[EMAIL PROTECTED] (Mark Post) writes:
That's still probably too much, if only by a little. The idea is to
force Linux to use as little storage as possible for buffers and
cache, and page out any programs, etc., that haven't been used very
recently. Letting z/VM handle this via expanded storage, and paging
some things out to real disk turns out to work very well in a shared
environment. Other techniques, such as having the kernel in a Named
Saved Segment, and executable userspace code in a DCSS using the
eXecute In Place file system helps even more.
previous posts in this thread:
http://www.garlic.com/~lynn/2007o.html#41 Virtual Storage implementation
http://www.garlic.com/~lynn/2007o.html#45 Virtual Storage implementation
http://www.garlic.com/~lynn/2007o.html#46 Virtual Storage implementation
http://www.garlic.com/~lynn/2007o.html#47 Virtual Storage implementation
for more archeological topic drift with regard to DCSS. i had
originally started what i called "virtual memory management"
on cp67 platform at the science center
http://www.garlic.com/~lynn/subtopic.html#545tech
this included mapping the cms filesystem to a paged mapped
infrastructure
http://www.garlic.com/~lynn/subtopic.html#mmap
which included a lot of fancy options about moving pages
to/from virtual address space and disk storage. i then
ported this to a vm370/cms environment with a lot of
options for sharing of segments. a variety of some of this
was used in some of the original relation/sql dbms work
... all done on vm370 platform
http://www.garlic.com/~lynn/subtopic.html#systemr
in the early 70s, there was a project called future system
http://www.garlic.com/~lynn/subtopic.html#futuresys
which was going to replace 360/370 with a radically different machine
architecture. this effort absorbed significant corporate resources and
when it was finally canceled (w/o even being announced) there was
significant scrambling to get all sort of items back into the
370 hardware and software product pipeline.
The resulting mad scramble open opportunity to get a lot of
work ... that had continued at the science center
http://www.garlic.com/~lynn/subtopic.html#545tech
on 370s into vm370 product ... including my resource manager
http://www.garlic.com/~lynn/subtopic.html#fairshare
that included a large amount of other work not strictly
related to resource management, things like lots of kernel
reorganization for multiprocessor support
http://www.garlic.com/~lynn/subtopic.html#smp
part of that opportunity resulted in releasing an extremely
small subset of the "virtual memory management" work
as DCSS (and the generalized paged mapped infrastructure was
not included). for additional topic drift ... some discussions
of various problems trying to reconcile generalized virtual
memory management features with os/360 address constant convention
http://www.garlic.com/~lynn/subtopic.html#adcon
----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
