Date: Sun, 18 May 2014 11:48:42 -0400 From: John Baldwin <jhb@FreeBSD.org> To: Chris Torek <torek@torek.net>, freebsd-hackers@freebsd.org Subject: Re: bad call to sched_bind() => hang, even with INVARIANTS Message-ID: <5378D65A.90905@FreeBSD.org> In-Reply-To: <201405151720.s4FHK8RC065430@elf.torek.net> References: <201405151720.s4FHK8RC065430@elf.torek.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On 5/15/14, 1:20 PM, Chris Torek wrote: > I was poking around with a bhyve emulation, where the emulation > has only one CPU but the real systems have more. > > In our real-system code we had a sched_bind() that just assumed there > were 2 or more CPUs, instead of just the 1. This caused the entire > system to hang. (Note: using SCHED_ULE.) > > It's not immediately obvious to me what went wrong "underneath" to > cause the whole-system hang, but clearly it is wrong to attempt to > pin a thread to a CPU that does not exist. Should sched_bind() > have a KASSERT in it to make sure that the cpu argument is > sensible? (Or maybe even something a little more aggressive?) A KASSERT() is probably a good idea. -- John Baldwin
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?5378D65A.90905>