toasters

toasters@lists.teaparty.net

13520 discussions

RE: CPU Stats on multi-proc filers
by Colby, Michael 15 Mar '06

15 Mar '06

You'd think: -----Original Message----- From: Brian Parent [mailto:bparent@calvin.ucsd.edu] Sent: Wednesday, March 15, 2006 9:47 AM To: toasters(a)mathworks.com Subject: Re: CPU Stats on multi-proc filers Since sysstat has the -m option which allows viewing AVG as well as individual CPU performance, it seems reasonable that the same data should be made available via SNMP.

1 0

RE: Mixed Mode
by Glenn Dekhayser 15 Mar '06

15 Mar '06

In my 10+ years of dealing with Netapp, I have never known them to remove a feature from OnTAP, and can't imagine them starting now- especially one used by thousands of installations today. Perhaps your users misunderstood what they heard in training? A trainer would also never disclose that kind of information in that forum as presumably not everyone in the room would be under NDA, and that kind of information, if true (and I suspect not) would be confidential. ________________________________ From: owner-toasters(a)mathworks.com [mailto:owner-toasters@mathworks.com] On Behalf Of JONES P.S. Sent: Wednesday, March 15, 2006 10:13 AM To: Tracy Russell; toasters(a)mathworks.com Subject: RE: Mixed Mode I trust this is an individual's surmise and no more. I have not heard of this remote possibility in any shape or form. We rely absolutely on mixed mode presentation to our users; its one of the keystone elements of our single authentication, single filestore architecture. Losing this would be too much to contemplate. Paul Jones, B.Sc, M.Sc, Ph.D. - Head of Systems Services, Information Technology Service, Durham University, South Road, Durham DH1 3LE Email: p.s.jones(a)durham.ac.uk Phone/Fax: 0191 334 2749/2701 ________________________________ From: owner-toasters(a)mathworks.com on behalf of Tracy Russell Sent: Wed 3/15/2006 2:19 PM To: toasters(a)mathworks.com Subject: Mixed Mode Does anyone know the future of the security mode -- "mixed mode"? Several co-workers returned from NetApp training stating that this particular mode is not encouraged and may be dropped in the not too distant future from NetApp support. Has anyone else heard this or can confirm this to any degree? We are about to set up a new Filer and I'm trying to decide what to do with a volume that is currently configured for mixed mode security on an old Filer. If anyone has experiences changes from mixed mode to either all CIFS or NFS, I'd appreciate their inputs as well. Thanks. Tracy

1 0

suscribe
by John Breyfogle 15 Mar '06

15 Mar '06

1 0

Re: CPU Stats on multi-proc filers
by Davin Milun 15 Mar '06

15 Mar '06

At 13:02, on Mar 15, 2006, Cornelius Bartke wrote: > Davin Milun 14.03.2006 23:17: > > At 22:18, on Mar 14, 2006, Cornelius Bartke wrote: > > [...] calculating CPU utilization via > >> delta(cpuBusyTime)*100/delta(cpuUpTime) on a FAS960 leaves us with a > >> no-so-satisfying ANY value. See also Bug-IDs 141441 and 148982. > >> > >> It would be better to have snmpd report a cpuTable with seperate data > >> for all CPUs. > > > > Actually - I disagree. Graphing cpuBusyTime indeed shows the average. > > Been using it for years. > > Hum. > > We noticed a 20% increase in CPU usage when we upgraded from 6.4.4P6 > to 6.5.4P1. First we were worried because there was little chance that > this was due to changed usage patterns. Then we investiged by > comparing sysstat output to snmpd output. Our conclusion was that in > OnTAP 6.4.4P6, snmpd reports cpu utilization as the average of each > CPU's utilization. With the upgrade to 6.5.4P1 snmpd reports CPU > utilization as percentage of time when at least one CPU is busy, i.e. > ANY instead of AVG. That has not changed when we upgraded to OnTAP > 6.5.6P3. Oh. I'm still running 6.4.x on the filers that I watch CPU most closely on. So if NetApp broke cpuBusyTime in 6.5.x to report ANY time, then (a) I stand corrected, and (b) I'm quite unhappy with that change. > My point is that reporting snmpd data for each individual CPU in a > snmp table would leave the ANY/AVG decision to the customer and I hope > you agree this would improve the usefulness of CPU utilisation data :) Yes. Definitely. Davin.

1 0

Re: CPU Stats on multi-proc filers
by Davin Milun 15 Mar '06

15 Mar '06

At 22:18, on Mar 14, 2006, Cornelius Bartke wrote: > > > > Which MRTG are you using? I've found that querying SNMP for the CPU > > busy (.1.3.6.1.4.1.789.1.2.1.2) use will indeed graph the AVG CPU, > > which is the sane one. > > Actually, .1.3.6.1.4.1.789.1.2.1.2 is cpuBusyTime (at least the MIB > for DOT 6.5.x says so) and calculating CPU utilization via > delta(cpuBusyTime)*100/delta(cpuUpTime) on a FAS960 leaves us with a > no-so-satisfying ANY value. See also Bug-IDs 141441 and 148982. > > It would be better to have snmpd report a cpuTable with seperate data > for all CPUs. Actually - I disagree. Graphing cpuBusyTime indeed shows the average. Been using it for years. And that's indeed was BugID 148982 is complaining about: SNMP reports cpu utilization as the average of each CPU's utilization while sysstat reports the percentage of time at least one CPU is busy. As a result, the CPU utilization reported by the two tools may not match. Davin.

2 1

RE: Block access (iSCSI etc)
by Willeke, Jochen 15 Mar '06

15 Mar '06

Hi Graeme, we are running two Exchange Systems with netapp storage. One is connected to the netapps via ISCSI and the bigger one has it's one SAN with 2 fabrics for redundancy reason. I must say that both systems are running more than well :-) We only had problems with the ISCSI connection when we set it up for the first time. Sometimes the exchange which runs as a clusterressource did not see all drives after a failover. But this was due to a bad Microsoft ISCSI Initiator installation. What i strongly recommend when using ISCSI is snapdrive which helps you managing your LUNS (e.g. for Exchange). First we tried to do without but got little problems with backups and now after 2 month with snapdrive i do not want to miss it anymore :-) Regards Jochen -----Original Message----- From: owner-toasters(a)mathworks.com [mailto:owner-toasters@mathworks.com] On Behalf Of Graeme Fowler Sent: Tuesday, March 14, 2006 5:34 PM To: toasters(a)mathworks.com Subject: Block access (iSCSI etc) Hi all I've recently moved jobs, and one of my new projects is being involved in a major email overhaul for my new employer. We're currently evaluating a whole heap of different aspects (desktop client, web client, clients for unsupported operating systems, diary/calendar, server software etc etc), two of which are Oracle Collaboration Suite (OCS) and MS Exchange. Both of these require block-level access to disk resources, whether direct attach, across a network using iSCSI, or directly into an FC SAN. Does anyone on the list have any stories - good, bad, or indifferent - about running the above pieces of software using a filer backend, generally over iSCSI *or* by breaking into the FC backend and hooking the filer into a SAN environment? If you do, I'd be pleased to hear them - offlist if necessary. If you're running either of them with a SAN backend which isn't NetApp, that's just as useful a data point. There's a lot of views being expressed in my direction at present which appear to be without foundation, so I'm very interested in any "real world" tales :) Thanks Graeme

1 0

OSSV questions !
by Premanshu Jain 14 Mar '06

14 Mar '06

Question 1 Netapp open source snap vault (OSSV) supports only a local attached disk based file system. I need to use OSSV to dump a NFS mounted partition. Any leads to this will be appreciated. Question 2 Anybody using OSSV to snapvault perforce data ?

2 1

RE: CPU Stats on multi-proc filers
by Hill, Aaron 14 Mar '06

14 Mar '06

Same issue with DFM for years and we have never come across a fix. We use sysstat -m as NetApp suggests when "zooming in" for closer analysis. Aaron _____ From: owner-toasters(a)mathworks.com [mailto:owner-toasters@mathworks.com] On Behalf Of markallen(a)micron.com Sent: Wednesday, 15 March 2006 6:25 AM To: markallen(a)micron.com; toasters(a)mathworks.com Subject: RE: CPU Stats on multi-proc filers I use DFM and MRTG to monitor several of filers. I've ran into issues with CPU stats for multi-processor systems. DFM and MRTG will report the "any value" versus the average value. I've had several discussions with Netapp tech support on this topic and there was never a clear direction on with metric to key off of. Tech support informed me that I should be looking at the CPU utilization with sysstat -m and key off of the AVG value. rsh filer sysstat -m 1 ANY AVG CPU0 CPU1 CPU2 CPU3 69% 25% 3% 50% 0% 44% 77% 23% 2% 48% 1% 43% 100% 30% 1% 46% 0% 49% 100% 31% 2% 70% 1% 81% 100% 33% 2% 67% 0% 62% 100% 30% 1% 62% 0% 55% 99% 30% 1% 61% 0% 56% 93% 29% 2% 60% 0% 54% 41% 13% 2% 28% 0% 22% 49% 16% 2% 34% 0% 28% 50% 16% 2% 34% 0% 28% 43% 14% 2% 30% 0% 26% 51% 17% 2% 34% 0% 32% My metrics using DFM and MRTG captures the "any" value. According to Netapp it is not the metric that should be captured. Is anyone else having these challenges and is their a fix in DFM to collect the correct metric on multi-proc systems? Thanks -Mark ************** IMPORTANT MESSAGE ************** This e-mail message is intended only for the addressee(s) and contains information which may be confidential. If you are not the intended recipient please advise the sender by return email, do not use or disclose the contents, and delete the message and any attachments from your system. Unless specifically indicated, this email does not constitute formal advice or commitment by the sender or the Commonwealth Bank of Australia (ABN 48 123 123 124) or its subsidiaries. We can be contacted through our web site: commbank.com.au. If you no longer wish to receive commercial electronic messages from us, please reply to this e-mail by typing Unsubscribe in the subject line. ***************************************************************

1 0

RE: CPU Stats on multi-proc filers
by Davin Milun 14 Mar '06

14 Mar '06

At 12:25, on Mar 14, 2006, markallen(a)micron.com wrote: > I use DFM and MRTG to monitor several of filers. I've ran into issues > with CPU stats for multi-processor systems. DFM and MRTG will report > the "any value" versus the average value. I've had several discussions > with Netapp tech support on this topic and there was never a clear > direction on with metric to key off of. Tech support informed me that > I should be looking at the CPU utilization with sysstat -m and key off > of the AVG value. > ... > > My metrics using DFM and MRTG captures the "any" value. According to > Netapp it is not the metric that should be captured. Is anyone else > having these challenges and is their a fix in DFM to collect the > correct metric on multi-proc systems? Which MRTG are you using? I've found that querying SNMP for the CPU busy (.1.3.6.1.4.1.789.1.2.1.2) use will indeed graph the AVG CPU, which is the sane one. I've never understood why most NetApp tools (all the way down to regular sysstat (except for -m)) report the ANY value. Davin.

2 1

RE: Block access (iSCSI etc)
by Glenn Walker 14 Mar '06

14 Mar '06

Having worked for NetApp supporting Exchange\iSCSI\FCP, and as a customer using NetApp\iSCSI storage for a rather large Exchange infrastructure, I have nothing but good things to say... it works and works very well. There are some things that FCP does better: - Speed 2Gb/s vs. iSCSI @ 1Gb/s - Resiliency MPIO on FCP has been around longer than MPIO on iSCSI - Track Record It's very old technology by comparison - iSCSI is still relatively new However: iSCSI will likely get a huge boost in speed once 10Gb/s networking hits with full force compared to FCP's next jump to only 4Gb/s. iSCSI costs way less to implement than FCP due to use of generic\commodity equipment (ie, off the shelf Gig-E switches\NICs\Cables) vs. FCP's specialized\expensive gear (ever price a McData or Brocade switch??). I am somewhat biased in my opinion - I know that NetApp makes very good HW\SW and has excellent support... I can't speak to the other vendors out there because I frankly don't know them all that well. Glenn -----Original Message----- From: owner-toasters(a)mathworks.com [mailto:owner-toasters@mathworks.com] On Behalf Of Graeme Fowler Sent: Tuesday, March 14, 2006 11:34 AM To: toasters(a)mathworks.com Subject: Block access (iSCSI etc) Hi all I've recently moved jobs, and one of my new projects is being involved in a major email overhaul for my new employer. We're currently evaluating a whole heap of different aspects (desktop client, web client, clients for unsupported operating systems, diary/calendar, server software etc etc), two of which are Oracle Collaboration Suite (OCS) and MS Exchange. Both of these require block-level access to disk resources, whether direct attach, across a network using iSCSI, or directly into an FC SAN. Does anyone on the list have any stories - good, bad, or indifferent - about running the above pieces of software using a filer backend, generally over iSCSI *or* by breaking into the FC backend and hooking the filer into a SAN environment? If you do, I'd be pleased to hear them - offlist if necessary. If you're running either of them with a SAN backend which isn't NetApp, that's just as useful a data point. There's a lot of views being expressed in my direction at present which appear to be without foundation, so I'm very interested in any "real world" tales :) Thanks Graeme

1 0

Jump to page:

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

2003

2002

2001

2000

1999

1998

1997

toasters