HP-UX Encrypted Volume and File System Performance and Tuning

64k Block Sequential Read - 100mb File Size
5%
11%
15%
18%
18%
10%
29%
27%
30% 30%
1
IOZone Threads
CPU Utilization %
Throughput KBs -
Scale30
Clear CPU EVFS CPU Clear read EVFS read
Figure 18: Sequential Reads with Default Tuning (Scale30)
64k Cached Sequential Reads - 100mb File Size
2%
11%
14%
27%
29%
1%
6%
14%
28%
31%
1 10 25 50 100
IOZone Threads
CPU Utilization %
Throughput KBs -
Scale30
Clear CPU EVFS CPU Clear Reads EVFS Reads
Figure 19: Cached Sequential Reads Default Tuning
By pre-fetching the read data and storing it in memory via buffer cache, the EVFS pseudo-driver is
removed from the path between data and application, thus perceived EVFS performance is equal to
that of clear I/O. Using default tuning, caching the read data improves throughput to the application
by about 50 times.