[Let's CC Andrew to pick up the patch - please see bellow] On Tue 04-01-11 23:52:42, CAI Qian wrote: > ----- Original Message ----- > > On Tue 04-01-11 05:21:46, CAI Qian wrote: > > > > > > > > 3) overcommit 2gb hugepages. > > > > > mmap(NULL, 18446744071562067968, PROT_READ|PROT_WRITE, > > > > > MAP_SHARED, > > > > > 3, 0) = -1 ENOMEM (Cannot allocate memory) > > > > > > > > Hmm, you are trying to reserve/mmap a lot of memory (17179869182 > > > > 1GB > > > > huge pages). > > > That is strange - the test code merely did this, > > > addr = mmap(ADDR, 2<<30, PROTECTION, FLAGS, fd, 0); > > > > Didn't you want 1<<30 instead? > No, it was expecting to use both the allocate + overcommited 1GB pages. Then you propably wanted 2*1UL<<30 rather than 2<<30 which is something different than you want, I guess. Anyway this is not related to the bogus value in nr_overcommit_hugepages after your testcase.