H7000
H7000 is the 1U TR7 hardware platform running on a 26-core 2nd generation Intel Xeon Scalable processor. The values on this page are given with the workloads and metric definitions defined on the Test Methodology page; the condition of each value is stated in the related section.
The H7000 platform is built on a 26-core, 2nd generation Intel Xeon Scalable processor. The TR7 software takes advantage of the hardware capabilities offered by the Intel processor and chipset to accelerate the cryptographic operations within TLS and the data compression workloads. The supported processor instructions and the acceleration resources of the platform are used together with optimized software components, ensuring efficient use of processor resources and the processing of high traffic volumes. The contribution of acceleration to performance depends on the algorithms used, the traffic characteristics and the configuration of the active services.
Summary
| Platform performance | H7040 | H7060 | H7080 | H7100 | H7140 | H7200 |
|---|---|---|---|---|---|---|
| Throughput | 40 Gbps | 60 Gbps | 80 Gbps | 100 Gbps | 140 Gbps | 200 Gbps |
| HTTP requests/s | 3 M | 3.2 M | 3.5 M | 3.5 M | 4.5 M | 4.5 M |
| TLS TPS (ECDSA-P256) | 50,000 | 60,000 | 70,000 | 80,000 | 80,000 | 90,000 |
| TLS throughput | 40 Gbps | 50 Gbps | 60 Gbps | 80 Gbps | 70 Gbps | 100 Gbps |
| Compression throughput | 30 Gbps | 35 Gbps | 40 Gbps | 40 Gbps | 50 Gbps | 80 Gbps |
| L4 HTTP RPS | - | - | - | - | 18 M | 36 M |
| L4 Concurrent Connections | - | - | - | - | 140 M | 145 M |
Metric definitions: Metric Definitions. Value classes (measured and capacity): Value Classes.
Platform
| Property | Value |
|---|---|
| Processor | 2nd generation Intel Xeon Scalable, 26 cores |
| Onboard network | 8 × GbE RJ-45 (copper), 2 × SFP; separate management port (IPMI 2.0) |
| Expansion | 4 network module slots (highest option 2 × 100 GbE QSFP28 / slot) |
| Storage | 2 × 1 TB SSD (RAID 1) |
| Power | 1+1 redundant, 400 W |
| Form factor | 1U · 44 × 430 × 561 mm |
L7 HTTP
| Metric | Condition |
|---|---|
| HTTP requests/s | Kept-open HTTP/1.1 connections; TR7 generates the response itself, no Backend Service |
Since the requests arrive over open connections, the TCP handshake cost is not included in this value. The values belong to a device serving only L7; if L4 vServices are also defined on the same device, HTTP requests/s reads about 15% lower.
SSL/TLS
| Metric | Condition |
|---|---|
| TLS TPS (ECDSA-P256) | Full handshake, session ticket off, TLS 1.2, cipher suite ECDHE-ECDSA-AES128-GCM-SHA256 |
The cryptographic operations within TLS take advantage of the hardware acceleration capabilities of the processor. In each full handshake, the device makes one ECDSA P-256 signature and performs the key exchange from scratch; the value scales with the number of processor cores.
Throughput
| Metric | Path |
|---|---|
| Throughput | The highest traffic the device can carry; on H7140 and H7200, the highest value on the L4 path |
| TLS throughput | TR7's own response, 64 KB, TLS 1.3 AES-GCM |
The values are the traffic the processor can carry; the achieved throughput is also limited by the line rate of the installed network modules. Reaching the processor capacity requires 100 GbE modules. The values are for 1500-byte frames. TLS throughput is the bytes sent by the network card and includes the TLS, TCP/IP and frame headers.
Software Compression
| Metric | Condition |
|---|---|
| Compression throughput | gzip, pre-compression (input) bytes |
The device compresses the response in gzip format, at the fastest level. The value depends on the repetition ratio of the content: highly repetitive content such as table and report output compresses noticeably faster than an ordinary HTML page.
| Content class | Ratio | Compressibility |
|---|---|---|
| Heavily repetitive: table and report output | 35.10:1 | 97% |
| Moderately repetitive: JSON and log | 9.62:1 | 90% |
| HTML: repeating template | 5.47:1 | 82% |
| Real report page | 3.60:1 | 72% |
L4
| Metric | Condition |
|---|---|
| L4 HTTP RPS | HTTP requests forwarded over established persistent connections; 1 million persistent connections, 128-byte requests, 8 Backend Services |
| L4 Concurrent Connections | Connections opened and kept idle; the value is the number of entries in the device's connection table |
In an L4 vService, the device does not terminate the connection and does not read HTTP content; it forwards the packets of the established connection to the Backend Service. In L4 HTTP RPS, persistent connections are opened at the start of the run and reused throughout the run; the value is the requests sent per second.
In L4 Concurrent Connections, connections are opened and kept open with a 60-second idle period; the value is not the generator's count but the number of entries in the device's own connection table. The measurement setup is limited to 100.7 M connections by the address space of the load generator; values above this limit are in the Capacity class.
