How Ideco Measures NGFW Performance Using TRex ASTF and RFC 9411 Methodology
Ideco has shared a comprehensive look at how its engineering team measures the performance of Ideco NGFW Novum on the Ideco EX platform. The article explains why raw performance numbers are meaningless without a clearly documented methodology and describes every parameter used in their lab tests.
Why Performance Numbers Vary Across Tests
The same NGFW device can produce very different results on two different test beds even when both tests are honest. Performance depends on packet size, enabled security functions, number of rules, test duration, and the acceptable loss threshold. Ideco therefore publishes its full methodology so that any reader can reproduce the measurements and understand exactly what each figure represents.
Traffic Generator and Test Modes
The team selected the open-source TRex generator running in ASTF (Advanced Stateful) mode. This choice enables realistic TCP session handling and L7 emulation, which is essential for testing stateful inspection engines. Stateless mode is used only for raw UDP throughput tests with 1518-byte frames. When TLS decryption is enabled on the firewall, the team switches to the hardware-based Keysight BreakingPoint system.
Test Bed Configuration
Both the device under test and the traffic generator use identical server hardware:
- CPU: Xeon Gold 6338N
- RAM: 128 GB
- NICs: Intel E810 2xQSFP28 (100 Gbps)
The topology is a simple two-port setup with TRex port 0 connected to the DUT and TRex port 1 returning the traffic.
Key Metrics and Traffic Profiles
The methodology measures four primary metrics: throughput in Gbit/s, connections per second (CPS), concurrent connections (CC), and latency. Tests are performed with the following profiles:
- UDP 1518-byte frames (raw L2/L3 ceiling)
- TCP/HTTP with 64 KB objects
- TCP/HTTP with 16 KB objects
- EMIX mixed corporate traffic
- TCP CPS and TCP CC specific tests
All tests run with a fixed set of firewall rules, IPS signatures, and application control profiles. TLS decryption remains disabled during these runs.
Loss Criterion and Test Duration
Loss is defined as dropped sessions rather than individual packets. The formula uses TRex counters for TCP connection drops, established session drops, and UDP keepalive drops. A test point passes only when session loss stays at or below 1 %. Each load point is held for 300 seconds after a 30-second ramp-up phase to reveal queue buildup, memory pressure, and thermal effects that short bursts would miss.
Results Summary
On the Ideco EX platform the measured maximums are:
- UDP 1518 B: 200 Gbit/s
- TCP/HTTP 64 KB: 100 Gbit/s
- TCP/HTTP 16 KB: 62 Gbit/s
- EMIX (firewall only): 92 Gbit/s
- EMIX + IPS: 31 Gbit/s
- Full NGFW stack: 15.5 Gbit/s
- TCP CPS: 800 000 new sessions per second
- TCP CC: 21 000 000 concurrent sessions
The article concludes that performance is always a range that depends on the actual traffic mix and enabled security functions. Full configuration files and commands are provided so the community can replicate the tests.
Related articles
OpenAI Releases GPT-6.1 Terra: Cost-Effective Model Focused on Computer Control, Image Analysis and Practical Automation
OpenAI has launched GPT-6.1 Terra, a new model positioned between its high-end GPT-6 Astra and more affordable options in the GPT-6 family. The model emphasizes real-world computer interaction, visual understanding of documents and interfaces, and reduced error rates rather than raw reasoning benchmarks. It supports a 1.05 million token context window, image inputs, and tool use through the Responses API while cutting input token prices by half compared with its predecessor. Published benchmarks show substantial gains on Terminal-Bench 4.0, OSWorld 2.1 and Agents' Last Exam, with error rates dropping sharply at both low and maximum reasoning levels. OpenAI stresses that the model still requires human oversight for high-stakes actions and does not directly process audio or video. The release targets developers and enterprises seeking reliable automation of repetitive multi-step tasks at lower cost than flagship models.
Yandex Black October: How Architectural Flaws and Capacity Mismanagement Turned Data Center Losses Into a 11-Day Fintech Coma
In October 2026 three Yandex data centers in Central Russia were physically destroyed within days, triggering the collapse of Yandex Cloud and multiple core services. Between the first and third site failures engineers had 74 hours to restore quorum and rebalance workloads yet failed to do so because Control Plane components remained tied to the lost zone and spare capacity had been eliminated to cut costs. Core banking and BNPL systems entered Read-Only mode after losing quorum, forcing a complete stop-the-world reconciliation that lasted until 22 October. Backups stored inside the same regional S3 buckets proved unusable, resulting in a seven-day RPO and primary-key collisions after restoration. The incident exposed that Metro-Cluster designs had been incorrectly treated as full Disaster Recovery and that aggressive AP microservice patterns created logical split-brain conditions outside the database layer.
Astra Group Releases Low-Code Astra AI Platform for Building Corporate AI Agents in Closed Environments
Astra Group has launched the Astra AI Platform, a low-code constructor designed for creating corporate AI applications that operate entirely within closed circuits without reliance on foreign clouds. The platform targets small and medium businesses as well as large corporations, enabling rapid deployment of AI secretaries, technical support assistants, and other agents in days rather than months. It forms part of the broader Astra AI ecosystem and includes two main constructors: one for machine learning model training and deployment, and another for LLM-based language assistants, document search, and process automation. Users can assemble scenarios from visual blocks, debug them in real time, or extend functionality with custom Python code when needed. The solution supports RAG-based knowledge bases, integration with external tools such as CRM and ERP systems, and the coordination of multiple agents for distributed task handling. One demonstrated use case involves processing ten pages of engineering drawings and specifications in five minutes to prepare data for downstream systems. The product is already listed in the Russian domestic software registry and available to customers.
Multi-Tenancy Isolation in VictoriaMetrics, VictoriaLogs and Grafana: Building Client Separation in a Shared Stack
Voltir runs a single shared monitoring stack consisting of VictoriaMetrics, VictoriaLogs, Grafana and vmalert for all customers instead of deploying separate instances per tenant. Isolation relies on numeric account IDs enforced at every layer: nginx validates tokens against the platform API before proxying writes, Grafana data sources hard-code tenant accounts, and vmalert rules receive automatic account filters. The team discovered that a single malformed rule or template could break alerting for every tenant because vmalert loads the entire rules directory at once. They also found that Grafana automatically created personal organizations granting Org Admin rights, accumulating hundreds of orphaned organizations and users that consumed disk space and resources. A dedicated cleanup module plus hourly reconciliation now removes rules, organizations, series and users when a tenant is deleted, while isolation tests verify both data and API objects across tenants.