home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.sys.hp
- Path: sparky!uunet!utcsri!helios.physics.utoronto.ca!alchemy.chem.utoronto.ca!system
- From: system@alchemy.chem.utoronto.ca (System Admin (Mike Peterson))
- Subject: Re: HP 7xx problem with virtual memory (thrashing)
- Message-ID: <1993Jan5.194958.10898@alchemy.chem.utoronto.ca>
- Organization: University of Toronto Chemistry Department
- References: <1993Jan3.034944.3556@alchemy.chem.utoronto.ca> <C0E6xu.E77@fc.hp.com>
- Distribution: comp.sys.hp
- Date: Tue, 5 Jan 1993 19:49:58 GMT
- Lines: 25
-
- In article <C0E6xu.E77@fc.hp.com> jk@fc.hp.com (John Kessenich) writes:
- > That the system thrashes means the amount of memory the CPU touches in a
- > short amount of time is larger than the amount of physical memory
- > available. The main variables are the amount of available memory (less
- > means more thrashing), the speed of the CPU (faster means more
- > thrashing), the size of the process (smaller means less thrashing),
- > speed of paging devices (faster/more discs means less thrashing), and
- > the access pattern of the process (more locality means less thrashing).
- > These will vary considerably from system to system, and knowing which
- > one changes when performance changes requires some work.
-
- Some added data: after boot, and for several days, the system would
- report that about 60 MB of our 128 MB was "free". After that, the "free"
- memory would decline slowly, until the system would become useless
- when about 5 MB or less was free. The number of processes remained more
- or less the same (i.e. not a huge number of defunct/zombies eating
- memory), and no task would show more "SIZE" than it would when the
- system was booted. It seems there is a black hole for memory; we have
- one program which may not be well-behaved about returning malloc'ed
- memory, but the system MUST recover all such memory when the process
- dies no matter how screwed up the process becomes.
- --
- core error - bus dumped -*- Mike Peterson, SysAdmin, U/Toronto Chemistry
- ******* As usual, I speak only for me, myself and I; nobody else *******
- E-mail: system@alchemy.chem.utoronto.ca Tel: (416)978-7094 Fax: (416)978-8775
-