Performance Results

To evaluate the performance of our remote memory pager, and compare it to traditional disk paging, we conducted a series of performance measurements using a number of representative applications that require a large amount of memory. Our applications include GAUSS, a gaussian elimination, QSORT, a quicksort program, FFT, a Fast-Fourier Transform and MVEC, a matrix-vector multiplication. All applications were executed on the DEC-Alpha 3000 model 300, and were compiled with the standard C compiler with the optimization enabled. All workstations that contributed their main memory for paging purposes were DEC-Alpha 3000 model 300, connected via a standard 10Mbits/sec Ethernet. The local disk that was used for paging is a DEC RZ55, providing 10Mbits/sec bandwidth, and average seek time of 16 msec.

  
Figure: Performance of applications using either the DISK, or the REMOTE_MEMORY as paging device. We see that for all applications, the use of REMOTE_MEMORY results in significantly faster execution. All applications were run on a DEC Alpha 3000 model 300 workstation. The input sizes for QSORT was 4000 records, for GAUSS, a 20002000 matrix, for MVEC, a 21002100 matrix, and for FFT an array with 900000 elements.

• Performance of Remote Memory Paging Over the Ethernet
• Scaling the Input
• Scaling the Network Bandwidth
• The Latency of Remote Memory Paging
• Using Busy Workstations as Servers
• Reliability
  • Parity Caching