Re: [PATCH] Revised fix for download corruption

Hi everyone!

Please note that the aufs patch in 20021111 snapshot have been working
now for 3hrs on my system.

I have not seen reported of problem and of yet and I am hoping that it
would remain this way.

Thank you very much Henrik, Robert and to the others.

Best regards

Edward Millington
BSc, Network+, I-Net+, CIW Associate
Systems Administrator, Sr
Cariaccess Communications Ltd.
Palm Plaza
Wildey
St. Michael
Barbados

Phone:  1 246 430 7435
Mobile: 1 246 234 6278
Fax:    1 246 431 0170

edward@cariaccess.com
www.cariaccess.com

-----Original Message-----
From: Henrik Nordstrom <hno@marasystems.com>
To: Phil Oester <kernel@theoesters.com>
Cc: squid-dev@squid-cache.org
Date: Sun, 10 Nov 2002 13:58:35 +0100
Subject: Re: [PATCH] Revised fix for download corruption

> The patch has been updated to work around this
>
> http://www.squid-cache.org/Versions/v2/2.5/bugs/
>
> Regards
> Henrik
>
> On Sunday 10 November 2002 12.29, Henrik Nordstrom wrote:
> > Some careful testing has revealed yet another cbdata barrier error
> > in aufs causing similar errors.. this time in aioCancel. Makes the
> > same damn read bug resurface
> >
> > How to repeat:
> > half_closed_clients off (makes detection simpler, not stricly
> > required)
> > patch aio to be slow at scheduling operations
> > run under a malloc debugger such as valgrind ("memory_pools off"
> > required for valgrind to see this error)
> > abort a request
> >
> > Regards
> > Henrik
> >
> > On Tuesday 05 November 2002 23.39, Phil Oester wrote:
> > > After 5 hours of testing with my 'corruption' patch, your patch
> > > has shown zero corruption (as expected).
> > >
> > > I'll load this up on some of our boxes today and see if anything
> > > breaks ;-)
> > >
> > > -Phil
> > >
> > > On Tue, Nov 05, 2002 at 12:31:03PM +0100, Henrik Nordstrom wrote:
> > > > Attached is a preleminary Squid-2.5 patch that inforces the
> > > > cbdata barrier on aufs reads.
> > > >
> > > > Quick summary: The responsibility of copying the read data into
> > > > the buffer is moved up to the storeAufsRead() layer who can
> > > > correcly verify if the swapin request has been aborted. It also
> > > > adds a few cbdata verifications to insure that aborted events
> > > > is properly ignored and a few on-free checks to avoid memory or
> > > > filedescriptor leakage.
Received on Mon Nov 11 2002 - 06:51:14 MST