Commit | Line | Data |
---|---|---|
471379a1 MCC |
1 | .. SPDX-License-Identifier: GPL-2.0 |
2 | ||
3 | ============================ | |
7ad920b5 SW |
4 | Ceph Distributed File System |
5 | ============================ | |
6 | ||
7 | Ceph is a distributed network file system designed to provide good | |
8 | performance, reliability, and scalability. | |
9 | ||
10 | Basic features include: | |
11 | ||
12 | * POSIX semantics | |
13 | * Seamless scaling from 1 to many thousands of nodes | |
8136b58d | 14 | * High availability and reliability. No single point of failure. |
7ad920b5 SW |
15 | * N-way replication of data across storage nodes |
16 | * Fast recovery from node failures | |
17 | * Automatic rebalancing of data on node addition/removal | |
18 | * Easy deployment: most FS components are userspace daemons | |
19 | ||
20 | Also, | |
471379a1 | 21 | |
7ad920b5 SW |
22 | * Flexible snapshots (on any directory) |
23 | * Recursive accounting (nested files, directories, bytes) | |
24 | ||
25 | In contrast to cluster filesystems like GFS, OCFS2, and GPFS that rely | |
26 | on symmetric access by all clients to shared block devices, Ceph | |
27 | separates data and metadata management into independent server | |
28 | clusters, similar to Lustre. Unlike Lustre, however, metadata and | |
d11ae8e0 | 29 | storage nodes run entirely as user space daemons. File data is striped |
7ad920b5 SW |
30 | across storage nodes in large chunks to distribute workload and |
31 | facilitate high throughputs. When storage nodes fail, data is | |
32 | re-replicated in a distributed fashion by the storage nodes themselves | |
33 | (with some minimal coordination from a cluster monitor), making the | |
34 | system extremely efficient and scalable. | |
35 | ||
36 | Metadata servers effectively form a large, consistent, distributed | |
37 | in-memory cache above the file namespace that is extremely scalable, | |
38 | dynamically redistributes metadata in response to workload changes, | |
39 | and can tolerate arbitrary (well, non-Byzantine) node failures. The | |
40 | metadata server takes a somewhat unconventional approach to metadata | |
41 | storage to significantly improve performance for common workloads. In | |
42 | particular, inodes with only a single link are embedded in | |
43 | directories, allowing entire directories of dentries and inodes to be | |
44 | loaded into its cache with a single I/O operation. The contents of | |
45 | extremely large directories can be fragmented and managed by | |
46 | independent metadata servers, allowing scalable concurrent access. | |
47 | ||
48 | The system offers automatic data rebalancing/migration when scaling | |
49 | from a small cluster of just a few nodes to many hundreds, without | |
50 | requiring an administrator carve the data set into static volumes or | |
51 | go through the tedious process of migrating data between servers. | |
52 | When the file system approaches full, new nodes can be easily added | |
53 | and things will "just work." | |
54 | ||
55 | Ceph includes flexible snapshot mechanism that allows a user to create | |
56 | a snapshot on any subdirectory (and its nested contents) in the | |
57 | system. Snapshot creation and deletion are as simple as 'mkdir | |
58 | .snap/foo' and 'rmdir .snap/foo'. | |
59 | ||
60 | Ceph also provides some recursive accounting on directories for nested | |
61 | files and bytes. That is, a 'getfattr -d foo' on any directory in the | |
62 | system will reveal the total number of nested regular files and | |
63 | subdirectories, and a summation of all nested file sizes. This makes | |
64 | the identification of large disk space consumers relatively quick, as | |
65 | no 'du' or similar recursive scan of the file system is required. | |
66 | ||
fb18a575 LH |
67 | Finally, Ceph also allows quotas to be set on any directory in the system. |
68 | The quota can restrict the number of bytes or the number of files stored | |
69 | beneath that point in the directory hierarchy. Quotas can be set using | |
471379a1 | 70 | extended attributes 'ceph.quota.max_files' and 'ceph.quota.max_bytes', eg:: |
fb18a575 LH |
71 | |
72 | setfattr -n ceph.quota.max_bytes -v 100000000 /some/dir | |
73 | getfattr -n ceph.quota.max_bytes /some/dir | |
74 | ||
75 | A limitation of the current quotas implementation is that it relies on the | |
76 | cooperation of the client mounting the file system to stop writers when a | |
77 | limit is reached. A modified or adversarial client cannot be prevented | |
78 | from writing as much data as it needs. | |
7ad920b5 SW |
79 | |
80 | Mount Syntax | |
81 | ============ | |
82 | ||
471379a1 | 83 | The basic mount syntax is:: |
7ad920b5 | 84 | |
e1b9eb50 | 85 | # mount -t ceph user@fsid.fs_name=/[subdir] mnt -o mon_addr=monip1[:port][/monip2[:port]] |
7ad920b5 SW |
86 | |
87 | You only need to specify a single monitor, as the client will get the | |
88 | full list when it connects. (However, if the monitor you specify | |
89 | happens to be down, the mount won't succeed.) The port can be left | |
90 | off if the monitor is using the default. So if the monitor is at | |
471379a1 | 91 | 1.2.3.4:: |
7ad920b5 | 92 | |
e1b9eb50 | 93 | # mount -t ceph cephuser@07fe3187-00d9-42a3-814b-72a4d5e7d5be.cephfs=/ /mnt/ceph -o mon_addr=1.2.3.4 |
7ad920b5 SW |
94 | |
95 | is sufficient. If /sbin/mount.ceph is installed, a hostname can be | |
e1b9eb50 VS |
96 | used instead of an IP address and the cluster FSID can be left out |
97 | (as the mount helper will fill it in by reading the ceph configuration | |
98 | file):: | |
7ad920b5 | 99 | |
e1b9eb50 | 100 | # mount -t ceph cephuser@cephfs=/ /mnt/ceph -o mon_addr=mon-addr |
7ad920b5 | 101 | |
e1b9eb50 VS |
102 | Multiple monitor addresses can be passed by separating each address with a slash (`/`):: |
103 | ||
104 | # mount -t ceph cephuser@cephfs=/ /mnt/ceph -o mon_addr=192.168.1.100/192.168.1.101 | |
105 | ||
106 | When using the mount helper, monitor address can be read from ceph | |
107 | configuration file if available. Note that, the cluster FSID (passed as part | |
108 | of the device string) is validated by checking it with the FSID reported by | |
109 | the monitor. | |
7ad920b5 SW |
110 | |
111 | Mount Options | |
112 | ============= | |
113 | ||
e1b9eb50 VS |
114 | mon_addr=ip_address[:port][/ip_address[:port]] |
115 | Monitor address to the cluster. This is used to bootstrap the | |
116 | connection to the cluster. Once connection is established, the | |
117 | monitor addresses in the monitor map are followed. | |
118 | ||
119 | fsid=cluster-id | |
120 | FSID of the cluster (from `ceph fsid` command). | |
121 | ||
7ad920b5 SW |
122 | ip=A.B.C.D[:N] |
123 | Specify the IP and/or port the client should bind to locally. | |
124 | There is normally not much reason to do this. If the IP is not | |
125 | specified, the client's IP address is determined by looking at the | |
a33f3224 | 126 | address its connection to the monitor originates from. |
7ad920b5 SW |
127 | |
128 | wsize=X | |
cb63483a | 129 | Specify the maximum write size in bytes. Default: 64 MB. |
7ad920b5 SW |
130 | |
131 | rsize=X | |
cb63483a | 132 | Specify the maximum read size in bytes. Default: 64 MB. |
92c1037c AG |
133 | |
134 | rasize=X | |
c7f04944 | 135 | Specify the maximum readahead size in bytes. Default: 8 MB. |
7ad920b5 SW |
136 | |
137 | mount_timeout=X | |
138 | Specify the timeout value for mount (in seconds), in the case | |
cb63483a | 139 | of a non-responsive Ceph file system. The default is 60 |
7ad920b5 SW |
140 | seconds. |
141 | ||
fe33032d YZ |
142 | caps_max=X |
143 | Specify the maximum number of caps to hold. Unused caps are released | |
144 | when number of caps exceeds the limit. The default is 0 (no limit) | |
145 | ||
7ad920b5 SW |
146 | rbytes |
147 | When stat() is called on a directory, set st_size to 'rbytes', | |
148 | the summation of file sizes over all files nested beneath that | |
149 | directory. This is the default. | |
150 | ||
151 | norbytes | |
152 | When stat() is called on a directory, set st_size to the | |
153 | number of entries in that directory. | |
154 | ||
155 | nocrc | |
23ab15ad | 156 | Disable CRC32C calculation for data writes. If set, the storage node |
7ad920b5 SW |
157 | must rely on TCP's error correction to detect data corruption |
158 | in the data payload. | |
159 | ||
a40dc6cc SW |
160 | dcache |
161 | Use the dcache contents to perform negative lookups and | |
162 | readdir when the client has the entire directory contents in | |
163 | its cache. (This does not change correctness; the client uses | |
164 | cached metadata only when a lease or capability ensures it is | |
165 | valid.) | |
166 | ||
167 | nodcache | |
168 | Do not use the dcache as above. This avoids a significant amount of | |
169 | complex code, sacrificing performance without affecting correctness, | |
170 | and is useful for tracking down bugs. | |
7ad920b5 | 171 | |
a40dc6cc SW |
172 | noasyncreaddir |
173 | Do not use the dcache as above for readdir. | |
7ad920b5 | 174 | |
9122eed5 LH |
175 | noquotadf |
176 | Report overall filesystem usage in statfs instead of using the root | |
177 | directory quota. | |
178 | ||
ea4cdc54 LH |
179 | nocopyfrom |
180 | Don't use the RADOS 'copy-from' operation to perform remote object | |
181 | copies. Currently, it's only used in copy_file_range, which will revert | |
182 | to the default VFS implementation if this option is used. | |
183 | ||
131d7eb4 | 184 | recover_session=<no|clean> |
0b98acd6 | 185 | Set auto reconnect mode in the case where the client is blocklisted. The |
131d7eb4 YZ |
186 | available modes are "no" and "clean". The default is "no". |
187 | ||
188 | * no: never attempt to reconnect when client detects that it has been | |
0b98acd6 | 189 | blocklisted. Operations will generally fail after being blocklisted. |
131d7eb4 YZ |
190 | |
191 | * clean: client reconnects to the ceph cluster automatically when it | |
0b98acd6 | 192 | detects that it has been blocklisted. During reconnect, client drops |
471379a1 MCC |
193 | dirty data/metadata, invalidates page caches and writable file handles. |
194 | After reconnect, file locks become stale because the MDS loses track | |
195 | of them. If an inode contains any stale file locks, read/write on the | |
196 | inode is not allowed until applications release all stale file locks. | |
131d7eb4 | 197 | |
7ad920b5 SW |
198 | More Information |
199 | ================ | |
200 | ||
201 | For more information on Ceph, see the home page at | |
d11ae8e0 | 202 | https://ceph.com/ |
7ad920b5 SW |
203 | |
204 | The Linux kernel client source tree is available at | |
471379a1 | 205 | - https://github.com/ceph/ceph-client.git |
7ad920b5 SW |
206 | |
207 | and the source for the full system is at | |
d11ae8e0 | 208 | https://github.com/ceph/ceph.git |