Hi, feel free to add an entry to the ideas list in the wiki, it is prominently linked in the top current links section. If you don't have access and don't want to register, just provide a nice text in the style of the ideas page and someone can add it.
And related to the subject: wasn't it you who developed the automatic benchmarking stuff? If yes, why not make it available? If you don't have he resources, I offer my help to make it available somewhere. Bye, Alexander. -- Send via an Android device, please forgive brevity and typographic and spelling errors. Erik Cederstrand <e...@cederstrand.dk> hat geschrieben: Den 21/12/2011 kl. 15.20 skrev Randy Schultz: > I agree whole-heartedly. I guess I wasn't clear. I wasn't trying to say most > SA's never tune, only that from watching other SA's over the years, little > tuning is done. As a casual SA, I often find I'm fumbling around in the dark to find out if my server is running optimally. I can check CPU and memory usage, but finding out if I could get my server to perform better by fiddling with block sizes or any number of sysctls is daunting. Who knows, maybe my batch jobs can complete 50% faster, or my CPU load can go from 20% to 10%? I really like the mysqltuner script for MySQL in this regard because it contains all the hard-earned experience of others and actually manages to suggest useful values for the configuration file for me to adjust. It would be great if there was something similar for FreeBSD that could suggest things like "hey, you are getting interrupt storms on em0, might want to check up on that" or "the block size on ada0 is insane for the current I/O load" or "on this particular hardware, try setting sysctls xxx and yyy to NNN instead" or "process 12345 is doing 1 billion system calls/sec, doesn't seem right". Something like taking the suggestions from http://serverfault.com/questions/64356/freebsd-performance-tuning-sysctls-loader-conf-kernel and trying to guess from my specific setup which knobs might apply, and possibly which values. I'm perfectly aware that this is not a substitution for actually thinking, profiling and benchmarking, but at least I'll have a place to start. Erik_______________________________________________ freebsd-performance@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-performance To unsubscribe, send any mail to "freebsd-performance-unsubscr...@freebsd.org"
_______________________________________________ freebsd-performance@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-performance To unsubscribe, send any mail to "freebsd-performance-unsubscr...@freebsd.org"
