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.
-- Joe Cooper <joe@swelltech.com> Web caching appliances and support. http://www.swelltech.comReceived on Thu May 08 2003 - 03:19:48 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:19:52 MST