Your best bet is to check with the support staff at Sun.. we no longer have this hardware, but I have heard that much of it is fixed.

-Nate

……….Effectively, as a first approximation, an N-disk RAID-Z group will
behave as a single device in terms of delivered random input
IOPS. Thus a 10-disk group of devices each capable of 200-IOPS, will
globally act as a 200-IOPS capable RAID-Z group. This is the price to
pay to achieve proper data protection without the 2X block overhead
associated with mirroring.

With 2-way mirroring, each FS block output must be sent to 2 devices.
Half of the available IOPS are thus lost to mirroring. However, for
Inputs each side of a mirror can service read calls independently from
one another since each side holds the full information. Given a
proper software implementation that balances the inputs between sides
of a mirror, the FS blocks delivered by a mirrored group is actually
no less than what a simple non-protected RAID-0 stripe would give.

So looking at random access input load, the number of FS blocks per
second (FSBPS), Given N devices to be grouped either in RAID-Z, 2-way
mirrored or simply striped (a.k.a RAID-0, no data protection !), the
equation would be (where dev represents the capacity in terms of
blocks of IOPS of a single device):

Random
Blocks Available FS Blocks / sec
—————- ————–
RAID-Z (N – 1) * dev 1 * dev
Mirror (N / 2) * dev N * dev
Stripe N * dev N * dev

Now lets take 100 disks of 100 GB, each each capable of 200 IOPS and
look at different possible configurations; In the table below the
configuration labeled:

“Z 5 x (19+1)”

refers to a dynamic striping of 5 RAID-Z groups, each group made of 20
disks (19 data disk + 1 parity). M refers to a 2-way mirror and S to a
simple dynamic stripe.

Random
Config Blocks Available FS Blocks /sec
———— —————- ———
Z 1 x (99+1) 9900 GB 200
Z 2 x (49+1) 9800 GB 400
Z 5 x (19+1) 9500 GB 1000
Z 10 x (9+1) 9000 GB 2000
Z 20 x (4+1) 8000 GB 4000
Z 33 x (2+1) 6600 GB 6600

M 2 x (50) 5000 GB 20000
S 1 x (100) 10000 GB 20000

So RAID-Z gives you at most 2X the number of blocks that mirroring
provides but hits you with much fewer delivered IOPS. That means
that, as the number of devices in a group N increases, the expected
gain over mirroring (disk blocks) is bounded (to at most 2X) but the
expected cost in IOPS is not bounded (cost in the range of [N/2, N]
fewer IOPS).

Configuration of these seem a little clunky i.e. you either get 4x 512 GB ZILs in a cluster for $48k or nothing. I read an authoritative source (like richard elling or someone) that said any RAIDZ implementation would limit disk throughput to one disks worth and explained the reasons behind it but no matter what I google, I cant find that page again. Think that explains the 15-30 MB/s people are seeing? So its really raid10 (pool of mirrors) or nothing for good throughput (which someone else posted)… which really means not using ZILs+read cache SSDs is not an option. Off the topic, anyone know if/when ZILs will be dedupe aware like netapp PAMs or if its fundamentally impossible since reads and writes are going to different devices (dont think it should be but throwing it out there)?

This pushes my solution away from the unified storage and toward a ‘regular’ oracle HA/ZFS/NFS cluster for a virtual infrastructure backend but I really want the dtrace gui and other cool stuff like that. Does anyone know if any/all features can be manually added to a traditional solaris 10/11 build/cluster? Anyone know if the unified storage just uses preconfigured sun cluster 3.2 or 3.3 and ha storage plus for NFS HA or some other secret sauce?

Im a n00b at oracle storage but love the idea of it all coming from a netapp background (like most people here) so sorry if the questions are elementary.

Sun was idealist and the customers took advantage of it, problem is they didnt make money… This was destined to end badly for everyone! I wish that IBM would have bought them but Larry screwed them out of that proposition too. Good news is the competition sees zfs and has gotten competitive on features and pricing.

I experimented with some OpenSolaris and 6 SATA disks using motherboard RAID, and with a SSD acting as a Logzilla there was a night and day difference, even with losing a disk to put the ssd in.

the new firmware is a lot better, I run about 30 VM’s across 3 hosts and use NFS mounts. It works, but its way to slow for production use. MS Patches can take hours.

Sorry for my frustrated expression. but this thing really boils me blood! I really wanted to share my love for SUN

I tell anyone who is considering any SUN product or solaris…. DON’T DO IT!!! They offer the worst Service I have ever had!!! we have a range of servers, Tape backup and SUN 7210 Storage. The storage for the past year and half has been giving us nothing but greif!!! I have only been here acouple of months and have already a new SAN product to replace it. we dont use it and have moved the Vmachines and data to temp HP drives. The unit every now and then decides to just powerdown! Sun keep telling us someone is turning it off. we have provided them with the electronic Key logs that show no one has been in the server room where this unit sits for 3 days prior! we have a P1 ticket and SUN just closes the job because they are as dense as their crappy product! if they review their logs on all our calls. they would see a pattern that every 8 weeks or so the unit dies! they have put in a new hard drive and its not showing it. their Techs have been in here a couple of times past two weeks (Very fast workers!), and he has a print out from another tech on some instructions to do something…. but the instructions dont match the gui of the bios and he has no idea. great for a global corporate solution. fortunatly we have other systems in place to manage this. xmas eve the SAN kept powering off then rebooting and off again and rebooting. Our monitoring solutions kept showing servers going up and down. but SUN keep saying nothing is wrong. I want to go into their office and really cause some serious pain! they have no incentive, no nothing. It has been the most frustrating, uncostomer focused organisation I have ever dealt with!!! a month ago they suggested that we need to get the backplain, Hard drive, controller and powermodule replaced. but they keep sending me a guy who has no idea on how to navigate the bios GUI! he looks at the serial number on his paper and tells me that his techs told him that this is the old drive serial and that the new one isnt working. but he doesnt know. my guy tells him go look at the unit. we have it sitting there now doing nothing! My point. IF YOU WANT TO BUY A SUN OR ANYTHING SOLARIS AFTER THIS!!!! THEN YOUR AN IDIOT! GIVE ME A THOUSAND LASHES ON THE BACK EVERY HOUR! Cause its less painful then dealing with SUN! The worst service and product support ever!!!

I have an SUN Storage 7210 with Oracle Sun Solaris O/S,it is remotely connected with ILOM and we are able to poweroff and poweron the storage,but its not booting up.It is hang after grub loading stage 2, the screen is complete black and the cursir is blinking,the ip address is giving us requested time out,than we directly connecte the moniter but the problem is still same,when we connect it through the putty(through SSH)ILOM’s ip and then we connected with the machine its like 7210 > Login,we loged in and than type the command “start /SP/console” after that with other command we find the interface information with storage O/S ip stating up than we tried to ping that os ip but its not pinging….plz tell me is this is the problem of grub or something else…..plz help

“Update [2010/08/27]: Thanks to some hard work from our reseller and people at Oracle, we were able to return these units a few months ago. I wish we had been able to work through the issues with Oracle, but needed to get something that we could trust online ASAP. For the record, I do think that we probably did receive a “batch” of bad units; I still have not heard from anyone else who has had multiple independent units fail simultaneously as we did. I will also keep comments open here, and encourage anyone who has had great deployments to post a followup – I do believe that there are people that have had great success with these units out there, or else they wouldn’t be selling so well! :) And again, thank you to the hard work from our reseller, and for all the people from Oracle (and those who used to work for Sun but did not move to Oracle) who did their best to help us!”

Thanks for your story, and sorry to hear that you have also had issues! :(

I have also heard about a lot of issues regarding head failover, etc, via private email.. at least that appears to be better with the newest release from what I’ve heard.

Also bummed to hear about the security group issues, but at least that is not “service-affecting” — annoying to have to reboot the head, but better than having things go entirely offline for any reason. Are you able to just fail over to the other head for that? (Not that you can do that during the business day anyways..)

We were allegedly one of the first companies in the UK to deploy a 7410 system and from Day 1 we’ve had a ridiculous number of problems with it. in fact, of all the server related issues we have in our company, the 7410 accounts for al least 80% of them, we have over 70 servers (including virtual).

Initially the device couldn’t connect to our windows 2008 AD domain as a NAS. The domain was a fresh, untouched vanilla domain and the CIFS service just couldn’t authenticate with the DC’s. It took months to resolve and in the end had one of Sun’s senior Unified Storage engineers come out to try and bugfix. A few weeks later and we got connected… Hooray I thought, all problems solved…. Heh!

Many hardware failures later, inexplicable fail-overs to our other active head, and other buggy problems we still have one huge outstanding issue…

If we create a security group in our AD, add a few members of staff to the group and give that group access to an area on the NAS CIFS share. It doesn’t actually apply… As far as windows is concerned it should, but, it doesn’t! The only fix…. Reboot the damn controller – and this is a production environment… We now have to explain to users that they can’t access that folder until the next day as we cant reboot the system during business hours.

It’s been months since this call was first logged. With Oracle support asking us to always apply the patches and see if that fixes the bug, when it doesn’t they ask for a fresh support bundle and spend another few weeks before they ask me to test another change (that never works) before asking for another support bundle… The last support response I got was to enable more in depth logging using a workflow, replicate the issue and you guessed it…. send them a support bundle! I’ve not done this yet as I have other things to manage and Oracle clearly have no idea what the hell is going on.

I honestly wish that we’d never bought the hardware and spent our money on an established storage provider (not that Sun wasn’t an established brand).

BTW Hi Andy P. – He’s my reseller support guy and in all fairness, his company have gone above and beyond in trying to help us sort this out. I can’t fault his company, but Sun(Oracle) are really being unhelpful.

Niels

We’ve also had stability issues with Netapp, but it’s mostly been because the systems aren’t set up in an ideal configuration — IE, aggregates are way over-provisioned, no redundant heads, etc.. can’t blame Netapp for that. ;)

Paul.

However, I have one customer that has 2 of these and wants to use the 2nd one for replication and DR.

A major problem I am having is this: Starting or Stopping replication on the source 7110 makes the production 7110 completely unresponsive! This essentially brings down the entire environment! Completely unacceptable! After waiting 15 mintues for it to come back – (even if it did, I am not sure Windows VM’s running on vSphere 4 would survive that long without their disk) – my only option was to power down the 7110 and power it back up. It did come back, but I had one VM that was corrupted – good thing I had good backups.

These units have so much potential! I just wish it all worked as advertised.

Jim

Have you tried Nexenta perchance? I am really curious how many of the issues are the kernel and ZFS itself, and how many are related to the management stack.