GL Communications Launches 400G Network Traffic Recording Solution
2026-06-04 17:56
Favorite

en.Wedoany.com Reported - On June 3, US network testing solutions provider GL Communications launched the Duplex 400G Packet Capture and Extraction Solution, offering high-speed traffic recording, intelligent filtering, real-time monitoring, and offline analysis capabilities for AI infrastructure, hyperscale data centers, cloud environments, and telecom backbone networks.

This solution addresses the operational pressure following the large-scale deployment of 400G Ethernet. As data throughput in AI data centers, cloud platforms, and telecom backbone networks continues to rise, network engineers need to capture critical traffic on bidirectional high-speed links without packet loss, and quickly identify abnormal sessions, congestion, packet loss, latency fluctuations, and protocol issues within massive data volumes. Traditional traffic analysis tools, which rely on sampling, short-term packet capture, or post-event log analysis in low-speed networks, struggle in 400G link scenarios where data expands rapidly. Without continuous recording and hardware-assisted filtering, key evidence at the moment of failure is easily overwritten or missed. GL Communications' new solution integrates full-speed packet capture, long-duration recording, session extraction, and offline analysis into a single platform, providing finer-grained observability for high-speed networks.

Based on the FastRecorder and PacketExtractor platforms, the solution supports full-duplex packet capture of up to 2×400Gbps, with an aggregate throughput of up to 800Gbps. The system enables continuous recording ranging from days to months, at speeds of up to 6TB per minute.

From a functional perspective, FastRecorder handles continuous recording, event-triggered recording, circular recording, multi-port traffic merging, and nanosecond timestamping. Hardware-assisted filtering allows selective capture based on parameters such as MAC, VLAN, IPv4/IPv6, tunnel traffic, TCP, and UDP, reducing storage consumption from irrelevant data. The browser interface provides real-time metrics including capture rate, recording throughput, link utilization, frame statistics, packet loss, and port performance, enabling engineers to monitor network status directly during recording. PacketExtractor enables secondary processing of recorded traffic, extracting specific packets, sessions, or protocol flows into PCAP and PCAPNG formats, with extraction conditions based on time, protocol, session, packet count, and file size, facilitating subsequent protocol diagnostics in PacketScan or Wireshark.

The value of such high-speed network recording tools is expanding from pure testing equipment to the daily operations of data centers and communication networks. As data exchanges between AI training clusters, distributed storage, cloud services, edge nodes, and operator backbone networks become more frequent, network failures are no longer just local connectivity issues but can impact compute utilization, business continuity, customer service quality, and compliance traceability. Fault localization on 400G links requires speed, duration, precision, and traceability. Engineering teams need both real-time status and the ability to trace the complete data path after an incident. By combining recording, filtering, remote management, REST API automation, and offline extraction, GL Communications helps enterprises and service providers advance high-speed network monitoring from manual troubleshooting to more automated traffic evidence management.

Future application effectiveness will depend on the scale of 400G link deployment in AI data centers and operator networks, enterprise investment in high-speed network observability, and whether engineering teams integrate continuous traffic recording into standard operational workflows. As 800G and higher-speed networks enter data center and backbone network planning, high-speed packet capture, fine-grained filtering, and protocol-level traceability will become critical pillars for network reliability.

This article is compiled by Wedoany. All AI citations must indicate the source as "Wedoany". If there is any infringement or other issues, please notify us promptly, and we will modify or delete it accordingly. Email: news@wedoany.com