http://vincent.bernat.im/en/blog/2011-ssl-benchmark.html Interesting test results comparing and analyzing SSL performance. Using right combination of software and proper tunning, you can get up to 14000 TPS (re-shake every 80 requests) on HP DL 380 G7, with two Xeon L5630 (running at 2.13GHz for a total of 8 cores), without hyperthreading, using a 2.6.39 kernel (HZ is set to 250) and two Intel 82576 NIC.
http://news.ycombinator.com/item?id=2972107 Also see http://lists.kde.org/?l=kde-scm-interest&m;=1276129572… Especially the attachment linked from that page.
http://news.ycombinator.com/item?id=2972107 Also see http://lists.kde.org/?l=kde-scm-interest&m;=1276129572… Especially the attachment linked from that page.
https://gerrit.wikimedia.org/r/gitweb?p=operations/puppet.git;a=tree;f=files;h=daedad4c7d4257fce2da9619ee169fbca7ffac1d;hb=HEAD
https://gerrit.wikimedia.org/r/gitweb?p=operations/puppet.git;a=tree;f=files;h=daedad4c7d4257fce2da9619ee169fbca7ffac1d;hb=HEAD All sysadmins: take a note: Wikipedia opened access to it’s site configuration management: a git repository with config files for various system software
https://gerrit.wikimedia.org/r/gitweb?p=operations/puppet.git;a=tree;f=files;h=daedad4c7d4257fce2da9619ee169fbca7ffac1d;hb=HEAD All sysadmins: take a note: Wikipedia opened access to it’s site configuration management: a git repository with config files for various system software
http://haproxy.1wt.eu/10g.html
http://haproxy.1wt.eu/10g.html HA Proxy [synthetic] benchmarks on 10Gbit traffic. Linux network stack is the bottle neck here, not HAProxy, i.e. you can 10G line rate on big frames and few connections.
http://forums.oracle.com/forums/thread.jspa?messageID=1108985 It appears to be an interesting bug in some versions of Oracle 10g, on Linux 2.6.x oracle process goes in loop doing times() system call if machine uptime < 199 days. Nice!!! / Oracle refs are bug 4612267 and 5867987 ) . The solution is to reboot.
http://aws.amazon.com/message/65648/ Postmortem for the April-2011 EC2/EBS outage. It looks like a human errors plus unfortunate cascade of events lead to a requests storm that brought down EBS storage. Also, it appears that Amazon mis-estimated spare storage capacity needed for recovery from such events.