Hello Toasters,
Just curious if anybody is running an ONTAP 8.2.x 7-mode release on a 2240, 3240 or comparable unit? If so, was there a noticeable increase in cpu utilization and/or client response time following the upgrade to 8.2.x?
We are currently evaluating an 8.2.3 7-mode upgrade from 8.1.3. On 8.1.3, we do see periods in which average processor utilization is in the 80-90% range. We're told we may want to avoid upgrading those units to an 8.2 release as 8.2 requires an additional 10-20% cpu out of the gate.
Thanks, Phil
I've upgraded a couple 8.1 7-mode systems to 8.2 as well performed a few net new installs with 8.2 - all on the 2240s. So far, no issues related to CPU, rather, the usual IOPS ceiling/need to add disks which comes with growth over time.
On Tue, Feb 17, 2015 at 3:30 PM, Philbert Rupkins <philbertrupkins@gmail.com
wrote:
Hello Toasters,
Just curious if anybody is running an ONTAP 8.2.x 7-mode release on a 2240, 3240 or comparable unit? If so, was there a noticeable increase in cpu utilization and/or client response time following the upgrade to 8.2.x?
We are currently evaluating an 8.2.3 7-mode upgrade from 8.1.3. On 8.1.3, we do see periods in which average processor utilization is in the 80-90% range. We're told we may want to avoid upgrading those units to an 8.2 release as 8.2 requires an additional 10-20% cpu out of the gate.
Thanks, Phil
Toasters mailing list Toasters@teaparty.net http://www.teaparty.net/mailman/listinfo/toasters
Thanks for the info!
Peter - I did not know flash cache would potentially be an issue. We are using flash cache on our 3240 systems. Will definitely look into this further.
Mike - glad to hear it has worked out well for you with the 2240s! That makes me feel a little more optimistic about the possibility that we can upgrade our 2240s.
On Tue, Feb 17, 2015 at 4:00 PM, Mike Brown michael.b.brown3@gmail.com wrote:
I've upgraded a couple 8.1 7-mode systems to 8.2 as well performed a few net new installs with 8.2 - all on the 2240s. So far, no issues related to CPU, rather, the usual IOPS ceiling/need to add disks which comes with growth over time.
On Tue, Feb 17, 2015 at 3:30 PM, Philbert Rupkins < philbertrupkins@gmail.com> wrote:
Hello Toasters,
Just curious if anybody is running an ONTAP 8.2.x 7-mode release on a 2240, 3240 or comparable unit? If so, was there a noticeable increase in cpu utilization and/or client response time following the upgrade to 8.2.x?
We are currently evaluating an 8.2.3 7-mode upgrade from 8.1.3. On 8.1.3, we do see periods in which average processor utilization is in the 80-90% range. We're told we may want to avoid upgrading those units to an 8.2 release as 8.2 requires an additional 10-20% cpu out of the gate.
Thanks, Phil
Toasters mailing list Toasters@teaparty.net http://www.teaparty.net/mailman/listinfo/toasters
--
Mike Brown michael.b.brown3@gmail.com Blog: http://VirtuallyMikeBrown.com Twitter: http://twitter.com/VirtuallyMikeB http://twitter.com/#%21/VirtuallyMikeB LinkedIn: http://linkedin.com/in/michaelbbrown
What flash cache issue do you mean (it was apparently off-list reply)? Flash cache is not supported on FAS3210, but the problem appeared in Data ONTAP 8.1 already. FAS3240 should be OK, at least from formal support PoV.
From: toasters-bounces@teaparty.net [mailto:toasters-bounces@teaparty.net] On Behalf Of Philbert Rupkins Sent: Wednesday, February 18, 2015 1:22 AM To: Mike Brown Cc: toasters@teaparty.net Subject: Re: 8.2.x on a 2240 or 3240?
Thanks for the info!
Peter - I did not know flash cache would potentially be an issue. We are using flash cache on our 3240 systems. Will definitely look into this further.
Mike - glad to hear it has worked out well for you with the 2240s! That makes me feel a little more optimistic about the possibility that we can upgrade our 2240s.
On Tue, Feb 17, 2015 at 4:00 PM, Mike Brown <michael.b.brown3@gmail.commailto:michael.b.brown3@gmail.com> wrote: I've upgraded a couple 8.1 7-mode systems to 8.2 as well performed a few net new installs with 8.2 - all on the 2240s. So far, no issues related to CPU, rather, the usual IOPS ceiling/need to add disks which comes with growth over time.
On Tue, Feb 17, 2015 at 3:30 PM, Philbert Rupkins <philbertrupkins@gmail.commailto:philbertrupkins@gmail.com> wrote: Hello Toasters,
Just curious if anybody is running an ONTAP 8.2.x 7-mode release on a 2240, 3240 or comparable unit? If so, was there a noticeable increase in cpu utilization and/or client response time following the upgrade to 8.2.x?
We are currently evaluating an 8.2.3 7-mode upgrade from 8.1.3. On 8.1.3, we do see periods in which average processor utilization is in the 80-90% range. We're told we may want to avoid upgrading those units to an 8.2 release as 8.2 requires an additional 10-20% cpu out of the gate.
Thanks, Phil
_______________________________________________ Toasters mailing list Toasters@teaparty.netmailto:Toasters@teaparty.net http://www.teaparty.net/mailman/listinfo/toasters
--
Mike Brown michael.b.brown3@gmail.commailto:michael.b.brown3@gmail.com Blog: http://VirtuallyMikeBrown.com Twitter: http://twitter.com/VirtuallyMikeBhttp://twitter.com/#%21/VirtuallyMikeB LinkedIn: http://linkedin.com/in/michaelbbrown
Philbert Rupkins wrote:
Peter - I did not know flash cache would potentially be an issue. We are using flash cache on our 3240 systems. Will definitely look into this further.
By "issue" was meant (presumably): severe restrictions/limitation around sizes w.r.t. config of the FlashPool. It can get virtually unusable in a small system, even if it's officially supported. Can depend on how the Aggrs are layed out in there, and there are restrictions on that as well on small systems (sizes...) I'd go for FlashCache in smaller FAS machines, any day.
So yes, this FlashPool issue is connected to the very limited amount of memory in these older small FAS boxes. E.g. WAFL really needs its memory buffers, it's crucial. Memory handling inside ONTAP is a bit... shall we say convoluted -- not well coordinated beetween different parts of the system
As for CPU cycles, I'm not sure that 8.1 -> 8.2 -> 8.2.2 would increase this in any way that it should potentially affect performance (protocol latency). I don't think so, not in general, but YMMV (as always :-) ) If anything I think that avg CPU could go up, due to higher parallelism in lopri work inside ONTAP (bg scanners been broken out of the big serialised chunk, the "kernel domain" long ago given the name Kahuna).
Lopri work doesn't contribute to protocol latency (except transients due to pressure -> level-off effects), only Hipri work does. So what 8.2.2 is doing is essentially utilising the HW you bought better, w.r.t. CPU. Much better in fact, than 8.1
/M
Mike - glad to hear it has worked out well for you with the 2240s! That makes me feel a little more optimistic about the possibility that we can upgrade our 2240s.
Here the responses I received regarding an upgrade to 8.2.x and Flash Cache that apparently didn't make it to everybody on the list.
- The 2240 Will Do well but considerably worse than its successor the 2552 - The 3240 please do not it has too little ram memory - Pls note the 3220 has 1.5 times memory of 3240 and the 8020 4x or so.... - Do not attempt upgrade 3240 if you use flashcache it might go belly up as it has too little ram to operate wall when flash cache is installed ;-(
On Wed, Feb 18, 2015 at 8:30 AM, Michael Bergman < michael.bergman@ericsson.com> wrote:
Philbert Rupkins wrote:
Peter - I did not know flash cache would potentially be an issue. We are using flash cache on our 3240 systems. Will definitely look into this further.
By "issue" was meant (presumably): severe restrictions/limitation around sizes w.r.t. config of the FlashPool. It can get virtually unusable in a small system, even if it's officially supported. Can depend on how the Aggrs are layed out in there, and there are restrictions on that as well on small systems (sizes...) I'd go for FlashCache in smaller FAS machines, any day.
So yes, this FlashPool issue is connected to the very limited amount of memory in these older small FAS boxes. E.g. WAFL really needs its memory buffers, it's crucial. Memory handling inside ONTAP is a bit... shall we say convoluted -- not well coordinated beetween different parts of the system
As for CPU cycles, I'm not sure that 8.1 -> 8.2 -> 8.2.2 would increase this in any way that it should potentially affect performance (protocol latency). I don't think so, not in general, but YMMV (as always :-) ) If anything I think that avg CPU could go up, due to higher parallelism in lopri work inside ONTAP (bg scanners been broken out of the big serialised chunk, the "kernel domain" long ago given the name Kahuna).
Lopri work doesn't contribute to protocol latency (except transients due to pressure -> level-off effects), only Hipri work does. So what 8.2.2 is doing is essentially utilising the HW you bought better, w.r.t. CPU. Much better in fact, than 8.1
/M
Mike - glad to hear it has worked out well for you with the 2240s! That
makes me feel a little more optimistic about the possibility that we can upgrade our 2240s.
Toasters mailing list Toasters@teaparty.net http://www.teaparty.net/mailman/listinfo/toasters
-
Borzenkov, Andrei -
Michael Bergman -
Mike Brown -
Philbert Rupkins