Very Computer

Would anyone be kind enough to explain to me why systems usually have
more page-outs than page-ins? It has got me stumped for quite some
time. I would think that if 100mb is paged out from memory to disk,
then similarly 100mb should be paged-in back from disk to physical
memory?

Or is my understand of paging-in and paging-out wrong? i.e Page-outs
occur when a page is pushed from main memory to the paging space due
to a variety of reasons (lack of physical memory being one of them)
while page-ins' occur when there is free physical memory and these
pages are pushed back from disk back to the physical memory.

TIA!

If the kernel takes a page fault and the resulting page is on paging
space.. then you will get a page in....

lrud (on the mp kernel) scans pages and markes them as candidates to
page out (to filesystem or paging space depending on the page type
"working/computational or file/persistient") based on the LRUD (least
recently used) algorythm.  it starts to do this when the number of pages
on the free list drops below minfree until it reaches maxfree.

so, if lrud marks a page for a candidate and then pages it out it will
only be paged back in if the kernel requires it...

if the kernel does not need it back in, then it will stay on paging
space until the process that it belongs to exits/dies or is killed or
the system shuts down.

Hope this helps
Mark

--
Posted via http://dbforums.com

If using vmstat to look at the pi, po:

po:
Incremented for each page written out by the virtual memory manager.
The count is incremented for page outs to page space AND FOR PAGE OUTS
TO FILE SPACE. Along with the page in statistic, this represents the
total amount of real I/O initiated by the virtual memory manager.

You will only page in working storage NOT persistant storage as the
vmstat output shows.  So, you can 'page out' without ever 'paging in'.
 Look at your fr column.  Are you freeing a lot pers pages from your
memory?  You may want to look at the vmtune command.

1) why is the norm to have more page-outs than page-ins?

2) if my definition of page-outs' and page-ins' is right?

3) when there is high page-ins and high page-outs, that equals to
swapping (of whole processes) which is normally a bad thing?

Thanks in Advance!

Quote:>> Not the whole truth.
>> You will only page in working storage NOT persistant
>>storage as the vmstat output shows.

Quote:>>po:
>>Incremented for each page written out by the virtual >>memory manager.
>>The count is incremented for page outs >>to page space AND FOR PAGE
>>OUTS TO FILE SPACE. >>Along with the page in statistic, this
>>represents the total >>amount of real I/O initiated by the virtual
>>memory >>manager.

Cheers
Mark

--
Posted via http://dbforums.com

hope this helps

--
Doing AIX support was the most monty-pythonesque
activity available at the time.
Eagerly awaiting my thin chocolat mint.