Oskar Pearson writes:
>Hi all
>
>Hmm - no core file, and this is only happening on the one machine that doesn't
>give me cores. I'll fiddle around on it and try and see what is happening.
>
>Sorry for not having the core - it sucks. I hope that this helps someone.
>
>(squid): client_side.c:1429: clientSendMoreData: Assertion `rep || (body_buf &
& body_size)' failed.
>(squid): client_side.c:1429: clientSendMoreData: Assertion `rep || (body_buf &
& 
>body_size)' failed.
>(squid): client_side.c:1429: clientSendMoreData: Assertion `rep || (body_buf &
& 
>body_size)' failed.
>(squid): client_side.c:1429: clientSendMoreData: Assertion `rep || (body_buf &
& 
>body_size)' failed.
These are probably due to HEAD requests.  I have a fix:
Index: client_side.c
===================================================================
RCS file: /surf1/CVS/squid/src/client_side.c,v
retrieving revision 1.371
retrieving revision 1.372
diff -w -u -r1.371 -r1.372
--- client_side.c	1998/07/31 00:15:38	1.371
+++ client_side.c	1998/07/31 14:48:13	1.372
@@ -1,6 +1,6 @@
 
 /*
- * $Id: client_side.c,v 1.371 1998/07/31 00:15:38 wessels Exp $
+ * $Id: client_side.c,v 1.372 1998/07/31 14:48:13 wessels Exp $
  *
  * DEBUG: section 33    Client-side Routines
  * AUTHOR: Duane Wessels
@@ -1378,9 +1378,14 @@
             body_size = 0;
             http->flags.done_copying = 1;
         } else {
-	    /* unparseable reply, stop and end-of-headers */
-	    body_size = headersEnd(buf, size);
-	    if (body_size)
+	    /*
+	     * If we are here, then store_status == STORE_OK and it
+	     * seems we have a HEAD repsponse which is missing the
+	     * empty end-of-headers line (home.mira.net, phttpd/0.99.72
+	     * does this).  Because clientBuildReply() fails we just
+	     * call this reply a body, set the done_copying flag and
+	     * continue...
+	     */
                 http->flags.done_copying = 1;
         }
     }
Received on Tue Jul 29 2003 - 13:15:51 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:11:50 MST