On 06/05/2012 05:16 PM, leonid.moiseichuk@xxxxxxxxx wrote: >> -----Original Message----- >> From: penberg@xxxxxxxxx [mailto:penberg@xxxxxxxxx] On Behalf Of ext >> Pekka Enberg >> Sent: 05 June, 2012 11:02 >> To: Minchan Kim > ... >>> Next concern is that periodic timer of implementation. >>> I think it would add direct hook in vmscan.c rather than peeking raw >>> vmstat periodically by timer so we can control more fine-grained way >> without unnecessary overhead. >> >> If the hooks are clean and it doesn't hurt the !CONFIG_VMEVENT case, I'm >> completely OK with that. > > On the previous iteration hooking vm was pointed as very bad idea, so in my version I installed shrinker to handle cases when we have memory pressure. > Using deferred timer with adequate timeout (0.250 ms or larger) fully suitable for userspace and produce adequate overhead > -> by nature such API should not be 100% accurate, anyhow applications cannot handle situation as good as kernel can provide, 0.5MB space accuracy, 100ms is maximum user-space require for 64-1024MB devices. > I didn't follow previous iteration you mentioned so I don't know the history. I think it's a not good idea if LMN(low memory notifier) is needed by only embedded world. Maybe in that case, we might control it enough by only vmstat events but now we know many folks want it so we are trying to make it general. IMHO, for meeting various requirement, vmstat raw event isn't enough so we need direct hook in vmscan and should abstract it to some levels. Of course, VM guys should maintain it to work best as VM algorithm are changing. -- Kind regards, Minchan Kim -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>