To: mckenney@sequent.com (Paul E. McKenney) cc: andi@suse.de, andrea@suse.de, aono@ed2.com1.fc.nec.co.jp, beckman@turbolabs.com, bjorn_helgaas@hp.com, Hubertus Franke/Watson/IBM@IBMUS, Jerry.Harrow@Compaq.com, jwright@engr.sgi.com, kanoj@engr.sgi.com, kumon@flab.fujitsu.co.jp, norton@mclinux.com, suganuma@hpc.bs1.fc.nec.co.jp, sunil.saxena@intel.com, tbutler@hi.com, woodman@missioncriticallinux.com Date: 03/30/01 09:49 AM From: Kanoj Sarcar Subject: Re: your mail > > An alternative way is to declare policies will affect underlying > > objects (the shm segment), which works quite well for cooperating > > programs sharing well defined resources. Unfortunately, this will > > not work well in case of random programs using dso text for example. > > Although you can claim that this case should be mitigated by > > replication. > > > > Unfortunately, another bullet item that I didn't get to discuss. > > Look for "Policies on objects or address ranges/spaces". > > Your presentation certainly did generate quite a bit of discussion, > which is to be expected, given your long experience with and many > contributions to both NUMA and Linux. I would have liked to have > let the discussion go on longer, but it was important for the other > people to have a chance to describe their work. > > Thanx, Paul > Oh, I am not at all rattled that I didn't get to present all the ideas up front. In fact, I am partly responsible for it, since I mentioned at the beginning that I wanted it to be informal, and discussions were welcome. In retrospect, I should have covered the entire list first, and then we could have had discussions on the most juicy topics. Much easier trying to convey certain ideas face-to-face than via email. Well, you live, you learn. At today's BOF, I will try hard to cover the main bullet items first, so Linus at least gets to know of the existance of these ideas, then have a second pass and see which items we can discuss more. Kanoj