lockless pagecache 2
Get series with b4
b4 am [email protected]Versions newest first
- v1 Latest7 patches 8 repliesIn review
Patches in v1 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/7 | mm: remove PageReserved rolluparch/ drivers/ drivers/ +17 more | +204 | 0 replies | |
| 2/7 | mm: PG_free flaginclude/ mm/ | +15 | 0 replies | |
| 3/7 | mm: speculative get_pageinclude/ include/ mm/ +3 more | +85 | 0 replies | |
| 4/7 | radix-tree: lookup_slotinclude/ lib/ | +33 | 0 replies | |
| 5/7 | radix-tree: lockless readsideinclude/ lib/ | +90 | 4 replies | |
| 6/7 | mm: lockless pagecacheinclude/ include/ include/ +6 more | +112 | 4 replies | |
| 7/7 | mm: spinlock tree_lockdrivers/ fs/ fs/ +9 more | +46 | 0 replies |
Reviews trailers per patch
No Reviewed-by, Acked-by or Tested-by trailers for v1 yet.
Cover letter [patch 0/7] lockless pagecache 2
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 ;)
Signature · 3 lines
SUSE Labs, Novell Inc. Send instant messages to your online friends http://au.messenger.yahoo.com