NGINX Workload Brief
Open-source web server used for reverse proxy, load balancer, mail proxy, media streaming and more.
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 Max supports up to 128 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.
NGINX is an open source, high performance HTTP server and reverse proxy with many other web service-related features bundled. It is often used as load balancer in the cloud. NGINX implements event driven architecture to handle incoming requests. It is built to offer a low memory footprint and high concurrency. NGINX is the most popular web server among high-traffic websites as of 2021.
In this workload brief, we compare Ampere Altra Max M128- 30 to the Intel® Xeon® 8380 and the AMD EPYC™ 7763 running NGINX while measuring the throughput and latencies on each of these processors.
NGINX on Ampere Altra Max
Ampere Altra Max is designed to deliver exceptional performance for cloud native applications like NGINX. This is achieved by using an innovative architectural design, operating at consistent frequencies, and using single-threaded cores that make applications more resistant to noisy neighbor issues. This allows workloads to run in a predictable manner with minimal variance under increasing loads.
Ampere processors are designed to deliver exceptional energy efficiency. This translates to industry leading performance/watt capability and a lower carbon footprint.
Benefits of running NGINX on Ampere Altra Max
-
Cloud Native: Designed for maximum performance and scalability for cloud customers, Ampere Altra Max can deliver up to 3. 19x higher performance than the best x86 servers for cloud native workloads like NGINX.
-
Energy Efficiency: With up to 128 energy-efficient Arm cores, Ampere Altra Max can consume 16% lower power while delivering 3x better raw performance than the best x86 servers.
-
Lower Carbon Footprint: Industry leading performance and high energy efficiency result in Ampere Altra Max demonstrating up to 3. 76x higher performance/watt, leading to lower TCO.
-
Consistency & Predictability: Single threaded cores running at fixed maximum frequencies ensure linear scaling under stringent SLAs and at high loads while running auto scaling NGINX instances.
Ampere Altra Max
- 128 64-bit cores at 3.0GHz
- 64KB i-Cache, 64KB d-Cache per core
- 1MB L2 Cache per core
- 16MB System Level Cache
- Coherent mesh-based interconnect
Memory
- 8x72 bit DDR4-3200 channels
- ECC and DDR4 RAS
- Up to 16 DIMMs (2 DPC) and 4TB addressable memory
Connectivity
- 128 lanes of PCIe Gen4
- Coherent multi-socket support
- 4x16 CCIX lanes
System
- Armv8.2+, SBSA Level 4
- Advanced Power Management
Performance
- SPECrate®2017Integer Estimated: 350
Benchmarking Configuration
An open-source http benchmarking tool, wrk, is used as the load generator. The wrk application running on the client system generates simultaneous HTTP requests over HTTPS connections to NGINX running on the target system. The test was configured to run with multiple threads and connections.
On the server side, NGINX is configured to serve static HTML file over https protocol using Brottli compression (quality 5). The server redirects the incoming request URL using LuaJIT, which does all the regex processing. In order to support the additional functionalities, NGINX is compiled with HTTP SSL module, openssl, brottli compression and NGINX-lua modules. The source code version of NGINX 1.15.4 and wrk v4.10 versions are used for this benchmarking.
The load generator, wrk, was configured to run with 96 clients and connections increasing from 100 to 500 in steps of 100 to observe the impact on throughput and p99 latency. We measure throughput, Requests Per Second (RPS) under SLA of 10ms p99 latency. Each test was run for 120 seconds and repeated at least 3 times, taking the average RPS and p99 across multiple runs. We observed little to no run-to-run variations in RPS or p99 latencies.
The workload was run on Ampere Altra Max M128-30, AMD EPYC 7763 and Intel Xeon 8380 (refer to the chart below for results). The same client system was used as load generator across all the platforms.
Ampere Altra Max M128-30 Industry-leading Performance and Energy Efficiency on NGINX
Benchmarking Results and Conclusions
In the chart above, results show Ampere Altra Max M128-30 has more than 3x higher performance compared to Intel Xeon 8380 and 1.74x better than the highest end AMD EPYC series.
For large-scale cloud deployments, performance/watt (i.e. energy efficiency) is an important metric in addition to raw performance. Ampere Altra Max processors lead in performance with significant performance/watt advantage as shown the graph, resulting in up to 3.76x better efficiency.
NGINX is one of the most popular web servers in the cloud today. It scales well with the compute resources that Ampere Altra Max series offers. Ampere Altra Max series is designed to deliver exceptional performance and energy efficiency for cloud native applications. In Ampere’s testing, these processors demonstrated up to 3.19x performance improvements and they achieved up to 3.76x energy efficiency improvements.
Footnotes
All data and information contained herein is for informational purposes only and Ampere reserves the right to change it without notice. This document may contain technical inaccuracies, omissions and typographical errors, and Ampere is under no obligation to update or correct this information. Ampere makes no representations or warranties of any kind, including but not limited to express or implied guarantees of noninfringement, merchantability, or fitness for a particular purpose, and assumes no liability of any kind. All information is provided “AS IS.” This document is not an offer or a binding commitment by Ampere. Use of the products contemplated herein requires the subsequent negotiation and execution of a definitive agreement or is subject to Ampere’s Terms and Conditions for the Sale of Goods.
System configurations, components, software versions, and testing environments that differ from those used in Ampere’s tests may result in different measurements than those obtained by Ampere.
©2022 Ampere Computing. All Rights Reserved. Ampere, Ampere Computing, Altra and the ‘A’ logo are all registered trademarks or trademarks of Ampere Computing. Arm is a registered trademark of Arm Limited (or its subsidiaries). All other product names used in this publication are for identification purposes only and may be trademarks of their respective companies.
Ampere Computing® / 4655 Great America Parkway, Suite 601 / Santa Clara, CA 95054 / amperecomputing.com
Ampere Computing LLC
4655 Great America Parkway Suite 601
Santa Clara, CA 95054
