What are SRPs, IRPs and LRPs?

Why does the number of SRPs, IRPs and LRPs in use increase when I/O Express is on the system?

These abbreviations stand for Small-, Intermediate- and Large Request Packets. They are used in OpenVMS versions prior to 6.0. Request packets are linked lists of memory, to speed up process requests for dynamic memory. When a memory request cannot be satisfied from one of the lists, non-paged pool is allocated. It is important that there always be a reasonable number of free request packets. If there are not enough free request packets, the system will spend additional overhead allocating memory from the non-paged pool.

I/O Express improves system performance by satisfying I/O requests faster and reducing the number of I/Os that actually have to be satisfied from disk. Therefore, more work can be done in a given amount of time. More work accomplished means more throughput. More throughput may mean that certain resources will be used more heavily than before. Some of the resources being used more heavily are the request packets.

The solution is to follow the standard rule of thumb, when dealing with increasing a memory parameter. Increase the number of request packets until the free amount stays at 100 free SRPs, 50 free IRPs and 25 free LRPs at peak loads.

If this FAQ helped, please let us know. If you didn't find the answer to your question here please e-mail

Executive Software Europe