Path to this page:
./
filesystems/glusterfs,
Cluster filesystem
Branch: pkgsrc-2013Q3,
Version: 3.4.0,
Package name: glusterfs-3.4.0,
Maintainer: pkgsrc-usersGlusterFS is a flexible, powerful, POSIX-compliant cluster filesystem
that can scale to several petabytes.
GlusterFS works over either TCP/IP or high-performance Infiniband
RDMA interconnect.
GlusterFS provides striping and on-the-fly synchronous replication
of files. GlusterFS has a fully distributed design, with no single
point of failure.
Please visit http://www.gluster.org/glusterfs.php for more info.
MESSAGE.NetBSD [+/-]===========================================================================
$NetBSD: MESSAGE.NetBSD,v 1.14 2013/04/08 11:17:13 rodent Exp $
*** GlusterFS clients ***
This is required in /etc/sysctl.conf in order to avoid hangs on I/O operations
kern.sbmax=4194304
net.inet.tcp.sendbuf_max=1048576
net.inet.tcp.recvbuf_max=1048576
In order to use mount -t glusterfs, please install this link
ln -s ${PREFIX}/sbin/mount.glusterfs /sbin/mount_glusterfs
* Only for netbsd-5 branch (later NetBSD GENERIC kernels have it enabled):
A kernel with the following option is required:
file-system PUFFS
pseudo-device putter
pseudo-device pud
*** GlusterFS servers ***
glusterfs servers will need extended attributes in exported filesystems.
This require a kernel with the following options:
options UFS_EXTATTR
You will need to create the directories below on exported filesystems' roots,
and then mount with -o extattr
.attribute/system
.attribute/user
* Only for netbsd-5 branch (later NetBSD version do not need that)
mount -o extattr shall not be used, but the kernel needs options below:
options UFS_EXTATTR_AUTOSTART
options UFS_EXTATTR_AUTOCREATE=1024
===========================================================================
Master sites:
SHA1: 8795bcb309730c173a226c8cb1e08587e56ea692
RMD160: 15a290ad890541ec365134eb998e5f0ec48d3bbc
Filesize: 3686.369 KB
Version history: (Expand)
- (2013-10-04) Package added to pkgsrc.se, version glusterfs-3.4.0 (created)