Re: Clock sweep not caching enough B-Tree leaf pages? - Mailing list pgsql-hackers

From Peter Geoghegan
Subject Re: Clock sweep not caching enough B-Tree leaf pages?
Date
Msg-id CAM3SWZSdfy1U9MAtPVEnDPuvghgBJoQEnk+3kpAhQ13=+A_fyg@mail.gmail.com
Whole thread Raw
In response to Re: Clock sweep not caching enough B-Tree leaf pages?  (Tom Lane <tgl@sss.pgh.pa.us>)
Responses Re: Clock sweep not caching enough B-Tree leaf pages?  (Tom Lane <tgl@sss.pgh.pa.us>)
Re: Clock sweep not caching enough B-Tree leaf pages?  (Peter Geoghegan <pg@heroku.com>)
List pgsql-hackers
On Mon, Apr 21, 2014 at 5:50 PM, Tom Lane <tgl@sss.pgh.pa.us> wrote:
> ARC *was* the predecessor algorithm.  See commit 5d5087363.

I believe that the main impetus for replacing ARC with clock sweep
came from patent issues, though. It was a happy coincidence that clock
sweep happened to be better than ARC, but that doesn't mean that ARC
didn't have some clear advantages, even if it wasn't worth it on
balance. LRU-K, and 2Q have roughly the same advantages. I'm
reasonably confident you can have the best of both worlds, or
something closer to it.

-- 
Peter Geoghegan



pgsql-hackers by date:

Previous
From: Tatsuo Ishii
Date:
Subject: Re: Perfomance degradation 9.3 (vs 9.2) for FreeBSD
Next
From: Josh Berkus
Date:
Subject: Re: assertion failure 9.3.4