toasters

toasters@lists.teaparty.net

1 participants
13515 discussions

smtape vs. dump
by Peter Kain 19 Oct '12

19 Oct '12

I'm looking at backing up our filer to tape for DR purposes. I've tested both smtape and dump and was surprised that dump was 3 times faster than smtape. The test was preformed on a idle filer. The filer is the destination for SnapMirrors at night and idle during the day. Given that smtape is a block backup I'd expect it to be as fast or faster than dump. The test Volume contains a single LUN. FAS3210> version NetApp Release 8.0.2P6 7-Mode: Fri Jan 27 14:48:08 PST 2012 - filer is idle FAS3210> sysstat -u 1 CPU Total Net kB/s Disk kB/s Tape kB/s Cache Cache CP CP Disk ops/s in out read write read write age hit time ty util 2% 0 1 0 0 0 0 0 2s 100% 0% - 0% 1% 0 2 2 0 0 0 0 2s 100% 0% - 0% - dump to null takes about 13 minutes FAS3210> date; dump f null /vol/papayasg1_mirror; date Tue Oct 16 12:48:06 PDT 2012 DUMP: Using Full Volume Dump DUMP: Dumping tape file 1 on null DUMP: Date of this level 0 dump: Tue Oct 16 03:17:08 2012. DUMP: Date of last level 0 dump: the epoch. DUMP: Dumping /vol/papayasg1_mirror to null DUMP: mapping (Pass I)[regular files] DUMP: mapping (Pass II)[directories] DUMP: estimated 126361315 KB. DUMP: dumping (Pass III) [directories] DUMP: dumping (Pass IV) [regular files] DUMP: Tue Oct 16 12:53:07 2012 : We have written 52672652 KB. 50GB@171MB/sec DUMP: Tue Oct 16 12:58:07 2012 : We have written 99181873 KB. 44GB@151MB/sec DUMP: dumping (Pass V) [ACLs] DUMP: 125867380 KB 120GB@155MB/sec DUMP: DUMP IS DONE Tue Oct 16 13:01:18 PDT 2012 - smtape backup to null takes 44 minutes FAS3210> rdfile /etc/log/backup (null) Tue Oct 16 13:05:32 PDT /vol/papayasg1_mirror CLI-Backup (null) 19 Tue Oct 16 13:05:32 PDT / vol/papayasg1_mirror BKP-Start (level 0 backup of Backup Set ID 2bc95ed2-195f-11e2-8766-00a09813e8e0) 19 Tue Oct 16 13:05:32 PDT /vol/papayasg1_mirror BKP-Params (originator=CLI mode=dw-data tape_record_size=240KB tape=null all_snapshots tape_seeding) 19 Tue Oct 16 13:05:33 PDT /vol/papayasg1_mirror BKP-DW-Start 19 Tue Oct 16 13:50:26 PDT /vol/papayasg1_mirror BKP-DW-End (phase completed in 0:44:53; 34394279 blocks moved) 19 Tue Oct 16 13:50:26 PDT /vol/papayasg1_mirror BKP-Tape-Stats (wait_time=0s wait_count=0 total_count=0 avail_count=0/0/0/0) 19 Tue Oct 16 13:50:26 PDT /vol/papayasg1_mirror BKP-End (backed up 137.577 GB bytes in 0:44:54; performance=183.844 GB/hour) -- Pete Kain 310-506-4475

2 1

IBM N Series and NetApp FAS -- Mixing Parts
by Ray Van Dolson 18 Oct '12

18 Oct '12

First of all -- I don't want to do this. :) But am curious -- can you mix parts (disks, shelves, etc) between IBM's N-Series and a FAS? e.g. use a NetApp disk in an N-Series or vice versa? I'm sure neither IBM nor NetApp would support this, but am curious if it would work. Ray

1 0

Fm 7.3.x to 8.1.1-what's about a roll back action?
by Milazzo Giacomo 17 Oct '12

17 Oct '12

Hi all, I'm quite sure that upgrade fm 7.3.x to 8.1.1 is a (quite) sure action to perform and this is not my first upgrade... But what's about if something fail? Is there a "revert to"? Thanks

2 1

RE: 8.1.1 CIFS and Snow Leopard Slowness?
by Randy Rue 17 Oct '12

17 Oct '12

For a hoot I tried using software update to load the 8.1.1P5 tgz file from the NOW download page. Loaded without errors but after a reboot my version hadn't changed. Worth a try. So how are we supposed to test an upgrade? -----Original Message----- From: Randy Rue [mailto:rrue@fhcrc.org] Sent: Wednesday, October 17, 2012 9:14 AM To: 'toasters(a)teaparty.net' Subject: RE: 8.1.1 CIFS and Snow Leopard Slowness? Looks like there's no simulator later than 8.1.1 available yet. Is there any way to upgrade a simulator to 8.1.1P1? On that subject, do they have any way yet to upgrade a simulator at all or do we still just scrap the old one and build a new one? -----Original Message----- From: Jeff Cleverley [mailto:jeff.cleverley@avagotech.com] Sent: Tuesday, October 16, 2012 4:56 PM To: Randy Rue Subject: Re: 8.1.1 CIFS and Snow Leopard Slowness? Randy, I know there was at least one BURT for Mac behavior, one in particular that could hang a filer. I think that may have been NFS though. I was looking at the 8.1.1P1 release yesterday. There were several CIFS related fixes in it. We do virtually no CIFS so I just skimmed over them. You may check it out and see if anything was fixed or applies. Jeff On Tue, Oct 16, 2012 at 3:41 PM, Randy Rue <rrue(a)fhcrc.org> wrote: > Hello All, > > We're gearing up to upgrade our v3170 pair from 7.3.5P5 to 8.1.1 at > the end of this month. > > We're testing some things against a 8.1.1 simulator and have had > reports of CIFS timeouts when running tests from a Mac OS X 10.6 (Snow > Leopard) client. > > Performance on the simulator is obviously abysmal when we're running a > VMware appliance on a Windows desktop using a single SATA disk, but > this appears to be more of a protocol timeout issue. The user gets a > spinning wheel for several minutes and only in Snow Leopard. > > Anyone know of any issues with 8.1.1 CIFS and Mac? We had heard some > anecdotal accounts of Office issues but we're tested for those. > > Hope to hear from you, > > Randy > > _______________________________________________ > Toasters mailing list > Toasters(a)teaparty.net > http://www.teaparty.net/mailman/listinfo/toasters -- Jeff Cleverley Unix Systems Administrator 4380 Ziegler Road Fort Collins, Colorado 80525 970-288-4611

1 0

RE: 8.1.1 CIFS and Snow Leopard Slowness?
by Randy Rue 17 Oct '12

17 Oct '12

Looks like there's no simulator later than 8.1.1 available yet. Is there any way to upgrade a simulator to 8.1.1P1? On that subject, do they have any way yet to upgrade a simulator at all or do we still just scrap the old one and build a new one? -----Original Message----- From: Jeff Cleverley [mailto:jeff.cleverley@avagotech.com] Sent: Tuesday, October 16, 2012 4:56 PM To: Randy Rue Subject: Re: 8.1.1 CIFS and Snow Leopard Slowness? Randy, I know there was at least one BURT for Mac behavior, one in particular that could hang a filer. I think that may have been NFS though. I was looking at the 8.1.1P1 release yesterday. There were several CIFS related fixes in it. We do virtually no CIFS so I just skimmed over them. You may check it out and see if anything was fixed or applies. Jeff On Tue, Oct 16, 2012 at 3:41 PM, Randy Rue <rrue(a)fhcrc.org> wrote: > Hello All, > > We're gearing up to upgrade our v3170 pair from 7.3.5P5 to 8.1.1 at > the end of this month. > > We're testing some things against a 8.1.1 simulator and have had > reports of CIFS timeouts when running tests from a Mac OS X 10.6 (Snow > Leopard) client. > > Performance on the simulator is obviously abysmal when we're running a > VMware appliance on a Windows desktop using a single SATA disk, but > this appears to be more of a protocol timeout issue. The user gets a > spinning wheel for several minutes and only in Snow Leopard. > > Anyone know of any issues with 8.1.1 CIFS and Mac? We had heard some > anecdotal accounts of Office issues but we're tested for those. > > Hope to hear from you, > > Randy > > _______________________________________________ > Toasters mailing list > Toasters(a)teaparty.net > http://www.teaparty.net/mailman/listinfo/toasters -- Jeff Cleverley Unix Systems Administrator 4380 Ziegler Road Fort Collins, Colorado 80525 970-288-4611

1 0

8.1.1 CIFS and Snow Leopard Slowness?
by Randy Rue 16 Oct '12

16 Oct '12

Hello All, We're gearing up to upgrade our v3170 pair from 7.3.5P5 to 8.1.1 at the end of this month. We're testing some things against a 8.1.1 simulator and have had reports of CIFS timeouts when running tests from a Mac OS X 10.6 (Snow Leopard) client. Performance on the simulator is obviously abysmal when we're running a VMware appliance on a Windows desktop using a single SATA disk, but this appears to be more of a protocol timeout issue. The user gets a spinning wheel for several minutes and only in Snow Leopard. Anyone know of any issues with 8.1.1 CIFS and Mac? We had heard some anecdotal accounts of Office issues but we're tested for those. Hope to hear from you, Randy

1 0

100% CPU utilization on "bored" IBM N6240E21 (FAS3240C)
by Ray Van Dolson 16 Oct '12

16 Oct '12

Hello all; A week or so ago, our N6240E21 (FAS3240C) started reporting 100% CPU utilization. Graphs from our monitoring system show the typical random peaks and valleys averaging around 20-30% utilization, then suddenly a plateau at 100% lasting for an entire week (and still ongoing). The weird thing is -- the filer really *isn't* that busy: red-str-napc1-p2> sysstat -x -c 10 1 CPU NFS CIFS HTTP Total Net kB/s Disk kB/s Tape kB/s Cache Cache CP CP Disk OTHER FCP iSCSI FCP kB/s iSCSI kB/s in out read write read write age hit time ty util in out in out 100% 1489 530 0 2019 13174 10363 14636 11588 0 0 4s 84% 20% : 21% 0 0 0 0 0 0 0 100% 2001 636 0 2637 29590 20895 25112 14140 0 0 4s 77% 15% Hn 16% 0 0 0 0 0 0 0 100% 1140 608 0 1748 11829 6349 14396 58396 0 0 4s 95% 100% :f 22% 0 0 0 0 0 0 0 99% 3703 404 0 4107 38005 108512 164912 23204 0 0 4s 65% 46% : 60% 0 0 0 0 0 0 0 100% 1429 195 0 1627 15986 10483 23296 53132 0 0 3s 93% 37% Hn 25% 3 0 0 0 0 0 0 100% 1440 35 0 1475 32821 11302 16796 35488 0 0 3s 91% 68% : 20% 0 0 0 0 0 0 0 100% 1461 0 0 1461 10467 8030 7912 32 0 0 3s 75% 0% - 23% 0 0 0 0 0 0 0 100% 1845 280 0 2125 28710 17652 19624 12636 0 0 3s 83% 17% Hn 24% 0 0 0 0 0 0 0 100% 2070 191 0 2261 6911 20148 23964 80048 0 0 3s 94% 66% : 19% 0 0 0 0 0 0 0 100% 1477 153 0 1633 29005 8196 8536 24 0 0 3s 76% 0% - 12% 3 0 0 0 0 0 0 red-str-napc1-p2*> sysstat -m -c 10 1 ANY AVG CPU0 CPU1 CPU2 CPU3 47% 65% 85% 70% 74% 30% 74% 76% 87% 78% 83% 56% 47% 65% 85% 70% 75% 31% 59% 68% 84% 71% 76% 41% 49% 66% 85% 72% 76% 32% 50% 68% 83% 77% 79% 33% 56% 70% 87% 76% 79% 37% 47% 66% 85% 72% 76% 29% 29% 62% 86% 70% 75% 16% 36% 64% 86% 72% 76% 23% red-str-napc1-p2*> priv set advanced red-str-napc1-p2*> ps -c 5 Process statistics over 1218393.619 seconds... ID State Domain %CPU StackUsed %StackUsed Name 5 RR i 76% 1016 24% idle_thread0 6 RR i 76% 904 22% idle_thread1 7 RR i 75% 904 22% idle_thread2 8 RR i 64% 1024 25% idle_thread3 89 BG 1 5% 4440 6% NwkThd_01 108 RR 2 7% 1944 5% 10GbE/e1b 294 BR r 12% 4104 25% raidio_thread 1539 BR w 6% 5736 17% wafl_exempt_0 1540 BR w 6% 5736 17% wafl_exempt_1 1541 BR w 6% 5736 17% wafl_exempt_2 1544 BR k 9% 13720 41% wafl_lopri (A few other processes are >0%, but these are the most notable). We are running on ONTAP 8.0.2P3 (7-mode) and the filer is primarily doing NFS for VMware datastores with a bit of CIFS sharing mixed in. We have opened a support case with IBM, but so far they are telling us that this may be "normal". They're still helping us investigate, so we may yet get something from that route, but wanted to throw this out here because this certainly doesn't seem normal. I'm guessing a controller reboot would solve the problem, but would like to see if there is an alternative or an explanation first. This thread[1] seems similar, but there wasn't really a resolution. Thanks, Ray [1] https://communities.netapp.com/thread/14321

2 2

CMDB for storage?
by Ray Van Dolson 12 Oct '12

12 Oct '12

Hi all; For those of you who track your SAN/NAS devices (including your NetApps) in a CMDB, I'm interestd in how you lay out your CI's. Do you have a CI for a "cluster" (two controllers), individual CI's for controllers themselves and additional CI's for shelves and disks with relationships mapped between? Our CMDB is a bit on the simplistic side, so am trying to figure out where folks have cut corners from the ideal. I'd love to track things like shares as well so we can maintain contact information and relationships with hardware for outage notifications. Mainly curious how others are handling this, and also what CMDB tools you use. Thanks, Ray

1 0

block zeroing
by Peter D. Gray 10 Oct '12

10 Oct '12

I have a question. A month or so back we had massive performance problems on our 3170A and disks were 100% for no apparent reason (SATA drives). Netapp eventually tracked down the problem to snapshot deletion. It seems that blocks are zeroed as they are returned to the aggregate. It was taking longer than 60 mins to delete the hourly snapshots. So, my questions are: 1) has anybody else seen this problem and been forced to avoid hourly snaps? 2) is there any way to disable the zeroing of freed blocks? 3) has anybody heard of a plan for a fix which would allow us to use hourly snaps again? It seems bizarre that a useful feature, which we have used for a long time, has become unusable. Basically, it appears I/O is doubled becuase the blocks are written when used, then written when freed. Regards, pdg

4 3

WAFL external cache I/O write error
by Kernel Panic 07 Oct '12

07 Oct '12

Good day. Got that message in log: Sun Oct 7 02:56:07 MSK [EMC2-a:extCache.io.writeError:error]: WAFL external cache I/O write error: FAL error: fal_response_get_status() failed , code 1. Is this fatal? We all die?

3 2

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