Disk Activity Test

On Linux systems, the test will return the input/output utilization of each "device" on the system. The device name is in the format "hdiskn" for 2.2 kernels, where "n" is the device number. For newer Linux kernels though, the device name is displayed as "devm-n", where m is the major number of the device, and n a distinctive number.

Target of the test : Any host system

Agent deploying the test : An internal agent

Outputs of the test : One set of results for each host monitored

Configurable parameters for the test
  1. Test period - How often should the test be executed
  2. Host - The host for which the test is to be configured.
  3. useexe - Setting the USEEXE flag to true, ensures that the disk activity metrics are collected by executing a binary instead of dynamically linking to the Performance instrumentation library. By default, this is set to false.
  4. disks- To obtain disk activity metrics for both logical and physical disks, enter all in the DISKS text box. To collect metrics for physical disks, set the DISKS parameter to Physical and to collect metrics for logical disks, set the parameter to Logical.

  5. use sudo – This parameter is of significance to Linux and Solaris platforms only. By default, the USE SUDO parameter is set to No. This indicates that, by default, this test will report the detailed diagnosis for the Disk busy measure of each disk partition being monitored by executing the /usr/bin/iotop command or /usr/sbin/iotop command. However, in some highly secure environments, the eG agent install user may not have the permissions to execute this command directly. In such cases, do the following:

    • Edit the sudoers file on the target host and append an entry of the following format to it:

      <eG_agent_install_user> ALL=(ALL) NOPASSWD:<Command_with_path>

      For instance, if the eG agent install user is eguser, then the entries in the sudoers file should be:

      eguser ALL=(ALL) NOPASSWD: /usr/bin/iotop

      eguser ALL=(ALL) NOPASSWD: /usr/sbin/iotop

    • Finally, save the file.
    • Then, when configuring the test using the eG admin interface, set the use sudo parameter to Yes. This will enable the eG agent to execute the sudo /usr/bin/iotop command or sudo /usr/sbin/iotop  and retrieve the detailed diagnosis of the Disk busy measure.
  6. iotop location - By default, the IOTOP Location parameter is set to none. This indicates that the eG agent would automatically discover the default location of the iotop package i.e. /usr/bin or /usr/sbin, for executing the sudo command when the use sudo flag is set to yes. However, if the iotop package is installed in a different location in your environment, then specify that location in the iotop location text box.

  7. HIGH SECURITY - This flag is applicable only when the target Linux host is monitored in agentless manner. In highly secure environments, eG Enterprise could not perform agentless monitoring on a Linux host using SSH. To enable monitoring of the Linux hosts in such environments, set the HIGH SECURITY flag to Yes. It indicates that eG Enteprise will connect to the target Linux host in a more secure way and collect performance metrics. By default, this flag is set to No.

  8. DETAILED DIAGNOSIS – To make diagnosis more efficient and accurate, the eG Enterprise suite embeds an optional detailed diagnostic capability. With this capability, the eG agents can be configured to run detailed, more elaborate tests as and when specific problems are detected. To enable the detailed diagnosis capability of this test for a particular server, choose the On option. To disable the capability, click on the Off option.

    The option to selectively enable/disable the detailed diagnosis capability will be available only if the following conditions are fulfilled:

    • The eG manager license should allow the detailed diagnosis capability
    • Both the normal and abnormal frequencies configured for the detailed diagnosis measures should not be 0.
Measurements made by the test
Measurement Description Measurement Unit Interpretation

Disk busy:

Indicates the percentage of elapsed time during which the disk is busy processing requests (i.e., reads or writes).

Percent

Comparing the percentage of time that the different disks are busy, an administrator can determine whether the application load is properly balanced across the different disks.

The detailed diagnosis of this measure will reveal the top-10 I/O-intensive processes executing on the host.

Disk read time:

Indicates the average time in seconds of a read of data from the disk.

Secs

 

Disk write time:

Indicates the average time in seconds of a write of data from the disk.

Secs

 

Data read rate from disk:

Indicates the rate at which bytes are transferred from the disk during read operations.

KB/Sec

A very high value indicates an I/O bottleneck on the server.

Data write rate to disk:

Indicates the rate at which bytes are transferred from the disk during write operations.

KB/Sec

A very high value indicates an I/O bottleneck on the server.

Disk service time:

Indicates the average time that this disk took to service each transfer request ( i.e., the average I/O operation time)

Secs

A sudden rise in the value of this measure can be attributed to a large amount of information being input or output. A consistent increase however, could indicate an I/O processing bottleneck.

Disk queue time:

Indicates the average time that transfer requests waited idly on queue for this disk.

Secs

Ideally, the value of this measure should be low.

Disk response time:

Indicates the average time taken for read  and write operations of this disk.

Secs

The value of this measure is the sum of the values of the Disk service time and Disk queue time measures.

A consistent increase in the value of this measure could indicate a latency in I/O processing.

Disk read rate:

Indicates the number of reads happening on a logical disk per second.

Reads/Sec

A dramatic increase in this value may be indicative of an I/O bottleneck on the server.

Disk write rate:

Indicates the number of writes happening on a local disk per second.

Writes/Sec

A dramatic increase in this value may be indicative of an I/O bottleneck on the server.

Avg queue length:

Indicates the average number of both read and write requests that were queued for the selected disk during the sample interval.

Number

 

Avg IO read size:

Indicates the average number of bytes transferred from disk during read operations.

KB

Larger I/Os tend to have higher latency (for example, BACKUP/RESTORE operations issue 1 MB transfers by default).

Avg IO write size:

Indicates the average number of bytes transferred into disk during write operations.

KB

Split IO:

Reports the rate at which the operating system divides I/O requests to the disk into multiple requests.

Splits/Sec

A split I/O request might occur if the program requests data in a size that is too large to fit into a single request or if the disk is fragmented. Factors that influence the size of an I/O request can include application design, the file system, or drivers. A high rate of split I/O might not, in itself, represent a problem. However, on single-disk systems, a high rate for this counter tends to indicate disk fragmentation.

This measure is reported for Windows VMs only.

Avg IO read size:

Indicates the average number of both read and write requests that were queued for the selected disk during the sample interval.

 

 

Avg IO write size:

Indicates the average number of both read and write requests that were queued for the selected disk during the sample interval.

 

 

Split IO:

Indicates the average number of both read and write requests that were queued for the selected disk during the sample interval.

 

 

Note:

  • For this test to report measures on Unix systems, the sysstat package must be installed on the server (check for the existence of the iostat command on the target system).
  • For this test to report measures on Linux systems in particular, the iotop command should exist on the system.
  • If the sysstat version installed on the target server is less than 4.0.7, the following measures also will not be available – Data read rate from disk and Data write rate to disk.