>Relegating kswapd to hardly more than idle status puts
>us back to where we were with Linux 1.1...
The efficient right/way is to free memory with the process that is
sleeping I think.
>Besides, does it make that much difference whether
>an RT task has to do MM work itself or if it is
>blocked by kswapd?
Yes:
1. if kswapd fails it will continue to run
2. if the process fails it will be killed soon
3. you free memory only when you really need memory
Andrea Arcangeli
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/