This topic describes the limits for CPFS file systems, clients, filesets, data flows, protocol services, and capacity monitoring.
File system
Limit | Threshold | Description |
Number of mount targets per file system | 1 | A CPFS file system supports a maximum of one mount target. |
Number of file systems per client | 1 | A client can mount a maximum of one CPFS file system. |
Can I mount a subdirectory? |
| CPFS-POSIX clients do not support mounting a CPFS file system from a subdirectory. CPFS-NFS clients support mounting a CPFS file system from a subdirectory. |
Number of compute nodes per file system | 2,000 | A file system can be mounted on a maximum of 2,000 compute nodes. |
Maximum capacity of a file system | 1 PiB | The maximum capacity of a single file system is 1 PiB. |
Maximum number of files or directories per file system | 4 billion | The maximum number of files and directories scales with the file system capacity. Each 1,200 GiB of capacity supports approximately 23 million files or directories, with a maximum of 4 billion per file system. |
Maximum number of files or subdirectories per directory | 100 million | A single directory supports a maximum of 100 million files or subdirectories. |
Maximum path length | 4,096 bytes | The maximum length of an access path in Linux VFS, such as /a/b/c, is 4,096 bytes. |
Maximum file name length | 255 bytes | A file name can be a maximum of 255 bytes. |
Operating systems
The CPFS-POSIX client software requires a minimum of 2 CPU cores and 4 GiB of memory to run properly.
If your operating system kernel version is not supported by the POSIX client, use the NFS client to access CPFS.
For CentOS users: The CentOS Project has announced the end of life (EOL) for CentOS Linux. The CentOS Linux public images on Alibaba Cloud are from the official CentOS source. After CentOS Linux reaches its EOL, Alibaba Cloud will no longer provide support for the operating system. To avoid service disruptions, migrate to a different operating system. For more information about migrating your operating system, see Operating system migration.
CPFS-POSIX client
The CPFS-POSIX client supports only Linux operating systems, including Alibaba Cloud Linux, Ubuntu, and CentOS. For information about the supported operating system versions, see the following table.
Operating system | Distribution | Kernel version |
Alibaba Cloud Linux | Alibaba Cloud Linux 2.1903 64-bit | 4.19.91-27.4.al7.x86_64 and earlier |
RHEL or CentOS | 8.4 | 4.18.0-305.19.1.el8_4 |
8.3 | 4.18.0-240.22.1.el8_3 | |
8.2 | 4.18.0-193.28.1.el8_2 | |
8.1 | 4.18.0-147.8.1.el8_1 | |
8.0 | 4.18.0-80.11.2.el8_0 | |
7.9 | 3.10.0-1160.42.2.el7 | |
7.8 | 3.10.0-1127.19.1.el7 | |
7.7 | 3.10.0-1062.18.1.el7 | |
7.6 | 3.10.0-957.54.1.el7 | |
7.5 | 3.10.0-862.14.4.el7 | |
7.4 | 3.10.0-693.2.2.el7 | |
7.3 | 3.10.0-514.26.2.el7 | |
7.2 | 3.10.0-514.26.2.el7 | |
Ubuntu | 20.04.3 LTS | 5.4.0-86-generic |
CPFS-NFS client
The CPFS-NFS client supports only Linux operating systems. For information about the supported operating system versions, see the following table.
Operating system | Operating system version |
Alibaba Cloud Linux |
|
CentOS |
|
Ubuntu |
|
Debian |
|
SUSE |
|
Filesets
Fileset specification limits
A CPFS file system supports a maximum of 10 filesets.
The maximum directory depth to which a fileset can be linked within a CPFS file system is 8.
The maximum number of files or directories in a fileset is 1 million.
Nested filesets are not supported.
Data flows
Data flow specification limits
A CPFS file system supports a maximum of 10 data flows.
A single data flow can have a maximum of five auto-updating directories.
A fileset in a CPFS file system can be linked to only one Object Storage Service (OSS) bucket.
Data flow task records are retained for a maximum of 90 days.
Data flow task reports are saved in the CPFS file system and consume storage space. A maximum of 1 million reports can be saved.
CPFS file systems do not support creating data flows with OSS buckets in other regions.
- Limits of dataflows on file systems
- You cannot rename a non-empty directory in a fileset that is associated with a dataflow. Otherwise, the error message
Permission Deniedor an error message indicating that the directory is not empty is returned. - Archive or Cold Archive objects in OSS do not support dataflows.
- Proceed with caution when you use special characters in the names of directories and files. The following characters can be contained: letters, digits, exclamation points (!), hyphens (-), underscores (_), periods (.), asterisks (*), and parentheses ().
- The path can be 1 to 1023 characters in length. A path that is too long is not supported.
- You cannot rename a non-empty directory in a fileset that is associated with a dataflow. Otherwise, the error message
- Limits of dataflows on export
- Hard links and symbolic links cannot be exported to an OSS bucket.
- Empty directories cannot exported to an OSS bucket.
- CHANGTIME attributes cannot be exported to an OSS bucket.
- The zero entries in sparase data are specified before they are exported to an OSS bucket.
Protocol services
Protocol service specification limits
Item
Threshold
Description
Maximum number of protocol services that can be created for a CPFS file system
1
You can create only one protocol service for a CPFS file system.
Maximum number of virtual private clouds (VPCs) to which export directories can be published by using a protocol service
2
You can use a protocol service to publish export directories to up to two VPCs.
Maximum number of export directories that can be created by using a protocol service
10
You can use a protocol service to create an export directory for up to 10 filesets or directories.
Maximum number of compute nodes that can be mounted by using a protocol service
10,000
You can mount up to 10,000 compute nodes by using a protocol service.
Maximum number of files that can be opened by using a protocol service at the same time
150,000
You can use a protocol service to open up to 150,000 files at the same time.
Other limits
A protocol service allows multiple clients to read and write files in a unified namespace in a shared manner. However, in scenarios in which multiple processes or clients concurrently write the same file such as a log file, the processes or clients maintain their own context information such as file descriptors and write locations, but the NFSv3 protocol itself does not support Atomic Append. In this case, write anomalies such as overwrite, crossover, and serialization may occur.
Network Lock Manager (NLM) is not supported.
NFSv4.x is not supported.