I work at a company that has had very similar issues. One of the suspected theories (because this seems to strike us even within the JVM where we aren't forking) is that it's a problem between the hypervisor and the hardware.
What kind of hardware were you running when you found this problem? We found that there are at least three varieties of m1.xlarge CPU architectures (cat /proc/cpuinfo). Easiest way to distinguish is by checking the cpu cache size. We've seen 1M cache, 4M and 6M. The problem you're detailing has been consistently reproduced for us on the 1M cache variety of instances. Is this true for you, too? -- You received this bug notification because you are a member of Ubuntu Bugs, which is a direct subscriber. https://bugs.launchpad.net/bugs/708920 Title: Strange 'fork/clone' blocking behavior under high cpu usage on EC2 -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
