Re: [RFC v5 0/8] Support volatile for anonymous range

2013-01-03 Thread Minchan Kim
Hello, On Thu, Jan 03, 2013 at 09:19:08AM -0800, Sanjay Ghemawat wrote: > On Wed, Jan 2, 2013 at 8:27 PM, Minchan Kim wrote: > > This is still RFC because we need more input from user-space > > people, more stress test, design discussion about interface/reclaim > > Speaking as one of the authors

Re: [RFC v5 0/8] Support volatile for anonymous range

2013-01-03 Thread Sanjay Ghemawat
On Wed, Jan 2, 2013 at 8:27 PM, Minchan Kim wrote: > This is still RFC because we need more input from user-space > people, more stress test, design discussion about interface/reclaim Speaking as one of the authors of tcmalloc, I don't see any particular need for this new system call for tcmalloc

[RFC v5 0/8] Support volatile for anonymous range

2013-01-02 Thread Minchan Kim
This is still RFC because we need more input from user-space people, more stress test, design discussion about interface/reclaim policy of volatile pages and I want to expand this concept to tmpfs volatile range if it is possbile without big performance drop of anonymous volatile range. (Let's defi