-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 All,
The message below was garbled when sent. Fortunately, it ended up being preserved correctly in my sent message folder. Here it is. - -chris - -------- Original Message -------- Subject: Re: Apache httpd vs Tomcat static content performance [more results] Date: Sat, 23 May 2009 11:16:35 -0400 From: Christopher Schultz <ch...@christopherschultz.net> To: Tomcat Users List <users@tomcat.apache.org> All, I have some more results to share. The other day, I ran my battery of tests using a concurrency of 40. The NIO connector failed (see thread "NIO Connector: Too many open files?") so I re-ran the tests last night for the 2 NIO connector configurations using the connectors for the upcoming 6.0.20 release (thanks Filip!). The setup is the same as last time with no changes except the upgrade to the NIO Connector and a concurrency of 40 instead of 1. Here's the data (again, apologies for the formatting: tabs are embedded and should copy-and-paste correctly into your favorite spreadsheet): File Size Apache httpd Coyote Coyote APR Coyote APR-sendfile Coyote NIO Coyote NIO-sendfile 4kiB 6307.55 7628.87 8230.45 9096.91 4969.78 4996.87 8kiB 11907.01 13625.75 15015.22 16216.13 8345.98 8331.45 16kiB 21511.06 20572.41 22564.75 22429.26 13932.04 14051.91 32kiB 36900.08 32013.61 35283.04 35281.78 23175.37 23213.86 64kiB 59987.84 45656.41 67222.52 46795.15 42869.37 34439.83 128kiB 89253.64 57845.10 111764.82 59878.29 72429.77 41162.18 256kiB 158988.25 68256.39 170342.89 71287.26 113206.39 43948.25 512kiB 199224.21 59159.82 193991.50 61591.43 143681.05 39052.58 1MiB 228606.84 62219.68 223536.86 65593.84 181073.70 40105.58 2MiB 204427.20 63819.99 241936.12 67755.48 193955.60 40158.96 4MiB 251554.92 65018.41 254518.59 68927.04 219885.29 41273.23 8MiB 252739.39 65325.90 260633.21 69351.87 230627.76 41579.37 16MiB 250098.08 65486.70 265946.32 69088.37 234902.65 41355.81 32MiB 262562.01 65041.41 268329.63 68747.39 242388.97 41055.28 Apache httpd and the APR+sendfile connector still appear to be giving similar results, which still makes sense given that the same code is really running in both cases. The NIO+sendfile connector politely didn't intrude on the contest between httpd and APR+sendfile, coming-in a close second. I'm interested to see what happens when I really start cranking-up the concurrency, since the NIO connector is really supposed to shine in that scenario. The other connector configurations remain poor performers for files larger than 32k. That last observation is interesting to me: it suggests that if you are running Tomcat as a static file server for small web app assets such as icons, CSS files, etc. then it really doesn't matter what connector you use: performance is comparable to using any of the other strategies. - -chris -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.9 (MingW32) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iEYEARECAAYFAkobHucACgkQ9CaO5/Lv0PDTgwCfZZdYHSJZ3vpaokHvDYmdB5vK 0vIAn2cHLp998j22SXzUZ2/CVwJenRPU =CsLL -----END PGP SIGNATURE----- --------------------------------------------------------------------- To unsubscribe, e-mail: users-unsubscr...@tomcat.apache.org For additional commands, e-mail: users-h...@tomcat.apache.org
