Return-Path: X-Original-To: apmail-cassandra-user-archive@www.apache.org Delivered-To: apmail-cassandra-user-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 1611579CE for ; Thu, 17 Nov 2011 02:46:58 +0000 (UTC) Received: (qmail 56935 invoked by uid 500); 17 Nov 2011 02:46:56 -0000 Delivered-To: apmail-cassandra-user-archive@cassandra.apache.org Received: (qmail 56914 invoked by uid 500); 17 Nov 2011 02:46:55 -0000 Mailing-List: contact user-help@cassandra.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: user@cassandra.apache.org Delivered-To: mailing list user@cassandra.apache.org Received: (qmail 56906 invoked by uid 99); 17 Nov 2011 02:46:55 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Thu, 17 Nov 2011 02:46:55 +0000 X-ASF-Spam-Status: No, hits=-0.1 required=5.0 tests=HTML_MESSAGE,RCVD_IN_DNSWL_MED,SPF_PASS X-Spam-Check-By: apache.org Received-SPF: pass (athena.apache.org: domain of JEREMIAH.JORDAN@morningstar.com designates 216.228.224.32 as permitted sender) Received: from [216.228.224.32] (HELO mx85.morningstar.com) (216.228.224.32) by apache.org (qpsmtpd/0.29) with SMTP; Thu, 17 Nov 2011 02:46:47 +0000 Received: from MSMAILC.morningstar.com ([172.28.6.23]) by mx85.morningstar.com with Microsoft SMTPSVC(6.0.3790.4675); Wed, 16 Nov 2011 20:46:26 -0600 Received: from [192.168.2.3] ([71.201.190.179]) by MSMAILC.morningstar.com over TLS secured channel with Microsoft SMTPSVC(6.0.3790.4675); Wed, 16 Nov 2011 20:46:13 -0600 From: Jeremiah Jordan Mime-Version: 1.0 (Apple Message framework v1251.1) Content-Type: multipart/alternative; boundary="Apple-Mail=_9EDE6501-4C3C-45DF-BAAB-CBB5CAE26734" Subject: Re: Efficiency of Cross Data Center Replication...? Date: Wed, 16 Nov 2011 20:46:05 -0600 In-Reply-To: To: user@cassandra.apache.org References: Message-Id: <5F189A91-3C9A-4AB5-A278-CBF5F3330550@morningstar.com> X-Mailer: Apple Mail (2.1251.1) X-OriginalArrivalTime: 17 Nov 2011 02:46:14.0468 (UTC) FILETIME=[12A3C840:01CCA4D3] --Apple-Mail=_9EDE6501-4C3C-45DF-BAAB-CBB5CAE26734 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=iso-8859-1 Pretty sure data is sent to the coordinating node in DC2 at the same = time it is sent to replicas in DC1, so I would think 10's of = milliseconds after the transport time to DC2. On Nov 16, 2011, at 3:48 PM, ehershey@gmail.com wrote: > On a related note - assuming there are available resources across the = board (cpu and memory on every node, low network latency, non-saturated = nics/circuits/disks), what's a reasonable expectation for timing on = replication? Sub-second? Less than five seconds?=20 >=20 > Ernie >=20 > On Wed, Nov 16, 2011 at 4:00 PM, Brian Fleming = wrote: > Great - thanks Jake >=20 > B. >=20 > On Wed, Nov 16, 2011 at 8:40 PM, Jake Luciani = wrote: > the former >=20 >=20 > On Wed, Nov 16, 2011 at 3:33 PM, Brian Fleming = wrote: >=20 > Hi All, > =20 > I have a question about inter-data centre replication : if you have 2 = Data Centers, each with a local RF of 2 (i.e. total RF of 4) and write = to a node in DC1, how efficient is the replication to DC2 - i.e. is that = data : > - replicated over to a single node in DC2 once and internally = replicated > or=20 > - replicated explicitly to two separate nodes? >=20 > Obviously from a LAN resource utilisation perspective, the former = would be preferable. >=20 > Many thanks, >=20 > Brian >=20 >=20 >=20 >=20 > --=20 > http://twitter.com/tjake >=20 >=20 --Apple-Mail=_9EDE6501-4C3C-45DF-BAAB-CBB5CAE26734 Content-Transfer-Encoding: 7bit Content-Type: text/html; charset=iso-8859-1 Pretty sure data is sent to the coordinating node in DC2 at the same time it is sent to replicas in DC1, so I would think 10's of milliseconds after the transport time to DC2.

On Nov 16, 2011, at 3:48 PM, ehershey@gmail.com wrote:

On a related note - assuming there are available resources across the board (cpu and memory on every node, low network latency, non-saturated nics/circuits/disks), what's a reasonable expectation for timing on replication? Sub-second? Less than five seconds? 

Ernie

On Wed, Nov 16, 2011 at 4:00 PM, Brian Fleming <bigbrianfleming@gmail.com> wrote:
Great - thanks Jake

B.

On Wed, Nov 16, 2011 at 8:40 PM, Jake Luciani <jakers@gmail.com> wrote:
the former


On Wed, Nov 16, 2011 at 3:33 PM, Brian Fleming <bigbrianfleming@gmail.com> wrote:

Hi All,
 
I have a question about inter-data centre replication : if you have 2 Data Centers, each with a local RF of 2 (i.e. total RF of 4) and write to a node in DC1, how efficient is the replication to DC2 - i.e. is that data :
 - replicated over to a single node in DC2 once and internally replicated
 or 
 - replicated explicitly to two separate nodes?

Obviously from a LAN resource utilisation perspective, the former would be preferable.

Many thanks,

Brian




--
http://twitter.com/tjake



--Apple-Mail=_9EDE6501-4C3C-45DF-BAAB-CBB5CAE26734--