One thing to keep in mind as well is that using multiple vcpus in a vm environment can actually decrease performance for all your VMs on the same host. If I weren't typing on a smartphone I would provide more detail on why this happens. I will try to elaborate in a bit.
Pete On Oct 15, 2012 11:40 AM, "Jonathan Billings" <[email protected]> wrote: > On Mon, Oct 15, 2012 at 11:01 AM, Jonathan Bayer < > [email protected]> wrote: > >> The problem is that when the req/sec starts to climb on the VM, all of a >> sudden the load average skyrockets to 40-50 or even higher. This kills the >> server and makes it totally unresponsive. >> >> Anybody have any suggestions? >> > > We monitor our web servers with Nagios, and use the check_apachestatus > plugin along with Apache HTTP's mod_status module. This lets us track the > httpd thread usage, so we can get a better idea on what's going on, and > what operations httpd is performing when it is slow. > > While our environment is probably not the same as yours, the problem we > had with RHEL5.x as a VM when it behaved similarly to yours was with the VM > guest's storage backend being less-than-ideally responsive. We also > monitored the disk I/O in nagios, so we could better correlate the httpd > behavior with the storage metrics. > > > -- > Jonathan Billings <[email protected]> > College of Engineering - CAEN - Unix and Linux Support > > > > _______________________________________________ > Discuss mailing list > [email protected] > https://lists.lopsa.org/cgi-bin/mailman/listinfo/discuss > This list provided by the League of Professional System Administrators > http://lopsa.org/ > >
_______________________________________________ Discuss mailing list [email protected] https://lists.lopsa.org/cgi-bin/mailman/listinfo/discuss This list provided by the League of Professional System Administrators http://lopsa.org/
