This is the mail archive of the libc-alpha@sourceware.org mailing list for the glibc project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: Question about madvise(DONTNEED) in glibc malloc


On Sun, Apr 14, 2013 at 09:37:16AM -0700, KOSAKI Motohiro wrote:
> Hi all,
> 
> Now, we linux MM folks discuss are discussing about new memory
> discarding feature. (https://lkml.org/lkml/2013/3/12/105). The
> motivation is similar wtih MADV_FREE, but more efficient.
> (http://lwn.net/Articles/230799)

If you're following this, do you know if vrange(VRANGE_NOVOLATILE) has
failure cases? This makes a big difference to how usable it is by
malloc implementations. madvise re-mmapping new zero pages over the
range are nice in that the range is not using physical memory, but
still remains committed and immediately usable without any risk of
failure to get it back. If vrange can fail to "get back" the range,
this makes it a lot harder to use robustly.

Rich


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]