Date: Mon, 12 May 2003 12:18:42 +1000 (EST) From: Bruce Evans <bde@zeta.org.au> To: Bakul Shah <bakul@bitblocks.com> Cc: "M. Warner Losh" <imp@bsdimp.com> Subject: Re: Interrupt latency problems Message-ID: <20030512121311.G77707@gamplex.bde.org> In-Reply-To: <200305112258.h4BMwWPF029180@bitblocks.com> References: <200305112258.h4BMwWPF029180@bitblocks.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sun, 11 May 2003, Bakul Shah wrote: > Is it possible to cheaply check how long a mutex was held? No, since reading the time can't be done cheaply. > If it crosses some sysctl var set threshold you can increment > some count and/or drop into the debugger. That is one way to > find all mutex slowpokes. You can even find a distribution > by incrementing an array element. Array indexed by heldtime > rounded down to multiples of 10ms or so. Just an idea -- > ignore it if it doesn't make sense! The MUTEX_PROFILING option implements most of this. Bruce
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20030512121311.G77707>