As a general statement (IPL is primarily I/O-bound), I agree, especially when considering only z/OS. But over time that's probably becoming less true. For example, WebSphere Application Server (on any platform) has certain CPU demands (which can include zAAPs) to get going, especially with certain applications, although there's been quite a bit of progress on that front recently.
It's probably also worth pointing out that many shops have significantly reduced the frequency of IPLs, and in particular they've designed their overall environment to avoid IPLs when there could be user demands pending. I'm referring in particular to such things as a "warm standby" production LPAR, Parallel Sysplex, and GDPS, as examples. For example, having an LPAR on warm standby at a remote site on a BC machine (typically A01 capacity plus CBU) is a very popular (and affordable) choice among shops that don't have GDPS. IPL time doesn't factor into the recovery time in that particular design. - - - - - Timothy Sipples Resident Architect (Based in Singapore) STG Value Creation and Complex Deals Team IBM Growth Markets E-Mail: timothy.sipp...@us.ibm.com ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html