BenchmarkXPRT Blog banner

Category: White papers

Looking back on 2022 with the XPRTs

Around the beginning of each new year, we like to take the opportunity to look back and summarize the XPRT highlights from the previous year. Readers of our newsletter are familiar with the stats and updates we include each month, but for our blog readers who don’t receive the newsletter, we’ve compiled some highlights from 2022 below.

Benchmarks
In the past year, we released WebXPRT 4, and the CloudXPRT v1.2 update package.

XPRTs in the media
Journalists, advertisers, and analysts referenced the XPRTs thousands of times in 2022. It’s always rewarding to know that the XPRTs have proven to be useful and reliable assessment tools for technology publications around the world. Media sites that used the XPRTs in 2022 include AnandTech, Android Authority, Benchlife.info (China), BodNara (South Korea), ComputerBase (Germany), DISKIDEE (Belgium), eTeknix, Expert Reviews, Gadgets 360, Hardware.info (The Netherlands), Hardware Zone (Singapore), ITC.ua (Ukraine), ITmedia (Japan), Itndaily.ru (Russia), Notebookcheck, PCMag, PC-Welt (Germany), PCWorld, TechPowerUp, Tom’s Guide, TweakTown, and ZOL.com (China).

Downloads and confirmed runs
In 2022, we had more than 10,800 benchmark downloads and 183,300 confirmed runs. Users have run our most popular benchmark, WebXPRT, more than 1,135,500 times since its debut in 2013! WebXPRT continues to be a go-to, industry-standard performance benchmark for OEM labs, vendors, and leading tech press outlets around the globe.

XPRT media, tools, and publications
Part of our mission with the XPRTs is to produce tools and materials that help testers better understand the ins and outs of benchmarking in general and the XPRTs in particular. To help achieve this goal, we published the following in 2022:

We’re thankful for everyone who used the XPRTs, joined the community, and sent questions and suggestions throughout 2022. We’re excited to see what’s in store for the XPRTs in 2023!

Justin

The WebXPRT 4 results calculation white paper is now available

Last week, we published the Exploring WebXPRT 4 white paper. The paper describes the design and structure of WebXPRT 4, including detailed information about the benchmark’s harness, HTML5 and WebAssembly capability checks, and the structure of the performance test workloads. This week, to help WebXPRT 4 testers understand how the benchmark calculates results, we’ve published the WebXPRT 4 results calculation and confidence interval white paper.

The white paper explains the WebXPRT 4 confidence interval and how it differs from typical benchmark variability, and the formulas the benchmark uses to calculate the individual workload scenario scores and overall score. The paper also provides an overview of the statistical techniques WebXPRT uses to translate raw timings into scores.

To supplement the white paper’s discussion of the results calculation process, we’ve also published a results calculation spreadsheet that shows the raw data from a sample test run and reproduces the calculations WebXPRT uses to produce workload scores and the overall score.

The paper is available on WebXPRT.com and on our XPRT white papers page. If you have any questions about the WebXPRT results calculation process, please let us know!

Justin

The Exploring WebXPRT 4 white paper is now available

This week, we published the Exploring WebXPRT 4 white paper. It describes the design and structure of WebXPRT 4, including detailed information about the benchmark’s harness, HTML5 and WebAssembly (WASM) capability checks, and changes we’ve made to the structure of the performance test workloads. We explain the benchmark’s scoring methodology, how to automate tests, and how to submit results for publication. The white paper also includes information about the third-party functions and libraries that WebXPRT 4 uses during the HTML5 and WASM capability checks and performance workloads.

The Exploring WebXPRT 4 white paper promotes the high level of transparency and disclosure that is a core value of the BenchmarkXPRT Development Community. We’ve always believed that transparency builds trust, and trust is essential for a healthy benchmarking community. That’s why we involve community members in the benchmark development process and disclose how we build our benchmarks and how they work.

You can find the paper on WebXPRT.com and our XPRT white papers page. If you have any questions about WebXPRT 4, please let us know, and be sure to check out our other XPRT white papers.

Justin

Feedback from the WebXPRT 4 tech press survey

In early May, we sent a survey to members of the tech press who regularly use WebXPRT in articles and reviews. We asked for their thoughts on several aspects of WebXPRT, as well as what they’d like to see in the upcoming fourth version of the benchmark. We also published the survey questions here in the blog, and invited experienced WebXPRT testers to send their feedback as well. We received some good responses to the survey, and for the benefit of our readers, we’ve summarized some of the key comments and suggestions below.

  • One respondent stated that WebXPRT is demanding enough to test performance, but if we want to simulate modern web usage, we should find the most up-to-date studies on common browser tasks and web technologies. This suggestion lines up with our intention to study the feasibility of adding a WebAssembly workload
  • One respondent liked that fact that unlike many other browser benchmarks, WebXPRT tests more than just JavaScript calculation speed.
  • One respondent suggested that we include a link to a WebXPRT white paper within the UI, or at least a guide describing what happens during each workload.
  • One respondent stated that they would like for WebXPRT to automatically produce a good result file on the local test system.
  • One respondent said that WebXPRT has a relatively long runtime for a browser benchmark, and they would prefer that the runtime not increase in WebXPRT 4.
  • We had no direct calls for a battery life test, because many testers already have scripts and/or methodologies in place for battery testing, but one tester suggested adding the ability to loop the test so users can measure performance over varying lengths of time.
  • There were no requests to bring back any aspects of WebXPRT 2015 that we removed in WebXPRT 3.
  • There were no reports of significant connection issues when testing with WebXPRT.

We greatly appreciate the members of the tech press that responded to the survey. We’re still in the planning stages of WebXPRT 4, so there’s still time for anyone to send comments or ideas to benchmarkxprtsupport@principledtechnologies.com. We look forward to hearing from you!

Justin

Default requirements for CloudXPRT results submissions

Over the past few weeks, we’ve received questions about whether we require specific test configuration settings for official CloudXPRT results submissions. Currently, testers have the option to edit up to 12 configuration options for the web microservices workload and three configuration options for the data analytics workload. Not all configuration options have an impact on testing and results, but a few of them can drastically affect key results metrics and how long it takes to complete a test. Because new CloudXPRT testers may not anticipate those outcomes, and so many configuration permutations are possible, we’ve come up with a set of requirements for all future results submissions to our site. Please note that testers are still free to adjust all available configuration options—and define service level agreement (SLA) settings—as they see fit for their own purposes. The requirements below apply only to results testers want to submit for publication consideration on our site, and to any resulting comparisons.


Web microservices results submission requirement

Starting with the May results submission cycle, all web microservices results submissions must have the workload.cpurequestsvalue, which lets the user designate the number of CPU cores the workload assigns to each pod, set to 4. Currently, the benchmark supports values of 1, 2, and 4, with the default value of 4. While 1 and 2 CPU cores per pod may be more appropriate for relatively low-end systems or configurations with few vCPUs, a value of 4 is appropriate for most datacenter processors, and it often enables CSP instances to operate within the benchmark’s max default 95th percentile latency SLA of 3,000 milliseconds.

In future CloudXPRT releases, we may remove the option to change the workload.cpurequests value from the config.json file and simply fix the value in the benchmark’s code to promote test predictability and reasonable comparisons. For more information about configuration options for the web microservices workload, please consult the Overview of the CloudXPRT Web Microservices Workload white paper.


Data analytics results submission requirement

Starting with the May results submission cycle, all data analytics results submissions must have the best reported performance (throughput_jobs/min) correspond to a 95th percentile SLA latency of 90 seconds or less. We have received submissions where the throughput was extremely high, but the 95th percentile SLA latency was up to 10 times the 90 seconds that we recommend in CloudXPRT documentation. High latency values may be acceptable for the unique purposes of individual testers, but they do not provide a good basis for comparison between clusters under test. For more information about configuration options with the data analytics workload, please consult the Overview of the CloudXPRT Data Analytics Workload white paper.

We will update CloudXPRT documentation to make sure that testers know to use the default configuration settings if they plan to submit results for publication. If you have any questions about CloudXPRT or the CloudXPRT results submission process, please let us know.

Justin

We’ve fixed an installation bug in the CloudXPRT Data Analytics Workload package

Yesterday, we published an updated CloudXPRT Data Analytics workload package that fixes a problem during the package installation process. CloudXPRT uses the Helm utility, which serves as a package manager for the Kubernetes container orchestration system. Helm accesses files in a default repository, and the version of Helm that we originally used with CloudXPRT tries to access files that are no longer available. We fixed the problem by updating the code to use the latest version of Helm.

This update does not change how the benchmark workload runs, and has no impact on benchmark results. We apologize if this bug caused headaches for any testers during installation, and we appreciate your patience as we worked on a fix.

As a reminder for testers interested in experimenting with the CloudXPRT Data Analytics workload, the Overview of the CloudXPRT Data Analytics Workload paper is now available. You can find links to the paper and other resources in the Helpful Info box on CloudXPRT.com and the CloudXPRT section of our XPRT white papers page.

If you have any questions, or have encountered any obstacles during testing, please let us know!

Justin

Check out the other XPRTs:

Forgot your password?