From hsu@clinet.fi  Sat Jun 17 19:28:08 1995
Received: from clinet.fi (root@clinet.fi [193.64.6.1])
          by freefall.cdrom.com (8.6.10/8.6.6) with ESMTP id TAA09800
          for <FreeBSD-gnats-submit@freebsd.org>; Sat, 17 Jun 1995 19:28:05 -0700
Received: from katiska.clinet.fi (root@katiska.clinet.fi [193.64.6.3]) by clinet.fi (8.6.10/8.6.4) with ESMTP id FAA05841 for <FreeBSD-gnats-submit@freebsd.org>; Sun, 18 Jun 1995 05:27:40 +0300
Received: (hsu@localhost) by katiska.clinet.fi (8.6.11/8.6.4) id FAA01387; Sun, 18 Jun 1995 05:27:39 +0300
Message-Id: <199506180227.FAA01387@katiska.clinet.fi>
Date: Sun, 18 Jun 1995 05:27:39 +0300
From: Heikki Suonsivu <hsu@clinet.fi>
Reply-To: hsu@clinet.fi
To: FreeBSD-gnats-submit@freebsd.org
Subject: interrupt-level buffer overflows
X-Send-Pr-Version: 3.2

>Number:         528
>Category:       kern
>Synopsis:       slow 386 reports excessive interrupt-level buffer overlows
>Confidential:   no
>Severity:       serious
>Priority:       high
>Responsible:    bde
>State:          closed
>Quarter:
>Keywords:
>Date-Required:
>Class:          sw-bug
>Submitter-Id:   current-users
>Arrival-Date:   Sat Jun 17 19:30:02 1995
>Closed-Date:    Sat Nov 9 20:15:17 PST 1996
>Last-Modified:  Sat Nov  9 20:16:11 PST 1996
>Originator:     Heikki Suonsivu
>Release:        FreeBSD 2.0-BUILT-19950507 i386
>Organization:
Helsinki University of Technology, Finland
>Environment:

	386-16, IDE disk, 10M.
	A ppp router, 38400 leased line.  16550 serial port. wd8013.
	It is dedicated solely for the purpose of routing this one
	single connection.

>Description:

	Kernel spits out lot of these

Jun 18 05:14:47 pommi /kernel: sio1: 119 more interrupt-level buffer over
flows (total 3642)
Jun 18 05:14:47 pommi /kernel: sio1: 119 more interrupt-level buffer overflows (
total 3642)

	It also very easily reboots when lots of PPP load exits. 
	Low tcp performance hints that it is loosing lots of data.

>How-To-Repeat:

	Use FreeBSD as a router for a PPP connection on a slow machine.

>Fix:
	
	I think this feature has already been discussed; grepping
	'interrupt-level' from FAQ's didn't help.  If this is a feature
	which can be worked around, this might be a doc-bug?  However, I
	find it curous how a 386-16 could be too slow to respond for a 38400
	bps link? 



>Release-Note:
>Audit-Trail:
State-Changed-From-To: open->closed 
State-Changed-By: scrappy 
State-Changed-When: Tue Apr 9 21:19:42 PDT 1996 
State-Changed-Why:  
fixed setting 'options RS_IBUFSIZE=1024', with appropriate  
modifications made to sio.c to allow for this 
State-Changed-From-To: closed->open 
State-Changed-By: scrappy 
State-Changed-When: Wed Apr 10 11:04:25 PDT 1996 
State-Changed-Why:  
incomplete analysis of solution/workaround 



Responsible-Changed-From-To: freebsd-bugs->bde 
Responsible-Changed-By: scrappy 
Responsible-Changed-When: Wed Apr 10 11:04:25 PDT 1996 
Responsible-Changed-Why:  
sio.c is Bruce's responsibility 
State-Changed-From-To: open->closed 
State-Changed-By: scrappy 
State-Changed-When: Sat Nov 9 20:15:17 PST 1996 
State-Changed-Why:  

duplicated in PR#kern/579, and describes workaround 

>Unformatted:


