Company
Solutions
Developers
EN
EN
EnglishChinese
Ampere Computing Logo
Ampere Computing Logo
Solutions
Solutions Home
Systems
Solutions
Performance Overview
Reference Architecture Overview
Tuning Guides for Cloud Native Processing
Tutorials
Workload Briefs Overview
Where to Try
Ampere Systems
Ampere Altra
Azure
Equinix
Google Cloud
Hewlett Packard Enterprise
Oracle
Tencent Cloud
Ampere AIDownloadsHow It WorksFAQs
Developers
Developer CenterDesigning Cloud ApplicationsBuilding Cloud ApplicationsDeploying Cloud ApplicationsUsing Your DataWorking with Open SourceAmpere Ready SoftwareCommunity Forum
Support
Hero Image

MongoDB Brief

On Bare Metal Ampere Altra Family

Print
Download
MongoDB Performance on Ampere
Benchmarking Results
Benchmarking Configuration
Key Benefits
Ampere - Empowering What’s Next
Footnotes
MongoDB Performance on Ampere

Ampere® Altra® Max 128-30 Outperforms AMD EPYC 7763 and Intel Xeon “Ice Lake” 8380 Running MongoDB

MongoDB is a popular source-available cross-platform document-oriented NoSQL database program. Its flexible data model enables the storage of unstructured data with full indexing support and replication. According to DB-Engines, MongoDB was the 5th most popular database as of January 2023.

Benchmarking Results

As can be seen in fig.2 below, we observed up to 44% higher performance on Ampere Altra Max compared to Intel 8380 and 10% compared to AMD 7763.

For large-scale cloud deployments, performance/Watt (i.e. energy efficiency) is an important metric in addition to raw performance. Ampere Altra Max processors have 2.1x better performance/Watt under the specified SLA compared on Intel Ice Lake and 1.7x better performance/Watt compared to AMD Milan.

Ampere Altra and Ampere Altra Max are designed to deliver exceptional performance and energy efficiency for cloud native applications like MongoDB. In Ampere’s testing, these processors demonstrated up to 44% higher performance compared to x86 servers while being more than 2x better on energy efficiency. For more information on this workload or other workloads our engineers have been working on, please visit amperecomputing.com/developers

Fig 1. Throughput (p99 Latency of 2ms)

Fig.1: Ampere Altra Max delivers up to 44% higher TPT vs Intel 8380 and 10% vs AMD 7763.

Fig 2. Performance/Watt

Fig.2: Perf/Watt on Ampere Altra Max is 2.1x better using the spec’d SLA vs Intel Ice Lake and 1.7x better vs AMD Milan.

Benchmarking Configuration

MongoDB tests were performed on bare-metal single socket servers with equivalent memory, networking and storage configurations for each of the platforms shown. The processors tested here are: the Intel Xeon 8380 "Ice Lake", AMD EPYC 7763 "Milan", and Ampere Altra Max M128-30.

4 MongoDB servers were deployed on each test platform and each takes ¼ of the processor resources. These tests used the YCSB framework as a load generator for benchmarking MongoDB. Each test was configured to run for 2 minutes with multiple threads and clients. The MongoDB data and commit log were stored on tmpfs to ensure storage did not become a bottleneck.

CentOS 8.4 (kernel 4.18) with MongoDB 6.0.3 were used on Altra Max. Fedora server 36 (kernel 5.17) with MongoDB 6.0.3 were used in Milan and Ice Lake. For each of the tests, the same client configuration was used to generate requests for MongoDB.

Since it is realistic to measure throughput under a specified Service Level Agreement (SLA), a 99th percentile latency (p.99) of 2 milliseconds was used. This ensures that 99 percent of the requests had a response time of 2 ms in the worst case.

We ran YCSB Workload A, which has a mix of 50% reads and 50% writes, which is typical for a database like MongoDB. The test ran with 5 million records and 5 million operations, with the maximum execution time set to 2 minutes. The appropriate number of clients and threads were used to increase the MongoDB load till the p.99 latency was reached.

YCSB clients issue requests to MongoDB instances and the aggregate throughput of all these instances was used as the primary performance metric with the worst p.99 latency among the YCSB instances noted. The test was run three times and minimal run-to-run variation was observed.

The Yahoo! Cloud Serving Benchmark (YCSB) is a mature open-source framework for evaluating the capabilities of different NoSQL databases in a standardized manner.


mongoDB.png

Key Benefits

Cloud Native: Designed from the ground up for cloud customers, Ampere Altra and Ampere Altra Max processors are ideal for cloud native usages such as MongoDB.

Scalable: With an innovative scale- out architecture, Ampere Altra and Ampere Altra Max processors have a high core count with compelling single-threaded performance combined with consistent frequency for all cores delivering greater performance at socket level.

Power Efficient: Industry-leading energy efficiency allows Ampere Altra and Ampere Altra Max processors to hit competitive levels of raw performance while consuming much lower power than the competition.

What it Enables

  • Consistent, predictable high performance, especially at high loads
  • Much higher resistance to noisy neighbors in multitenant environments
  • Lower TCO and carbon footprint at a datacenter-level
Ampere - Empowering What’s Next

The Ampere® Altra® and Ampere® Altra® Max processors are complete system-on-chip (SOC) solutions built for cloud native applications. Ampere Altra supports up to 80 cores and Ampere Altra Max supports up to 128 aarch64 cores. In addition to incorporating a large number of high-performance cores, the innovative architecture delivers predictable high performance, linear scaling and high energy efficiency.

Footnotes

Ampere Computing reserves the right to make changes to its products, its datasheets, or related documentation, without notice and warrants its products solely pursuant to its terms and conditions of sale, only to substantially comply with the latest available datasheet.

Ampere, Ampere Computing, the Ampere Computing and ‘A’ logos, and Altra are registered trademarks of Ampere Computing.

Arm is a registered trademark of Arm Limited (or its subsidiaries) in the US and/or elsewhere. All other trademarks are the property of their respective holders.

©2023 Ampere Computing. All Rights Reserved.

Ampere Computing

4655 Great America Parkway

Suite 601 Santa Clara, CA 95054

Tel: +1-669-770-3700

info[at]amperecomputing.com

About
image
image
image
image
© 2023 Ampere Computing LLC. All rights reserved. Ampere, Altra and the A and Ampere logos are registered trademarks or trademarks of Ampere Computing.