On Sun, May 15, 2011 at 2:43 AM, Andi Kleen <andi@xxxxxxxxxxxxxx> wrote: > Copying back linux-mm. > >> Recently, we added following patch. >> https://lkml.org/lkml/2011/4/26/129 >> If it's a culprit, the patch should solve the problem. > > It would be probably better to not do the allocations at all under > memory pressure. ÂEven if the RA allocation doesn't go into reclaim Fair enough. I think we can do it easily now. If page_cache_alloc_readahead(ie, GFP_NORETRY) is fail, we can adjust RA window size or turn off a while. The point is that we can use the fail of __do_page_cache_readahead as sign of memory pressure. Wu, What do you think? > it may still "steal" allocations recently freed and needed by other > actors. This problem is general thing as well as RA. But it would be not a big problem in order-0 pages. If it's a really problem, it might sign we have to increase SWAP_CLUSTER_MAX. The concern I thought is order-0 allocation happens with other higher-order reclaims in parallel. order-0 allocation can steal other's high order pages. For it, I sent a patch but I didn't have enough time to dig in. https://lkml.org/lkml/2011/5/2/93 I have a plan to do. > > -Andi > -- > ak@xxxxxxxxxxxxxxx -- Speaking for myself only. > -- Kind regards, Minchan Kim -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxxx 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