Continued: MySQL connection benchmarking
Posted by Robert Swarthout | Filed under Apache, Benchmarking, MySQL, PHP
I was asked by a fellow Schematicer to see if there was a performance difference if the fourth parameter of mysql_connect was set to true if it would make any difference. I would assume that it would not make any difference but I went ahead and ran the variation to be sure, the results are below.
Run #1:
11409 fetches, 20 max parallel, 45636 bytes, in 600.011 seconds
4 mean bytes/connection
19.0146 fetches/sec, 76.0586 bytes/sec
msecs/connect: 0.211857 mean, 39.668 max, 0.029 min
msecs/first-response: 1050.65 mean, 2662.53 max, 323.514 min
HTTP response codes: code 200 — 11409
Run #2:
11141 fetches, 20 max parallel, 44564 bytes, in 600.005 seconds
4 mean bytes/connection
18.5682 fetches/sec, 74.2727 bytes/sec
msecs/connect: 0.206869 mean, 30.293 max, 0 min
msecs/first-response: 1076.17 mean, 2317.13 max, 350.16 min
HTTP response codes: code 200 — 11141
Run #3:
11183 fetches, 20 max parallel, 44732 bytes, in 600 seconds
4 mean bytes/connection
18.6383 fetches/sec, 74.5533 bytes/sec
msecs/connect: 0.201182 mean, 24.691 max, 0.03 min
msecs/first-response: 1071.81 mean, 2448.18 max, 366.686 min
HTTP response codes: code 200 — 11183
Results Analysis
- Average requests per second: 18.7043
- Average requests completed: 11,244
These results can be compared to the previous post on this topic.
