Hello,

I am using a DELL Equallogic at work and I use a SLES10 SP2 (was
SP1 before last week-end), are they known problems with the SLES SP2 ?
I didn't notice any problem since the upgrade !

Could you explain your Ethernet settings to boost performance ?


Regards

JP Pozzi
 



Le lundi 27 juillet 2009 à 14:01 -0700, jnantel a écrit :
> Hi Joseph, we also have Dell equallogics in our shop.  I can tell you
> A LOT about them and how to setup with multipath/iscsi..etc.  Mike
> Christie is an incredible resource for sure, and he helped me a great
> deal with my setup.  Be thankful you aren't using SLES10 SP2.
> 
> Performance, you should be able to hit 200-210 meg/s write performance
> with RAID10 and around 150-160 with RAID6. Read performance for both
> usually pegged at 215-220meg/sec sustained. This is of course with
> sequential data.
> 
> couple of goofy things I did notice in multipath.conf:
> 
> 1. features "1 queue_if_no_path"   and no_path_retry conflict
> 2. rr_min_io has the largest effect on performance in multipath.  Play
> with different options (8/16/32/64) depending on your data sizes.  You
> can reconfigure on the fly using "multipathd -k"  and the
> "reconfigure" command. I am currently using 16 as I have lots of small
> data chunks and I want lots of io in flight.
> 
> iscsid.conf
> node.session.cmds_max = 1024
> node.session.queue_depth = 64 (96 works good here as well if you have
> small data sizes)
> 
> node.conn[0].timeo.noop_out_interval = 15
> node.conn[0].timeo.noop_out_timeout = 45
> 
> The above are my settings, Mike's probably work better.
> 
> Couple of performance inhibiters I found...Make sure you have flow
> control set on the switch.  TSO/SG/TX and RX offloading work by
> assembly packets into 64k chunks prior to sending...This is death to
> performance.
> 
> If you have a beefy CPU turn them off like this:
> 
> ethtool -K eth4 rx off
> ethtool -K eth4 tso off
> ethtool -K eth4 tx off
> ethtool -K eth4 sg off
> 
> Tune your TCP stack for gigabit performance for sure.
> 
> On Jul 22, 12:01 pm, "Hoot, Joseph" <joe.h...@itec.suny.edu> wrote:
> > Mike or others,
> >
> > Do you or others think that my "ping/CHAP" issue that I'm having -- aka
> > sessions resetting (logging out) could be related to the more recent
> > "ping timeout" and maxcmds patch that has been worked on and discussed?
> >
> > I am attempting to get my test systems updated to test this, but I
> > figured that I'd toss it out there to see if they might be related.
> >
> > Thanks,
> > Joe
> >
> > -----Original Message-----
> > From: open-iscsi@googlegroups.com [mailto:open-is...@googlegroups.com]
> >
> > On Behalf Of Mike Christie
> > Sent: Tuesday, July 14, 2009 6:01 PM
> > To: open-iscsi@googlegroups.com
> > Subject: Re: iscsiadm -m iface + routing
> >
> > On 07/13/2009 09:20 AM, Hoot, Joseph wrote:
> > > Mike,
> >
> > > Just as an FYI (in case you were most curious about this issue) I've
> > > narrowed this issue down to something with CHAP.  On my EqualLogic, if
> > I
> > > disable CHAP, I can't reproduce this issue.
> >
> > > So I did the following.  I after upgrading to the latest OEL 5.3
> > release
> > > of the iscsi-initiator, I could still reproduce the problem.
> > Therefore,
> > > I did the following:
> >
> > > 1) Setup another test environment using the same hardware (physical
> > > different hardware, but all same firmware, models, etc..)
> > > 2) presented a new test volume from EqualLogic
> > > 3) ran the ping test (ping -Ieth2 192.168.0.19&  ping -Ieth3
> > > 192.168.0.19).
> > > 4) I couldn't reproduce the issue.
> > > 5) I checked what the difference were-- CHAP the only difference.
> > > 6) So I turned on CHAP authentication to the volume.
> > > 7) rm -rf /var/lib/iscsi/nodes/* /var/lib/iscsi/send_targets/*
> > > 8) rediscovered targets (after modifying /etc/iscsi/iscsid.conf with
> > > CHAP information)
> >
> > > node.session.auth.authmethod = CHAP
> > > node.session.auth.username = mychapuserhere
> > > node.session.auth.password = mypasshere
> >
> > > 9) ran the same ping test and was able to get iscsi sessions to fail
> > > within 2 minutes.
> > > 10) I wanted to prove that CHAP was the issue. So I logout out of all
> > > iscsi sessions.
> > > 11) I disabled CHAP on the EqualLogic
> > > 12) rediscovery targets and re-logged in to the sessions (without CHAP
> > > authentication)
> > > 13) ran the ping tests and couldn't break it after 30 minutes.
> > > 14) added CHAP again and was able to break the sessions within 2
> > > minutes.
> >
> > > So definitely something odd with CHAP (my guess, either in open-iscsi
> > > code or EqualLogic code).  I've asked Roger Lopez, from Dell, to
> > attempt
> > > to reproduce this in his lab.  He has EqualLogic and Oracle VM
> > Servers.
> > > Oracle developers that I'm working with don't currently have access to
> > > an EqualLogic, but they are attempting to reproduce this with their
> > > iSCSI equipment as well.  I'm going to setup port mirroring on our
> > > switch and run tcpdumps to see what I can get.
> >
> > This is strange because CHAP does not come into play in the normal IO
> > path. When we login we will do authentication with CHAP, but after that
> > succeeds it nevers comes up when doing IO. It would only come up again
> > when the session/connection is dropped/disconnected and we relogin. For
> > the relogin we will do the CHAP authentication again.
> >
> > Maybe some memory error where chap values are overwriting some other
> > memory.
> >
> > There was one recent fix by Dell, where when using CHAP they could
> > segfault iscsid. Here is the updated RPM that I am working on for RHEL
> > 5.4 that has the fix:
> >
> > http://people.redhat.com/mchristi/iscsi/rhel5.4/iscsi-initiator-utils/
> >
> >
> > 
> 
> 



--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups 
"open-iscsi" group.
To post to this group, send email to open-iscsi@googlegroups.com
To unsubscribe from this group, send email to 
open-iscsi+unsubscr...@googlegroups.com
For more options, visit this group at http://groups.google.com/group/open-iscsi
-~----------~----~----~----~------~----~------~--~---

Reply via email to