1 Ceph Distributed File System
2 ============================
4 Ceph is a distributed network file system designed to provide good
5 performance, reliability, and scalability.
7 Basic features include:
10 * Seamless scaling from 1 to many thousands of nodes
11 * High availability and reliability. No single point of failure.
12 * N-way replication of data across storage nodes
13 * Fast recovery from node failures
14 * Automatic rebalancing of data on node addition/removal
15 * Easy deployment: most FS components are userspace daemons
18 * Flexible snapshots (on any directory)
19 * Recursive accounting (nested files, directories, bytes)
21 In contrast to cluster filesystems like GFS, OCFS2, and GPFS that rely
22 on symmetric access by all clients to shared block devices, Ceph
23 separates data and metadata management into independent server
24 clusters, similar to Lustre. Unlike Lustre, however, metadata and
25 storage nodes run entirely as user space daemons. Storage nodes
26 utilize btrfs to store data objects, leveraging its advanced features
27 (checksumming, metadata replication, etc.). File data is striped
28 across storage nodes in large chunks to distribute workload and
29 facilitate high throughputs. When storage nodes fail, data is
30 re-replicated in a distributed fashion by the storage nodes themselves
31 (with some minimal coordination from a cluster monitor), making the
32 system extremely efficient and scalable.
34 Metadata servers effectively form a large, consistent, distributed
35 in-memory cache above the file namespace that is extremely scalable,
36 dynamically redistributes metadata in response to workload changes,
37 and can tolerate arbitrary (well, non-Byzantine) node failures. The
38 metadata server takes a somewhat unconventional approach to metadata
39 storage to significantly improve performance for common workloads. In
40 particular, inodes with only a single link are embedded in
41 directories, allowing entire directories of dentries and inodes to be
42 loaded into its cache with a single I/O operation. The contents of
43 extremely large directories can be fragmented and managed by
44 independent metadata servers, allowing scalable concurrent access.
46 The system offers automatic data rebalancing/migration when scaling
47 from a small cluster of just a few nodes to many hundreds, without
48 requiring an administrator carve the data set into static volumes or
49 go through the tedious process of migrating data between servers.
50 When the file system approaches full, new nodes can be easily added
51 and things will "just work."
53 Ceph includes flexible snapshot mechanism that allows a user to create
54 a snapshot on any subdirectory (and its nested contents) in the
55 system. Snapshot creation and deletion are as simple as 'mkdir
56 .snap/foo' and 'rmdir .snap/foo'.
58 Ceph also provides some recursive accounting on directories for nested
59 files and bytes. That is, a 'getfattr -d foo' on any directory in the
60 system will reveal the total number of nested regular files and
61 subdirectories, and a summation of all nested file sizes. This makes
62 the identification of large disk space consumers relatively quick, as
63 no 'du' or similar recursive scan of the file system is required.
65 Finally, Ceph also allows quotas to be set on any directory in the system.
66 The quota can restrict the number of bytes or the number of files stored
67 beneath that point in the directory hierarchy. Quotas can be set using
68 extended attributes 'ceph.quota.max_files' and 'ceph.quota.max_bytes', eg:
70 setfattr -n ceph.quota.max_bytes -v 100000000 /some/dir
71 getfattr -n ceph.quota.max_bytes /some/dir
73 A limitation of the current quotas implementation is that it relies on the
74 cooperation of the client mounting the file system to stop writers when a
75 limit is reached. A modified or adversarial client cannot be prevented
76 from writing as much data as it needs.
81 The basic mount syntax is:
83 # mount -t ceph monip[:port][,monip2[:port]...]:/[subdir] mnt
85 You only need to specify a single monitor, as the client will get the
86 full list when it connects. (However, if the monitor you specify
87 happens to be down, the mount won't succeed.) The port can be left
88 off if the monitor is using the default. So if the monitor is at
91 # mount -t ceph 1.2.3.4:/ /mnt/ceph
93 is sufficient. If /sbin/mount.ceph is installed, a hostname can be
94 used instead of an IP address.
102 Specify the IP and/or port the client should bind to locally.
103 There is normally not much reason to do this. If the IP is not
104 specified, the client's IP address is determined by looking at the
105 address its connection to the monitor originates from.
108 Specify the maximum write size in bytes. Default: 16 MB.
111 Specify the maximum read size in bytes. Default: 16 MB.
114 Specify the maximum readahead size in bytes. Default: 8 MB.
117 Specify the timeout value for mount (in seconds), in the case
118 of a non-responsive Ceph file system. The default is 30
122 When stat() is called on a directory, set st_size to 'rbytes',
123 the summation of file sizes over all files nested beneath that
124 directory. This is the default.
127 When stat() is called on a directory, set st_size to the
128 number of entries in that directory.
131 Disable CRC32C calculation for data writes. If set, the storage node
132 must rely on TCP's error correction to detect data corruption
136 Use the dcache contents to perform negative lookups and
137 readdir when the client has the entire directory contents in
138 its cache. (This does not change correctness; the client uses
139 cached metadata only when a lease or capability ensures it is
143 Do not use the dcache as above. This avoids a significant amount of
144 complex code, sacrificing performance without affecting correctness,
145 and is useful for tracking down bugs.
148 Do not use the dcache as above for readdir.
151 Report overall filesystem usage in statfs instead of using the root
155 Don't use the RADOS 'copy-from' operation to perform remote object
156 copies. Currently, it's only used in copy_file_range, which will revert
157 to the default VFS implementation if this option is used.
162 For more information on Ceph, see the home page at
163 http://ceph.newdream.net/
165 The Linux kernel client source tree is available at
166 git://ceph.newdream.net/git/ceph-client.git
167 git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
169 and the source for the full system is at
170 git://ceph.newdream.net/git/ceph.git