.\"
.\" Copyright (c) 2015, 2016, Intel Corporation.
.\"
-.TH Lustre 7 "2006 Jun 15" Lustre "A high-performance cluster file system"
+.TH LUSTRE 7 "2021 Nov 08" Lustre "A high-performance cluster file system"
.SH NAME
Lustre
.SH SYNOPSIS
-A high-performance file system designed for clusters.
+A high-performance file system designed for Linux clusters.
.SH DESCRIPTION
-.B Lustre®
-is a high-performance, massively-scalable, POSIX-compliant network file system
-designed for the world's largest high-performance compute clusters.
+.B Lustre
+is a high-performance, massively-scalable, POSIX-compliant GPL network file
+system that runs on the world's largest high-performance compute clusters.
Lustre filesystems are made up of multiple services typically distributed
-across multiple nodes. Lustre clients can contact these server nodes over
-multiple high-speed network fabrics via LNET, the Lustre NETworking
+across multiple server nodes. Lustre clients can contact these server nodes
+over multiple high-speed network fabrics via LNet, the Lustre Network
system. Clients then present the filesystem at a mount point to userspace.
-A filesystem is comprised of a
-.I MDT
-, MetaData Target, which stores directory and file meta-information such as
-file ownership, timestamps, access permissions, etc, and a
-series of
-.I OSTs
-, Object Storage Targets, which hold the file data in one or more objects.
-There is typically not a 1:1 mapping of OST objects and what is presented
-as a file on a Lustre client.
+A Lustre filesystem is comprised of one or more
+.IR MDTs ,
+MetaData Targets, which store directory and file meta-information such as
+file ownership, timestamps, access permissions, etc, and one or more
+.IR OSTs ,
+Object Storage Targets, which hold each file's data in one or more objects.
+There is sometimes, but not always, a 1:1 mapping of regular files on a
+client to OST objects on the server. Each file may have a different
+mapping of file offset to one or more OST object(s), known as the file
+layout, that can be managed with the
+.BR lfs-setstripe (1)
+command.
-Lustre and LNET are implemented as a series of kernel modules, for both
-servers and clients. LNET networks are defined in the modprobe.conf file on
+Lustre and LNet are implemented as a series of Linux kernel modules, for both
+servers and clients. LNet networks are defined in the modprobe.conf file on
all nodes. Lustre is started on the clients and servers using the
.BR mount (8)
command.
.SH COMMANDS
.TP
.BR mkfs.lustre (8)
-Format a physical disk for use as a Lustre server's backend storage (aka
-target).
+Format a Linux block device for use as a Lustre server's backend storage
+(aka target).
.TP
.BR tunefs.lustre (8)
Modify configuration information on a Lustre target disk.
that starts Lustre servers and clients mounts the client filesystem.
.TP
.BR lctl (8)
-A low-level interface to control various aspects of Lustre
+A low-level tool for administrators to control Lustre configuration.
.TP
.BR lfs (1)
-A user-level interface to control Lustre-specific information for
+A user-level tool to control Lustre-specific information for
individual files.
-.B lustre_config.sh
-Format multiple Lustre targets simultaneously from definitions in a CSV
-file.
.SH BUGS
Please report all bugs https://jira.whamcloud.com/
.SH AVAILABILITY
.B The
.BR Lustre (7)
-filesystem package is available via
+filesystem packages are available for download at:
.br
https://downloads.whamcloud.com/
+and GPL source code is available at:
+.br
+https://git.whamcloud.com/
.SH SEE ALSO
.BR mkfs.lustre (8),
.BR tunefs.lustre (8),
.BR mount.lustre (8),
.BR lctl (8),
.BR lfs (1),
-.BR lfs_migrate (1),
-.BR lustreapi (7),
-.BR l_getidentity (8),
+.BR llobdstat (8),
.BR llstat (8),
.BR llverdev (8),
-.BR lst (8),
-.BR llobdstat (8),
-.BR ll_decode_filter_fid (8),
.BR llog_reader (8),
.BR lshowmount (8),
+.BR lustreapi (7),
.BR lustre_rsync (8)
git://git.whamcloud.com / fs / lustre-release.git / blobdiff