toasters

toasters@lists.teaparty.net

13514 discussions

Very high CIFS ops
by Uros Lampret 29 Oct '01

29 Oct '01

Hi! Can anybody explain this? I have very high number of CIFS ops/sec but very low trafic. This client uses 10Mbit Ethernet interface. CPU NFS CIFS HTTP Net kB/s Disk kB/s Tape kB/s Cache in out read write read write age 33% 0 1266 0 149 175 48 0 0 0 5 32% 0 1264 0 148 152 0 0 0 0 5 32% 0 1267 0 148 152 0 0 0 0 5 32% 0 1268 0 149 152 0 0 0 0 5 32% 0 1263 0 148 154 0 0 0 0 5 33% 0 1264 0 148 154 0 0 0 0 5 33% 0 1269 0 149 155 0 0 0 0 5 31% 0 1217 0 143 149 0 0 0 0 5 30% 0 1135 0 133 142 0 0 0 0 5 32% 0 1152 0 135 151 84 280 0 0 5 31% 0 1196 0 140 151 0 0 0 0 5 32% 0 1230 0 144 149 0 0 0 0 5 32% 0 1253 0 147 151 0 0 0 0 5 32% 0 1266 0 148 152 0 0 0 0 5 CPU NFS CIFS HTTP Net kB/s Disk kB/s Tape kB/s Cache in out read write read write age 33% 0 1267 0 149 154 0 0 0 0 5 33% 0 1259 0 182 154 0 0 0 0 5 33% 0 1265 0 148 152 0 0 0 0 5 33% 0 1271 0 149 153 0 0 0 0 5 33% 0 1271 0 149 153 0 0 0 0 5 33% 0 1274 0 166 155 0 0 0 0 5 35% 0 1238 0 145 151 100 380 0 0 5 33% 0 1270 0 149 153 0 0 0 0 5 33% 0 1266 0 151 152 0 0 0 0 5 Regards, Uros

1 0

Used gear?
by Nick Steel. (lists) 29 Oct '01

29 Oct '01

Does Netapp have any problems providing hardware support for used equipment? I'm looking at adding some additional space to our F840's and I'd like to shop the used market if the price break is worth it and the support is there from Netapp. Also, does anyone have a vendor they'd recommend for used Netapp gear? Thanks! - Nick

1 0

Virus Alert
by postmaster＠mathworks.com 27 Oct '01

27 Oct '01

Have detected a virus (TROJ_SIRCAM.A) in your mail traffic on 10/27/2001 01:13:01 with an action quarantined.

1 0

Re: F720 CPU Maxing out
by Michael Rogan 27 Oct '01

27 Oct '01

We found that symlinks were causing 60% of the CPU load on our F740. -------------------------- Sent from my BlackBerry Wireless Handheld (www.BlackBerry.net) -----Original Message----- From: Jean-Christophe Smith <jsmith(a)vitalstream.com> To: toasters(a)mathworks.com <toasters(a)mathworks.com> CC: jsmith(a)publichost.com <jsmith(a)publichost.com> Sent: Thu Oct 25 13:51:06 2001 Subject: F720 CPU Maxing out We have a NetApp F720 doing both NFS and CIFS using mixed mode security. It has 256 megs of ram. During parts of the day the CPU and RAM spike to %100 utilization. We do a lot of sendmail, windows media, apache and IIS traffic over the filer. I have two questions: 1. Is there a way we can add more ram, perhaps 512 or a gig? The docs say we are maxxed out with 256. 2. Is it possible that the extra cpu overhead that provides the NFS/CIFS user mapping is causing much of the ram and cpu starvation? Perhaps going to a simpler security model would offload a lot of CPU cycles. Any suggestions would be appreciated.. Jean-Christophe Smith VitalStream jsmith(a)vitalstream.com

4 5

»õ·Î ¸¸µé±â Microsoft Word ¹®¼
by unknown＠example.com 26 Oct '01

26 Oct '01

------------------ Virus Warning Message (on scanner) Found virus TROJ_SIRCAM.A in file �� Microsoft Word ��.doc.com The uncleanable file �� Microsoft Word ��.doc.com is moved to /etc/iscan/virus/virDZBO.aq7V. --------------------------------------------------------- Hi! How are you? I send you this file in order to have your advice See you later. Thanks ------------------ Virus Warning Message (on scanner) �� Microsoft Word ��.doc.com is removed from here because it contains a virus. ---------------------------------------------------------

1 0

RE: F720 CPU Maxing out
by Michael Rogan 26 Oct '01

26 Oct '01

We are using NFSV3, TCP/IP and ONTAP 5.3.5 The symlinks we removed were pointing to another machine and path so the only IO on the F740 (for the 1/3 of our writes that are affected) was the symlink lookup. From our observations the symlink caused a 60% load on the F740 for less than 10% of the NFS operations. Michael -----Original Message----- From: Muhlestein, Mark [mailto:mark.muhlestein@netapp.com] Sent: Friday, October 26, 2001 3:45 PM To: 'Michael Rogan'; 'eli.bottrell(a)corp.terralycos.com'; 'kgraham(a)dotnetdotcom.org' Cc: 'toasters(a)mathworks.com' Subject: RE: F720 CPU Maxing out Assuming you are talking about NFS access, this is likely not an issue with ONTAP. NFS clients have to look up each component of a path as it is parsed, regardless of whether it is a symlink or not. But if it is a symlink, you have to read then look up each component of the symlink, so that adds to the total lookup load, perhaps significantly, depending on the number of components in the symlink. In your case, where you are doing relatively small I/Os against a large number of files, path lookup will probably dominate the mix. Removing symlinks will reduce the lookups, so you would expect a benefit. But I would not expect this to be something that would be affected much by changing ONTAP, since it is a fundamental property of your load. Mark -----Original Message----- From: Michael Rogan [mailto:mrogan@rim.net] Sent: Friday, October 26, 2001 11:22 AM To: 'eli.bottrell(a)corp.terralycos.com'; 'kgraham(a)dotnetdotcom.org' Cc: 'toasters(a)mathworks.com' Subject: Re: F720 CPU Maxing out In our environment we are doing 1-2MB/s write and 2-3MB/s reads, on many small files. 1/3 of our writes were going through symlinks. When looking at the stats for one of our systems, lookup was the highest on the list of operations. When we changed our software to avoid the symlink the CPU load dropped about 60%. We are running 5.3.5 so this may have been fixed in later versions of Ontap. -------------------------- Sent from my BlackBerry Wireless Handheld (www.BlackBerry.net) -----Original Message----- From: Eli Bottrell <eli.bottrell(a)corp.terralycos.com> To: kevin graham <kgraham(a)dotnetdotcom.org> CC: 'toasters(a)mathworks.com' <toasters(a)mathworks.com> Sent: Fri Oct 26 13:13:40 2001 Subject: Re: F720 CPU Maxing out kevin graham wrote: > > I've got a 720 that's becoming very unresponsive under high loads. It doesn't > > get up to 100%, but it does hit 85-90%. This is during times of high writes to > > one volume, on the order of 5-10 Megs/sec. > > The unresponsiveness to pings seems odd, but those writes are probably > about as much as you'll get out of the 720. Looking at my 760's in the > past, they had exhausted cpu at just over 20MB/s of writes (those were > full-frame packets over a non-jumbo'ed Gig-II). Having been at a > cash-strapped dot com for some time now, I haven't had the luxury of > perusing new hardware options much, but does anyone know what kind of > performance benefit is picked up w/ ZCS vs. BCS volumes? Is this a memory bottleneck? I think I only have 256 mb in my filers, should I upgrade for better performance? > > > > Could it be symlinks causing my woes? Any tips for solving this > > problem? > > No matter how many, or how inefficient the symlinks are, they won't affect > write performance (unless of course you've got writes competing wiht > lookups). Once the file's open, it doesn't matter how the filesystem got > there. The sluggishness is noticed on lookups and read. Mainly because all of our developers have paths on that filer sourced in their profiles in their unix shells (/usr/local/ and home directories for instance) their shells get REALLY REALLY slow all of the sudden. I think I may need to rethink my storage architecture if heavy reads/writes are going to the filers performance this much. Basically, I guess I should balance it between my 2 filers that the one with the highest traffic is not where the home directories and /usr/local sit. This is on my older f720, and I just got a f740. Is it much of an upgrade in CPU? Can I just swap heads and have a faster filer? - Eli > > ..kg..

1 0

RE: Legato Networker NDMP backup of Filers
by Kim, Christopher 26 Oct '01

26 Oct '01

Michael, Please take a look at patch LGTpa31270. This is not related but it will help on recovery. ftp.legato.com \pub\LGTpa31270 -Chris -----Original Message----- From: Marcus Smiley [mailto:marcus.smiley@ericsson.com] Sent: Friday, October 26, 2001 9:21 AM To: mcope(a)isisph.com Cc: toasters(a)mathworks.com Subject: Re: Legato Networker NDMP backup of Filers Yeah, I am. Running Networker 6.1 on a Solaris box, with the latest patches from Legato. It did fix the problem you talk about. The patch below replaces the nwsave/save apps with shiny brand new ones. LGTpa31247 Hope this helps. -Marc On Thu, 27 Sep 2001, mcope(a)isisph.com wrote: | | | Are there any other brave souls out there using Legato Networker's NDMP software | to backup a Filer? I know most everyone uses Veritas but the locally Veritas | has some customer support/satisfaction issues. | | I'm running Networker 6.1 build 186 backing up Filers running DOT 6.1R1. The | problem I'm having is restoring files using their Direct Access Restore (DAR) | which they crow so loudly about as THE feature that puts them ahead of the | competition. For restores from multi- tape backups the restore fails when | trying to find files on the second or third tape. I've applied their unreleased | patches for nwrecover and recover which made some improvements but I'm still | getting failures. I starting to feel like I payed to be a beta-tester for them. | | Is there anyone else using Legato's NDMP backup that has any info, tips, war | stories to share? | | Thanx, | | Michael Cope | UNIX/Linux Systems Administrator | ISIS Pharmaceuticals | mcope(a)isisph.com | | UNIX is very user friendly... | it's just highly selective about who it makes friends WITH! | Marcus Smiley Ericsson Wireless Sr. Unix Sys Admin

1 0

RE: F720 CPU Maxing out
by Muhlestein, Mark 26 Oct '01

26 Oct '01

Assuming you are talking about NFS access, this is likely not an issue with ONTAP. NFS clients have to look up each component of a path as it is parsed, regardless of whether it is a symlink or not. But if it is a symlink, you have to read then look up each component of the symlink, so that adds to the total lookup load, perhaps significantly, depending on the number of components in the symlink. In your case, where you are doing relatively small I/Os against a large number of files, path lookup will probably dominate the mix. Removing symlinks will reduce the lookups, so you would expect a benefit. But I would not expect this to be something that would be affected much by changing ONTAP, since it is a fundamental property of your load. Mark -----Original Message----- From: Michael Rogan [mailto:mrogan@rim.net] Sent: Friday, October 26, 2001 11:22 AM To: 'eli.bottrell(a)corp.terralycos.com'; 'kgraham(a)dotnetdotcom.org' Cc: 'toasters(a)mathworks.com' Subject: Re: F720 CPU Maxing out In our environment we are doing 1-2MB/s write and 2-3MB/s reads, on many small files. 1/3 of our writes were going through symlinks. When looking at the stats for one of our systems, lookup was the highest on the list of operations. When we changed our software to avoid the symlink the CPU load dropped about 60%. We are running 5.3.5 so this may have been fixed in later versions of Ontap. -------------------------- Sent from my BlackBerry Wireless Handheld (www.BlackBerry.net) -----Original Message----- From: Eli Bottrell <eli.bottrell(a)corp.terralycos.com> To: kevin graham <kgraham(a)dotnetdotcom.org> CC: 'toasters(a)mathworks.com' <toasters(a)mathworks.com> Sent: Fri Oct 26 13:13:40 2001 Subject: Re: F720 CPU Maxing out kevin graham wrote: > > I've got a 720 that's becoming very unresponsive under high loads. It doesn't > > get up to 100%, but it does hit 85-90%. This is during times of high writes to > > one volume, on the order of 5-10 Megs/sec. > > The unresponsiveness to pings seems odd, but those writes are probably > about as much as you'll get out of the 720. Looking at my 760's in the > past, they had exhausted cpu at just over 20MB/s of writes (those were > full-frame packets over a non-jumbo'ed Gig-II). Having been at a > cash-strapped dot com for some time now, I haven't had the luxury of > perusing new hardware options much, but does anyone know what kind of > performance benefit is picked up w/ ZCS vs. BCS volumes? Is this a memory bottleneck? I think I only have 256 mb in my filers, should I upgrade for better performance? > > > > Could it be symlinks causing my woes? Any tips for solving this > > problem? > > No matter how many, or how inefficient the symlinks are, they won't affect > write performance (unless of course you've got writes competing wiht > lookups). Once the file's open, it doesn't matter how the filesystem got > there. The sluggishness is noticed on lookups and read. Mainly because all of our developers have paths on that filer sourced in their profiles in their unix shells (/usr/local/ and home directories for instance) their shells get REALLY REALLY slow all of the sudden. I think I may need to rethink my storage architecture if heavy reads/writes are going to the filers performance this much. Basically, I guess I should balance it between my 2 filers that the one with the highest traffic is not where the home directories and /usr/local sit. This is on my older f720, and I just got a f740. Is it much of an upgrade in CPU? Can I just swap heads and have a faster filer? - Eli > > ..kg..

1 0

Re: F720 CPU Maxing out
by Michael Rogan 26 Oct '01

26 Oct '01

In our environment we are doing 1-2MB/s write and 2-3MB/s reads, on many small files. 1/3 of our writes were going through symlinks. When looking at the stats for one of our systems, lookup was the highest on the list of operations. When we changed our software to avoid the symlink the CPU load dropped about 60%. We are running 5.3.5 so this may have been fixed in later versions of Ontap. -------------------------- Sent from my BlackBerry Wireless Handheld (www.BlackBerry.net) -----Original Message----- From: Eli Bottrell <eli.bottrell(a)corp.terralycos.com> To: kevin graham <kgraham(a)dotnetdotcom.org> CC: 'toasters(a)mathworks.com' <toasters(a)mathworks.com> Sent: Fri Oct 26 13:13:40 2001 Subject: Re: F720 CPU Maxing out kevin graham wrote: > > I've got a 720 that's becoming very unresponsive under high loads. It doesn't > > get up to 100%, but it does hit 85-90%. This is during times of high writes to > > one volume, on the order of 5-10 Megs/sec. > > The unresponsiveness to pings seems odd, but those writes are probably > about as much as you'll get out of the 720. Looking at my 760's in the > past, they had exhausted cpu at just over 20MB/s of writes (those were > full-frame packets over a non-jumbo'ed Gig-II). Having been at a > cash-strapped dot com for some time now, I haven't had the luxury of > perusing new hardware options much, but does anyone know what kind of > performance benefit is picked up w/ ZCS vs. BCS volumes? Is this a memory bottleneck? I think I only have 256 mb in my filers, should I upgrade for better performance? > > > > Could it be symlinks causing my woes? Any tips for solving this > > problem? > > No matter how many, or how inefficient the symlinks are, they won't affect > write performance (unless of course you've got writes competing wiht > lookups). Once the file's open, it doesn't matter how the filesystem got > there. The sluggishness is noticed on lookups and read. Mainly because all of our developers have paths on that filer sourced in their profiles in their unix shells (/usr/local/ and home directories for instance) their shells get REALLY REALLY slow all of the sudden. I think I may need to rethink my storage architecture if heavy reads/writes are going to the filers performance this much. Basically, I guess I should balance it between my 2 filers that the one with the highest traffic is not where the home directories and /usr/local sit. This is on my older f720, and I just got a f740. Is it much of an upgrade in CPU? Can I just swap heads and have a faster filer? - Eli > > ..kg..

1 0

Legato Networker NDMP backup of Filers
by mcope＠isisph.com 26 Oct '01

26 Oct '01

Are there any other brave souls out there using Legato Networker's NDMP software to backup a Filer? I know most everyone uses Veritas but the locally Veritas has some customer support/satisfaction issues. I'm running Networker 6.1 build 186 backing up Filers running DOT 6.1R1. The problem I'm having is restoring files using their Direct Access Restore (DAR) which they crow so loudly about as THE feature that puts them ahead of the competition. For restores from multi- tape backups the restore fails when trying to find files on the second or third tape. I've applied their unreleased patches for nwrecover and recover which made some improvements but I'm still getting failures. I starting to feel like I payed to be a beta-tester for them. Is there anyone else using Legato's NDMP backup that has any info, tips, war stories to share? Thanx, Michael Cope UNIX/Linux Systems Administrator ISIS Pharmaceuticals mcope(a)isisph.com UNIX is very user friendly... it's just highly selective about who it makes friends WITH!

2 1

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