Messages in this thread | | | Date | Wed, 27 Feb 2008 11:09:12 -0600 | From | Paul Jackson <> | Subject | Re: [patch 5/6] mempolicy: add MPOL_F_RELATIVE_NODES flag |
| |
Lee wrote: > 1) this IS a change in behavior, right? My first inclination is to shy > away from this. However, ... > > 2) the current interaction of mempolicies with cpusets is not well > documented--until Paul's cpuset.4 man page hits the streets, anyway. > That doc does say that mempolicy is not allowed to use a node outside > the cpuset. It does NOT say how this is enforced--reject vs masking vs
We should strive to minimize change in existing behaviour, especially on points where either way could be arguably a reasonable choice in some situations, and neither way is a clearly inescapable bug in other situations.
One almost always breaks someone, somewhere with such changes. You need a compelling reason to do that, not just a "on this hand, on that hand" design choice.
-- I won't rest till it's the best ... Programmer, Linux Scalability Paul Jackson <pj@sgi.com> 1.940.382.4214
| |