[squid-users] squid 2.6-rproxy: assertion store_client.c:211: "sc->cmp_offset == copy_offset"

I get this error every couple of hours in squid_cache:

2002/06/09 10:31:42| assertion failed: store_client.c:211:
"sc->cmp_offset == copy_offset"
2002/06/09 12:02:05| assertion failed: store_client.c:211:
"sc->cmp_offset == copy_offset"
2002/06/09 16:24:01| assertion failed: store_client.c:211:
"sc->cmp_offset == copy_offset"
2002/06/09 16:31:12| assertion failed: store_client.c:211:
"sc->cmp_offset == copy_offset"
2002/06/09 18:45:39| assertion failed: store_client.c:211:
"sc->cmp_offset == copy_offset"
2002/06/09 19:34:49| assertion failed: store_client.c:211:
"sc->cmp_offset == copy_offset"

squid restarts itself and goes about its business, but I would prefer to
eliminate this.

This occurs with squid built from the current rproxy tag on OpenBSD 3.0
and FreeBSD 4.6-RC.

I checked the source and this assertion looks like parameter checking in
storeClientCopy(). I don't really understand what the cmp_offset
property is used for or what this test is checking. Perhaps this is
related to freshness checking (cmp_) or range handling (_offset) in some
way?

I've correlated squid_access, and there doesn't seem to be any
particular pattern. The last request before the crash is generally a
small graphic, but I've had both hits and misses leading up to it. It
does not appear load related. Today's peak load on this machine was
after the crash at 12:02 and had abated by 16:24.

Web searches and a scan of the mailing list archives didn't turn up
anything on this.

Is this a known problem with the rproxy/2.6 branch? If not, what can I
do to help debug it? I'm attempting to collect a core file now. I'm
also happy to run it under gdb if I know what to look for once I catch
the assert.

Thanks very much for any pointers!

Jeff

--
NearlyFreeSpeech.NET 
$1/1GB Web Hosting, no minimums, no monthly fees, no kidding.
http://www.nearlyfreespeech.net/