| From: | Pailloncy Jean-Gerard <jg(at)rilk(dot)com> |
|---|---|
| To: | pgsql-hackers <pgsql-hackers(at)postgresql(dot)org> |
| Cc: | Simon Riggs <simon(at)2ndquadrant(dot)com> |
| Subject: | Concurrent wait-lock |
| Date: | 2005-02-07 22:48:56 |
| Message-ID: | 024f8fb06469ffb872b918a2f391efc2@rilk.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
Hi,
There is better than lock-free algorithm, this is wait-free.
A lock-free algorithm guarantees progress regardless of whether some
processes are delayed or even killed and regardless of scheduling
policies. By definition, a lock-free object must be immune to deadlock
and livelock.
A wait-free algorithm guarantees that ALL processes will progress and
FINISH in a finite number of steps.
Wait-Free Reference Counting and Memory Management
http://www.cs.chalmers.se/~phs/TechnicalReports/Sun04_WaitFreeRef.pdf
There are many other paper at
http://www.cs.chalmers.se/~phs/
Cordialement,
Jean-Gérard Pailloncy
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Pailloncy Jean-Gerard | 2005-02-07 22:57:28 | Re: Thinking about breaking up the BufMgrLock |
| Previous Message | Greg Stark | 2005-02-07 22:45:23 | Re: Query optimizer 8.0.1 (and 8.0) |