Messages in this thread | | | Date | Sat, 2 May 1998 14:19:24 -0700 (PDT) | From | Linus Torvalds <> | Subject | Re: [PATCH] kswapd fully sysctl tunable |
| |
On Sat, 2 May 1998, MOLNAR Ingo wrote: > > > +dcache_agressive This option can be used when the dcache > > + is taking up too much memory. This usually > > + only happens on machines with less than 16 > > + megabytes of RAM. Increasing this value makes > > + kswapd prune the dcache more agressively, but > > + it makes name cacheing less effective, causing > > + more disk reads and decreased performance. > > + Use this when you need to, but use with care! > > not nitpicking, but i'm wondering wether this option just hides the real > problem. Shouldnt the dcache notice such low-mem situations automagically?
I have something which should work. I think Rik has been hiding the problem and I just noticed that I accepted into 99 a patch that definitely should _not_ go in (the thing to change the "state" variable whether a free operation works or not is wrong - we want to keep freeing from one pool as long as it is "easy".
Rik, if you have problems with this under certain circumstances (like swapping out too much even though there is plenty of buffers left), that indicates that something is being too aggressive even though "i" (the "aggressivemess factor") is set to a high value ("i = 6" means that it shouldn't try all that hard, while "i = 0" means that we're really close to meltdown and we should go crazy).
Linus
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu
| |