Performance metrics for IBM Spectrum Scale

Monitor the performance metrics that are collected for IBM Storage Scale storage systems.

Overview

The performance metrics are divided into the following categories:

Node performance metrics

You can view the following metrics for each IBM Storage Scale cluster node.

Table 1. Metrics for nodes
Metric Definition
CPU Utilization (User) The average percentage of time that the processors on a node are busy doing user tasks.
CPU Utilization (System) The average percentage of time that the processors on a node are busy doing system tasks.
CPU Utilization (Total) The average percentage of time that the processors on a node are busy doing user tasks and system tasks.
Memory Used (Cache and Buffer) The average percentage of memory on a node that is used for cache and buffer memory.
Memory Used The average percentage of memory that is used on a node. This value does not include the memory that is used for cache and buffer memory.
Memory Used (Total) The average percentage of memory that is used on a node. This value includes the memory that is used for cache and buffer memory.
I/O Rate (Read) The average number of read operations per second.
I/O Rate (Write) The average number of write operations per second.
I/O Rate (Total) The average number of read operations and write operations per second.

File system performance metrics

You can view file system metrics for the following resources:
  • File systems
  • IBM Storage Scale storage systems
    Tip: For a storage system, the metrics contain summary values for all the file systems on the storage system.
Table 2. Metrics for file systems
Metric Definition
Data Rate (Read) The average number of MiB per second that are transferred for read operations.
Data Rate (Write) The average number of MiB per second that are transferred for write operations.
Data Rate (Total) The average number of MiB per second that are transferred for read operations and write operations.
Maximum Data Rate (Read) The maximum number of MiB per second that are transferred for read operations.
Maximum Data Rate (Write) The maximum number of MiB per second that are transferred for write operations.
Maximum Data Rate (Total) The maximum number of MiB per second that are transferred for read operations and write operations.
I/O Rate (Read) The average number of read operations per second.
I/O Rate (Write) The average number of write operations per second.
I/O Rate (Total) The average number of read operations and write operations per second.
Maximum I/O Rate (Read) The maximum number of read operations per second.
Maximum I/O Rate (Write) The maximum number of write operations per second.
Maximum I/O Rate (Total) The maximum number of read operations and write operations per second.
Response Time (Read) The average number of milliseconds for the back-end storage resources to respond to a read operation from the file system.
Response Time (Write) The average number of milliseconds for the back-end storage resources to respond to a write operation from the file system.
Response Time (Overall) The average number of milliseconds for the back-end storage resources to respond to a read operation or a write operation from the file system.