Heads up, remap_file_pages() possibly slated for removal from Linux
Howdy folks, I wrote an article a ways back about PyPy and STM ( https://lwn.net/Articles/587923/ ) that talked PyPy using the remap_file_pages() system call on Linux. So I thought of you folks when I read an article in this week's LWN titled "The possible demise of remap_file_pages()". It is behind the subscription gate for the next week, but this link should allow you to read it: http://lwn.net/SubscriberLink/597632/6f444e69b9931d1a/ If you folks are still using remap_file_pages(), you may want to speak up in the thread on linux-kernel ... jake -- Jake Edge - LWN - jake@lwn.net - http://lwn.net
Hi Jake, On 8 May 2014 02:50, Jake Edge <jake@lwn.net> wrote:
http://lwn.net/SubscriberLink/597632/6f444e69b9931d1a/
If you folks are still using remap_file_pages(), you may want to speak up in the thread on linux-kernel ...
Thank you for the notice! I've explained the PyPy situation, and it looks now like they're going to replace remap_file_pages() with an emulation based on mmap() and, I hope, take care of the issue that the mmap() solution is limited to 65536 by default (i.e., increase the default limit). This would be good enough for PyPy, where the calls to remap_file_pages() are themselves not highly performance-critical. A bientôt, Armin.
participants (2)
-
Armin Rigo -
Jake Edge