Matthew Dillon said: > > We are attempting to reproduce the problem with a smaller dataset, but > if anyone is hot on the pipe code in the kernel and can give it a > once-over > we may be able to find the bug more quickly. > After a quick code inspection (and I really don't remember the details much anymore), it seems that there is a possibility for parts of the state of a pipe to be grabbed before certain locking operations (e.g. pipelock), and that state might change. This could be worse in a multi-writer or multi-reader situation. Just a hint. -- John | Never try to teach a pig to sing, dy...@iquest.net | it makes one look stupid jdy...@nc.com | and it irritates the pig.
To Unsubscribe: send mail to majord...@freebsd.org with "unsubscribe freebsd-hackers" in the body of the message