From beepwg-bounces@dbc.mtview.ca.us Tue Sep 26 17:55:35 2006 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1GSKtr-0001CE-IY for beep-archive@lists.ietf.org; Tue, 26 Sep 2006 17:55:35 -0400 Received: from drakken.dbc.mtview.ca.us ([168.143.123.173]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1GSKtq-0005Vc-5j for beep-archive@lists.ietf.org; Tue, 26 Sep 2006 17:55:35 -0400 Received: from drakken.dbc.mtview.ca.us (localhost.localdomain [127.0.0.1]) by drakken.dbc.mtview.ca.us (8.12.11/8.12.8) with ESMTP id k8QLnn6A026405; Tue, 26 Sep 2006 14:50:08 -0700 Received: from web31803.mail.mud.yahoo.com (web31803.mail.mud.yahoo.com [68.142.207.66])k8QLnlmj026401 for ; Tue, 26 Sep 2006 14:49:47 -0700 Received: (qmail 74065 invoked by uid 60001); 26 Sep 2006 21:49:28 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=Message-ID:Received:Date:From:Subject:To:Cc:MIME-Version:Content-Type:Content-Transfer-Encoding; b=W4BEl81Aorn5qnl+9+M58dwWNP3doaGJdsC51CRb8rYL3A5bPVbfhBjQydZDJ0wpMf01vkNw+Nrkhi/z3vG0V5duNbDvZua6b9vsGfUdRHCSXxBod7/6c/p63WUN0opfDhyy6GNK39OZ4XqjhCpbYIka4yrYwIooLsfbExAxCOg= ; Message-ID: <20060926214928.74063.qmail@web31803.mail.mud.yahoo.com> Received: from [171.71.27.71] by web31803.mail.mud.yahoo.com via HTTP; Tue, 26 Sep 2006 14:49:28 PDT Date: Tue, 26 Sep 2006 14:49:28 -0700 (PDT) From: Vikas Deolaliker To: beepwg@lists.beepcore.org MIME-Version: 1.0 Content-Type: text/plain; charset=ascii Content-Transfer-Encoding: 8bit X-MIME-Autoconverted: from quoted-printable to 8bit by drakken.dbc.mtview.ca.us id k8QLnlmj026401 Subject: [BEEPwg] BEEP over Infiniband X-BeenThere: beepwg@lists.beepcore.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Mailing list for the IETF's BEEP working group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: beepwg-bounces@dbc.mtview.ca.us Errors-To: beepwg-bounces@dbc.mtview.ca.us X-Spam-Score: 0.0 (/) X-Scan-Signature: 68c8cc8a64a9d0402e43b8eee9fc4199 Has anybody implemented/heard about BEEP over Infiniband? Given that IB gives a full L2/L3 fabric and BEEP everything else, we could use this combination to speed up various applications in SOA/Web2.0 space. Love to hear the group's thoughts on this. Thanks Vikas Deolaliker _______________________________________________ BEEPwg mailing list BEEPwg@lists.beepcore.org http://drakken.dbc.mtview.ca.us/mailman/listinfo/beepwg From beepwg-bounces@dbc.mtview.ca.us Wed Sep 27 07:56:22 2006 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1GSY1W-0003wv-Ok for beep-archive@lists.ietf.org; Wed, 27 Sep 2006 07:56:22 -0400 Received: from drakken.dbc.mtview.ca.us ([168.143.123.173]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1GSY1U-0006HV-CW for beep-archive@lists.ietf.org; Wed, 27 Sep 2006 07:56:22 -0400 Received: from drakken.dbc.mtview.ca.us (localhost.localdomain [127.0.0.1]) by drakken.dbc.mtview.ca.us (8.12.11/8.12.8) with ESMTP id k8RBt3SO006984; Wed, 27 Sep 2006 04:55:05 -0700 Received: from [127.0.0.1] (localhost.localdomain [127.0.0.1]) k8RBsw0B006971; Wed, 27 Sep 2006 04:54:59 -0700 In-Reply-To: <20060926214928.74063.qmail@web31803.mail.mud.yahoo.com> References: <20060926214928.74063.qmail@web31803.mail.mud.yahoo.com> Mime-Version: 1.0 (Apple Message framework v752.2) Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: Content-Transfer-Encoding: 7bit From: Marshall Rose Subject: Re: [BEEPwg] BEEP over Infiniband Date: Wed, 27 Sep 2006 12:55:00 +0100 To: Vikas Deolaliker X-Mailer: Apple Mail (2.752.2) cc: beepwg@lists.beepcore.org X-BeenThere: beepwg@lists.beepcore.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Mailing list for the IETF's BEEP working group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: beepwg-bounces@dbc.mtview.ca.us Errors-To: beepwg-bounces@dbc.mtview.ca.us X-Spam-Score: 0.0 (/) X-Scan-Signature: cf4fa59384e76e63313391b70cd0dd25 > Has anybody implemented/heard about BEEP over Infiniband? Given > that IB gives a full L2/L3 fabric and BEEP everything else, we > could use this combination to speed up various applications in SOA/ > Web2.0 space. > > Love to hear the group's thoughts on this. is there a transport layer between beep and infiniband that provides the things that tcp provides? am i missing something? /mtr _______________________________________________ BEEPwg mailing list BEEPwg@lists.beepcore.org http://drakken.dbc.mtview.ca.us/mailman/listinfo/beepwg From beepwg-bounces@dbc.mtview.ca.us Wed Sep 27 08:52:21 2006 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1GSYth-0007Pj-RG for beep-archive@lists.ietf.org; Wed, 27 Sep 2006 08:52:21 -0400 Received: from drakken.dbc.mtview.ca.us ([168.143.123.173]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1GSYtd-00014b-Ea for beep-archive@lists.ietf.org; Wed, 27 Sep 2006 08:52:21 -0400 Received: from drakken.dbc.mtview.ca.us (localhost.localdomain [127.0.0.1]) by drakken.dbc.mtview.ca.us (8.12.11/8.12.8) with ESMTP id k8RCpTGe007976; Wed, 27 Sep 2006 05:51:29 -0700 Received: from smtp4.suscom.net (smtp4.suscom.net [64.78.119.249]) k8RCpQBY007973 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=FAIL) for ; Wed, 27 Sep 2006 05:51:27 -0700 Received: from localhost (unknown [127.0.0.1]) by smtp4.suscom.net (Postfix) with ESMTP id C629215005D; Wed, 27 Sep 2006 08:51:20 -0400 (EDT) Received: from smtp4.suscom.net ([127.0.0.1]) by localhost (smtp4.suscom.net [127.0.0.1]) (amavisd-new, port 10024) with LMTP id 13868-02-83; Wed, 27 Sep 2006 08:51:09 -0400 (EDT) Received: from [127.0.0.1] (c-67-189-226-42.hsd1.ma.comcast.net [67.189.226.42]) by smtp4.suscom.net (Postfix) with SMTP id 1B04C150038; Wed, 27 Sep 2006 08:51:09 -0400 (EDT) Message-ID: <451A73B8.6090108@saraswat.org> Date: Wed, 27 Sep 2006 08:51:04 -0400 From: Vijay Saraswat User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.7.2) Gecko/20040804 Netscape/7.2 (ax) X-Accept-Language: en-us, en MIME-Version: 1.0 To: Marshall Rose Subject: Re: [BEEPwg] BEEP over Infiniband References: <20060926214928.74063.qmail@web31803.mail.mud.yahoo.com> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: amavisd-new at suscom.net cc: beepwg@lists.beepcore.org X-BeenThere: beepwg@lists.beepcore.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Mailing list for the IETF's BEEP working group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: beepwg-bounces@dbc.mtview.ca.us Errors-To: beepwg-bounces@dbc.mtview.ca.us X-Spam-Score: 0.0 (/) X-Scan-Signature: e5ba305d0e64821bf3d8bc5d3bb07228 Marshall Rose wrote: >> Has anybody implemented/heard about BEEP over Infiniband? Given that >> IB gives a full L2/L3 fabric and BEEP everything else, we could use >> this combination to speed up various applications in SOA/ Web2.0 space. >> >> Love to hear the group's thoughts on this. > > > is there a transport layer between beep and infiniband that provides > the things that tcp provides? am i missing something? > > /mtr (I had sent this pointer to the list earlier...) http://www.emsl.pnl.gov/docs/parsoft/armci/ (There is also GASNet from Berkeley.) Its not TCP, but its worth looking at whether a BEEP-like protocol might be layered on top. IBM also has a LAPI product (low-level API) which should be available on Linux as well soon. _______________________________________________ BEEPwg mailing list BEEPwg@lists.beepcore.org http://drakken.dbc.mtview.ca.us/mailman/listinfo/beepwg From beepwg-bounces@dbc.mtview.ca.us Wed Sep 27 09:18:21 2006 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1GSZIr-0004tc-Uv for beep-archive@lists.ietf.org; Wed, 27 Sep 2006 09:18:21 -0400 Received: from drakken.dbc.mtview.ca.us ([168.143.123.173]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1GSZIq-00078Z-HN for beep-archive@lists.ietf.org; Wed, 27 Sep 2006 09:18:21 -0400 Received: from drakken.dbc.mtview.ca.us (localhost.localdomain [127.0.0.1]) by drakken.dbc.mtview.ca.us (8.12.11/8.12.8) with ESMTP id k8RDDLow008458; Wed, 27 Sep 2006 06:13:24 -0700 Received: from [127.0.0.1] (localhost.localdomain [127.0.0.1]) k8RDDGoX008454; Wed, 27 Sep 2006 06:13:17 -0700 In-Reply-To: <451A73B8.6090108@saraswat.org> References: <20060926214928.74063.qmail@web31803.mail.mud.yahoo.com> <451A73B8.6090108@saraswat.org> Mime-Version: 1.0 (Apple Message framework v752.2) Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: <44FD4B8E-BF3E-4118-AAEB-C9BE447B60FE@dbc.mtview.ca.us> Content-Transfer-Encoding: 7bit From: Marshall Rose Subject: Re: [BEEPwg] BEEP over Infiniband Date: Wed, 27 Sep 2006 14:13:17 +0100 To: Vijay Saraswat X-Mailer: Apple Mail (2.752.2) cc: beepwg@lists.beepcore.org X-BeenThere: beepwg@lists.beepcore.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Mailing list for the IETF's BEEP working group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: beepwg-bounces@dbc.mtview.ca.us Errors-To: beepwg-bounces@dbc.mtview.ca.us X-Spam-Score: 0.0 (/) X-Scan-Signature: 798b2e660f1819ae38035ac1d8d5e3ab > http://www.emsl.pnl.gov/docs/parsoft/armci/ > > (There is also GASNet from Berkeley.) > > Its not TCP, but its worth looking at whether a BEEP-like protocol > might be layered on top. > > IBM also has a LAPI product (low-level API) which should be > available on Linux as well soon. interesting. you can certainly layer beep on top of a messaging passing api, providing it gives you ordered, reliable delivery. presumably, you wouldn't need any flow management for the channels. so, this leaves the performance issue down to using the default content-transfer-encoding when moving data. /mtr _______________________________________________ BEEPwg mailing list BEEPwg@lists.beepcore.org http://drakken.dbc.mtview.ca.us/mailman/listinfo/beepwg