On Thu, 2008-08-07 at 15:36 +0200, Michael Kerrisk wrote: > Lee, > > As for the previous... Is this a documentation improvement, or is it a > kerenl behavior change? Again, a change in behavior in 2.6.26. > > Cheers, > > Michael > > Lee Schermerhorn wrote: > > man2/mbind.2 | 7 +++---- > > 1 files changed, 3 insertions(+), 4 deletions(-) > > > > Index: man-pages-3.05/man2/mbind.2 > > =================================================================== > > --- man-pages-3.05.orig/man2/mbind.2 2008-07-29 16:54:13.000000000 -0400 > > +++ man-pages-3.05/man2/mbind.2 2008-07-29 16:57:04.000000000 -0400 > > @@ -212,10 +212,9 @@ the nodes specified in > > If > > .I nodemask > > specifies more than one node, page allocations will come from > > -the node with the lowest numeric node ID first, until that node > > -contains no free memory. > > -Allocations will then come from the node with the next highest > > -node ID specified in > > +the node closest to the node from which the allocation was requested, > > +until that node contains no free memory. > > +Allocations will then come from the next closest node specified in > > .I nodemask > > and so forth, until none of the specified nodes contain free memory. > > Pages will not be allocated from any node not specified in the > > > -- To unsubscribe from this list: send the line "unsubscribe linux-numa" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
