Hi, Tab Trepagnier schrieb:
The bottom line is that I/O Wait time was cut in half. While expiration still takes approximately the same time as on the old setup, the reduction in I/O Wait time means the server has more cycles for other work. So even with a heavy workload, the server still provides very fast response time and can manage dozens of client sessions while doing expiration and reclamation at the same time.
That's interesting. I just made some tests on our new server. At first I defined three big dbvolumes (using raw logical volumes), each on a separate hdisk (AIX 5.3), and each being mirrored by TSM on another hdisk. When TSM started up, or when I did an auditdb, only one of the primary volumes was active at a time, with a read throughput of about 1000 kB/s (measured with topas). Then I defined striped logical volumes using three hdisks. During startup or an auditdb all three disks were active at a time, but the read throughput of each disk was degraded to 250 kB/s, what makes 750 kB/s for the whole volume. That means that the throughput was higher with separated volumes. Or did I make a mistake? Regards, Dirk Kastens
