John Fremlin's swap patch
Hi John, I haven't had a chance to test your patch yet, but I will be sure to try it when I get the chance.
Your analysis of the problems with the current use of swap_cnt seems accurate - though i don't know much about cache miss speeds and such. I guess the problem won't fully be solved until the swapping routine is based on pages instead of processes, and can scan pages on the inactive list only.
-BenRI
Signature · 8 lines
"I want to be in the light, as He is in the Light, I want to shine like the stars in the heavens." - DC Talk, "In the Light" Benjamin Redelings I <>< http://www.bol.ucla.edu/~bredelin/ -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM, see: http://www.linux.eu.org/Linux-MM/
Quoted 5 lines · Benjamin Redelings I
Your analysis of the problems with the current use of
swap_cntseems accurate - though i don't know much about cache miss speeds and such. I guess the problem won't fully be solved until the swapping routine is based on pages instead of processes, and can scan pages on the inactive list only.
I agree. My patch was just a quick hack, the root of the problem is to get a good way of finding pages to swap out.
I agree that going through the set of pages that can be discarded is more reasonable (and logically less complex though I haven't got a clear picture of how difficult it is to implement).
Signature · 5 lines
http://altern.org/vii -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM, see: http://www.linux.eu.org/Linux-MM/