kern/51982: sio1: interrupt-level buffer overflows

Bruce Evans bde at
Thu May 8 17:04:52 PDT 2003

On Fri, 9 May 2003, Bruce Evans wrote:

> ...
> The original version provides enough buffering for about 4 hardclock
> ticks (default 40 msec on i386's; much smaller on some other arches)
> of input at full speed.  The third version provides 400 msec of
> buffering.

PS: you should also try to find what is holding Giant for more than 40
msec.  Most syscalls hold it from near their start to near their
completion, but most syscalls don't take nearly that long.  It is
easy to write broken ones that do - just spin for a long time, or
return a huge amount of data via sysctl.


More information about the freebsd-bugs mailing list