ceph/rbd block driver for qemu-kvm

RBD is an block driver for the distributed file system Ceph
(http://ceph.newdream.net/). This driver uses librados (which is part
of the Ceph server) for direct access to the Ceph object store and is
running entirely in userspace (Yehuda also wrote a driver for the
linux kernel, that can be used to access rbd volumes as a block
device).

Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
Signed-off-by: Christian Brunner <chb@muc.de>
Reviewed-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

Makefile.objs

@@ -24,6 +24,7 @@ block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o
 block-nested-$(CONFIG_WIN32) += raw-win32.o
 block-nested-$(CONFIG_POSIX) += raw-posix.o
 block-nested-$(CONFIG_CURL) += curl.o
+block-nested-$(CONFIG_RBD) += rbd.o
 
 block-obj-y +=  $(addprefix block/, $(block-nested-y))
 

block/rbd_types.h

@@ -0,0 +1,71 @@
+/*
+ * Ceph - scalable distributed file system
+ *
+ * Copyright (C) 2004-2010 Sage Weil <sage@newdream.net>
+ *
+ * This is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License version 2.1, as published by the Free Software
+ * Foundation.  See file COPYING.LIB.
+ *
+ */
+
+#ifndef CEPH_RBD_TYPES_H
+#define CEPH_RBD_TYPES_H
+
+
+/*
+ * rbd image 'foo' consists of objects
+ *   foo.rbd      - image metadata
+ *   foo.00000000
+ *   foo.00000001
+ *   ...          - data
+ */
+
+#define RBD_SUFFIX              ".rbd"
+#define RBD_DIRECTORY           "rbd_directory"
+#define RBD_INFO                "rbd_info"
+
+#define RBD_DEFAULT_OBJ_ORDER   22   /* 4MB */
+
+#define RBD_MAX_OBJ_NAME_SIZE   96
+#define RBD_MAX_BLOCK_NAME_SIZE 24
+#define RBD_MAX_SEG_NAME_SIZE   128
+
+#define RBD_COMP_NONE           0
+#define RBD_CRYPT_NONE          0
+
+#define RBD_HEADER_TEXT         "<<< Rados Block Device Image >>>\n"
+#define RBD_HEADER_SIGNATURE    "RBD"
+#define RBD_HEADER_VERSION      "001.005"
+
+struct rbd_info {
+    uint64_t max_id;
+} __attribute__ ((packed));
+
+struct rbd_obj_snap_ondisk {
+    uint64_t id;
+    uint64_t image_size;
+} __attribute__((packed));
+
+struct rbd_obj_header_ondisk {
+    char text[40];
+    char block_name[RBD_MAX_BLOCK_NAME_SIZE];
+    char signature[4];
+    char version[8];
+    struct {
+        uint8_t order;
+        uint8_t crypt_type;
+        uint8_t comp_type;
+        uint8_t unused;
+    } __attribute__((packed)) options;
+    uint64_t image_size;
+    uint64_t snap_seq;
+    uint32_t snap_count;
+    uint32_t reserved;
+    uint64_t snap_names_len;
+    struct rbd_obj_snap_ondisk snaps[0];
+} __attribute__((packed));
+
+
+#endif

configure

@@ -332,6 +332,7 @@ zero_malloc=""
 trace_backend="nop"
 trace_file="trace"
 spice=""
+rbd=""
 
 # OS specific
 if check_define __linux__ ; then
@@ -741,6 +742,10 @@ for opt do
   ;;
   --*dir)
   ;;
+  --disable-rbd) rbd="no"
+  ;;
+  --enable-rbd) rbd="yes"
+  ;;
   *) echo "ERROR: unknown option $opt"; show_help="yes"
   ;;
   esac
@@ -934,6 +939,7 @@ echo "  --trace-file=NAME        Full PATH,NAME of file to store traces"
 echo "                           Default:trace-<pid>"
 echo "  --disable-spice          disable spice"
 echo "  --enable-spice           enable spice"
+echo "  --enable-rbd             enable building the rados block device (rbd)"
 echo ""
 echo "NOTE: The object files are built at the place where configure is launched"
 exit 1
@@ -1745,6 +1751,48 @@ if test "$mingw32" != yes -a "$pthread" = no; then
   exit 1
 fi
 
+##########################################
+# rbd probe
+if test "$rbd" != "no" ; then
+  cat > $TMPC <<EOF
+#include <stdio.h>
+#include <rados/librados.h>
+int main(void) { rados_initialize(0, NULL); return 0; }
+EOF
+  rbd_libs="-lrados -lcrypto"
+  if compile_prog "" "$rbd_libs" ; then
+    librados_too_old=no
+    cat > $TMPC <<EOF
+#include <stdio.h>
+#include <rados/librados.h>
+#ifndef CEPH_OSD_TMAP_SET
+#error missing CEPH_OSD_TMAP_SET
+#endif
+int main(void) {
+    int (*func)(const rados_pool_t pool, uint64_t *snapid) = rados_selfmanaged_snap_create;
+    rados_initialize(0, NULL);
+    return 0;
+}
+EOF
+    if compile_prog "" "$rbd_libs" ; then
+      rbd=yes
+      libs_tools="$rbd_libs $libs_tools"
+      libs_softmmu="$rbd_libs $libs_softmmu"
+    else
+      rbd=no
+      librados_too_old=yes
+    fi
+  else
+    if test "$rbd" = "yes" ; then
+      feature_not_found "rados block device"
+    fi
+    rbd=no
+  fi
+  if test "$librados_too_old" = "yes" ; then
+    echo "-> Your librados version is too old - upgrade needed to have rbd support"
+  fi
+fi
+
 ##########################################
 # linux-aio probe
 
@@ -2354,6 +2402,7 @@ echo "vhost-net support $vhost_net"
 echo "Trace backend     $trace_backend"
 echo "Trace output file $trace_file-<pid>"
 echo "spice support     $spice"
+echo "rbd support       $rbd"
 
 if test $sdl_too_old = "yes"; then
 echo "-> Your SDL version is too old - please upgrade to have SDL support"
@@ -2627,6 +2676,9 @@ echo "CONFIG_UNAME_RELEASE=\"$uname_release\"" >> $config_host_mak
 if test "$zero_malloc" = "yes" ; then
   echo "CONFIG_ZERO_MALLOC=y" >> $config_host_mak
 fi
+if test "$rbd" = "yes" ; then
+  echo "CONFIG_RBD=y" >> $config_host_mak
+fi
 
 # USB host support
 case "$usb" in