1 v9fs: Plan 9 Resource Sharing for Linux 2 ======================================= 3 4ABOUT 5===== 6 7v9fs is a Unix implementation of the Plan 9 9p remote filesystem protocol. 8 9This software was originally developed by Ron Minnich <rminnich@sandia.gov> 10and Maya Gokhale. Additional development by Greg Watson 11<gwatson@lanl.gov> and most recently Eric Van Hensbergen 12<ericvh@gmail.com>, Latchesar Ionkov <lucho@ionkov.net> and Russ Cox 13<rsc@swtch.com>. 14 15The best detailed explanation of the Linux implementation and applications of 16the 9p client is available in the form of a USENIX paper: 17 http://www.usenix.org/events/usenix05/tech/freenix/hensbergen.html 18 19Other applications are described in the following papers: 20 * XCPU & Clustering 21 http://xcpu.org/papers/xcpu-talk.pdf 22 * KVMFS: control file system for KVM 23 http://xcpu.org/papers/kvmfs.pdf 24 * CellFS: A New Programming Model for the Cell BE 25 http://xcpu.org/papers/cellfs-talk.pdf 26 * PROSE I/O: Using 9p to enable Application Partitions 27 http://plan9.escet.urjc.es/iwp9/cready/PROSE_iwp9_2006.pdf 28 * VirtFS: A Virtualization Aware File System pass-through 29 http://goo.gl/3WPDg 30 31USAGE 32===== 33 34For remote file server: 35 36 mount -t 9p 10.10.1.2 /mnt/9 37 38For Plan 9 From User Space applications (http://swtch.com/plan9) 39 40 mount -t 9p `namespace`/acme /mnt/9 -o trans=unix,uname=$USER 41 42For server running on QEMU host with virtio transport: 43 44 mount -t 9p -o trans=virtio <mount_tag> /mnt/9 45 46where mount_tag is the tag associated by the server to each of the exported 47mount points. Each 9P export is seen by the client as a virtio device with an 48associated "mount_tag" property. Available mount tags can be 49seen by reading /sys/bus/virtio/drivers/9pnet_virtio/virtio<n>/mount_tag files. 50 51OPTIONS 52======= 53 54 trans=name select an alternative transport. Valid options are 55 currently: 56 unix - specifying a named pipe mount point 57 tcp - specifying a normal TCP/IP connection 58 fd - used passed file descriptors for connection 59 (see rfdno and wfdno) 60 virtio - connect to the next virtio channel available 61 (from QEMU with trans_virtio module) 62 rdma - connect to a specified RDMA channel 63 64 uname=name user name to attempt mount as on the remote server. The 65 server may override or ignore this value. Certain user 66 names may require authentication. 67 68 aname=name aname specifies the file tree to access when the server is 69 offering several exported file systems. 70 71 cache=mode specifies a caching policy. By default, no caches are used. 72 none = default no cache policy, metadata and data 73 alike are synchronous. 74 loose = no attempts are made at consistency, 75 intended for exclusive, read-only mounts 76 fscache = use FS-Cache for a persistent, read-only 77 cache backend. 78 mmap = minimal cache that is only used for read-write 79 mmap. Northing else is cached, like cache=none 80 81 debug=n specifies debug level. The debug level is a bitmask. 82 0x01 = display verbose error messages 83 0x02 = developer debug (DEBUG_CURRENT) 84 0x04 = display 9p trace 85 0x08 = display VFS trace 86 0x10 = display Marshalling debug 87 0x20 = display RPC debug 88 0x40 = display transport debug 89 0x80 = display allocation debug 90 0x100 = display protocol message debug 91 0x200 = display Fid debug 92 0x400 = display packet debug 93 0x800 = display fscache tracing debug 94 95 rfdno=n the file descriptor for reading with trans=fd 96 97 wfdno=n the file descriptor for writing with trans=fd 98 99 msize=n the number of bytes to use for 9p packet payload 100 101 port=n port to connect to on the remote server 102 103 noextend force legacy mode (no 9p2000.u or 9p2000.L semantics) 104 105 version=name Select 9P protocol version. Valid options are: 106 9p2000 - Legacy mode (same as noextend) 107 9p2000.u - Use 9P2000.u protocol 108 9p2000.L - Use 9P2000.L protocol 109 110 dfltuid attempt to mount as a particular uid 111 112 dfltgid attempt to mount with a particular gid 113 114 afid security channel - used by Plan 9 authentication protocols 115 116 nodevmap do not map special files - represent them as normal files. 117 This can be used to share devices/named pipes/sockets between 118 hosts. This functionality will be expanded in later versions. 119 120 access there are four access modes. 121 user = if a user tries to access a file on v9fs 122 filesystem for the first time, v9fs sends an 123 attach command (Tattach) for that user. 124 This is the default mode. 125 <uid> = allows only user with uid=<uid> to access 126 the files on the mounted filesystem 127 any = v9fs does single attach and performs all 128 operations as one user 129 client = ACL based access check on the 9p client 130 side for access validation 131 132 cachetag cache tag to use the specified persistent cache. 133 cache tags for existing cache sessions can be listed at 134 /sys/fs/9p/caches. (applies only to cache=fscache) 135 136RESOURCES 137========= 138 139Protocol specifications are maintained on github: 140http://ericvh.github.com/9p-rfc/ 141 1429p client and server implementations are listed on 143http://9p.cat-v.org/implementations 144 145A 9p2000.L server is being developed by LLNL and can be found 146at http://code.google.com/p/diod/ 147 148There are user and developer mailing lists available through the v9fs project 149on sourceforge (http://sourceforge.net/projects/v9fs). 150 151News and other information is maintained on a Wiki. 152(http://sf.net/apps/mediawiki/v9fs/index.php). 153 154Bug reports are best issued via the mailing list. 155 156For more information on the Plan 9 Operating System check out 157http://plan9.bell-labs.com/plan9 158 159For information on Plan 9 from User Space (Plan 9 applications and libraries 160ported to Linux/BSD/OSX/etc) check out http://swtch.com/plan9 161 162