summaryrefslogtreecommitdiffstats
path: root/xlators/mgmt/glusterd/src/glusterd-utils.c
diff options
context:
space:
mode:
authorM. Mohan Kumar <mohan@in.ibm.com>2013-11-13 22:44:42 +0530
committerAnand Avati <avati@redhat.com>2013-11-13 11:38:42 -0800
commit48c40e1a42efe1b59126406084821947d139dd0e (patch)
tree74959ecda9b9bd56c85e0e32991c11c06b022296 /xlators/mgmt/glusterd/src/glusterd-utils.c
parent15a8ecd9b3eedf80881bd3dba81f16b7d2cb7c97 (diff)
bd: posix/multi-brick support to BD xlator
Current BD xlator (block backend) has a few limitations such as * Creation of directories not supported * Supports only single brick * Does not use extended attributes (and client gfid) like posix xlator * Creation of special files (symbolic links, device nodes etc) not supported Basic limitation of not allowing directory creation is blocking oVirt/VDSM to consume BD xlator as part of Gluster domain since VDSM creates multi-level directories when GlusterFS is used as storage backend for storing VM images. To overcome these limitations a new BD xlator with following improvements is suggested. * New hybrid BD xlator that handles both regular files and block device files * The volume will have both POSIX and BD bricks. Regular files are created on POSIX bricks, block devices are created on the BD brick (VG) * BD xlator leverages exiting POSIX xlator for most POSIX calls and hence sits above the POSIX xlator * Block device file is differentiated from regular file by an extended attribute * The xattr 'user.glusterfs.bd' (BD_XATTR) plays a role in mapping a posix file to Logical Volume (LV). * When a client sends a request to set BD_XATTR on a posix file, a new LV is created and mapped to posix file. So every block device will have a representative file in POSIX brick with 'user.glusterfs.bd' (BD_XATTR) set. * Here after all operations on this file results in LV related operations. For example opening a file that has BD_XATTR set results in opening the LV block device, reading results in reading the corresponding LV block device. When BD xlator gets request to set BD_XATTR via setxattr call, it creates a LV and information about this LV is placed in the xattr of the posix file. xattr "user.glusterfs.bd" used to identify that posix file is mapped to BD. Usage: Server side: [root@host1 ~]# gluster volume create bdvol host1:/storage/vg1_info?vg1 host2:/storage/vg2_info?vg2 It creates a distributed gluster volume 'bdvol' with Volume Group vg1 using posix brick /storage/vg1_info in host1 and Volume Group vg2 using /storage/vg2_info in host2. [root@host1 ~]# gluster volume start bdvol Client side: [root@node ~]# mount -t glusterfs host1:/bdvol /media [root@node ~]# touch /media/posix It creates regular posix file 'posix' in either host1:/vg1 or host2:/vg2 brick [root@node ~]# mkdir /media/image [root@node ~]# touch /media/image/lv1 It also creates regular posix file 'lv1' in either host1:/vg1 or host2:/vg2 brick [root@node ~]# setfattr -n "user.glusterfs.bd" -v "lv" /media/image/lv1 [root@node ~]# Above setxattr results in creating a new LV in corresponding brick's VG and it sets 'user.glusterfs.bd' with value 'lv:<default-extent-size' [root@node ~]# truncate -s5G /media/image/lv1 It results in resizig LV 'lv1'to 5G New BD xlator code is placed in xlators/storage/bd directory. Also add volume-uuid to the VG so that same VG can't be used for other bricks/volumes. After deleting a gluster volume, one has to manually remove the associated tag using vgchange <vg-name> --deltag <trusted.glusterfs.volume-id:<volume-id>> Changes from previous version V5: * Removed support for delayed deleting of LVs Changes from previous version V4: * Consolidated the patches * Removed usage of BD_XATTR_SIZE and consolidated it in BD_XATTR. Changes from previous version V3: * Added support in FUSE to support full/linked clone * Added support to merge snapshots and provide information about origin * bd_map xlator removed * iatt structure used in inode_ctx. iatt is cached and updated during fsync/flush * aio support * Type and capabilities of volume are exported through getxattr Changes from version 2: * Used inode_context for caching BD size and to check if loc/fd is BD or not. * Added GlusterFS server offloaded copy and snapshot through setfattr FOP. As part of this libgfapi is modified. * BD xlator supports stripe * During unlinking if a LV file is already opened, its added to delete list and bd_del_thread tries to delete from this list when a last reference to that file is closed. Changes from previous version: * gfid is used as name of LV * ? is used to specify VG name for creating BD volume in volume create, add-brick. gluster volume create volname host:/path?vg * open-behind issue is fixed * A replicate brick can be added dynamically and LVs from source brick are replicated to destination brick * A distribute brick can be added dynamically and rebalance operation distributes existing LVs/files to the new brick * Thin provisioning support added. * bd_map xlator support retained * setfattr -n user.glusterfs.bd -v "lv" creates a regular LV and setfattr -n user.glusterfs.bd -v "thin" creates thin LV * Capability and backend information added to gluster volume info (and --xml) so that management tools can exploit BD xlator. * tracing support for bd xlator added TODO: * Add support to display snapshots for a given LV * Display posix filename for list-origin instead of gfid Change-Id: I00d32dfbab3b7c806e0841515c86c3aa519332f2 BUG: 1028672 Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Reviewed-on: http://review.gluster.org/4809 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
Diffstat (limited to 'xlators/mgmt/glusterd/src/glusterd-utils.c')
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-utils.c81
1 files changed, 81 insertions, 0 deletions
diff --git a/xlators/mgmt/glusterd/src/glusterd-utils.c b/xlators/mgmt/glusterd/src/glusterd-utils.c
index d4f33f2ce..f0445cf0b 100644
--- a/xlators/mgmt/glusterd/src/glusterd-utils.c
+++ b/xlators/mgmt/glusterd/src/glusterd-utils.c
@@ -49,6 +49,11 @@
#include <unistd.h>
#include <fnmatch.h>
#include <sys/statvfs.h>
+#include <ifaddrs.h>
+#ifdef HAVE_BD_XLATOR
+#include <lvm2app.h>
+#endif
+
#ifdef GF_LINUX_HOST_OS
#include <mntent.h>
@@ -622,6 +627,7 @@ glusterd_brickinfo_new_from_brick (char *brick,
char *path = NULL;
char *tmp_host = NULL;
char *tmp_path = NULL;
+ char *vg = NULL;
GF_ASSERT (brick);
GF_ASSERT (brickinfo);
@@ -640,6 +646,17 @@ glusterd_brickinfo_new_from_brick (char *brick,
if (ret)
goto out;
+#ifdef HAVE_BD_XLATOR
+ vg = strchr (path, '?');
+ /* ? is used as a delimiter for vg */
+ if (vg) {
+ strncpy (new_brickinfo->vg, vg + 1, PATH_MAX - 1);
+ *vg = '\0';
+ }
+ new_brickinfo->caps = CAPS_BD;
+#else
+ vg = NULL; /* Avoid compiler warnings when BD not enabled */
+#endif
ret = gf_canonicalize_path (path);
if (ret)
goto out;
@@ -743,6 +760,62 @@ out:
return available;
}
+#ifdef HAVE_BD_XLATOR
+/*
+ * Sets the tag of the format "trusted.glusterfs.volume-id:<uuid>" in
+ * the brick VG. It is used to avoid using same VG for another brick.
+ * @volume-id - gfid, @brick - brick info, @msg - Error message returned
+ * to the caller
+ */
+int
+glusterd_bd_set_vg_tag (unsigned char *volume_id, glusterd_brickinfo_t *brick,
+ char *msg, int msg_size)
+{
+ lvm_t handle = NULL;
+ vg_t vg = NULL;
+ char *uuid = NULL;
+ int ret = -1;
+
+ gf_asprintf (&uuid, "%s:%s", GF_XATTR_VOL_ID_KEY,
+ uuid_utoa (volume_id));
+ if (!uuid) {
+ snprintf (msg, sizeof(*msg), "Could not allocate memory "
+ "for tag");
+ return -1;
+ }
+
+ handle = lvm_init (NULL);
+ if (!handle) {
+ snprintf (msg, sizeof(*msg), "lvm_init failed");
+ goto out;
+ }
+
+ vg = lvm_vg_open (handle, brick->vg, "w", 0);
+ if (!vg) {
+ snprintf (msg, sizeof(*msg), "Could not open VG %s",
+ brick->vg);
+ goto out;
+ }
+
+ if (lvm_vg_add_tag (vg, uuid) < 0) {
+ snprintf (msg, sizeof(*msg), "Could not set tag %s for "
+ "VG %s", uuid, brick->vg);
+ goto out;
+ }
+ lvm_vg_write (vg);
+ ret = 0;
+out:
+ GF_FREE (uuid);
+
+ if (vg)
+ lvm_vg_close (vg);
+ if (handle)
+ lvm_quit (handle);
+
+ return ret;
+}
+#endif
+
int
glusterd_validate_and_create_brickpath (glusterd_brickinfo_t *brickinfo,
uuid_t volume_id, char **op_errstr,
@@ -825,6 +898,14 @@ glusterd_validate_and_create_brickpath (glusterd_brickinfo_t *brickinfo,
}
}
+#ifdef HAVE_BD_XLATOR
+ if (brickinfo->vg[0]) {
+ ret = glusterd_bd_set_vg_tag (volume_id, brickinfo, msg,
+ sizeof(msg));
+ if (ret)
+ goto out;
+ }
+#endif
ret = glusterd_check_and_set_brick_xattr (brickinfo->hostname,
brickinfo->path, volume_id,
op_errstr, is_force);