LWN.net Logo

lockless pagecache 2

From:  Nick Piggin <nickpiggin@yahoo.com.au>
To:  Paul McKenney <paul.mckenney@us.ibm.com>, Dipankar Sarma <dipankar@in.ibm.com>, Ingo Molnar <mingo@elte.hu>, linux-kernel <linux-kernel@vger.kernel.org>
Subject:  [patch 0/7] lockless pagecache 2
Date:  Thu, 11 Aug 2005 22:18:09 +1000

This is my second attempt at a lockless pagecache.

Patches are against 2.6.13-rc6, and have had reasonable
stressing (albeit on small SMPs).

Main changes since last seen:
* Code clarity and commenting improvement.

* Fix race where multiple concurrent failed speculative
   reference takers could be confused into thinking a free
   page wasn't free, due to the elevated refcounts.

* Convert radix tree node freeing over to RCU. I completely
   missed this problem in my first attempt. (My first real
   RCU attempt - completely wrong?).

* page_cache_get_speculative previously used only preempt_
   disable to stop the current CPU from entering the page
   allocator. Needs to turn off interrupts too.

   Paul picked this bug up without seeing the code, just a
   vague description of what I was trying to do. All I
   picked up was my jaw from the ground ;)

-- 
SUSE Labs, Novell Inc.

Send instant messages to your online friends http://au.messenger.yahoo.com 
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Copyright © 2005, Eklektix, Inc.
Comments and public postings are copyrighted by their creators.
Linux is a registered trademark of Linus Torvalds