On Tue, 2023-07-18 at 16:57 -0500, Haitao Huang wrote: > On Tue, 18 Jul 2023 16:36:53 -0500, Dave Hansen <dave.hansen@xxxxxxxxx> > wrote: > > > On 7/18/23 14:22, Haitao Huang wrote: > > > I agree this is the race. But for this to happen, that is at #1 you have > > > only one non-SECS page left so #3 can happen. That means it is already > > > high pressure > > > > I think our definitions of memory pressure differ. > > > > Pressure is raised by allocations and dropped by reclaim. This > > raise->drop cycle is (or should be) time-limited and can't take forever. > > The reclaim either works in a short period of time or something dies. > > If allocations are transient, pressure is transient. > > > > Let's say a pressure blip (a one-time event) comes along and pages out > > that second-to-last page. That's pretty low pressure. Years pass. The > > enclave never gets run. Nothing pages the second-to-last page back in. > > A second pressure blip comes along. The SECS page gets paged out. > > > > That's two pressure blips in, say 10 years. Is that "high pressure"? > > Okay, that explains. I would consider it still triggered by high pressure > blips :-) > > But I agree we can drop the mentioning of pressure altogether and just > state the race so no confusions. Also perhaps the patch title is too vague. Adding more information doesn't hurt I think, e.g., mentioning it is a fix for NULL pointer dereference in the EAUG flow.
