Hi everyone,
i am doing some research work that need to utilize
the swapping stuff of linux kernel. i add one separate zone, which only
used for my application, i prevent the other application or kernel from
allocating from that zone. i marked every page that allocated form my
zone with reclaimable flag. but when my zone is nearly full, which will
trigger the kswapd to swap out some pages, the balance_pgdat found the
reclaimable pages inside my zone is 0. because the NR_INACTIVE_FILE,
NR_ACTIVE_FILE, NR_INACTIVE_ANON, NR_ACTIVE_ANON lru list are all empty.
i do not know why kernel did not do any statistics on my own zone.
Does anyone know why this happen? and how to solve this? i need swapping support on my own zone too.
Thanks,
Sheng
--
Sheng Qiu
Texas A & M University
Room 302 Wisenbaker
email: herbert1984106@xxxxxxxxx
College Station, TX 77843-3259