Locking effects in multiprocessor implementations of protocols
SIGCOMM '93 Conference proceedings on Communications architectures, protocols and applications
Eliminating receive livelock in an interrupt-driven kernel
ATEC '96 Proceedings of the 1996 annual conference on USENIX Annual Technical Conference
Comparative packet-forwarding measurement of three popular operating systems
Journal of Network and Computer Applications
| Hi-index | 0.00 |
The use of high performance networking technologies, e.g., ATM networks, demands much from both operating systems and processors. During high network loads, user threads may be starved because the processor spends all its time handling interrupts. To alleviate this problem, we propose using a two level network interface servicing scheme that uses interrupts during low network loads to provide low latency, and polling threads during high network loads to avoid user thread starvation. In this paper, we examine the use of such a scheme on dual-processor workstations running Windows NT connected by an ATM network. Performance evaluation of our multiprocessor prototype implementation shows that using our two level scheme can improve performance when used carefully.