Messages in this thread | | | Date | Mon, 29 Apr 1996 17:29:52 +0100 | Subject | Small swapfile.c patch | From | Stephen Tweedie <> |
| |
Hi,
In article <MlUxb1Nz0001Q0n0pi@vorlon.unl.edu>, Jeff Haumont <operator@abel-jhaumont.unl.edu> writes:
> After reading the message about how to enable striped swapping a while > ago, I tried it and it made an absolutely tremendous difference for me. > (It doubled the performance of the stupid little benchmark I was using) > Because of this I suggest:
> diff linux/mm/swapfile.c linux/mm/swapfile.c.old
Your patch is reversed...
> The first change will give all swap partitions the same priority if they > are not set explicitly or set incorrectly, basically enabling striping > by default. The only time that I can think of that this would not give > a performance increase would be when more than one swap partition exists > on a drive.
Nope. There are many reasons to prioritise swap. For example, you might want to use a slow drive to act as overflow with a fast primary swap drive, or your overflow swap partition might be on the same drive as your /usr and /lib. Keeping primary swap and libs+binaries on separate drives makes a huge difference in perforance.
> The second change is pretty obvious. Its nice to see the priority when > you are trying to set this up and want to make sure the kernel is > getting the message. It also might help more people become aware of > this feature.
Not a bad idea.
Cheers, Stephen. --- Stephen Tweedie <sct@dcs.ed.ac.uk> Department of Computer Science, Edinburgh University, Scotland.
| |