Microsoft Storage Optimized Azure VMs Deliver Higher Performance for Data Intensive Workloads

By Sasha Melamed, senior product manager, Azure Compute Platform, Microsoft Corp.

The company announced the general availability of the Lsv3 and Lasv3 series Azure Virtual VMs. These storage optimized L-series VMs offer high local disk capacity, throughput, and IO/s, along with low SSD access latency. These VMs are suited for big data, SQL, NoSQL databases, data analytics, and data warehousing. Examples include Cassandra, MongoDB, Cloudera, Spark, ElasticSearch, Redis, and other data-intensive applications.

The Lasv3 and Lsv3 VMs run on the latest AMD and Intel processors, respectively. These VMs deliver new capabilities that Azure customers will appreciate – faster CPUs, while maintaining excellent local NVMe IO/s and throughput. Customers reported up to 2x higher performance versus Lsv2 VMs (depending on the workload).

Additional improvements include:

• Networking and remote storage throughputs have been increased by up to 290% (depending on the VM size).
• Added support for Memory Preserving Updates.
• Added support for Nested Virtualization.
• Added support for flexible orchestration mode for Virtual Machine Scale Sets (VMSS).

The Lasv3-series runs on the 3rd gen AMD EPYC 7763v processor with up to 256MB L3 cache, which can achieve a maximum frequency of 3.5GHz.

The Lsv3-series runs on the 3rd gen Intel Xeon Platinum 8370C (Ice Lake) processor featuring an all-core turbo clock speed of 3.5GHz with Intel Turbo Boost Technology, Advanced-Vector Extensions 512 (AVX-512) and Intel DL Boost.

Partners excited about Lasv3 and Lsv3 VMs
Customers and partners from all over the globe and across a range of industries participated in the preview and shared with Microsoft their excitement about the new storage optimized VMs and their performance. Companies like Databricks, Silk, SAS, and the Microsoft Azure Data Explorer team tested the performance of these VMs.

The Databricks Lakehouse Platform combines the elements of data lakes and data warehouses to deliver the reliability, strong governance and performance of data warehouses with the openness, flexibility and ML support of data lakes.

“At Databricks, we’ve evaluated the Lsv3 and Lasv3 Azure VMs for the lakehouse using a comprehensive series of benchmarks that reflect common and critical patterns present in real-world analytics workloads. Relative to an Lsv2 VM series baseline for several customer representative dataset sizes, we measured throughput improvements ranging from 1.5x to 2.7x and with price/performance improvements ranging from 1.3x to 2.3x. The v3 L-series’ local NVMe devices and faster CPU options enable Databricks Photon, the native vectorized query engine, to deliver leading price/performance for the most demanding data warehousing workloads. We are excited to enable and recommend the v3 L-series VMs with Photon to Azure Databricks customers that have workloads with high storage and IO requirementsn,” said Zach Christopherson, staff performance engineer, Databricks.

The Silk Cloud Platform is a virtualization layer between your cloud infrastructure and databases – delivering game-changing performance.

“Silk uses the LS series VMs to underpin our Cloud Platform on Azure. Their excellent performance profile combined with the extremely fast ephemeral media make them ideal for modern cloud architectures. We have tested the new capabilities of the Lsv3 and Lasv3 versions including the support of data encryption and have seen incredible performance significantly faster than the v2. We combine them together using Azure availability sets to make them HA and use them to accelerate mission critical database workloads. We are pleased to add support for the Lsv3 and Lasv3 to our product,” said Tom O’Neill, CTO, Silk.

Elastic is a data analytics platform for search-powered solutions.

“At Elastic, we tested the new Lasv3-series Azure Virtual Machines (VMs) running on AMD’s 3rd Generation EPYC 7763v processor. Across the benchmarks that represent the performance of common use-case patterns of customers using Elasticsearch, we saw up to 35% better price-performance compared to previous generation Lsv2-series VMs running on AMD’s 1st Generation EPYC 7551 processor. We are excited about the introduction of Lasv3-series VMs which promises to provide improved price-performance for Elasticsearch users deploying on Azure,” said Yuvraj Gupta, senior product manager, Elastic

SAS is a provider in analytics. Through software and services, it empowers and inspires customers around the world to transform data into intelligence.

“Microsoft has introduced the Lsv3 Azure Virtual Machines series for application that require high IO throughput for both external (persistent) and internal (ephemeral) storage to process large volumes of data. We have run several computationally and IO intensive tests to measure concurrent, mixed analytics workload performance. The Lsv3 VMs, with their new NVMe ephemeral storage, can offer overall performance to meet our SAS application requirements. We are excited to start using the Lsv3 Vms to run SAS data and analytics solution on Azure., said Margaret Crevar, senior manager, software development, SAS R&D, compute services division.

Weka is a data platform on the public cloud delivering first-to-market results with modern workloads including AI and ML.

“Weka is delighted to have participated in the evaluation of the new Lsv3 and Lasv3 instances on the Azure cloud. These new instance types provide a significant boost in performance compared to prior generation Lsv2. The combination of higher network bandwidth, improved CPU processing and memory resulted In a doubling of performance of the Weka Data Platform. This in turn will deliver up to 2x improvement in price/performance for customers. We look forward to leveraging these new powerful instance in the future to deliver high performance for our customers,” said Barbara Murphy, VP, cloud strategy, Weka.

Microsoft Azure Data Explorer is a fast, fully managed data analytics service for real-time analysis on large volumes of data streaming from applications, websites, IoT devices, and more.

“The Lasv3/Lsv3 family is the hardware we have been waiting for to run interactive big data analytics. The combination of a modern, high performance CPU, modern superfast NVME SSD storage in an affordable price is a game changer. Azure Data Explorer with Lasv3 and Lsv3 immediately transfers these benefits to end customers and users. Azure Data Explorer with Lasv3 and Lsv3 dramatically reduces the cost of observation analytics like telemetry, log and time series analysis to a degree that enables scenarios that were not feasible before,” said Uri Barash, principal group PM, Microsoft Corp.

Getting startedTo select the VM for your workload we recommend using the virtual machine selector.

The Lasv3 and Lsv3 VMs feature high-throughput, low latency, and directly mapped local NVMe storage.  These VMs come in sizes from 8 to 80 vCPUs. There are 8GB of memory per vCPU, and 1×1.92TB NVMe SSD device per 8 vCPUs, with up to 19.2TB (10×1.92TB) available on the largest VM sizes.

The Lsv3 VMs are available in more than 20 regions and the Lasv3 VMs are initially available in Central US, East US, South Central US, and West Europe regions with more to follow.

Resources:
To check regional availability, visit Microsoft Azure Products by Region. Check out pricing on the following pages for Windows and Linux.
Documentation for Lasv3-series and Lsv3-series.