Abstract

IBM commissioned The Tolly Group, as part of its 1994 Industry Benchmark for Local Token Ring Bridges, to evaluate the IBM 8229 Bridge with the main focus on measuring local Token Ring bridge performance across source-route bridging scenarios and documenting the platform’s technical capabilities for enterprise LAN interconnection. The report emphasizes frame-handling efficiency, maximum effective unidirectional throughput, and the bridge’s ability to sustain high offered loads without packet loss in 16Mbit/s Token Ring environments.  

The December 1994 Technology Spotlight presents the IBM 8229 Bridge as a two-port device designed to bring high-speed, plug-and-play connectivity to Token Ring and Ethernet networks. According to the product-specification panel on page 3, the tested unit ran software version 1.00.11, supported two fully interconnected interfaces per chassis, used IBM LANStreamer Token Ring technology, and operated at 4 or 16Mbit/s over STP and UTP media. The bridge supported Source Route Bridging for Token Ring and transparent bridging for Ethernet, with additional listed features including SNMP and IBM LAN Network Manager support, flash memory, Novell IPX support, Token-Ring-to-Ethernet connectivity, and Token-Ring-to-WAN connectivity.  

Tolly’s benchmark suite measured overall throughput for source-route bridged frames across a range of frame sizes: 28, 64, 256, 512, 1,024, 2,048, and 4,096 bytes. As shown in the throughput chart on page 1, the IBM 8229 delivered 5.28Mbit/s at 28-byte frames, 11.07Mbit/s at 64-byte frames, 14.57Mbit/s at 256-byte frames, 15.00Mbit/s at 512-byte frames, 15.48Mbit/s at 1,024-byte frames, 15.73Mbit/s at 2,048-byte frames, and 15.86Mbit/s at 4,096-byte frames. Tolly states that this corresponds to 23,582fps at 28-byte frames, 21,625fps at 64-byte frames, 7,115fps at 256-byte frames, 3,663fps at 512-byte frames, 1,890fps at 1,024-byte frames, 960fps at 2,048-byte frames, and 484fps at 4,096-byte frames. The report defines near-wire-speed throughput as 90% or more of link bandwidth and notes that the IBM 8229 achieved that level for 256-byte frames and larger.  

Tolly explains that bridge performance depends primarily on frame-handling capability and maximum throughput without loss, since smaller frames create higher processing overhead in frame-by-frame forwarding architectures. Even so, the report indicates that the IBM 8229 Bridge delivered strong source-route bridging performance and fit into the broader 1994 benchmark trend of markedly improved local Token Ring bridge throughput. Overall, the report presents the IBM 8229 as a high-performance local Token Ring bridge combining solid frame-processing capability, near-wire-speed throughput on larger frames, and enterprise-oriented connectivity and management features.