Akamas Docs
3.5
3.5
  • Home
  • Getting started
    • Introduction
    • Free Trial
    • Licensing
    • Deployment
      • Cloud Hosting
    • Security
    • Maintenance & Support (M&S) Services
      • Customer Support Services
      • Support levels for Customer Support Services
      • Support levels for software versions
      • Support levels with Akamas
  • Installing
    • Architecture
    • Docker compose installation
      • Prerequisites
        • Hardware Requirements
        • Software Requirements
        • Network requirements
      • Install Akamas dependencies
      • Install the Akamas Server
        • Online installation mode
          • Online installation behind a Proxy server
        • Offline installation mode
        • Changing UI Ports
        • Setup HTTPS configuration
      • Troubleshoot Docker installation issues
    • Kubernetes installation
      • Prerequisites
        • Cluster Requirements
        • Software Requirements
      • Install Akamas
        • Online Installation
        • Offline Installation - Private registry
      • Installing on OpenShift
      • Accessing Akamas
      • Useful commands
    • Install the CLI
      • Setup the CLI
      • Initialize the CLI
      • Change CLI configuration
      • Use a proxy server
    • Verify the installation
    • Installing the toolbox
    • Install the license
    • Manage anonymous data collection
  • Managing Akamas
    • Akamas logs
    • Audit logs
    • Upgrade Akamas
      • Docker compose
      • Kubernetes
    • Monitor Akamas status
    • Backup & Recover of the Akamas Server
    • Users management
      • Accessing Keycloak admin console
      • Configure an external identity provider
        • Azure Active Directory
        • Google
      • Limit users sessions
        • Local users
        • Identity provider users
    • Collecting support information
  • Using
    • System
    • Telemetry
    • Workflow
    • Study
      • Offline Study
      • Live Study
        • Analyzing results of live optimization studies
      • Windowing
      • Parameters and constraints
  • Optimization Guides
    • Optimize application costs and resource efficiency
      • Kubernetes microservices
        • Optimize cost of a Kubernetes deployment subject to Horizontal Pod Autoscaler
        • Optimize cost of a Kubernetes microservice while preserving SLOs in production
        • Optimize cost of a Java microservice on Kubernetes while preserving SLOs in production
      • Application runtime
        • Optimizing a sample Java OpenJDK application
        • Optimizing cost of a Node.js application with performance tests
        • Optimizing cost of a Golang application with performance tests
        • Optimizing cost of a .NET application with performance tests
      • Applications running on cloud instances
        • Optimizing a sample application running on AWS
      • Spark applications
        • Optimizing a Spark application
    • Optimize application performance and reliability
      • Kubernetes microservices
        • Optimizing cost of a Kubernetes microservice while preserving SLOs in production
        • Optimizing cost of a Java microservice on Kubernetes while preserving SLOs in production
      • Applications running on cloud instances
      • Spark applications
  • Integrating
    • Integrating Telemetry Providers
      • CSV provider
        • Install CSV provider
        • Create CSV telemetry instances
      • Dynatrace provider
        • Install Dynatrace provider
        • Create Dynatrace telemetry instances
          • Import Key Requests
      • Prometheus provider
        • Install Prometheus provider
        • Create Prometheus telemetry instances
        • CloudWatch Exporter
        • OracleDB Exporter
      • Spark History Server provider
        • Install Spark History Server provider
        • Create Spark History Server telemetry instances
      • NeoLoadWeb provider
        • Install NeoLoadWeb telemetry provider
        • Create NeoLoadWeb telemetry instances
      • LoadRunner Professional provider
        • Install LoadRunner Professional provider
        • Create LoadRunner Professional telemetry instances
      • LoadRunner Enterprise provider
        • Install LoadRunner Enterprise provider
        • Create LoadRunner Enterprise telemetry instances
      • AWS provider
        • Install AWS provider
        • Create AWS telemetry instances
    • Integrating Configuration Management
    • Integrating with pipelines
    • Integrating Load Testing
      • Integrating NeoLoad
      • Integrating LoadRunner Professional
      • Integrating LoadRunner Enterprise
  • Reference
    • Glossary
      • System
      • Component
      • Metric
      • Parameter
      • Component Type
      • Workflow
      • Telemetry Provider
      • Telemetry Instance
      • Optimization Pack
      • Goals & Constraints
      • KPI
      • Optimization Study
      • Workspace
      • Safety Policies
    • Construct templates
      • System template
      • Component template
      • Parameter template
      • Metric template
      • Component Types template
      • Telemetry Provider template
      • Telemetry Instance template
      • Workflows template
      • Study template
        • Goal & Constraints
        • Windowing policy
          • Trim windowing
          • Stability windowing
        • Parameter selection
        • Metric selection
        • Workload selection
        • KPIs
        • Steps
          • Baseline step
          • Bootstrap step
          • Preset step
          • Optimize step
        • Parameter rendering
        • Optimizer Options
    • Workflow Operators
      • General operator arguments
      • Executor Operator
      • FileConfigurator Operator
      • LinuxConfigurator Operator
      • WindowsExecutor Operator
      • WindowsFileConfigurator Operator
      • Sleep Operator
      • OracleExecutor Operator
      • OracleConfigurator Operator
      • SparkSSHSubmit Operator
      • SparkSubmit Operator
      • SparkLivy Operator
      • NeoLoadWeb Operator
      • LoadRunner Operator
      • LoadRunnerEnteprise Operator
    • Telemetry metric mapping
      • Dynatrace metrics mapping
      • Prometheus metrics mapping
      • NeoLoadWeb metrics mapping
      • Spark History Server metrics mapping
      • LoadRunner metrics mapping
    • Optimization Packs
      • Linux optimization pack
        • Amazon Linux
        • Amazon Linux 2
        • Amazon Linux 2022
        • CentOS 7
        • CentOS 8
        • RHEL 7
        • RHEL 8
        • Ubuntu 16.04
        • Ubuntu 18.04
        • Ubuntu 20.04
      • DotNet optimization pack
        • DotNet Core 3.1
      • Java OpenJDK optimization pack
        • Java OpenJDK 8
        • Java OpenJDK 11
        • Java OpenJDK 17
      • OpenJ9 optimization pack
        • IBM J9 VM 6
        • IBM J9 VM 8
        • Eclipse Open J9 11
      • Node JS optimization pack
        • Node JS 18
      • GO optimization pack
        • GO 1
      • Web Application optimization pack
        • Web Application
      • Docker optimization pack
        • Container
      • Kubernetes optimization pack
        • Kubernetes Pod
        • Kubernetes Container
        • Kubernetes Workload
        • Kubernetes Namespace
        • Kubernetes Cluster
      • WebSphere optimization pack
        • WebSphere 8.5
        • WebSphere Liberty ND
      • AWS optimization pack
        • EC2
        • Lambda
      • PostgreSQL optimization pack
        • PostgreSQL 11
        • PostgreSQL 12
      • Cassandra optimization pack
        • Cassandra
      • MySQL Database optimization pack
        • MySQL 8.0
      • Oracle Database optimization pack
        • Oracle Database 12c
        • Oracle Database 18c
        • Oracle Database 19c
        • RDS Oracle Database 11g
        • RDS Oracle Database 12c
      • MongoDB optimization pack
        • MongoDB 4
        • MongoDB 5
      • Elasticsearch optimization pack
        • Elasticsearch 6
      • Spark optimization pack
        • Spark Application 2.2.0
        • Spark Application 2.3.0
        • Spark Application 2.4.0
    • Command Line commands
      • Administration commands
      • User and Workspace management commands
      • Authentication commands
      • Resource management commands
      • Optimizer options commands
    • Release Notes
  • Knowledge Base
    • Creating custom optimization packs
    • Setting up a Konakart environment for testing Akamas
    • Modeling a sample Java-based e-commerce application (Konakart)
    • Optimizing a web application
    • Optimizing a sample Java OpenJ9 application
    • Optimizing a sample Linux system
    • Optimizing a MongoDB server instance
    • Optimizing a Kubernetes application
    • Leveraging Ansible to automate AWS instance management
    • Guidelines for optimizing AWS EC2 instances
    • Optimizing an Oracle Database server instance
    • Optimizing an Oracle Database for an e-commerce service
    • Guidelines for optimizing Oracle RDS
    • Optimizing a MySQL server database running Sysbench
    • Optimizing a MySQL server database running OLTPBench
    • Optimizing a live full-stack deployment (K8s + JVM)
    • Setup Instana integration
Powered by GitBook
On this page
  • Using
  • Operator arguments
  • Supported Component Properties
  • Filter parameters and block/network devices
  • Examples
  • How are parameters applied to the system?

Was this helpful?

Export as PDF
  1. Reference
  2. Workflow Operators

LinuxConfigurator Operator

The LinuxConfigurator operator allows configuring systems tuned by Akamas by applying parameters related to the Linux kernel using different strategies.

The operator can configure provided Components or can configure every Component which has parameters related to the Linux kernel.

The parameters are applied via SSH protocol.

Using

In the most basic use of the Operator, it is sufficient to add a task of type LinuxConfigurator in the workflow.

- name: LinuxConf
  operator: LinuxConfigurator
  arguments:
    component: ComponentName

The operator makes use of properties specified in the component to identify which instance should be configured, how to access it, and any other information required to apply the configuration.

Operator arguments

Name

Type

Value restrictions

Required

Default

Description

component

String

It should match the name of an existing Component of the System under test

No

The name of the Component for which available Linux kernel parameters will be configured

If no component is provided, this operator will try to configure every parameter defined for the Components of the System under test

Supported Component Properties

The following table highlights the properties that can be specified on components and are used by this operator.

Name

Type

Value restrictions

Required

Default

Description

hostname

String

It should be a valid SSH host address

Yes

SSH host address

sshPort

Integer

1≤sshPort≤65532

Yes

22

SSH port

username

String

Yes

SSH login username

key

Multiline string

Either key or password is required

SSH login key, provided directly its value or the path of the file to import from. The operator supports RSA and DSA Keys

password

String

Either key or password is required

blockDevices

List of objects

No

Allows the user to restrict and specify to which block-device apply block-device-related parameters

networkDevices

List of objects

No

Allows the user to restrict and specify to which network-device apply network-device-related parameters

Filter parameters and block/network devices

The properties blockDevices and networkDevices allow specifying which parameters to apply to each block/network-device associated with the Component, as well as which block/network-device should be left untouched by the LinuxConfigurator.

If the properties are omitted, then all block/network-devices associated with the Component will be configured will all the available related parameters.

All block-devices called loopN (where N is an integer number greater or equal to 0) are automatically excluded from the Component’s block-devices

The properties blockDevices and networkDevices are lists of objects with the following structure:

Name

Type

Value restrictions

Required

Default

Description

name

String

It should be a valid regular expression to match block/network-devices

Yes

A regular expression that matches block/network-devices to configure with related parameters of the Component

parameters

List of strings

It should contain the names of matching parameters of the Component

No

The list of parameters to be configured for the specified block/network-devices. If the list is empty, then no parameter will be applied for the block/network-devices matched by name

Examples

blockDevices:
- name: "xvd[a-z]"
  parameters:
    - os_StorageReadAhead
    - os_StorageQueueScheduler

In this example, only the parameters os_StorageReadAhead and os_StorageQeueuScheduler are applied to all the devices that match the regex "xvd[a-z]" (i.e. xvda, xvdb, …, xvdc).

blockDevices:
- name: "xvdb|loop0"
  parameters:
    - os_StorageMaxSectorsKb

In these examples, only the parameter os_StorageMaxSectorKb is applied to block device xvdb and loop0.

Note that the parameter is applied also to the block device loop0, since it is specified in the name filter, this overrides the default behavior since loopN devices are excluded by the Linux Optimization Pack

networkDevices:
  - name: wlp4s0
    parameters: []

In this example, no parameters are applied to the wlp4s0 network device, which is therefore excluded from the optimization.

How are parameters applied to the system?

To support the scenario in which some configuration parameters related to the Linux kernel may be applied using the strategies supported by this operator, while others with other strategies (e.g, using a file to be written on a remote machine), it is necessary to specify which parameters should be applied with the LinuxConfigurator, and this is done at the ComponentType level; moreover, still at the ComponentType level, it is necessary to specify which strategy should be used to configure each parameter. This information is already embedded in the Linux Optimization pack and, usually, no customization is required.

Sysctl strategy

With this strategy, a parameter is configured by leveraging the sysctl utility. The sysctl variable to map to the parameter that needs to be configured is specified using the key argument.

name: Component Type 1
description: My Component type
parameters:
  - name: net_forwarding
    domain:
      type: integer
      domain: [0, 1]
    defaultValue: 1
    operators:
      # the parameter is configured using LinuxConfigurator
      LinuxConfigurator:
        sysctl:
          key: net.ipv4.forwarding

Echo strategy

With this strategy, a parameter is configured by echoing and piping its value into a provided file. The path of the file is specified using the file argument.

name: Component Type 1
description: My Component type
parameters:
  - name: os_MemoryTransparentHugepageEnabled
    domain:
      type: categorical
      categories: [always, never]
    defaultValue: always
    operators:
      LinuxConfigurator:
        echo:
          file: /sys/kernel/mm/transparent_hugepage/enabled

Map strategy

With this strategy, each possible value of a parameter is mapped to a command to be executed on the machine the LinuxConfigurator operates on(this is especially useful for categorical parameters).

name: Component Type 1
description: My Component type
parameters:
  - name: os_MemorySwap
    domain:
      type: categorical
      categories: [swapon, swapoff]
    defaultValue: swapon
    operators:
      LinuxConfigurator:
        map:
          swapon: command1
          swapoff: command2

Command strategy

With this strategy, a parameter is configured by executing a command into which the parameter value is interpolated.

name: Component Type 1
description: My Component type
parameters:
  - name: os_MemorySwap
    domain:
      type: categorical
      categories: [swapon, swapoff]
    defaultValue: swapon
    operators:
      LinuxConfigurator:
        command:
          cmd: sudo ${value} -a

Last updated 1 year ago

Was this helpful?

It should have a structure like the one described in the

It should have a structure like the one described in the

next section
next section