Re: Squid and SIGPIPE

On Thu, Jul 05, 2007, Amos Jeffries wrote:
>
> I have been overlooking these for a while on the assumption that it was
> gdb catching something when it should have left it. I have just started
> wondering if this was in fact bad unexpected behaviour for the squid
> signals. Should I be looking into it?

Nope!

put this in ~/.gdbinit:

handle all nostop noprint
handle SIGSEGV stop
handle SIGPIPE stop

Adrian

>
> I run all my test builds under gdb with -ND to catch any big problems
> visibly instead of silent child restarts.
>
> It has been giving me
> Program received signal SIGPIPE, Broken pipe.
> 0xffffe410 in __kernel_vsyscall ()
> #0 0xffffe410 in __kernel_vsyscall ()
> #1 0xb7ce60b3 in __write_nocancel () from /lib/tls/i686/cmov/libc.so.6
> #2 0x081128e2 in commHandleWrite (fd=14, data=0x8326884) at comm.cc:1963
> #3 0x080876d5 in comm_select (msec=10) at comm_epoll.cc:309
> #4 0x0811623e in CommSelectEngine::checkEvents (this=0xbfbb92fc,
> timeout=10) at comm.cc:2614
> #5 0x0809ba81 in EventLoop::checkEngine (this=0xbfbb92bc,
> engine=0xbfbb92fc, primary=true) at EventLoop.cc:50
> #6 0x0809bc1a in EventLoop::runOnce (this=0xbfbb92bc) at EventLoop.cc:124
> #7 0x0809bd4a in EventLoop::run (this=0xbfbb92bc) at EventLoop.cc:100
> #8 0x080d62ee in main (argc=4, argv=0xbfbb93b4) at main.cc:1310
>
> or similar under some easily repeatable conditions.
Received on Thu Jul 05 2007 - 07:44:56 MDT