DO NOT REPLY TO THIS EMAIL, BUT PLEASE POST YOUR BUG RELATED COMMENTS THROUGH THE WEB INTERFACE AVAILABLE AT <http://nagoya.apache.org/bugzilla/show_bug.cgi?id=23795>. ANY REPLY MADE TO THIS MESSAGE WILL NOT BE COLLECTED AND INSERTED IN THE BUG DATABASE.
http://nagoya.apache.org/bugzilla/show_bug.cgi?id=23795 mod_status reports too much CPU when using worker mpm Summary: mod_status reports too much CPU when using worker mpm Product: Apache httpd-2.0 Version: 2.0.47 Platform: Other OS/Version: Other Status: NEW Severity: Minor Priority: Other Component: mod_status AssignedTo: [email protected] ReportedBy: [EMAIL PROTECTED] When looking at /server-status, it is reporting about 10 times too much CPU time when compared to the prefork MPM. This is on SGI IRIX 6.5.20m compiled with the following flags and the SGI MIPsPro compiler: ./configure --enable-ssl=static --enable-deflate --enable-mods-shared=most --with-ssl=/usr/local/ssl --with-devrandom --with-mpm=worker Here's the relevant output from mod_status when compiled without --with-mpm=worker: Total accesses: 41 - Total Traffic: 1.9 MB CPU Usage: u6 s.26 cu0 cs0 - 29.8% CPU load 1.95 requests/sec - 94.1 kB/second - 48.2 kB/request 1 requests currently being processed, 7 idle workers And with it: Total accesses: 41 - Total Traffic: 1.9 MB CPU Usage: u67.21 s3.64 cu0 cs0 - 221% CPU load 1.28 requests/sec - 61.8 kB/second - 48.2 kB/request 1 requests currently being processed, 49 idle workers With a bit of stress testing with multiple clients, I can get the CPU load reported to be on the order of 2-4000%, the machine only has 2 CPUs. The requests on each run was generated from a fresh start over SSL and using the requests. mod_jk 1.2.5 is also loaded into the server. --------------------------------------------------------------------- To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
