1GlusterFS(8) Gluster Inc. GlusterFS(8)
2
6 GlusterFS - Clustered Filesystem.
7
9 glusterfsd [options] [mountpoint]
10
12 GlusterFS is a clustered file-system capable of scaling to several
13 peta-bytes. It aggregates various storage bricks over Infiniband RDMA
14 or TCP/IP interconnect into one large parallel network file system.
15 Storage bricks can be made of any commodity hardware such as x86-64
16 server with SATA-II RAID and Infiniband HBA.
17 GlusterFS is fully POSIX compliant FileSystem. On client side, it has
19 dependency on FUSE package, on server side, it works seemlessly on dif‐
20 ferent OSes. (Currently supported on GNU/Linux, Solaris).
21
24 Mandatory or optional arguments to long options are also mandatory or
25 optional for any corresponding short options.
26 Basic options
28 -f, --volfile=VOLUME-FILE
29 File to use as VOLUME-FILE [default:/etc/glusterfs/glus‐
30 terfs.vol]
31 -l, --log-file=LOGFILE
33 File to use for logging [default:/var/log/glusterfs/glus‐
34 terfs.log]
35 -L, --log-level=LOGLEVEL
37 Logging severity. Valid options are TRACE, DEBUG, INFO, WARN‐
38 ING, ERROR and CRITICAL [default: WARNING]
39 -s, --volfile-server=SERVER
41 Server to get the volume from. This option overrides --volfile
42 option
43 Advanced options
46 --localtime-logging
47 Enable localtime log timestamps.
48 --debug
50 Run in debug mode. This option sets --no-daemon, --log-level to
51 DEBUG and --log-file to console
52 -N, --no-daemon
54 Run in foreground
55 --read-only
57 Makes the filesystem read-only
58 -p, --pid-file=PIDFILE
60 File to use as pid file
61 -S SOCKFILE
63 Socket file to used for inter-process communication
64 --brick-name DIRECTORY
66 Directory to be used as export directory for GlusterFS
67 --brick-port PORT
69 Brick Port to be registered with Gluster portmapper
70 --volfile-id=KEY
72 KEY of the volume file to be fetched from server
73 --volfile-server-port=PORT
75 Port number of volfile server
76 --volfile-server-transport=TRANSPORT
78 Transport type to get volume file from server [default: tcp]
79 --volume-name=VOLUME-NAME
81 Volume name to be used for MOUNT-POINT [default: top most volume
82 in VOLUME-FILE]
83 --xlator-option=VOLUME-NAME.OPTION=VALUE
85 Add/override a translator option for a volume with the specified
86 value
87 Fuse options
90 --attribute-timeout=SECONDS
91 Set attribute timeout to SECONDS for inodes in fuse kernel mod‐
92 ule [default: 1]
93 --entry-timeout=SECONDS
95 Set entry timeout to SECONDS in fuse kernel module [default: 1]
96 --direct-io-mode=BOOL
98 Enable/Disable direct-io mode in fuse module [default: enable]
99 --resolve-gids
101 Resolve all auxiliary groups in fuse translator (max 32 other‐
102 wise)
103 --auto-invalidation=BOOL
105 controls whether fuse-kernel can auto-invalidate attribute, den‐
106 try and page-cache. Disable this only if same files/directories
107 are not accessed across two different mounts concurrently
108 [default: on]
109 Miscellaneous Options
112 -?, --help
113 Give this help list
114 --usage
116 Give a short usage message
117 -V, --version
119 Print program version
120
123 /etc/glusterfs/*.vol
124
127 Start a GlusterFS server on localhost with volume name foo
128 glusterfsd -s localhost --volfile-id foo.server.media-disk-1 -p
130 /var/lib/glusterd/vols/foo/run/server-media-disk-1.pid -S
131 /tmp/<uniqueid>.socket --brick-name /media/disk-1 -l /var/log/glus‐
132 terfs/bricks/media-disk-1.log --brick-port 24009 --xlator-option
133 foo-server.listen-port=24009
134
137 fusermount(1), mount.glusterfs(8), gluster(8)
138
140 Copyright(c) 2006-2011 Gluster, Inc. <http://www.gluster.com>
14119 March 2010 Cluster Filesystem GlusterFS(8)