From: John L. <le...@mo...> - 2002-09-13 21:09:23
|
On Fri, Sep 13, 2002 at 08:29:38PM +0200, David Smith wrote: > All that is needed is a patch to the nmi handler to make sure the page > fault handler knows we're in an interrupt (see below). > > The patch I'm currently using has get_user() instead of locking, and > so far there have been no problems (that is still all with RTC on > a single pentium classic, though...). If you can send me a patch that should work using NMI, I'll see to give it a go on my two-way. My biggest concern about all this is simply interpretation. How can we present this data to the user in a useful way ? No arc information is present, meaning that the user must apply his knowledge of the source to work out the most likely "user" of stack samples. I'd be interested in people's ideas here. My 2.5 stuff might actually allow true call stack profiling. e.g. set depth 4, then simply dump 4 EIPs in the sample buffer. This would increase throughput by a factor of 4, but would allow true call stack profiling. I have no idea whether this would be too slow, but it's something interesting to consider. regards john -- "Be advised. Your bedroom may quietly detach from the house while you sleep." - Sarah Bee |