Date: Mon, 19 Jul 2004 01:25:34 -0400 From: Brian Fundakowski Feldman <green@FreeBSD.org> To: current@FreeBSD.org Subject: lockups with src/tools/regression/gaithrstress Message-ID: <20040719052534.GA1038@green.homeunix.org>
next in thread | raw e-mail | index | archive | help
Running with or without kern.smp.disabled, with a very up-to-date kernel, I can easily lock up the system by running gaithrstress -t 50 a few times at once. There is nothing special that has changed in the last few weeks, though I have extensive changes to kqueue and VM which I consider entirely stable at this point. Anything causing a problem like this seems like it's due to changes within the last few weeks. The only clue I have comes from a previous panic() (which promptly just locked up going into "KDB: enter: panic"), "kse/thread mismatch" as generated by choosethread(). The connect() system call was trying to do an mi_switch() inside a mtx_lock() at the time. -- Brian Fundakowski Feldman \'[ FreeBSD ]''''''''''\ <> green@FreeBSD.org \ The Power to Serve! \ Opinions expressed are my own. \,,,,,,,,,,,,,,,,,,,,,,\
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20040719052534.GA1038>