Chapter 1. Introduction to the Ceph File System
As a storage administrator, you can gain an understanding of the features, system components, and limitations to manage a Ceph File System (CephFS) environment.
1.1. Ceph File System features and enhancements
The Ceph File System (CephFS) is a file system compatible with POSIX standards that is built on top of Ceph’s distributed object store, called RADOS (Reliable Autonomic Distributed Object Storage). CephFS provides file access to a Red Hat Ceph Storage cluster, and uses the POSIX semantics wherever possible. For example, in contrast to many other common network file systems like NFS, CephFS maintains strong cache coherency across clients. The goal is for processes using the file system to behave the same when they are on different hosts as when they are on the same host. However, in some cases, CephFS diverges from the strict POSIX semantics.
The Ceph File System has the following features and enhancements:
- The Ceph File System is highly scalable due to horizontal scaling of metadata servers and direct client reads and writes with individual OSD nodes.
- Shared File System
- The Ceph File System is a shared file system so multiple clients can work on the same file system at once.
- High Availability
- The Ceph File System provides a cluster of Ceph Metadata Servers (MDS). One is active and others are in standby mode. If the active MDS terminates unexpectedly, one of the standby MDS becomes active. As a result, client mounts continue working through a server failure. This behavior makes the Ceph File System highly available. In addition, you can configure multiple active metadata servers.
- Configurable File and Directory Layouts
- The Ceph File System allows users to configure file and directory layouts to use multiple pools, pool namespaces, and file striping modes across objects.
- POSIX Access Control Lists (ACL)
The Ceph File System supports the POSIX Access Control Lists (ACL). ACL are enabled by default with the Ceph File Systems mounted as kernel clients with kernel version
kernel-3.10.0-327.18.2.el7or newer. To use an ACL with the Ceph File Systems mounted as FUSE clients, you must enable them.
- Client Quotas
- The Ceph File System supports setting quotas on any directory in a system. The quota can restrict the number of bytes or the number of files stored beneath that point in the directory hierarchy. CephFS client quotas are enabled by default.
- The Ceph File System size is only bound by the capacity of the OSDs servicing its data pool. To increase the capacity, add more OSDs to the CephFS data pool. To decrease the capacity, use either client quotas or pool quotas.
- The Ceph File System supports read-only snapshots but not writable clones.
- POSIX file system operations
The Ceph File System supports standard and consistent POSIX file system operations including the following access patterns:
- Buffered write operations via the Linux page cache.
- Cached read operations via the Linux page cache.
- Direct I/O asynchronous or synchronous read/write operations, bypassing the page cache.
- Memory mapped I/O.
1.2. Ceph File System components
The Ceph File System has two primary components:
The CephFS clients perform I/O operations on behalf of applications using CephFS, such as,
ceph-fusefor FUSE clients and
kcephfsfor kernel clients. CephFS clients send metadata requests to an active Metadata Server. In return, the CephFS client learns of the file metadata, and can begin safely caching both metadata and file data.
- Metadata Servers (MDS)
The MDS does the following:
- Provides metadata to CephFS clients.
- Manages metadata related to files stored on the Ceph File System.
- Coordinates access to the shared Red Hat Ceph Storage cluster.
- Caches hot metadata to reduce requests to the backing metadata pool store.
- Manages the CephFS clients' caches to maintain cache coherence.
- Replicates hot metadata between active MDS.
- Coalesces metadata mutations to a compact journal with regular flushes to the backing metadata pool.
CephFS requires at least one Metadata Server daemon (
ceph-mds) to run.
The diagram below shows the component layers of the Ceph File System.
The bottom layer represents the underlying core storage cluster components:
Ceph OSDs (
ceph-osd) where the Ceph File System data and metadata are stored.
Ceph Metadata Servers (
ceph-mds) that manages Ceph File System metadata.
Ceph Monitors (
ceph-mon) that manages the master copy of the cluster map.
The Ceph Storage protocol layer represents the Ceph native
librados library for interacting with the core storage cluster.
The CephFS library layer includes the CephFS
libcephfs library that works on top of
librados and represents the Ceph File System.
The top layer represents two types of Ceph clients that can access the Ceph File Systems.
The diagram below shows more details on how the Ceph File System components interact with each other.
1.3. Ceph File System and SELinux
Starting with Red Hat Enterprise Linux 8.3 and Red Hat Ceph Storage 4.2, support for using Security-Enhanced Linux (SELinux) on Ceph File Systems (CephFS) environments is available. You can now set any SELinux file type with CephFS, along with assigning a particular SELinux type on individual files. This support applies to the Ceph File System Metadata Server (MDS), the CephFS File System in User Space (FUSE) clients, and the CephFS kernel clients.
- See the Using SELinux Guide on Red Hat Enterprise Linux 8 for more information on SELinux.
1.4. Ceph File System limitations and the POSIX standards
Creation of multiple Ceph File Systems on one Red Hat Ceph Storage cluster is disabled by default. An attempt to create an additional Ceph File System fails with the following error message:
Error EINVAL: Creation of multiple filesystems is disabled.
While technically possible, Red Hat does not support having multiple Ceph File Systems on one Red Hat Ceph Storage cluster. Doing so can cause the MDS or CephFS client nodes to terminate unexpectedly.
The Ceph File System diverges from the strict POSIX semantics in the following ways:
If a client’s attempt to write a file fails, the write operations are not necessarily atomic. That is, the client might call the
write()system call on a file opened with the
O_SYNCflag with an 8MB buffer and then terminates unexpectedly and the write operation can be only partially applied. Almost all file systems, even local file systems, have this behavior.
- In situations when the write operations occur simultaneously, a write operation that exceeds object boundaries is not necessarily atomic. For example, writer A writes "aa|aa" and writer B writes "bb|bb" simultaneously, where "|" is the object boundary, and "aa|bb" is written rather than the proper "aa|aa" or "bb|bb".
POSIX includes the
seekdir()system calls that allow you to obtain the current directory offset and seek back to it. Because CephFS can fragment directories at any time, it is difficult to return a stable integer offset for a directory. As such, calling the
seekdir()system call to a non-zero offset might often work but is not guaranteed to do so. Calling
seekdir()to offset 0 will always work. This is an equivalent to the
Sparse files propagate incorrectly to the
st_blocksfield of the
stat()system call. CephFS does not explicitly track parts of a file that are allocated or written to, because the
st_blocksfield is always populated by the quotient of file size divided by block size. This behavior causes utilities, such as
du, to overestimate used space.
mmap()system call maps a file into memory on multiple hosts, write operations are not coherently propagated to caches of other hosts. That is, if a page is cached on host A, and then updated on host B, host A page is not coherently invalidated.
CephFS clients present a hidden
.snapdirectory that is used to access, create, delete, and rename snapshots. Although this directory is excluded from the
readdir()system call, any process that tries to create a file or directory with the same name returns an error. The name of this hidden directory can be changed at mount time with the
-o snapdirname=.<new_name>option or by using the
1.5. Additional Resources
- See the Installing Metadata Servers section in the Red Hat Ceph Storage Installation Guide for more details.
- If you want to use NFS Ganesha as an interface to the Ceph File System with Red Hat OpenStack Platform, see the CephFS with NFS-Ganesha deployment section in the CephFS via NFS Back End Guide for the Shared File System Service for instructions on how to deploy such an environment.