-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Chuck,
On 5/18/2009 4:40 PM, Caldarale, Charles R wrote: >> From: Christopher Schultz [mailto:ch...@christopherschultz.net] >> Subject: Re: Apache httpd vs Tomcat static content performance >> [Revised/Updated] >> >> After reading some of your feedback, I've decided to make some changes: >> >> - - Using TC 6.0.18 exclusively instead of 5.5 >> - - Using tcnative 1.1.16 instead of 1.1.12 >> - - Using httpd 2.2.11 instead of 2.2.10 >> - - Running tests for a certain amount of time instead of a >> certain number of requests > > JVM version? Still: java version "1.6.0_13" Java(TM) SE Runtime Environment (build 1.6.0_13-b03) Java HotSpot(TM) Client VM (build 11.3-b02, mixed mode, sharing) (don't worry, I'll also test the -server VM) I'll also be publishing /all/ config information when I actually publish my findings. Still default heap (turns out to be 64MB for my config). Interesting that after all my little 10-second tests, the JVM has only allocated 11MiB of its 64MiB max, and it's about 75% (8MiB) used right now. I have all connectors configured simultaneously, each with their own thread pools: Coyote/non-APR, Coyote/APR+sendfile, Coyote/APR-sendfile, Coyote/NIO+sendfile, Coyote/NIO-sendfile. Most connectors have allocated fewer than 5 request processor threads. We'll see what happens when I crank-up the concurrency. I suspect we'll see better things from the NIO connector, for instance. - -chris -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.9 (MingW32) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iEYEARECAAYFAkoRyg4ACgkQ9CaO5/Lv0PCcfwCfbwyxHYGBisMZy83kzFwoI4Vx JhQAni3uwBGhlOIVXf0JK7IYnZn0m3k0 =BWow -----END PGP SIGNATURE----- --------------------------------------------------------------------- To unsubscribe, e-mail: users-unsubscr...@tomcat.apache.org For additional commands, e-mail: users-h...@tomcat.apache.org
