All Products
Search
Document Center

Cloud Parallel File Storage:Data monitoring

Last Updated:Jun 22, 2026

Cloud Parallel File Storage (CPFS) General-purpose Edition integrates with CloudMonitor to track file system capacity, read/write throughput, and IOPS. Configure alert rules to receive notifications when metrics exceed specified thresholds.

Background

CloudMonitor monitors Alibaba Cloud resources and internet applications. You can track resource metrics, configure alert rules, and maintain application availability. For more information, see What is CloudMonitor?

Retention policy of monitoring data

Monitoring data is retained for 90 days from the time it is generated and then automatically cleared.

Metrics

CPFS integrates with CloudMonitor to monitor file system capacity, performance, and NFS protocol services.

Capacity monitoring

Note
  • Capacity monitoring requires CPFS General-purpose Edition V2.3.1 or later. To check the version, go to the NAS console, open the File Systems page, and click the target CPFS General-purpose Edition file system name to view its version on the Basic Information page.

  • The root fileset is the root directory of the file system. All files that are not in independently created filesets belong to the root fileset.

Type

Metric

Metric name

Unit

Description

File system

CPFSCapacity

Total storage capacity

Bytes

Total storage capacity of the file system per collection period.

CPFSCapacityUsed

Data volume

Bytes

Actual data volume consumed by the file system per collection period.

CPFSInode Limit

Maximum number of files

Unit

Maximum number of files allowed in the file system per collection period.

CPFSInode Alloc

Number of allocated files

Unit

Number of files allocated in the file system per collection period.

CPFSInode Used

Number of used files

Unit

Number of files in use in the file system per collection period.

Fileset

FsetInode Used

Number of used files in the fileset

item

Number of files in use in the fileset per collection period.

FsetInode Alloc

Number of allocated files in the fileset

Unit

Number of files allocated in the fileset per collection period.

Performance monitoring

Type

Metric

Metric name

Unit

Description

File system

ThruputRead

Read throughput

Bytes/s

Average read throughput (bytes/s) of the file system per collection period.

ThruputWrite

Write throughput

Bytes/s

Average write throughput (bytes/s) of the file system per collection period.

IopsRead

Read IOPS

Count/s

Average number of read I/O operations per second for the file system per collection period.

IopsWrite

Write IOPS

Count/s

Average number of write I/O operations per second for the file system per collection period.

LatencyRead

Read latency

ms

Average read latency (ms) of the file system per collection period.

LatencyWrite

Write latency

ms

Average write latency (ms) of the file system per collection period.

QpsMeta

Metadata QPS

Count/s

Average number of metadata requests per second for the file system per collection period. Includes open, close, stat, create, and chmod operations.

NFS protocol service

NFSReadThroughput

NFS read throughput

Bytes/s

Average read throughput (bytes/s) of the NFS protocol service per collection period.

NFSWriteThroughput

NFS write throughput

Bytes/s

Average write throughput (bytes/s) of the NFS protocol service per collection period.

NFSRead IOPS

NFS read IOPS

Count/s

Average number of read I/O operations per second for the NFS protocol service per collection period.

NFSWrite IOPS

NFS write IOPS

Count/s

Average number of write I/O operations per second for the NFS protocol service per collection period.

Alert rules

You can configure alert rules for metrics in the CloudMonitor console. When a metric value meets an alert condition, CloudMonitor sends notifications to the specified recipients. The following table describes the alert severity levels, notification methods, and conditions.

Alert severity

Notification method

Alert condition

Critical

Phone call, Short Message Service (SMS) message, Email, and DingTalk chatbot

An alert triggers when the average metric value reaches the specified threshold for N consecutive cycles. Set N based on the alert severity.

Note

Alert conditions vary by metric type. Refer to the console for details.

Warning

SMS message, Email, and DingTalk chatbot

Info

Email and DingTalk chatbot

Next steps