Block pull request

-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQEcBAABAgAGBQJTENUMAAoJEJykq7OBq3PIXoQH/R7Q9CqASrBEfbT1GJDSr3E5
 yq0ZZ4nJBhhn0f8tOw9NWGCmTH1UZn0u4PbYEj4jTGJyWY2POkCKLPRvurge4c+Q
 L+OwzspW14O35o7WuBC8uWvSxh8ExaiwwrutCsIsz68UAcnoiwyTMSKghIy9+Osk
 lJKRFz6IFbgxCocqeNQrilj84vYSv9VzXZY8/nIhDMFsbjaKW7sKwu4jnXB7+v5J
 cA0+voafINNICNMeXzkqBbKwWIFtYOkPe287MZQNbpS2vCS2bsZeivDxsBJ26Cmx
 Xho8Xz5utvBMBrNtidHCTsd2jrj0VBdGgksYoHPyIwK/gBr1EVTGKpebraKXBEU=
 =rgw9
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/stefanha/tags/block-pull-request' into staging

Block pull request

# gpg: Signature made Fri 28 Feb 2014 18:27:24 GMT using RSA key ID 81AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>"
# gpg:                 aka "Stefan Hajnoczi <stefanha@gmail.com>"
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 8695 A8BF D3F9 7CDA AC35  775A 9CA4 ABB3 81AB 73C8

* remotes/stefanha/tags/block-pull-request:
  block/vmdk: do not report file offset for compressed extents
  discard rbd error output when not relevant in qemu-iotests
  block: use /var/tmp instead of /tmp for -snapshot
  qemu-io-test: Disable Quorum test when not compiled in.
  qmp: Make Quorum error events more palatable.
  qmp: Fix BlockdevOptionQuorum.
  block: gluster - add reopen support.
  block: gluster - code movements, state storage changes
  qemu-iotests: add more tests to the "quick" group

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

block.c

@@ -547,8 +547,9 @@ int get_tmp_filename(char *filename, int size)
     int fd;
     const char *tmpdir;
     tmpdir = getenv("TMPDIR");
-    if (!tmpdir)
+    if (!tmpdir) {
-        tmpdir = "/tmp";
+        tmpdir = "/var/tmp";
+    }
     if (snprintf(filename, size, "%s/vl.XXXXXX", tmpdir) >= size) {
         return -EOVERFLOW;
     }

block/gluster.c

@@ -45,11 +45,13 @@ typedef struct GlusterConf {
 
 static void qemu_gluster_gconf_free(GlusterConf *gconf)
 {
-    g_free(gconf->server);
+    if (gconf) {
-    g_free(gconf->volname);
+        g_free(gconf->server);
-    g_free(gconf->image);
+        g_free(gconf->volname);
-    g_free(gconf->transport);
+        g_free(gconf->image);
-    g_free(gconf);
+        g_free(gconf->transport);
+        g_free(gconf);
+    }
 }
 
 static int parse_volume_options(GlusterConf *gconf, char *path)
@@ -272,11 +274,28 @@ static QemuOptsList runtime_opts = {
     },
 };
 
+static void qemu_gluster_parse_flags(int bdrv_flags, int *open_flags)
+{
+    assert(open_flags != NULL);
+
+    *open_flags |= O_BINARY;
+
+    if (bdrv_flags & BDRV_O_RDWR) {
+        *open_flags |= O_RDWR;
+    } else {
+        *open_flags |= O_RDONLY;
+    }
+
+    if ((bdrv_flags & BDRV_O_NOCACHE)) {
+        *open_flags |= O_DIRECT;
+    }
+}
+
 static int qemu_gluster_open(BlockDriverState *bs,  QDict *options,
                              int bdrv_flags, Error **errp)
 {
     BDRVGlusterState *s = bs->opaque;
-    int open_flags = O_BINARY;
+    int open_flags = 0;
     int ret = 0;
     GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
     QemuOpts *opts;
@@ -299,15 +318,7 @@ static int qemu_gluster_open(BlockDriverState *bs,  QDict *options,
         goto out;
     }
 
-    if (bdrv_flags & BDRV_O_RDWR) {
+    qemu_gluster_parse_flags(bdrv_flags, &open_flags);
-        open_flags |= O_RDWR;
-    } else {
-        open_flags |= O_RDONLY;
-    }
-
-    if ((bdrv_flags & BDRV_O_NOCACHE)) {
-        open_flags |= O_DIRECT;
-    }
 
     s->fd = glfs_open(s->glfs, gconf->image, open_flags);
     if (!s->fd) {
@@ -329,6 +340,96 @@ out:
     return ret;
 }
 
+typedef struct BDRVGlusterReopenState {
+    struct glfs *glfs;
+    struct glfs_fd *fd;
+} BDRVGlusterReopenState;
+
+
+static int qemu_gluster_reopen_prepare(BDRVReopenState *state,
+                                       BlockReopenQueue *queue, Error **errp)
+{
+    int ret = 0;
+    BDRVGlusterReopenState *reop_s;
+    GlusterConf *gconf = NULL;
+    int open_flags = 0;
+
+    assert(state != NULL);
+    assert(state->bs != NULL);
+
+    state->opaque = g_malloc0(sizeof(BDRVGlusterReopenState));
+    reop_s = state->opaque;
+
+    qemu_gluster_parse_flags(state->flags, &open_flags);
+
+    gconf = g_malloc0(sizeof(GlusterConf));
+
+    reop_s->glfs = qemu_gluster_init(gconf, state->bs->filename);
+    if (reop_s->glfs == NULL) {
+        ret = -errno;
+        goto exit;
+    }
+
+    reop_s->fd = glfs_open(reop_s->glfs, gconf->image, open_flags);
+    if (reop_s->fd == NULL) {
+        /* reops->glfs will be cleaned up in _abort */
+        ret = -errno;
+        goto exit;
+    }
+
+exit:
+    /* state->opaque will be freed in either the _abort or _commit */
+    qemu_gluster_gconf_free(gconf);
+    return ret;
+}
+
+static void qemu_gluster_reopen_commit(BDRVReopenState *state)
+{
+    BDRVGlusterReopenState *reop_s = state->opaque;
+    BDRVGlusterState *s = state->bs->opaque;
+
+
+    /* close the old */
+    if (s->fd) {
+        glfs_close(s->fd);
+    }
+    if (s->glfs) {
+        glfs_fini(s->glfs);
+    }
+
+    /* use the newly opened image / connection */
+    s->fd         = reop_s->fd;
+    s->glfs       = reop_s->glfs;
+
+    g_free(state->opaque);
+    state->opaque = NULL;
+
+    return;
+}
+
+
+static void qemu_gluster_reopen_abort(BDRVReopenState *state)
+{
+    BDRVGlusterReopenState *reop_s = state->opaque;
+
+    if (reop_s == NULL) {
+        return;
+    }
+
+    if (reop_s->fd) {
+        glfs_close(reop_s->fd);
+    }
+
+    if (reop_s->glfs) {
+        glfs_fini(reop_s->glfs);
+    }
+
+    g_free(state->opaque);
+    state->opaque = NULL;
+
+    return;
+}
+
 #ifdef CONFIG_GLUSTERFS_ZEROFILL
 static coroutine_fn int qemu_gluster_co_write_zeroes(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
@@ -619,6 +720,9 @@ static BlockDriver bdrv_gluster = {
     .instance_size                = sizeof(BDRVGlusterState),
     .bdrv_needs_filename          = true,
     .bdrv_file_open               = qemu_gluster_open,
+    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
+    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
+    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
     .bdrv_close                   = qemu_gluster_close,
     .bdrv_create                  = qemu_gluster_create,
     .bdrv_getlength               = qemu_gluster_getlength,
@@ -643,6 +747,9 @@ static BlockDriver bdrv_gluster_tcp = {
     .instance_size                = sizeof(BDRVGlusterState),
     .bdrv_needs_filename          = true,
     .bdrv_file_open               = qemu_gluster_open,
+    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
+    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
+    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
     .bdrv_close                   = qemu_gluster_close,
     .bdrv_create                  = qemu_gluster_create,
     .bdrv_getlength               = qemu_gluster_getlength,
@@ -667,6 +774,9 @@ static BlockDriver bdrv_gluster_unix = {
     .instance_size                = sizeof(BDRVGlusterState),
     .bdrv_needs_filename          = true,
     .bdrv_file_open               = qemu_gluster_open,
+    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
+    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
+    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
     .bdrv_close                   = qemu_gluster_close,
     .bdrv_create                  = qemu_gluster_create,
     .bdrv_getlength               = qemu_gluster_getlength,
@@ -691,6 +801,9 @@ static BlockDriver bdrv_gluster_rdma = {
     .instance_size                = sizeof(BDRVGlusterState),
     .bdrv_needs_filename          = true,
     .bdrv_file_open               = qemu_gluster_open,
+    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
+    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
+    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
     .bdrv_close                   = qemu_gluster_close,
     .bdrv_create                  = qemu_gluster_create,
     .bdrv_getlength               = qemu_gluster_getlength,

block/quorum.c

@@ -200,11 +200,14 @@ static void quorum_report_bad(QuorumAIOCB *acb, char *node_name, int ret)
 {
     QObject *data;
     assert(node_name);
-    data = qobject_from_jsonf("{ 'ret': %d"
+    data = qobject_from_jsonf("{ 'node-name': %s"
-                              ", 'node-name': %s"
                               ", 'sector-num': %" PRId64
                               ", 'sectors-count': %d }",
-                              ret, node_name, acb->sector_num, acb->nb_sectors);
+                              node_name, acb->sector_num, acb->nb_sectors);
+    if (ret < 0) {
+        QDict *dict = qobject_to_qdict(data);
+        qdict_put(dict, "error", qstring_from_str(strerror(-ret)));
+    }
     monitor_protocol_event(QEVENT_QUORUM_REPORT_BAD, data);
     qobject_decref(data);
 }

block/vmdk.c

@@ -1184,7 +1184,7 @@ static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs,
         break;
     case VMDK_OK:
         ret = BDRV_BLOCK_DATA;
-        if (extent->file == bs->file) {
+        if (extent->file == bs->file && !extent->compressed) {
             ret |= BDRV_BLOCK_OFFSET_VALID | offset;
         }
 

docs/qmp/qmp-events.txt

@@ -225,6 +225,45 @@ Data:
   "timestamp": { "seconds": 1368697518, "microseconds": 326866 } }
 }
 
+QUORUM_FAILURE
+--------------
+
+Emitted by the Quorum block driver if it fails to establish a quorum.
+
+Data:
+
+- "reference":    device name if defined else node name.
+- "sector-num":   Number of the first sector of the failed read operation.
+- "sector-count": Failed read operation sector count.
+
+Example:
+
+{ "event": "QUORUM_FAILURE",
+     "data": { "reference": "usr1", "sector-num": 345435, "sector-count": 5 },
+     "timestamp": { "seconds": 1344522075, "microseconds": 745528 } }
+
+QUORUM_REPORT_BAD
+-----------------
+
+Emitted to report a corruption of a Quorum file.
+
+Data:
+
+- "error":        Error message (json-string, optional)
+                  Only present on failure.  This field contains a human-readable
+                  error message.  There are no semantics other than that the
+                  block layer reported an error and clients should not try to
+                  interpret the error string.
+- "node-name":    The graph node name of the block driver state.
+- "sector-num":   Number of the first sector of the failed read operation.
+- "sector-count": Failed read operation sector count.
+
+Example:
+
+{ "event": "QUORUM_REPORT_BAD",
+     "data": { "node-name": "1.raw", "sector-num": 345435, "sector-count": 5 },
+     "timestamp": { "seconds": 1344522075, "microseconds": 745528 } }
+
 RESET
 -----
 
@@ -500,39 +539,3 @@ Example:
 
 Note: If action is "reset", "shutdown", or "pause" the WATCHDOG event is
 followed respectively by the RESET, SHUTDOWN, or STOP events.
-
-QUORUM_FAILURE
---------------
-
-Emitted by the Quorum block driver if it fails to establish a quorum.
-
-Data:
-
-- "reference":    device name if defined else node name.
-- "sector-num":   Number of the first sector of the failed read operation.
-- "sector-count": Failed read operation sector count.
-
-Example:
-
-{ "event": "QUORUM_FAILURE",
-     "data": { "reference": "usr1", "sector-num": 345435, "sector-count": 5 },
-     "timestamp": { "seconds": 1344522075, "microseconds": 745528 } }
-
-QUORUM_REPORT_BAD
------------------
-
-Emitted to report a corruption of a Quorum file.
-
-Data:
-
-- "ret":          The IO return code.
-- "node-name":    The graph node name of the block driver state.
-- "sector-num":   Number of the first sector of the failed read operation.
-- "sector-count": Failed read operation sector count.
-
-Example:
-
-{ "event": "QUORUM_REPORT_BAD",
-     "data": { "ret": 0, "node-name": "1.raw", "sector-num": 345435,
-               "sector-count": 5 },
-     "timestamp": { "seconds": 1344522075, "microseconds": 745528 } }

qapi-schema.json

@@ -4436,10 +4436,11 @@
 # Driver specific block device options for Quorum
 #
 # @blkverify:      #optional true if the driver must print content mismatch
+#                  set to false by default
 #
-# @children:       the children block device to use
+# @children:       the children block devices to use
 #
-# @vote_threshold: the vote limit under which a read will fail
+# @vote-threshold: the vote limit under which a read will fail
 #
 # Since: 2.0
 ##

tests/qemu-iotests-quick.sh

@@ -8,6 +8,7 @@ export QEMU_PROG="this_should_be_unused"
 
 export QEMU_IMG_PROG="$(pwd)/qemu-img"
 export QEMU_IO_PROG="$(pwd)/qemu-io"
+export QEMU_NBD_PROG="$(pwd)/qemu-nbd"
 
 cd $SRC_PATH/tests/qemu-iotests
 

tests/qemu-iotests/081

@@ -56,6 +56,9 @@ function run_qemu()
     do_run_qemu "$@" 2>&1 | _filter_testdir | _filter_qmp | _filter_qemu_io
 }
 
+test_quorum=$($QEMU_IMG --help|grep quorum)
+[ "$test_quorum" = "" ] && _supported_fmt quorum
+
 quorum="file.driver=quorum,file.children.0.file.filename=$TEST_DIR/1.raw"
 quorum="$quorum,file.children.1.file.filename=$TEST_DIR/2.raw"
 quorum="$quorum,file.children.2.file.filename=$TEST_DIR/3.raw,file.vote-threshold=2"

tests/qemu-iotests/081.out

@@ -30,7 +30,7 @@ Testing: -drive file=TEST_DIR/2.IMGFMT,format=IMGFMT,if=none,id=drive2
 QMP_VERSION
 {"return": {}}
 {"return": {}}
-{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "QUORUM_REPORT_BAD", "data": {"node-name": "", "ret": 0, "sectors-count": 20480, "sector-num": 0}}
+{"timestamp": {"seconds":  TIMESTAMP, "microseconds":  TIMESTAMP}, "event": "QUORUM_REPORT_BAD", "data": {"node-name": "", "sectors-count": 20480, "sector-num": 0}}
 read 10485760/10485760 bytes at offset 0
 10 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 {"return": ""}

tests/qemu-iotests/common.rc

@@ -203,7 +203,7 @@ _cleanup_test_img()
             ;;
 
         rbd)
-            rbd rm "$TEST_DIR/t.$IMGFMT" > /dev/null
+            rbd --no-progress rm "$TEST_DIR/t.$IMGFMT" > /dev/null
             ;;
 
         sheepdog)

tests/qemu-iotests/group

@@ -58,30 +58,30 @@
 049 rw auto
 050 rw auto backing quick
 051 rw auto
-052 rw auto backing
+052 rw auto backing quick
-053 rw auto
+053 rw auto quick
-054 rw auto
+054 rw auto quick
 055 rw auto
 056 rw auto backing
 057 rw auto
-058 rw auto
+058 rw auto quick
-059 rw auto
+059 rw auto quick
-060 rw auto
+060 rw auto quick
-061 rw auto
+061 rw auto quick
-062 rw auto
+062 rw auto quick
-063 rw auto
+063 rw auto quick
-064 rw auto
+064 rw auto quick
 065 rw auto
-066 rw auto
+066 rw auto quick
 067 rw auto
 068 rw auto
-069 rw auto
+069 rw auto quick
-070 rw auto
+070 rw auto quick
 071 rw auto
-072 rw auto
+072 rw auto quick
-073 rw auto
+073 rw auto quick
-074 rw auto
+074 rw auto quick
-077 rw auto
+077 rw auto quick
 079 rw auto
 081 rw auto
 082 rw auto quick