SD4Health Resources and Flavours Definitions

Contents

High Availability (HA) Flavour

This flavour is designed for general-purpose workloads, such as web servers, databases that can't afford being down. The virtual machines in this flavour are optimized for web applications and can handle moderate traffic. Web flavors are VM spawn for host that have hyper threading turned on. These hosts are  located in the High Availability room, which is connected to UPS batteries and Diesel Generators to keep the room running in case of  grid failure.

COMPUTE Flavour

This flavour is designed for compute-intensive workloads, such as batch processing, scientific computing, and high-performance computing. It provides a high-performance computing environment with dedicated CPU resources, high memory, and fast storage. The virtual machines in this flavour are optimized for compute-intensive workloads and can handle large-scale parallel processing. Compute flavors are VM spawn for host that have hyper threading turned off. These host are  located in the Compute room. They are not connected to UPS or Generator. In case of grid failure, these host will shut down.

HI-MEM Flavour

This flavour is designed for memory-intensive workloads, such as large databases, in-memory analytics, and caching. It provides a high-memory computing environment with dedicated memory resources, fast storage, and high-speed networking. The virtual machines in this tier are optimized for memory-intensive workloads and can handle large data sets.

GPU Flavour

This flavour is designed for GPU-intensive workloads, such as machine learning, deep learning, and scientific simulations. It provides a high-performance computing environment with dedicated GPU resources, high memory, and fast storage. The virtual machines in this tier are optimized for GPU-intensive workloads and can handle large-scale parallel processing.

Definitions

GPU

GPU computing is the use of a graphics processing unit (GPU) to accelerate deep learning, analytics, and engineering applications, for example. GPU accelerators now power energy-efficient data centres in government labs, universities, enterprises, and small-and-medium businesses around the world.

vGPU

Stands for virtual graphics processing unit (VGPU). One or more VGPUs can be assigned to Virtual Machines (VM) within a cloud environment. Each VGPU is seen as a single physical GPU device by the VM's operating system.

CPU

Is the abbreviation for central processing unit. Sometimes referred to simply as the central processor, but more commonly called processor, the CPU is the brains of the computer where most calculations take place.

vCPU

Stands for virtual central processing unit. One or more VCPUs are assigned to every Virtual Machine (VM) within a cloud environment. Each VCPU is seen as a single physical CPU core by the VM’s operating system.

vRAM

The amount of memory (RAM) per CPU core

Public IP address

A public IP address that a project can associate with a VM so that the instance has the same public IP address each time that it boots. You create a pool of floating IP addresses and assign them to instances as they are launched to maintain a consistent IP address for maintaining DNS assignment.

SSD Block Storage

SSD block storage efficiently manages data by dividing it into uniform blocks, optimizing fast access and retrieval on the underlying physical storage.

CepthFS SSD

(Ceph File System) A filesystem with Ceph storage, which allows data to be mounted simultaneously on multiple OpenStack instances.

Object Store

Non-hierarchical storage where data is created or uploaded in whole-file form. Persistent object storage space used to store large amounts of data that is mostly read access (such as images and data sets). This is considered 'bulk' storage. Accessible from anywhere in the world. Offered as S3 and Swift protocols. Measured in TB.

Attached SSD

Refers to solid-state drives physically connected to a virtual machine (VM) or instance. SSDs use flash memory to store data, resulting in faster data access speeds and lower latency than traditional hard drives

HDD Storage

A cost-effective storage option in cloud environments, attached HDD storage refers to hard disk drives connected to a virtual machine (VM) or instance. HDDs use spinning disks to read and write data, which leads to higher latency and slower access speeds compared to SSDs. Attached HDD storage is ideal for workloads where affordability and capacity are prioritized over speed.