[Beowulf] Beowulf Digest, Vol 102, Issue 19

RA Creacy fallsoffmotorcycle at gmail.com
Sun Aug 26 08:54:15 PDT 2012


*Agreed.
Long term lurker/subscriber. *
*Bob** Creacy
**Don't poop where you eat.  (Stephen King)**
We're not in Wonderland anymore Alice. (C. Manson)*

 **
**

**
*
*
* *





On Sat, Aug 25, 2012 at 8:04 PM, <beowulf-request at beowulf.org> wrote:

> Send Beowulf mailing list submissions to
>         beowulf at beowulf.org
>
> To subscribe or unsubscribe via the World Wide Web, visit
>         http://www.beowulf.org/mailman/listinfo/beowulf
> or, via email, send a message with subject or body 'help' to
>         beowulf-request at beowulf.org
>
> You can reach the person managing the list at
>         beowulf-owner at beowulf.org
>
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of Beowulf digest..."
>
>
> Today's Topics:
>
>    1. Re: RFC: Restrict posting to subscribers only ? (Prentice Bisbal)
>    2. Re: RFC: Restrict posting to subscribers only ? (Prentice Bisbal)
>    3. Re: RFC: Restrict posting to subscribers only ?
>       (graham.mullier at syngenta.com)
>    4. Re: RFC: Restrict posting to subscribers only ? (Jeff Johnson)
>    5. Re: RFC: Restrict posting to subscribers only ? (Prentice Bisbal)
>    6. NFSoIB and SRP benchmarking (holway at th.physik.uni-frankfurt.de)
>    7. [hpc-announce] CFP: DISCS-2012 Workshop at SC'12 with Cluster
>       Computing journal special issue (Chen, Yong)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Fri, 24 Aug 2012 09:43:31 -0400
> From: Prentice Bisbal <prentice.bisbal at rutgers.edu>
> Subject: Re: [Beowulf] RFC: Restrict posting to subscribers only ?
> To: beowulf at beowulf.org
> Message-ID: <50378503.60007 at rutgers.edu>
> Content-Type: text/plain; charset=ISO-8859-1; format=flowed
>
> I'm all for this. I always thought this was standard policy for every
> mailing list. I don't see any legitimate reason to post to a list you
> don't subscribe to, since if you're not a subscriber, you're not going
> to see the replies to your post.
>
> Prentice
>
> On 08/23/2012 09:06 PM, Christopher Samuel wrote:
> > -----BEGIN PGP SIGNED MESSAGE-----
> > Hash: SHA1
> >
> > Hi all,
> >
> > I'd like to solicit opinions from list members on changing the policy
> > of the list on messages from non-subscribers from the current default
> > of holding them for moderation to the position of rejecting them (with
> > an explanatory message).
> >
> > The reason is that currently us new list admins get many dozens of
> > spams a day being held for moderation and it would be very hard to
> > spot a legitimate message (from either a new subscriber or from a new
> > member who is having messages held for moderation) amongst them.
> >
> > It seems fairer to me for legitimate non-members to get an email
> > saying that their post has been rejected because they're not a member,
> > but pointing them to the web page to subscribe, rather than just a
> > message saying it's been held for moderation and then nothing (if it
> > gets missed).
> >
> > It's also fairer to new members who are under moderation (as spammers
> > do sign up to lists too) as their messages won't get missed in the
> > general flood of non-member spam.
> >
> > This is how all the other Mailman lists I run are configured and it's
> > not caused issues or complaints there.
> >
> > Thoughts please!
> >
> > cheers,
> > Chris
> > - --
> >   Christopher Samuel        Senior Systems Administrator
> >   VLSCI - Victorian Life Sciences Computation Initiative
> >   Email: samuel at unimelb.edu.au Phone: +61 (0)3 903 55545
> >   http://www.vlsci.org.au/      http://twitter.com/vlsci
> >
> > -----BEGIN PGP SIGNATURE-----
> > Version: GnuPG v1.4.11 (GNU/Linux)
> > Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/
> >
> > iEYEARECAAYFAlA2034ACgkQO2KABBYQAh+bKwCePy8HxXFL/cXH3HCvmcyNZcPB
> > kYsAn3pa2/pWewv0wJ9Ee7pAJessq3iR
> > =RDNl
> > -----END PGP SIGNATURE-----
> > _______________________________________________
> > Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin Computing
> > To change your subscription (digest mode or unsubscribe) visit
> http://www.beowulf.org/mailman/listinfo/beowulf
>
>
> ------------------------------
>
> Message: 2
> Date: Fri, 24 Aug 2012 09:51:49 -0400
> From: Prentice Bisbal <prentice.bisbal at rutgers.edu>
> Subject: Re: [Beowulf] RFC: Restrict posting to subscribers only ?
> To: beowulf at beowulf.org
> Message-ID: <503786F5.9050701 at rutgers.edu>
> Content-Type: text/plain; charset=ISO-8859-1; format=flowed
>
> Doesn't the subscription confirmation e-mail kind of handle this
> already? I suspect spammers send from random or fictitious addresses and
> don't check (or even receive) email sent to those addresses, so it's
> unlikely they'll be confirmed as subscribers to the mailing list.
>
> I think Greg raises an excellent point that we shouldn't reply to
> spammers. Perhaps we should just silently ignore posts from
> non-subscribers. If they are real humans, they should figure it out
> easily enough that they need to subscribe to post. Most mailing lists
> have a web page advertising the list, with instructions on how to
> subscribe to the list and list policy, such as needing to subscribe in
> order to post. I think that should be adequate to keep spam away but not
> real humans.
>
> Besides, don't we hate when people post something that clearly indicates
> they didn't RTFM? ;)
>
> --
> Prentice
>
>
> On 08/24/2012 06:47 AM, Andrew Holway wrote:
> > Maybe we should have a
> >
> > 'Please send us a brief email explaining why you would like to join
> > the list so that we know that your not a spammer"
> >
> >
> > 2012/8/24 Christopher Samuel<samuel at unimelb.edu.au>:
> >> -----BEGIN PGP SIGNED MESSAGE-----
> >> Hash: SHA1
> >>
> >> Hi all,
> >>
> >> I'd like to solicit opinions from list members on changing the policy
> >> of the list on messages from non-subscribers from the current default
> >> of holding them for moderation to the position of rejecting them (with
> >> an explanatory message).
> >>
> >> The reason is that currently us new list admins get many dozens of
> >> spams a day being held for moderation and it would be very hard to
> >> spot a legitimate message (from either a new subscriber or from a new
> >> member who is having messages held for moderation) amongst them.
> >>
> >> It seems fairer to me for legitimate non-members to get an email
> >> saying that their post has been rejected because they're not a member,
> >> but pointing them to the web page to subscribe, rather than just a
> >> message saying it's been held for moderation and then nothing (if it
> >> gets missed).
> >>
> >> It's also fairer to new members who are under moderation (as spammers
> >> do sign up to lists too) as their messages won't get missed in the
> >> general flood of non-member spam.
> >>
> >> This is how all the other Mailman lists I run are configured and it's
> >> not caused issues or complaints there.
> >>
> >> Thoughts please!
> >>
> >> cheers,
> >> Chris
> >> - --
> >>   Christopher Samuel        Senior Systems Administrator
> >>   VLSCI - Victorian Life Sciences Computation Initiative
> >>   Email: samuel at unimelb.edu.au Phone: +61 (0)3 903 55545
> >>   http://www.vlsci.org.au/      http://twitter.com/vlsci
> >>
> >> -----BEGIN PGP SIGNATURE-----
> >> Version: GnuPG v1.4.11 (GNU/Linux)
> >> Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/
> >>
> >> iEYEARECAAYFAlA2034ACgkQO2KABBYQAh+bKwCePy8HxXFL/cXH3HCvmcyNZcPB
> >> kYsAn3pa2/pWewv0wJ9Ee7pAJessq3iR
> >> =RDNl
> >> -----END PGP SIGNATURE-----
> >> _______________________________________________
> >> Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin
> Computing
> >> To change your subscription (digest mode or unsubscribe) visit
> http://www.beowulf.org/mailman/listinfo/beowulf
> > _______________________________________________
> > Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin Computing
> > To change your subscription (digest mode or unsubscribe) visit
> http://www.beowulf.org/mailman/listinfo/beowulf
>
>
> ------------------------------
>
> Message: 3
> Date: Fri, 24 Aug 2012 15:56:53 +0200
> From: <graham.mullier at syngenta.com>
> Subject: Re: [Beowulf] RFC: Restrict posting to subscribers only ?
> To: <samuel at unimelb.edu.au>, <beowulf at beowulf.org>
> Message-ID:
>         <
> 3E91C69ADC46C4408C85991183A275F40BC8204827 at FRGOCMSXMB04.EAME.SYNGENTA.ORG>
>
> Content-Type: text/plain; charset="Windows-1252"
>
> Gentlethings
>
> While you're noting people who aren't spammers but who are currently
> locked out despite being subscribers, I'm another. I seem never to have
> been flagged as 'OK' so gradually (this is over some years) came to regard
> the list as an interesting thing to watch but not something to participate
> in.
>
> Chris, while it would be helpful for me to be flagged as OK to post (for
> me), what about the several or many others who are stuck in the same sort
> of limbo? Is there a way to identify them, open up the list, and breathe a
> bit more life into it?
>
> Regards
> Graham
>
> Graham Mullier | Head Information Connection & Design, R&DIS | R&D
> architecture CoE lead
> graham.mullier at syngenta.com | Syngenta, Jealott's Hill International
> Research Station, Bracknell, RG42 6EY, UK
>
>
>
> -----Original Message-----
> From: beowulf-bounces at beowulf.org [mailto:beowulf-bounces at beowulf.org] On
> Behalf Of Christopher Samuel
> Sent: 24 August 2012 08:55
> To: beowulf at beowulf.org
> Subject: Re: [Beowulf] RFC: Restrict posting to subscribers only ?
>
> On 08/24/2012 10:11 PM, J?rg Sa?mannshausen wrote:
>
> > Hi all,
>
> Hiya!
>
> > I am one of the many who cannot post to the list despite being a member
> of it
> > for some years. :-/
>
> Well I spotted your message in the queue and let it through, so welcome!
>
> > I think the policy was that only members can post (good thing in my
> opinion)
> > and new members are moderated.
> > I am moderating an email list here as well and unfortunately the list's
> email
> > address got to the outside world. I do get some spam but it is something
> I can
> > cope with.
> > Once a new member has established themselves as not being a spammer (and
> here
> > I really mean the type of: buy vi online! I mean, I got vi installed on
> my
> > machines so why shall I buy it? :D ) you can remove the moderation flag.
> If
> > that member then becomes a spammer or troll you can them put back into
> > moderation only.
>
> That's precisely how the list works at the moment, in that new
> subscribers have posts moderated at first and that flag gets cleared
> after a while.  The only problem is that the list has been running on
> autopilot for quite a while (I don't know how long) and so people
> haven't been getting unmoderated or having posts approved.
>
> > Does that sound like a good idea? We do not have to rule out the usual
> anti-
> > spam mechanisms here.
>
> Agreed, we need defence in depth on this. :-)
>
> > My two cents from somebody who got put on the observer chair :D
>
> You are now unmoderated, so you can get off that chair now. ;-)
>
> cheers!
> Chris
> _______________________________________________
> Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin Computing
> To change your subscription (digest mode or unsubscribe) visit
> http://www.beowulf.org/mailman/listinfo/beowulf
>
>
>
> Syngenta Limited, Registered in England No 2710846
> Registered Office : Syngenta Limited, European Regional Centre, Priestley
> Road, Surrey Research Park, Guildford, Surrey, GU2 7YH, United Kingdom
>
>
>
> This message may contain confidential information. If you are not the
> designated recipient, please notify the sender immediately, and delete the
> original and any copies. Any use of the message by you is prohibited.
>
>
>
> ------------------------------
>
> Message: 4
> Date: Fri, 24 Aug 2012 09:30:56 -0700
> From: Jeff Johnson <jeff.johnson at aeoncomputing.com>
> Subject: Re: [Beowulf] RFC: Restrict posting to subscribers only ?
> To: beowulf at beowulf.org
> Message-ID: <5037AC40.3090703 at aeoncomputing.com>
> Content-Type: text/plain; charset=ISO-8859-1; format=flowed
>
> I think I've seen another list or site do that very thing.
>
> Oh wait, now I remember. It is inside the systemimager source somewhere.
>
>
> On 8/24/12 9:10 AM, Joe Landman wrote:
> > I am thinking we need a Monty Python Captcha
> >
> > "What is your name"
> >
> > "What is your quest"
> >
> > "What is the airspeed of an unladen swallow"
> >
> > ...
> >
>
> --
> ------------------------------
> Jeff Johnson
> Manager
> Aeon Computing
>
> jeff.johnson at aeoncomputing.com
> www.aeoncomputing.com
> t: 858-412-3810 x101   f: 858-412-3845
> m: 619-204-9061
>
> /* New Address */
> 4170 Morena Boulevard, Suite D - San Diego, CA 92117
>
>
>
> ------------------------------
>
> Message: 5
> Date: Fri, 24 Aug 2012 14:12:35 -0400
> From: Prentice Bisbal <prentice.bisbal at rutgers.edu>
> Subject: Re: [Beowulf] RFC: Restrict posting to subscribers only ?
> To: beowulf at beowulf.org
> Message-ID: <5037C413.1040407 at rutgers.edu>
> Content-Type: text/plain; charset=ISO-8859-1; format=flowed
>
> African or European?
>
>
> On 08/24/2012 12:10 PM, Joe Landman wrote:
> > I am thinking we need a Monty Python Captcha
> >
> > "What is your name"
> >
> > "What is your quest"
> >
> > "What is the airspeed of an unladen swallow"
> >
> > ...
> >
> >
> > On 08/24/2012 09:01 AM, Christopher Samuel wrote:
> >> On 08/24/2012 10:03 PM, Bogdan Costescu wrote:
> >>
> >>> Does someone have a figure of how many non-subscribers posts we are
> >>> talking about ? I have the impression that lately I've seen only
> >>> messages coming from "regulars". If non-subscribers post very little,
> >>> then such a change would not be very annoying IMHO.
> >> Well in the 6 hours since I last checked at work there have were over 30
> >> new messages waiting to be processed, of which 1 was from a subscriber
> >> still moderated and 1 was a legitimate post from a non-member
> >> (presumably subscribed at a different address as they replied to my list
> >> post).
> >>
> >> The other 30 plus were just spam.
> >>
> >>> OTOH, I hope that archives (wherever they are) remain publicly
> available.
> >> I don't think anyone is planning to change those at all.
> >>
> >> http://www.beowulf.org/pipermail/beowulf/
> >>
> >>> We should be very thankful to Don Becker for doing a wonderful job
> >>> with the list for many years :)
> >> Oh indeed!  Very much so...
> >>
> >> All the best,
> >> Chris
> >> _______________________________________________
> >> Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin
> Computing
> >> To change your subscription (digest mode or unsubscribe) visit
> http://www.beowulf.org/mailman/listinfo/beowulf
> >>
> >
>
>
> ------------------------------
>
> Message: 6
> Date: Sun, 26 Aug 2012 00:22:16 +0200
> From: holway at th.physik.uni-frankfurt.de
> Subject: [Beowulf] NFSoIB and SRP benchmarking
> To: beowulf at beowulf.org
> Message-ID:
>         <
> 59905dbf784579608a180b56bb8cb8a3.squirrel at th.physik.uni-frankfurt.de>
> Content-Type: text/plain;charset=utf-8
>
> Hello Beowulf 2.0
>
> I've just started playing with NFSoIB to provide super fast backend
> storage for a bunch of databases that we look after here. Oracle and
> Nexenta are both sending me ZFS based boxes to test and I hope to compare
> the performance and stability of these with the Netapp (formally lsi
> engenio) E5400.
>
> This will be the first time I will be getting into serious storage
> benchmarking. Does anyone have any interesting tests they would like to
> run or and experience performing these kinds of tests?
>
> I have 4 HP G8 boxes with 96GB ram each QDR IB and 10G ethernet as
> consumers.
>
> I will also be testing the performance of KVM and Virtuozzo (commercial
> version of OpenVZ) which is a kernel sharing virtualization similar to BSD
> Jails.
>
> Thanks,
>
> Andrew
>
>
>
> ------------------------------
>
> Message: 7
> Date: Thu, 23 Aug 2012 15:21:20 +0000
> From: "Chen, Yong" <yong.chen at ttu.edu>
> Subject: [Beowulf] [hpc-announce] CFP: DISCS-2012 Workshop at SC'12
>         with Cluster Computing journal special issue
> To: "hpc-announce at mcs.anl.gov" <hpc-announce at mcs.anl.gov>,
>         "distributed-computing-announce at datasys.cs.iit.edu"
>         <distributed-computing-announce at datasys.cs.iit.edu>,
>         "cse-cfp at cse.stfx.ca"   <cse-cfp at cse.stfx.ca>, "
> cfp at grid.chu.edu.tw"
>         <cfp at grid.chu.edu.tw>
> Message-ID:
>         <AC0D521357876C4AA01C144CD17C58D9012896B7 at centaur09.ttu.edu>
> Content-Type: text/plain; charset="us-ascii"
>
> [Apologies if you got multiple copies of this email. If you'd like to
> opt out of these announcements, information on how to unsubscribe is
> available at the bottom of this email.]
> -------------- next part --------------
>
> [Apologize for any duplicated posts]
>
>                  ****************
>                  CALL FOR PAPERS
>                  ****************
>           The International Workshop on
> Data-Intensive Scalable Computing Systems (DISCS)
>           http://data.cs.ttu.edu/discs/
>
>           November 16th, 2012, Salt Lake City
>               In conjunction with the
>  2012 ACM/IEEE Supercomputing Conference (SC'12)
>
>                  *********************
>                  Scope of the Workshop
>                  *********************
> High-performance computing (HPC) is a major strategic tool
> for science, engineering, and industry. Existing HPC systems,
> however, are largely designed and developed for computation-
> intensive applications with a computing-centric paradigm. With
> the emerging and timely needs of supporting data-intensive
> scientific discovery and innovations, there is a need of
> rethinking the system architectures, programming models, runtime
> systems, and tools available for data-intensive HPC. The DISCS
> workshop provides a forum for researchers and developers in the
> high-performance computing, data-intensive computing, and
> parallel computing fields to take the Big Data challenges
> together and present innovative ideas, experiences, and latest
> developments that help address these challenges.
>
>                    ******************
>                    Topics of Interest
>                    ******************
> The focus areas of the DISCS-2012 workshop include, but are not
> limited to:
>     -> HPC system architectures for supporting data intensive
>        applications
>          # Data-centric system architectures
>          # I/O systems and architectures
>          # System area networks
>          # Power efficient systems for data intensive applications
>     -> Programming models for supporting data intensive
>        applications
>          # Data-centric programming models
>          # MPI extensions for data intensive applications
>          # GAS/PGAS/OpenMP programming model extensions for data-
>            intensive applications
>          # New programming languages/methodologies for data-
>            intensive HPC
>     -> Runtime systems for supporting data intensive applications
>          # Communication systems for supporting data intensive
>            applications
>          # Data compression and deduplication
>          # Caching and prefetching
>          # Data integrity and consistency
>     -> Tools for supporting data intensive applications
>          # Data analytic, tracing, and trace analysis tools
>          # Data mining and knowledge discovery tools
>          # Computational, mathematical and statistical techniques
>            and tools
>          # Data visualization techniques and tools
>
>                       ***************
>                       Important Dates
>                       ***************
>     -> Paper Submission: September 8th, 2012
>     -> Author Notification: October 22nd, 2012
>     -> Workshop Date: November 16th, 2012
>     -> Camera-Ready Copy: December 7th, 2012
>
>                    ***********************
>                    Submission Instructions
>                    ***********************
> Submissions should be in PDF format in U.S. letter size paper,
> and should be formatted according to the IEEE standard double-
> column single-space format. They should not exceed 5 pages (all-
> inclusive). Please access the IEEE site for the manuscript template.
>
> Please visit the following site to make paper submissions:
> https://www.easychair.org/account/signin.cgi?conf=discs2012
>
> All accepted papers will appear in the SC-2012 digital proceedings
> in the IEEE digital library.
>
>                    *********************
>                    Journal Special Issue
>                    *********************
> DISCS-2012 workshop papers will be invited to extend the manuscripts
> to be considered for a journal Special Issue on Data-Intensive High
> Performance Computing of the Cluster Computing by Springer, edited
> by Yong Chen and Xian-He Sun. The target journal special issue
> submission deadline is Jan. 16th, 2013.
>
>                      ***********
>                      Organizers
>                      ***********
> STEERING COMMITTEE
> William D. Gropp, University of Illinois Urbana-Champaign
> Xian-He Sun, Illinois Institute of Technology
> Rajeev Thakur, Argonne National Laboratory
>
> PROGRAM CHAIRS
> Yong Chen, Texas Tech University
> Xian-He Sun, Illinois Institute of Technology
>
> TECHNICAL PROGRAM COMMITTEE
> Suren Byna, Lawrence Berkeley National Laboratory
> Shane Canon, Lawrence Berkeley National Laboratory
> Hui Jin, Oracle
> Scott Klasky, Oak Ridge National Laboratory
> Quincey Koziol, HDF5 Group
> Wei-keng Liao, Northwestern University
> Jay Lofstead, Sandia National Laboratory
> Carlos Maltzahn, University of California at Santa Cruz
> Ioan Raicu, Illinois Institute of Technology
> Philip C. Roth, Oak Ridge National Laboratory
> Weikuan Yu, Auburn University
>
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL:
> http://www.beowulf.org/pipermail/beowulf/attachments/20120823/d32dae69/attachment.html
> -------------- next part --------------
>
> ********************************************************************************
> The hpc-announce mailing list has been setup to have a common mailing
> list to share information with respect to upcoming HPC related
> events. You are included in this mailing list based on your
> participation or interest in a previous HPC conference or other event.
>
> The purpose for providing a single mailing list is to allow
> participants to easily identify such emails, and handle them
> appropriately. Some options include:
>
> 1. If you feel that the number of such emails is too many, filter them
> to less-frequently-read folders in your email client.
>
> 2. Change your subscription to a digest option
> (https://lists.mcs.anl.gov/mailman/listinfo/hpc-announce) which will
> consolidate emails sent that week into a single summary email.
>
> 3. Finally, if you do not wish to receive any emails from hpc-announce,
> you can unsubscribe from the mailing list
> (https://lists.mcs.anl.gov/mailman/listinfo/hpc-announce). Once
> unsubscribed, we guarantee that you will not be added back in through
> participation in a different HPC related conference or event. You will
> need to send an email to hpc-announce-owner at mcs.anl.gov to be added
> back on.
>
> If you need help with any of the above, please email us at
> hpc-announce-owner at mcs.anl.gov.
>
> ********************************************************************************
>
> ------------------------------
>
> _______________________________________________
> Beowulf mailing list
> Beowulf at beowulf.org
> http://www.beowulf.org/mailman/listinfo/beowulf
>
>
> End of Beowulf Digest, Vol 102, Issue 19
> ****************************************
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.beowulf.org/pipermail/beowulf/attachments/20120826/13f7e9c6/attachment-0001.html 


More information about the Beowulf mailing list