Abstract
An important aspect of a high-speed network system is the ability to transfer data directly between the network interface and application buffers. Such a direct data path requires the network interface to `know' the virtual-to-physical address translation of a user buffer, i.e., the physical memory location of the buffer. This paper presents an efficient address translation architecture, User-managed TLB (UTLB), which eliminates system calls and device interrupts from the common communication path. UTLB also supports application-specific policies to pin and unpin application memory. We report micro-benchmark results for an implementation on Myrinet PC clusters. A trace-driven analysis is used to compare the UTLB approach with the interrupt-based approach. It is also used to study the effects of UTLB cache size, associativity, and prefetching. Our results show that the UTLB approach delivers robust performance with relatively small translation cache sizes.
Original language | English (US) |
---|---|
Pages | 193-204 |
Number of pages | 12 |
State | Published - 1998 |
Event | Proceedings of 1998 8th International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS-8 - San Jose, CA, USA Duration: Oct 3 1998 → Oct 7 1998 |
Other
Other | Proceedings of 1998 8th International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS-8 |
---|---|
City | San Jose, CA, USA |
Period | 10/3/98 → 10/7/98 |
All Science Journal Classification (ASJC) codes
- Software
- Information Systems
- Hardware and Architecture