GlusterFS(8)

💖 GlusterFS — the clustered filesystem era 💖

okay bestie, sit down, hydrate, and let me tell you about GlusterFS(8) from the Gluster Inc. girlies. this is the manual page for the big one. the peta-scale one. the way it eats storage bricks for breakfast? iconic. let's get into it. 🦋

---

✨ NAME ✨

GlusterFS — Clustered Filesystem. that's it. that's the whole vibe. she contains multitudes (and also your bricks). 💅

---

✨ SYNOPSIS ✨

glusterfsd [options] [mountpoint]

that's the shape of it. options go in, mountpoint goes at the end if you have one. no notes. 🎀

---

✨ DESCRIPTION ✨

okay so. GlusterFS is a clustered file-system and she is not playing around — she's capable of scaling to several petabytes. like. several. peta. bytes. 💀

the way it works is it aggregates various storage bricks over Infiniband RDMA or TCP/IP interconnect into one big large parallel network file system. one filesystem. many bricks. that's the energy. ✨

and the bricks themselves? they can be made of literally any commodity hardware — like an x86-64 server with SATA-II RAID and Infiniband HBA. no fancy proprietary nonsense required, we love a budget queen. 👑

GlusterFS is a fully POSIX compliant FileSystem. periodt. on the client side, it has a dependency on the FUSE package. on the server side, it works seemlessly on different OSes. (Currently supported on GNU/Linux, Solaris.) 🫶

---

✨ OPTIONS ✨

quick heads up bestie: mandatory or optional arguments to long options are also mandatory or optional for any corresponding short options. the rules travel with the option, iykyk. 💫

🌸 Basic options 🌸

• -f, --volfile=VOLUME-FILE — the File to use as VOLUME-FILE. [default: /etc/glusterfs/glusterfs.vol] 🍓
• -l, --log-file=LOGFILE — the File to use for logging. [default: /var/log/glusterfs/glusterfs.log]
• -L, --log-level=LOGLEVEL — Logging severity. the valid options are TRACE, DEBUG, INFO, WARNING, ERROR and CRITICAL. [default: WARNING] choose your drama level wisely 💅
• -s, --volfile-server=SERVER — the Server to get the volume from. lowkey important: this option overrides the --volfile option. no cap. 🔥

🧚 Advanced options 🧚

• --localtime-logging — Enable localtime log timestamps. your logs, your timezone, your rules. ⭐
• --debug — Run in debug mode. this one sets --no-daemon, sets --log-level to DEBUG and sets --log-file to console. she's doing a lot. let her cook. 🫶
• -N, --no-daemon — Run in foreground. main character energy, no backgrounding. 👑
• --read-only — Makes the filesystem read-only. look but don't touch, bestie. 🙈
• -p, --pid-file=PIDFILE — the File to use as pid file.
• -S SOCKFILE — Socket file to used for inter-process communication. (yes that's how the original says it, we keep the facts exact around here 💖)
• --brick-name DIRECTORY — the Directory to be used as export directory for GlusterFS.
• --brick-port PORT — the Brick Port to be registered with Gluster portmapper.
• --volfile-id=KEY — the KEY of the volume file to be fetched from server.
• --volfile-server-port=PORT — the Port number of volfile server.
• --volfile-server-transport=TRANSPORT — the Transport type to get volume file from server. [default: tcp]
• --volume-name=VOLUME-NAME — the Volume name to be used for MOUNT-POINT. [default: top most volume in VOLUME-FILE]
• --xlator-option=VOLUME-NAME.OPTION=VALUE — Add/override a translator option for a volume with the specified value. yes, the whole VOLUME-NAME.OPTION=VALUE shape, exactly like that. ✨

🎀 Fuse options 🎀

• --attribute-timeout=SECONDS — Set attribute timeout to SECONDS for inodes in fuse kernel module. [default: 1]
• --entry-timeout=SECONDS — Set entry timeout to SECONDS in fuse kernel module. [default: 1]
• --direct-io-mode=BOOL — Enable/Disable direct-io mode in fuse module. [default: enable]
• --resolve-gids — Resolve all auxiliary groups in fuse translator (max 32 otherwise). thirty-two. that's the limit. remember it. 🦋
• --auto-invalidation=BOOL — controls whether fuse-kernel can auto-invalidate attribute, dentry and page-cache. Disable this only if same files/directories are not accessed across two different mounts concurrently. [default: on]

not me stressing this one: only turn auto-invalidation off if the same files/directories aren't being accessed across two different mounts at the same time. otherwise? do not. 💀

🌈 Miscellaneous Options 🌈

• -?, --help — Give this help list. the classic. the icon. 🫶
• --usage — Give a short usage message.
• -V, --version — Print program version.

---

✨ FILES ✨

/etc/glusterfs/*.vol

the vol files live there. that's the spot. 🏠

---

✨ EXAMPLES ✨

okay so the assignment: Start a GlusterFS server on localhost with volume name foo ✨

glusterfsd -s localhost --volfile-id foo.server.media-disk-1 -p
/var/lib/glusterd/vols/foo/run/server-media-disk-1.pid -S
/tmp/<uniqueid>.socket --brick-name /media/disk-1 -l
/var/log/glusterfs/bricks/media-disk-1.log --brick-port 24009
--xlator-option foo-server.listen-port=24009

copy it, run it, slay it. 💅

---

✨ SEE ALSO ✨

• fusermount(1)
• mount.glusterfs(8)
• gluster(8)

go read those too bestie, the lore is deep 📚

---

✨ COPYRIGHT ✨

Copyright(c) 2006-2011 Gluster, Inc. <http://www.gluster.com>

---

and that's the page, fr fr. this was the Cluster Filesystem manual, page GlusterFS(8) from Gluster Inc., dated 19 March 2010. okay bye bestie, go mount something iconic 💖✨🎀🦋