All Products
Search
Document Center

Cloud Parallel File Storage:Specifications

Last Updated:Jan 06, 2026

CPFS General-purpose Edition is available in two performance specifications: 100 MB/s/TiB Baseline and 200 MB/s/TiB Baseline. This topic compares their performance metrics, advanced features, and dataflow performance for file systems of the same capacity. This comparison is designed to guide the selection of the most appropriate specification.

File system instance performance

General-purpose CPFS file systems can be accessed using POSIX or NFS clients. The following sections detail the throughput, input/output operations per second (IOPS), and I/O latency for the 100 MB/s/TiB and 200 MB/s/TiB Baseline classes on file systems of the same capacity.

CPFS-POSIX

CPFS file systems that use zone-redundant storage (ZRS) do not support the POSIX protocol.

After you create a CPFS POSIX mount target, access the file system using a CPFS-POSIX client.

Important

Metric

100 MB/s/TiB Baseline

200 MB/s/TiB Baseline

File system version number

v2.3.4 and later

v2.3.4 and later

Supported regions

  • China (Hangzhou)

  • China (Shanghai)

  • China (Beijing)

  • China (Hangzhou)

  • China (Shanghai)

  • China (Beijing)

Throughput

min{0.1 × storage capacity (GiB), 30,000} MBps

min{0.2 × storage capacity (GiB), 45,000} MBps

The throughput can reach up to 100,000 MBps. To request a higher throughput, submit a ticket.

IOPS

min{15 × storage capacity (GiB), 3,600,000}

min{30 × storage capacity (GiB), 7,200,000}

The IOPS can reach up to 10,000,000. To request a higher IOPS, submit a ticket.

Average single-stream 4k read latency

0.6 ms

0.4 ms

Average single-stream 4k write latency

0.8 ms

0.6 ms

CPFS-NFS

After you enable the CPFS protocol service, access a general-purpose CPFS file system using a CPFS-NFS client. The protocol service provides NFS mount targets that are independent of POSIX mount targets. The General-purpose Edition offers two NFSv3 protocol service types: General-purpose and Cache. The following table compares the metrics for both types. Select the protocol service type that meets your business needs.

Protocol service type

Metric

100 MB/s/TiB Baseline

(LRS*)

200 MB/s/TiB Baseline

(LRS*)

100 MB/s/TiB Baseline

(ZRS*)

This feature is available only to users on the whitelist.

General-purpose

Throughput

Read/Write: min[100 × storage capacity (TiB), 20,000] MB/s.

Read/Write: min[200 × storage capacity (TiB), 20,000] MB/s.

  • Read throughput: min[100 × storage capacity (TiB), 8,750] MB/s

  • Write throughput: min[50 × storage capacity (TiB), 4,375] MB/s

IOPS

Read/Write: min[4,000 × storage capacity (TiB), 960,000]

Read/Write: min[8,000 × storage capacity (TiB), 960,000]

  • Read IOPS: min[4,000 × storage capacity (TiB), 350,000]

  • Write IOPS: min[2,000 × storage capacity (TiB), 175,000]

Single-stream latency

  • Read latency: 0.8 ms

  • Write latency: 0.8 ms

  • Read latency: 0.6 ms

  • Write latency: 0.6 ms

  • Read latency: 3 to 5 ms

  • Write latency: 3 to 5 ms

Maximum throughput per client

600 MB/s

600 MB/s

300 MB/s

Maximum IOPS per client

  • Read: 80,000 IOPS

  • Write: 30,000 IOPS

  • Read: 80,000 IOPS

  • Write: 30,000 IOPS

  • Read: 40,000 IOPS

  • Write: 15,000 IOPS

Cache

Throughput

The maximum read bandwidth specified when you create the protocol service. The maximum value is 100 GB/s.

The maximum read bandwidth specified when you create the protocol service. The maximum value is 100 GB/s.

Not supported

IOPS

  • Read: min[7,500 × protocol service bandwidth (GB/s), 15,000 × storage capacity (TiB), 1,900,000]

  • Write: min[4,000 × storage capacity (TiB), 960,000]

  • Read: min[7,500 × protocol service bandwidth (GB/s), 30,000 × storage capacity (TiB), 1,900,000]

  • Write: min[8,000 × storage capacity (TiB), 960,000]

Not supported

Single-stream latency

  • Read latency (cache hit): 0.2 ms

  • Read latency (cache miss): 0.8 ms

  • Write latency: 0.8 ms

  • Read latency (cache hit): 0.2 ms

  • Read latency (cache miss): 0.6 ms

  • Write latency: 0.6 ms

Not supported

Maximum throughput per client

1.1 GB/s

1.1 GB/s

Not supported

Maximum IOPS per client

  • Read: 90,000 IOPS

  • Write: 40,000 IOPS

  • Read: 90,000 IOPS

  • Write: 40,000 IOPS

Not supported

* LRS refers to locally redundant storage, and ZRS refers to zone-redundant storage.

Recommendations for choosing between CPFS-POSIX and CPFS-NFS

If you do not have extreme performance requirements, enable the General-purpose protocol service in the console and use a CPFS-NFS client to access the general-purpose CPFS file system for a better user experience.

CPFS-NFS supports the following operating systems:

Operating system

Version

Alibaba Cloud Linux

  • Alibaba Cloud Linux 3.2104 64-bit

  • Alibaba Cloud Linux 2.1903 64-bit

CentOS

  • CentOS 8.x 64-bit

  • CentOS 7.x 64-bit

Ubuntu

  • Ubuntu 20.04 64-bit

  • Ubuntu 18.04 64-bit

  • Ubuntu 16.04 64-bit

Debian

  • Debian 10.x 64-bit

  • Debian 9.x 64-bit

  • Debian 8.x 64-bit

If you require extreme performance and your environment meets all the following conditions, use a CPFS-POSIX client:

  • You do not rely on the Container Storage Interface (CSI) to access CPFS.

  • You do not use mmap.

  • Your operating system is one of the following versions:

    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 versions

    Red Hat Enterprise Linux (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

Dataflow performance

Dataflow is not supported for CPFS file systems that use ZRS.

CPFS General-purpose Edition supports dataflow with Object Storage Service (OSS). Creation of a dataflow task automatically synchronizes metadata from an OSS bucket, making the OSS data accessible for high-performance processing through the POSIX-compatible file interface. Conversely, data can be exported from the CPFS file system back to an OSS bucket via the console or OpenAPI. The relevant performance metrics are detailed in the following table.

OperationMetricDescription
Data importThe throughput of files that are larger than 1 GB.
  • The throughput of a single file is 200 MB/s.
  • The throughput of multiple files reaches the level of bandwidth.
The IOPS of files that are larger than 1 MB.The IOPS of one or more directories is 1000.
Data exportThe throughput of files that are larger than 1 GB.
  • The throughput of a single file is 200 MB/s.
  • The throughput of multiple files reaches the level of bandwidth.
The IOPS of files that are larger than 1 MB.The IOPS of one or more directories is 600.
Data deletionOPSThe IOPS of one or more directories is 2000.
On-demand data loadingThe throughput of files that are larger than 1 GB.
  • The throughput of a single file is 200 MB/s.
  • The throughput of multiple files reaches the level of bandwidth.
The IOPS of files that are larger than 1 MB.The IOPS of one or more directories is 1000.
Automatic metadata updateOPS
  • Dataflows at 600 MB/s: 2000.
  • Dataflows at 1200 MB/s: 3000.
  • Dataflows at 1500 MB/s: 4000.

Capacity specifications

LRS

  • Initial capacity: 3600 GiB

  • Scaling step size: 1200 GiB

  • Maximum capacity: 1 PiB

ZRS

  • Initial capacity: 500 GiB

  • Scaling step size: 100 GiB

  • Maximum capacity: Approximately 88 TiB (89,600 GiB)

References