From 48c40e1a42efe1b59126406084821947d139dd0e Mon Sep 17 00:00:00 2001 From: "M. Mohan Kumar" Date: Wed, 13 Nov 2013 22:44:42 +0530 Subject: 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: --deltag > 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 Reviewed-on: http://review.gluster.org/4809 Tested-by: Gluster Build System Reviewed-by: Anand Avati --- configure.ac | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'configure.ac') diff --git a/configure.ac b/configure.ac index 9d676cd15..0cecafb46 100644 --- a/configure.ac +++ b/configure.ac @@ -53,6 +53,8 @@ AC_CONFIG_FILES([Makefile xlators/storage/Makefile xlators/storage/posix/Makefile xlators/storage/posix/src/Makefile + xlators/storage/bd/Makefile + xlators/storage/bd/src/Makefile xlators/cluster/Makefile xlators/cluster/afr/Makefile xlators/cluster/afr/src/Makefile @@ -301,6 +303,43 @@ if test "x$enable_fuse_client" != "xno"; then BUILD_FUSE_CLIENT="yes" fi +AC_ARG_ENABLE([bd-xlator], + AC_HELP_STRING([--enable-bd-xlator], [Build BD xlator])) + +if test "x$enable_bd_xlator" != "xno"; then + AC_CHECK_LIB([lvm2app], + [lvm_init,lvm_lv_from_name], + [HAVE_BD_LIB="yes"], + [HAVE_BD_LIB="no"]) + +if test "x$HAVE_BD_LIB" = "xyes"; then + # lvm_lv_from_name() has been made public with lvm2-2.02.79 + AC_CHECK_DECLS( + [lvm_lv_from_name], + [NEED_LVM_LV_FROM_NAME_DECL="no"], + [NEED_LVM_LV_FROM_NAME_DECL="yes"], + [[#include ]]) + fi +fi + +if test "x$enable_bd_xlator" = "xyes" -a "x$HAVE_BD_LIB" = "xno"; then + echo "BD xlator requested but required lvm2 development library not found." + exit 1 +fi + +BUILD_BD_XLATOR=no +if test "x${enable-bd-xlator}" != "xno" -a "x${HAVE_BD_LIB}" = "xyes"; then + BUILD_BD_XLATOR=yes + AC_DEFINE(HAVE_BD_XLATOR, 1, [define if lvm2app library found and bd xlator + enabled]) + if test "x$NEED_LVM_LV_FROM_NAME_DECL" = "xyes"; then + AC_DEFINE(NEED_LVM_LV_FROM_NAME_DECL, 1, [defined if lvm_lv_from_name() + was not found in the lvm2app.h header, but can be linked]) + fi +fi + +AM_CONDITIONAL([ENABLE_BD_XLATOR], [test x$BUILD_BD_XLATOR = xyes]) + AC_SUBST(FUSE_CLIENT_SUBDIR) # end FUSE section @@ -821,6 +860,7 @@ echo "georeplication : $BUILD_SYNCDAEMON" echo "Linux-AIO : $BUILD_LIBAIO" echo "Enable Debug : $BUILD_DEBUG" echo "systemtap : $BUILD_SYSTEMTAP" +echo "Block Device xlator : $BUILD_BD_XLATOR" echo "glupy : $BUILD_GLUPY" echo "Use syslog : $USE_SYSLOG" echo "XML output : $BUILD_XML_OUTPUT" -- cgit