Messages in this thread | | | Date | Thu, 14 Feb 2008 17:44:11 -0800 (PST) | From | David Rientjes <> | Subject | Re: [patch 3/4] mempolicy: add MPOL_F_STATIC_NODES flag |
| |
On Thu, 14 Feb 2008, David Rientjes wrote:
> We'll need to decide whether mpol_equal() is determining the equality of > the currently effected mempolicy (whereas policy->user_nodemask is > irrelevant) or the whole intended mempolicy overall. >
I've done the latter in the latest patchset.
Since mpol_equal() is only used for determining whether nearby vmas can be merged, it is only logical to merge them if they share the mempolicy intent of the user if MPOL_F_STATIC_NODES or any flag that makes sense of policy->user_nodemask is used.
> > Could we have mpol_to_str() mark policies which are > > MPOL_F_RELATIVE_NODES or MPOL_F_STATIC_NODES? Perhaps > > by adding a suffix of "|relative" or "|static" or some > > such. > > > > I'd like to keep it in the same format as the tmpfs mount option which is > '=relative' and '=static'. >
In preparation for mode flags in addition to MPOL_F_STATIC_NODES to be added (like MPOL_F_RELATIVE_NODES or whatever Paul decides to call it based on the latest feedback, I've prepared mpol_to_str() to have this format
interleave=static|relative=1-3
as viewable from /proc/pid/numa_maps. This is also how tmpfs mount options will be specified.
[ Of course the above example can't happen since MPOL_F_STATIC_NODES and MPOL_F_RELATIVE_NODES are disjoint, but it's sufficient for the example. ]
| |