Re: assertion failed: stmem.cc:270: "0" in Squid 3

I'll review that code section.

A core is always good - you can then get squid up again and review the
state at leisure...

Rob

On Thu, 2003-05-08 at 19:19, Joe Cooper wrote:
> Hi Robert (I only single you out Robert, because your initials are in
> the assert that comes right before this one in the code ;-),
>
> With large objects and/or range requests, I'm seeing the following:
>
> 2003/05/07 22:19:35| ClientSocketContext::getNextRangeOffset: http offset 0
> 2003/05/07 22:19:35| ClientSocketContext::getNextRangeOffset: http
> offset 1186
> 2003/05/07 22:19:38| ClientSocketContext::getNextRangeOffset: http offset 0
> 2003/05/07 22:19:38| ClientSocketContext::getNextRangeOffset: http
> offset 1186
> 2003/05/07 22:19:38| ClientSocketContext::getNextRangeOffset: http
> offset 12288
> 2003/05/07 22:19:41| memCopy: could not find offset 261 in memory.
> 2003/05/07 22:19:41| assertion failed: stmem.cc:270: "0"
>
>
> The range request errors may be unrelated, since they happened a few
> seconds later, but that's all that's in the logs before the crash. I
> see the same crash everytime the Squid restarted after this point.
>
> In fact, it even looks kind of like a continuation of the same exact
> request causing the error because it does this on the next restart/crash:
>
> 2003/05/07 22:19:46| memCopy: could not find offset 262 in memory.
> 2003/05/07 22:19:46| assertion failed: stmem.cc:270: "0"
>
> And this one repeats a bunch (with restart jabber in between).
>
> I can probably get a gdb backtrace of this if needed. I'll have to wait
> until tomorrow to put it back into a working environment though.

-- 
GPG key available at: <http://users.bigpond.net.au/robertc/keys.txt>.