On Monday, 08/25/2008 at 10:11 EDT, dave <[EMAIL PROTECTED]> wrote: > Well, there is no such thing as a free lunch, so > establishing *large* numbers of IUCV connections between > virtual machines does cost something. Control blocks must be > allocated, must be managed by CP, interrupts fielded, etc. > Off of the top of my head, I don't know how much storage > these control blocks take, but I would suspect that with CP > now being 64-bit, the amount of storage taken would not be a > significant issue.
The primary memory allocation for IUCV connections is sufficient, IIRC, for 256 connections. On the 257th connection, another allocation for 256 is made. Access to those control blocks is fast due to the fact that they are not chained, but are maintained as an array of pointers (256 adjacent entries per pointer). The control block for any path id is easy to locate. No searching required. I'm more concerned in how the SVM guest getting all those IUCV messages is handling *its* memory allocation. Alan Altmark z/VM Development IBM Endicott
