Home
Using the Command Line Interface
You can administer and use MemVerge Memory Machine using the Command Line Interface (CLI) on any installed host.
Managing Application Memory
To manage application memory with Memory Machine, you run the application on a data host in an environment with Transparent Memory Service (TMS) and Distributed Persistent Memory Engine (DPME).
Using Containers with Memory Machine
You can configure Memory Machine to manage memory for containers running in OpenShift or Kubernetes.
The Memory Machine Container Model
To manage containers, Memory Machine runs in a single pod on each container node and manages memory in a local persistent volume (PV). Application container pods on that node mount the PV to gain access to managed memory.

Overview and Installation
Getting started with MemVerge Memory Machine requries that you understand some background information about how persistent memory works. You can then install Memory Machine on a server and begin monitoring memory usage and capturing application snapshots.
Using the Memory Machine Management Center
Memory Machine Management Center (M3C) is a web UI application available on the host that is running the Memory Machine Management Service. You can view system resources and performance metrics; create and restore snapshots; schedule jobs; and more in M3C.
Using the Command Line Interface
You can administer and use MemVerge Memory Machine using the Command Line Interface (CLI) on any installed host.
- MemVerge Memory Machine Administration
  MemVerge Memory Machine can be installed and run using CLI commands.
- Managing Application Memory
  To manage application memory with Memory Machine, you run the application on a data host in an environment with Transparent Memory Service (TMS) and Distributed Persistent Memory Engine (DPME).
  - Calculating Process Count Limits
  - Running an Application in Memory Machine
    To run an application with Memory Machine memory management, use the mm script supplied with Memory Machine.
  - Stopping an Application Instance
    Stop an application instance in whatever manner is recommended for the application you are running.
  - Configuring Application Memory
    Configure managed memory to optimize for individual application instances. You can do this by setting the size of DRAM Tier and configuring Linux HugePages. To facilitate experimentation, these adjustments can be made "on the fly" while the application instance is running.
  - Using Containers with Memory Machine
    You can configure Memory Machine to manage memory for containers running in OpenShift or Kubernetes.
    - The Memory Machine Container Model
      To manage containers, Memory Machine runs in a single pod on each container node and manages memory in a local persistent volume (PV). Application container pods on that node mount the PV to gain access to managed memory.
    - Container Management Overview
      To manage containers in Memory Machine, deploy a Kubernetes or OpenShift® cluster and deploy Memory Machine on the cluster.
    - Configuring the Container Manager
      Configure access to the Memory Machine OpenShift or Kubernetes packages.
    - Configuring HugePages
    - Configuring PMEM
    - Deploying the Container Webhook
    - Deploy the DaemonSet
    - Testing the Container Setup
- Using Snapshots in the Memory Machine CLI
  Use the mvmcli snapshot command from the CLI on a Memory Machine host to capture the state of a running process, then later restore the running process to the captured state.
- Troubleshooting
- Preparing Intel® Optane™ DC Persistent Memory PMEM
  Prepare PMEM for use by configuring the Intel Optane DC Direct Access (DAX) devices in AppDirect mode.
- Preparing to Run an Application
  Normally you run applications by using the mm wrapper script supplied with Memory Machine. See oxy_ex-3/topics/t_mvmm_running_an_application_with_mvmm.html. If you do not use the mm to run your application, you must set up the Memory Machine environment manually before running the application.
Working with Applications
MemVerge provides additional instructions for some popular applications supported by Memory Machine, either to assist with complex setup or to support additional functionality.
All Documentation
Links to documentation for all releases of MemVerge Memory Machine.

The Memory Machine Container Model

To manage containers, Memory Machine runs in a single pod on each container node and manages memory in a local persistent volume (PV). Application container pods on that node mount the PV to gain access to managed memory.

Memory Machine uses a supplied script, config-pmem.sh, to reconfigure the Persistent Memory namespace to fsdax mode. A daemonSet is used to create one Distributed Persistent Memory Engine (DPME) pod on each node. This pod runs mvmallocd, the Memory Machine memory manager.

A local PV is created on top of the configured PMEM fsdax directory. The Memory Machine DPME pod claims the PV, mounts it, and passes the PMEM file to mvmallocd. Application pods can mount this PV through persistent volume claim (PVC); the pods share the domain socket among the application pods and the DPME pod on each node.

See Memory Machine Container Architecture for a high-level picture of the container configuration.

An initContainer in the DPME pod copies Memory Machine binaries and dependent libraries to the shared PV. Before an application pod is started, Memory Machine uses a mutating webhook to inject an initContainer into the pod. The initContainer copies these binaries and libraries to the directories required by Memory Machine. The initContainer also configures Memory Machine environment variables on the application pod.

Figure 1. Memory Machine Container Architecture

For more in-depth information about the Memory Machine container implementation, see the MemVerge container GitHub repository.