I've been twiddling around with HEAD, since it supports BDB 4.5 and OL 2.3 doesn't, and noticed that when I do speed tests, HEAD is 66% slower than 2.3 (+ my patches from HEAD for connections). This seems interesting to me, since my connection code is largely from HEAD. In 2.3, I get 15,000+ auths/second on my 64 bit test systems, but with straight HEAD code, I only get 5,000 auths/second.
In both cases, the lightweight dispatcher code is enabled. Any thoughts on what else may be affecting HEAD? The configuration is very simple, just a small 250k bdb database.
--Quanah
-- Quanah Gibson-Mount Product Engineer Symas Corporation Packaged, certified, and supported LDAP solutions powered by OpenLDAP: http://www.symas.com
Quanah Gibson-Mount wrote:
I've been twiddling around with HEAD, since it supports BDB 4.5 and OL 2.3 doesn't, and noticed that when I do speed tests, HEAD is 66% slower than 2.3 (+ my patches from HEAD for connections). This seems interesting to me, since my connection code is largely from HEAD. In 2.3, I get 15,000+ auths/second on my 64 bit test systems, but with straight HEAD code, I only get 5,000 auths/second.
In both cases, the lightweight dispatcher code is enabled. Any thoughts on what else may be affecting HEAD? The configuration is very simple, just a small 250k bdb database.
I'm not seeing any slowdown against back-null, so it would seem to be BDB or back-bdb related.
Howard Chu wrote:
Quanah Gibson-Mount wrote:
I've been twiddling around with HEAD, since it supports BDB 4.5 and OL 2.3 doesn't, and noticed that when I do speed tests, HEAD is 66% slower than 2.3 (+ my patches from HEAD for connections). This seems interesting to me, since my connection code is largely from HEAD. In 2.3, I get 15,000+ auths/second on my 64 bit test systems, but with straight HEAD code, I only get 5,000 auths/second.
In both cases, the lightweight dispatcher code is enabled. Any thoughts on what else may be affecting HEAD? The configuration is very simple, just a small 250k bdb database.
I'm not seeing any slowdown against back-null, so it would seem to be BDB or back-bdb related.
Actually, there's no functional difference in back-bdb between HEAD and RE23. But I'm definitely seeing a 10% slowdown in HEAD vs RE23 now. Will have to profile it to see where the difference lies.
Interesting that I'm not seeing the same extremes as you; I'm getting 6600 auths/second on RE23, and 6200/sec on HEAD on my dev machine.
--On Monday, October 16, 2006 3:48 AM -0700 Howard Chu hyc@symas.com wrote:
Howard Chu wrote:
Quanah Gibson-Mount wrote:
I've been twiddling around with HEAD, since it supports BDB 4.5 and OL 2.3 doesn't, and noticed that when I do speed tests, HEAD is 66% slower than 2.3 (+ my patches from HEAD for connections). This seems interesting to me, since my connection code is largely from HEAD. In 2.3, I get 15,000+ auths/second on my 64 bit test systems, but with straight HEAD code, I only get 5,000 auths/second.
In both cases, the lightweight dispatcher code is enabled. Any thoughts on what else may be affecting HEAD? The configuration is very simple, just a small 250k bdb database.
I'm not seeing any slowdown against back-null, so it would seem to be BDB or back-bdb related.
Actually, there's no functional difference in back-bdb between HEAD and RE23. But I'm definitely seeing a 10% slowdown in HEAD vs RE23 now. Will have to profile it to see where the difference lies.
Interesting that I'm not seeing the same extremes as you; I'm getting 6600 auths/second on RE23, and 6200/sec on HEAD on my dev machine.
Hm, are you using slamd, with 5 different hosts and 20 clients on that system? I'm betting the slowdown you are seeing is the same slowdown, it is just exasperated by the number of systems being used to slam(d) it. Of course, I don't exactly know how your test was configured. ;)
--Quanah
-- Quanah Gibson-Mount Product Engineer Symas Corporation Packaged, certified, and supported LDAP solutions powered by OpenLDAP: http://www.symas.com
-
Howard Chu -
Quanah Gibson-Mount