High Performance MongoDB Clusters on Azure

MongoDB Cluster

Fully managed MongopDB instsnces in your managed MongoDB instances in your own Azure account, or host with us through our Azure Dedicated Clusters plan.

High-performance clusters use powerful CPU’s and premium disks to deliver enhanced performance. Based on our performance tests (details below), our high-performance clusters on Azure deliver 4x the performance of our competition and 2x the performance of our standard clusters. for more info mongodb online training

High-Performance MongoDB: 3-Node Replica Set

Why do our clusters perform so much better? The high performance MongoDB configuration on Azur uses a hybrid of local SSD and premium disks to achieve both high performance and high reliability. A typical configuration is deployed using a 3-node replica set.

• The Primary and the Secondary
• 1. use local SSD disks
• Secondary
• 2. uses an Azure Premium Disk
• Specifications

  High performance clusters are offered in three configurations as detailed below, If you are using the BYOC plan, the sizes can also be customized.

• Performance

  We ran detailed to demonstrate the improved performance, and compared ScaleGrid Azure High Performance XLarge vs. ScaleGrid standard Azure XLarge vs. a competitor with an equivalent size. All configurations are similar with 14GB RAM, and were deployed in Azure region Australia Easy – Sydney.

• ScaleGrid High Performance
• High-Perf XLarge
• DS3_v2
• 14 GB RAM
• 4 cores
• 1024 GB
• Premium SSD disk
• 5000 IOPS
• (2+1) Replica Set
• MongoDB version 3.4.3
• ScaleGrid Standard
  • XLarge
  • D11_v2
  • 14 GB RAM
  • 2 cores
  • 240 GB
  • 4 disk RAID
  • Up to 2000 IOPS
  • (2+1) Replica Set
  • MongoDB version 3.4.3
  • Competitor
• • Azure Dedicated
  • (2 + 1) Replica Set
  • 14 GB RAM
  • 240 GB block storage per node
  • MongoDB version 3.4.4
  Workloads
  • 100 percent Write workload (Workload A Load phase): Write 3 million records into the database at varied levels of loading by increasing the number of client threads from 4 going up to 64, doubling every time.
  • 50 % Read/ 50% update workload (Workload A run phase): Run workload for 6 million operations at varying levels of loading by increasing the number of client threads from 4 going up to 64, doubling every time.
  • Summary
    • With no RAID or premium SSD disks, the competitor’s performance is pretty low. It saturates its block storage at low loads and throughput remains almost flat throughout. CPU saturates completely at 16 threads. Latency growth is almost exponential.
    • With RAID configured, the standard ScaleGrid Azure solution greatly outperforms the competitor as it’s throughput increases almost linearly with load. Latency numbers are also very low. This is expected with a RAID setup and a sequential workload. At their best, our standard Azure solution was more than 3 times better than the competitors!
    • ScaleGrid Azure High Performance deployment with its premium disks outperforms the standard block storage. At it’s best, it is 5 times as fast the competitor’s solution, and about 1.4 times as fast as our standard solution.

    • Openhour wanted to take advantage of all of these innovations for their new MongoDB cluster and we partnered with them on this problem as the ARM script in the repo did not support premium storage. Our team at Microsoft works with customers and partners on technical problems like this to prove out scenarios that we believe should be possible but haven’t been attempted before.

      Anyone could have added support for premium storage, but our team is also empowered to make contributions to open source to unblock customers and partners. So we cloned the existing repo, created a "new t-shirt size" (a preset for the instance types and count for the new cluster) as Openhour wanted to use very high end DS12 instances for its cluster, added dropdown options for the storage account type and VM instance type to the parameters section of the script, and then used the ability of ARM templates to express concatenation to build up the vm sizes.

    • If you need a high performance MongoDB cluster on Azure, reach out to support mongodb online training

OnlineITguru is the globally professional in IT courses training which emphasizes hands-on experience with examples from real-time scenarios by experts. It is the largest provider of high-quality online training courses.