QUICompare VirtualBox Type-2 Hypervisor Dataset: Auto-Research Benchmarking of 15 TCP Congestion-Control Algorithms across Apache2, NGINX HTTP/2 and QUIC
Description
This dataset contains reproducible network-performance experiments generated with QUICompare Auto-Research in an Oracle VirtualBox Type-2 hypervisor environment. The infrastructure consists of two virtual machines: a QUICompare VM, responsible for workload generation and measurements, and a Device Under Test (DUT) VM The DUT was configured with 5 vCPUs while its virtual memory was varied between 1 GB and 4 GB vRAM. The QUICompare benchmarking tool obey the RFC 2544/6815. For each memory configuration, experiments were executed with 10, 50, and 100 concurrent users, producing six principal workload/resource scenarios: 1 GB × 10 users; 1 GB × 50 users; 1 GB × 100 users; 4 GB × 10 users; 4 GB × 50 users; and 4 GB × 100 users. The dataset evaluates 15 Linux TCP congestion-control algorithms under equivalent virtualized conditions, varying Web-server and protocol configurations based on Apache2, NGINX HTTP/2, and NGINX QUIC/HTTP/3. TCP congestion-control algorithms are directly applied to TCP-based Apache2 and NGINX HTTP/2 scenarios. QUIC/HTTP/3 is analyzed as a separate comparative branch because QUIC operates over UDP and implements congestion control independently from the Linux TCP stack. Experiments were automated using QUICompare Auto-Research mode, with FFmpeg-based traffic generation and configurable acquisition density through the `--sample-rate` parameter. The workflow systematically varies congestion-control algorithm, service/protocol, concurrent users, DUT vRAM, and experiment repetition. The experimental matrix can be summarized as: Congestion Control × Service/Protocol × Users × vRAM × Repetition The resulting files support analysis of throughput, transferred data, latency, jitter, packet behavior, TCP/UDP characteristics, and temporal network-performance series. When the corresponding QUICompare modes are enabled, the data can also support studies involving long-range dependence, self-similarity, fractal behavior, heavy-tailed traffic, Hurst-related measures, sensitivity analysis, machine learning, and Data Envelopment Analysis (DEA). The dataset was designed for reproducibility and controlled comparison of congestion-control mechanisms, Web protocols, workload intensity, and virtualized computational resources. Tutorials, research articles, software, preconfigured virtual machines, installation instructions, datasets, and reproducibility resources are available at the official QUICompare website: https://lhraphael.github.io/quicompare/quicompare.html Our more recent FRANCISCO DEA network predictor/comparison tool is available at URL: https://israellmt.shinyapps.io/Francisco-3-0/
Files
Steps to reproduce
1. Access the official QUICompare website at: https://lhraphael.github.io/quicompare/quicompare.html 2. Download the preconfigured virtual machines and follow the installation and environment-setup instructions available in the QUICompare tutorials. 3. Import the QUICompare VM and the Device Under Test (DUT) VM into Oracle VirtualBox, using a Type-2 hypervisor configuration. 4. Configure the DUT VM with 5 vCPUs and execute the experiments under the two virtual-memory configurations used in this dataset: 1 GB and 4 GB of vRAM. 5. Configure the network interfaces and connectivity between the QUICompare VM and the DUT VM according to the topology and instructions provided on the QUICompare website. 6. Install or enable the required Web services on the DUT, including Apache2 and NGINX, with the corresponding HTTPS, HTTP/2, and QUIC/HTTP/3 configurations described in the QUICompare documentation. 7. Verify the availability of the Linux TCP congestion-control algorithms to be evaluated on the DUT. The experiments in this dataset compare 15 TCP congestion-control algorithms under equivalent virtualized conditions. 8. Run the QUICompare Auto-Research workflow from the QUICompare VM. The experiments must be executed for 10, 50, and 100 concurrent users, repeating the complete experiment for both DUT memory configurations. A representative execution pattern is: ```bash for CLIENTS in 10 50 100 do quicompare --auto-research \ --ssh-auth key \ --ssh-key ~/.ssh/id_ed25519 \ --modes superlight \ --traffic-mode ffmpeg \ --dut-host <DUT_IP_ADDRESS> \ --dut-user <DUT_USER> \ --dut-iface <DUT_NETWORK_INTERFACE> \ --duration 120 \ --clients ${CLIENTS} \ --sample-rate 100 \ --settle-seconds 5 \ --skip-unavailable-algorithms done ``` 9. Repeat the Auto-Research procedure for the complete set of Web-service, protocol, and congestion-control configurations used in the dataset. 10. Collect the structured output files generated by QUICompare and organize the results according to the experimental factors: **Congestion-control algorithm × Web service/protocol × concurrent users × DUT vRAM × repetition.** 11. Use the QUICompare output files for conventional network-performance analysis and, when the corresponding acquisition modes are enabled, for time-series, statistical, fractal, long-range-dependence, heavy-tail, sensitivity, machine-learning, or Data Envelopment Analysis. Detailed tutorials, virtual machines, installation instructions, software resources, research publications, datasets, and additional reproducibility material are maintained on the official QUICompare website: https://lhraphael.github.io/quicompare/quicompare.html