[e2e] favor - please post test to E2E list

Sat Sep 14 00:17:04 PDT 2013

Just configure mailman to reject instead of discard, so people get a notification.

Lars

On Sep 14, 2013, at 1:48, Matt Mathis <mattmathis at google.com> wrote:

> The problem is that you have to be subscribed to the end2end-interest list
> *exactly as your mail agent/MTA sends your mail.   Be aware that
> the  end2end list is configured to silently discard mail from addresses
> which are not members of the list.    So for example if you are subscribed
> as me at mydomain.com, but your mail agent send your messages from
> me at myhost.mydoamin.com, you will see messages from the list, but your posts
> will be silently discarded.
> 
> *For some definition of exactly.   I did not try:
> Me at MyDomain.com vs me at mydomain.com
> me+folder at mydomain.com vs me at mydomain.com
> 
> If you think you are having problems, look at the "receivedfrom" lines in
> messages from others, and I bet your inbound subscription address doesn't
> match your own outbound address.
> 
> I am pretty sure that groups.{yahoo, hotmail, google, ...}.com all get this
> right.
> 
> Thanks,
> --MM--
> The best way to predict the future is to create it.  - Alan Kay
> 
> Privacy matters!  We know from recent events that people are using our
> services to speak in defiance of unjust governments.   We treat privacy and
> security as matters of life and death, because for some users, they are.
> 
> 
> Forwarded conversation
> Subject: favor - please post test to E2E list
> ------------------------
> 
> From: *Joe Touch* <touch at isi.edu>
> Date: Fri, Sep 6, 2013 at 6:45 PM
> To: James Sterbenz <jpgs at sterbenz.org>, Matt Mathis <mattmathis at google.com>,
> Mark Allman <mallman at icir.org>
> 
> 
> Hi, all,
> 
> I have a report of problems posting to the list.
> 
> Can each of you post a test with the subject "testing - as requested by
> list admin"?
> 
> This will let me know if the issue is more pervasive or limited in scope.
> 
> Thanks,
> 
> Joe
> 
> 
> ----------
> From: *Matt Mathis* <mattmathis at google.com>
> Date: Sat, Sep 7, 2013 at 6:30 PM
> To: Joe Touch <touch at isi.edu>
> Cc: James Sterbenz <jpgs at sterbenz.org>, Mark Allman <mallman at icir.org>
> 
> 
> I sent 2 messages, one each from mattmathis at google.com (1/2) and
> matt.mathis at gmail.com (2/2).
> 
> I was also suspicious of delivery problems, however since Google normally
> hides our own messages I was not sure.
> 
> In absence of any facts..... The common failure is for the list not to
> properly strip/update all DKIM (whatever) headers from the originator, and
> then email services which are enforcing signatures discard the messages as
> being forged.   The case I commonly run into is from google to google
> through a broken list.....
> 
> I have not yet received my own message 1/2 to either account.   Have any of
> you received it?
> 
> Thanks,
> --MM--
> The best way to predict the future is to create it.  - Alan Kay
> 
> Privacy matters!  We know from recent events that people are using our
> services to speak in defiance of unjust governments.   We treat privacy and
> security as matters of life and death, because for some users, they are.
> 
> ----------
> From: *Matt Mathis* <mattmathis at google.com>
> Date: Sat, Sep 7, 2013 at 8:15 PM
> To: Joe Touch <touch at isi.edu>
> Cc: James Sterbenz <jpgs at sterbenz.org>, Mark Allman <mallman at icir.org>
> 
> 
> Message 1 came, after a 40 minute delay.  This probably means that it got
> greylisted.
> 
> Let me know if you want to dissect the headers.
> 
> 
> 
> Thanks,
> --MM--
> The best way to predict the future is to create it.  - Alan Kay
> 
> Privacy matters!  We know from recent events that people are using our
> services to speak in defiance of unjust governments.   We treat privacy and
> security as matters of life and death, because for some users, they are.
> 
> 
> 
> ----------
> From: *Joe Touch* <touch at isi.edu>
> Date: Mon, Sep 9, 2013 at 7:36 AM
> To: Matt Mathis <mattmathis at google.com>
> Cc: James Sterbenz <jpgs at sterbenz.org>, Mark Allman <mallman at icir.org>
> 
> 
> Thanks - the delay is not unusual (our servers are configured so that both
> spam filters and mailman run only periodically rather than on-demand).
> 
> Joe
> 
> 
>> ----------
> From: *Joe Touch* <touch at isi.edu>
> Date: Mon, Sep 9, 2013 at 7:38 AM
> To: Matt Mathis <mattmathis at google.com>
> Cc: James Sterbenz <jpgs at sterbenz.org>, Mark Allman <mallman at icir.org>
> 
> 
> 
> 
> On 9/7/2013 6:30 PM, Matt Mathis wrote:
> 
>> I sent 2 messages, one each from mattmathis at google.com
>> <mailto:mattmathis at google.com> (1/2) and matt.mathis at gmail.com
>> <mailto:matt.mathis at gmail.com> (2/2).
>> 
> 
> Thanks - the first got through, but not the second. That's not surprising,
> because only the first is subscribed to the list.
> 
> Joe
> 
> ----------
> From: *Matt Mathis* <mattmathis at google.com>
> Date: Mon, Sep 9, 2013 at 8:44 AM
> To: Joe Touch <touch at isi.edu>
> Cc: James Sterbenz <jpgs at sterbenz.org>, Mark Allman <mallman at icir.org>
> 
> 
> And that would be your problem: no bounce messages.   In this case the name
> was canonicalized slightly differently - mattmathis at gmail.com is subscribed
> and receiving messages.  Google considers the addresses to be equivalent (I
> know, I know...), but the list did not tell me that my posting got rejected.
> 
> Note that this sort of problem is impossible for the user to diagnose
> themselves because without bounce messages it has no identifying symptom.
> Further it is compounded by modern mail agents that try real hard to hide
> the 822 addresses.
> 
> I suggest turning on bounce messages.
> 
> Thanks,
> --MM--
> The best way to predict the future is to create it.  - Alan Kay
> 
> Privacy matters!  We know from recent events that people are using our
> services to speak in defiance of unjust governments.   We treat privacy and
> security as matters of life and death, because for some users, they are.
> 
> 
> 
> ----------
> From: *Joe Touch* <touch at isi.edu>
> Date: Mon, Sep 9, 2013 at 8:57 AM
> To: Matt Mathis <mattmathis at google.com>
> Cc: James Sterbenz <jpgs at sterbenz.org>, Mark Allman <mallman at icir.org>
> 
> 
> 
> 
> On 9/9/2013 8:44 AM, Matt Mathis wrote:
> 
>> And that would be your problem: no bounce messages.   In this case the
>> name was canonicalized slightly differently - mattmathis at gmail.com
>> <mailto:mattmathis at gmail.com> is subscribed and receiving messages.
>> 
>>  Google considers the addresses to be equivalent (I know, I know...),
>> but the list did not tell me that my posting got rejected.
>> 
>> Note that this sort of problem is impossible for the user to diagnose
>> themselves because without bounce messages it has no identifying
>> symptom.  Further it is compounded by modern mail agents that try real
>> hard to hide the 822 addresses.
>> 
>> I suggest turning on bounce messages.
>> 
> 
> I don't see how to do that in Mailman without responding to spam, which we
> don't have the resources to handle (and don't want to do).
> 
> Joe
> 
>> 
>> 
> ----------
> From: *Matt Mathis* <mattmathis at google.com>
> Date: Mon, Sep 9, 2013 at 10:03 AM
> To: Joe Touch <touch at isi.edu>
> Cc: James Sterbenz <jpgs at sterbenz.org>, Mark Allman <mallman at icir.org>
> 
> 
> I thought the proper action was to return a 500 level error to the
> originating MTA.   Perhaps the list needs to move to newer platform?
> 
> Thanks,
> --MM--
> The best way to predict the future is to create it.  - Alan Kay
> 
> Privacy matters!  We know from recent events that people are using our
> services to speak in defiance of unjust governments.   We treat privacy and
> security as matters of life and death, because for some users, they are.
> 
> 
> 
> ----------
> From: *Joe Touch* <touch at isi.edu>
> Date: Mon, Sep 9, 2013 at 11:00 AM
> To: Matt Mathis <mattmathis at google.com>
> Cc: James Sterbenz <jpgs at sterbenz.org>, Mark Allman <mallman at icir.org>
> 
> 
> 
> 
> On 9/9/2013 10:03 AM, Matt Mathis wrote:
> 
>> I thought the proper action was to return a 500 level error to the
>> originating MTA.   Perhaps the list needs to move to newer platform?
>> 
> 
> That would happen at the SMTP level; there's no way to generate that
> message from within SMTP on behalf of an exploder that doesn't process mail
> until after SMTP has already accepted it.
> 
> Joe
> 
> 
>> 
>> 
> ----------
> From: *Matt Mathis* <mattmathis at google.com>
> Date: Mon, Sep 9, 2013 at 11:16 AM
> To: Joe Touch <touch at isi.edu>
> Cc: James Sterbenz <jpgs at sterbenz.org>, Mark Allman <mallman at icir.org>
> 
> 
> Yes, I know.  Like I said, perhaps the list needs to move to a more up to
> date platform.    I would bet that all of the big list services get this
> right.
> 
> Thanks,
> --MM--
> The best way to predict the future is to create it.  - Alan Kay
> 
> Privacy matters!  We know from recent events that people are using our
> services to speak in defiance of unjust governments.   We treat privacy and
> security as matters of life and death, because for some users, they are.
> 
> 
> 
> ----------
> From: *Joe Touch* <touch at isi.edu>
> Date: Mon, Sep 9, 2013 at 1:58 PM
> To: Matt Mathis <mattmathis at google.com>
> Cc: James Sterbenz <jpgs at sterbenz.org>, Mark Allman <mallman at icir.org>
> 
> 
> Hi, Matt,
> 
> I'm not aware of such systems. We use mailman here at ISI, as do a few
> other organizations (IEEE, etc.), and it operates on email only after it
> has been received by sendmail AFAICT. That appears to be true for other
> systems, because none appear to have their servers integrated with sendmail
> servers AFAICT.
> 
> Joe