Linux disk IO stress

Linux disk IO stress applies stress on the disk of the target Linux machines over I/O operations for a specific duration.

Use cases

• Simulates slower disk operations for the applications.
• Simulates noisy neighbour problems by exhausting the disk bandwidth.
• Verifies the disk performance on increasing I/O threads and varying I/O block sizes.
• Checks how the application functions under high disk latency conditions, when I/O traffic is high and includes large I/O blocks, and when other services monopolize the I/O disks.

note

• This fault can be executed on Ubuntu 16 or higher, Debian 10 or higher, CentOS 7 or higher, RHEL 7 or higher, and openSUSE LEAP 15.4 or higher.
• The linux-chaos-infrastructure systemd service should be in an active state, and the infrastructure should be in CONNECTED state.

Fault tunables

Optional tunables

Tunable	Description	Notes
fileSystemUtilisationBytes	File size consumed for the disk I/O operations (in bytes).	Mutually exclusive with fileSystemUtilisationPercentage
fileSystemUtilisationPercentage	File size consumed during the disk I/O operations (in percentage of the total available disk size).	Mutually exclusive with fileSystemUtilisationBytes. Default: 10%
workers	Number of worker processes to start.	Default: 1
volumeMountPath	Volume mount path used for the disk I/O operations.	Default: user HOME directory
duration	Duration through which chaos is injected into the target resource (in seconds).	Default: 30 s
rampTime	Period to wait before and after injecting chaos (in seconds).	Default: 0 s

Workers

The workers input variable utilizes a specific number of workers during the disk I/O stress.

The following YAML snippet illustrates the use of this environment variable:

# workers to utilize
apiVersion: litmuchaos.io/v1alpha1
kind: LinuxFault
metadata:
  name: linux-disk-io-stress
  labels:
    name: disk-io-stress
spec:
  stressChaos/inputs:
    workers: 1
    fileSystemUtilisationPercentage: 10

File system utilization in bytes

The fileSystemUtilisationBytes input variable utilizes a specific amount of file system disk space or bandwidth as a part of the disk I/O operations in bytes.

The following YAML snippet illustrates the use of this environment variable:

# file system amount to be utilized
apiVersion: litmuchaos.io/v1alpha1
kind: LinuxFault
metadata:
  name: linux-disk-io-stress
  labels:
    name: disk-io-stress
spec:
  stressChaos/inputs:
    workers: 3
    fileSystemUtilisationBytes: 10000

File system utilization in percentage

The fileSystemUtilisationPercentage input variable utilizes a specific amount of file system disk space or bandwidth as a part of the disk I/O operations in terms of percentage of the total available disk space.

The following YAML snippet illustrates the use of this environment variable:

# file system percentage to be utilized
apiVersion: litmuchaos.io/v1alpha1
kind: LinuxFault
metadata:
  name: linux-disk-io-stress
  labels:
    name: disk-io-stress
spec:
  stressChaos/inputs:
    workers: 3
    fileSystemUtilisationPercentage: 70

Volume mount path

The volumeMountPath input variable utilizes the volume mount path where the disk I/O operations are performed.

The following YAML snippet illustrates the use of this environment variable:

# configure volume mount path
apiVersion: litmuchaos.io/v1alpha1
kind: LinuxFault
metadata:
  name: linux-disk-io-stress
  labels:
    name: disk-io-stress
spec:
  stressChaos/inputs:
    workers: 1
    fileSystemUtilisationPercentage: 50
    volumeMountPath: "/tmp"