From owner-freebsd-current  Thu Sep 14 13:06:08 1995
Return-Path: current-owner
Received: (from majordom@localhost)
          by freefall.freebsd.org (8.6.12/8.6.6) id NAA20267
          for current-outgoing; Thu, 14 Sep 1995 13:06:08 -0700
Received: from ibp.ibp.fr (ibp.ibp.fr [132.227.60.30])
          by freefall.freebsd.org (8.6.12/8.6.6) with ESMTP id NAA20219
          for <current@freebsd.org>; Thu, 14 Sep 1995 13:05:54 -0700
Received: from blaise.ibp.fr (blaise.ibp.fr [132.227.60.1])
	by ibp.ibp.fr (8.6.12/jtpda-5.0) with ESMTP id WAA22150
	; Thu, 14 Sep 1995 22:05:31 +0200
Received: from (uucp@localhost)
	by blaise.ibp.fr (8.6.12/jtpda-5.0) with UUCP id WAA18446
	; Thu, 14 Sep 1995 22:05:30 +0200
Received: (from roberto@localhost) by keltia.Freenix.FR (8.7.Beta.14/keltia-uucp-2.4) id UAA26870; Thu, 14 Sep 1995 20:49:35 +0200 (MET DST)
From: Ollivier Robert <roberto@keltia.Freenix.FR>
Message-Id: <199509141849.UAA26870@keltia.Freenix.FR>
Subject: Re: Finding solve to severe sig11 problem:
To: jehamby@lightside.com (Jake Hamby)
Date: Thu, 14 Sep 1995 20:49:34 +0200 (MET DST)
Cc: current@freebsd.org
In-Reply-To: <Pine.BSF.3.91.950913233555.9447A-100000@localhost> from "Jake Hamby" at Sep 13, 95 11:40:41 pm
X-Operating-System: FreeBSD 2.2-CURRENT ctm#1085
X-Mailer: ELM [version 2.4 PL24 ME7a+]
MIME-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Sender: current-owner@freebsd.org
Precedence: bulk

It seems that Jake Hamby said:
> plan is to slowly step forward and see exactly which patch in which file 
> is causing the Sig 11 problem in my case.  If I can isolate this problem 
> to a single patch, I will then apply all the subsequent CTM deltas and 
> reverse that one patch.  If all goes well, I'll post a diff to the list.  

As David said, the  patches are related and  the  one that cause  the sig11
will  not be easely  pointed out. Here are  the patches you'll have to look
for if you want to try anyway:

Even with that, it will probably be hard to find  because (a wild guess) it
is either a  long-time-well-hidden  bug discovered by   some new way to  do
things or a new bug. My knowledge on VM stuff is unfortunately slim :-(

dyson       95/09/03 12:56:16

  Modified:    sys/kern  vfs_bio.c vfs_cluster.c
  Log:
  Improvements to the cluster code, minor vfs_bio efficiency:
        Better performance -- more aggressive read-ahead
        under certain circumstanses.
  
        Mods to support clustering on small
        ( < PAGE_SIZE) block size filesystems (e.g. ext2fs,
        msdosfs.)

dyson       95/09/03 12:57:26

  Modified:    sys/vm    vm_page.c
  Log:
  New subroutine "vm_page_set_validclean" for a vfs_bio improvement.

dyson       95/09/03 13:11:29

  Modified:    sys/vm    vm_page.h
  Log:
  Added prototype for new routine "vm_page_set_validclean" and initial
  declarations for the prezeroed pages mechanism.

dyson       95/09/03 13:32:53

  Modified:    sys/kern  vfs_cluster.c
  Log:
  VOP_BMAP will eventually need an additional argument, but not yet.  This
  backs out that modification to minimize the window during which this
  is not yet correct.

dyson       95/09/03 13:39:23

  Modified:    sys/i386/i386  swtch.s vm_machdep.c
  Log:
  Machine dependent routines to support pre-zeroed free pages.  This
  significantly improves demand zero performance.

dyson       95/09/03 13:40:44

  Modified:    sys/vm    vm_kern.c vm_fault.c vm_page.c
  Log:
  Machine independent changes to support pre-zeroed free pages.  This
  significantly improves demand-zero performance.

dyson       95/09/03 21:44:28

  Modified:    sys/vm    swap_pager.c vnode_pager.c vm_fault.c
  Log:
  Allow the fault code to use additional clustering info from both
  bmap and the swap pager.  Improved fault clustering performance.

-- 
Ollivier ROBERT    -=- The daemon is FREE! -=-    roberto@keltia.frmug.fr.net
 FreeBSD keltia.Freenix.FR 2.2-CURRENT #1: Sun Sep 10 18:50:19 MET DST 1995