On Mon, Sep 30, 2024 at 12:17:40PM GMT, Lennart Poettering <lennart@xxxxxxxxxxxxxx> wrote: > > Does this mean that if something can't afford its working set to be > > paged out for latency reasons, it _also_ can't afford its own code to be > > paged out, and therefore should call mlockall() or otherwise explicitly > > mlock() the code and data it is operating on, rather than expecting that > > swap be disabled? > > Sure, if you want to make sure that your memory is never paged out, > then mlockal() or something similar is the way to go. Something (not so) similar can also be: MemoryLow=$workingset MemoryMin=$workingset or MemorySwapMax=0 > But of course you need ot know what you are doing, Ditto (this will affect reclaim on the rest of the system and truly sensitive app should better mark explicitly what's critical with the mlocks above). Michal
Attachment:
signature.asc
Description: PGP signature
