;
 
-    if (is_write) {
-        ts->cfg.buckets[THROTTLE_BPS_WRITE].level += size;
-        ts->cfg.buckets[THROTTLE_OPS_WRITE].level += units;
-    } else {
-        ts->cfg.buckets[THROTTLE_BPS_READ].level += size;
-        ts->cfg.buckets[THROTTLE_OPS_READ].level += units;
+        bkt = &ts->cfg.buckets[bucket_types_size[is_write][i]];
+        bkt->level += size;
+        if (bkt->burst_length > 1) {
+            bkt->burst_level += size;
+        }
+
+        bkt = &ts->cfg.buckets[bucket_types_units[is_write][i]];
+        bkt->level += units;
+        if (bkt->burst_length > 1) {
+            bkt->burst_level += units;
+        }
     }
 }