Ok, OOM...yea it has been around. My experience is once it starts killing processes, it is time to cycle that image.
The hard part is knowing how much vdisk you need to handle the exception conditions (like maintenance or compiling or...) but not so much as that the only time it would be fully used, is in some sort of runaway process. And that all depends on the application mix you have. And there are no good rules of thumb. Without a VM performance monitor (don't have one, yet), you really have no idea of your high water mark of your vdisk usage. Well, there is a file in Linux, that contains this info tracked by time. And, of course, all of this depends on your size of processer, memory in the lpar, workload, etc. Vdisk is just one of those things, that, if taken too lightly, will bite you later. But everything is like that. Tom Duerbusch THD Consulting >>> "Mark Post" <[EMAIL PROTECTED]> 2/23/2007 3:51 PM >>> >>> On Fri, Feb 23, 2007 at 4:35 PM, in message <[EMAIL PROTECTED]>, "Tom Duerbusch" <[EMAIL PROTECTED]> wrote: > What is the "Linux OOM killer"? > > Is it part of the standard Linux install, a product to be installed, or > a product to be bought? > > The problems I had with vdisk abuse, and the paging system, was on > SLES8 on the MP3000. Perhaps later favors have OOM? The Out of Memory Killer is a feature of the kernel virtual storage management function. It's been around for quite a while, but was improved quite a bit for the 2.6 kernels. The only thing you have to do to activate it is run out of virtual storage (i.e., what Linux thinks of as real storage and swap space), and it will start killing processes semi-randomly. :) Vastly preferable to swamping your z/VM paging subsystem. Mark Post ---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
