The Register® — Biting the hand that feeds IT

Feeds

* Posts by M. B.

82 posts • joined Wednesday 26th August 2009 19:12 GMT

Page:

M. B.

Okay then...

...now get on to making a car I can actually afford and you can have some of my dollars back!

M. B.

Re: My two cents

Larry actually appeared in Iron Man 2 (even though there was Dell PowerEdge servers in the Stark mansion). The Avengers featured several racks of Exadata kit in the opening scenes in the garish red racks. Yay product placement.

M. B.

We did...

...Oracle Database Appliance is a good fit for us. I wish the storage on the original was more expandable though. 4TB with triple-mirroring on the v1.0 isn't really a ton of space. At least the new one is 6TB and has an expansion shelf option for 12TB with triple mirroring.

It also supports Oracle VM with hard partitioning for virtualizing apps alongside the DB so cores not licensed don't have to go unused. Use Data Guard between a pair of ODA's for DR and point RMAN to a Data Domain box with DD Boost plug-in and you have some happy DBAs. It actually does offer a fair bit of value for us.

M. B.

The problems I have with the graphic...

...as a small enterprise and sometimes-buyer of Linux systems is that:

1) The street price on an R720 is much lower than list (we get them for ~$8000 in a dual 8-core, 256GB config), not sure how much IBM will bend on that POWER price;

2) Why would I run Linux on vSphere Enterprise for an all-Linux system instead of virtualizing on Red Hat, which is considerably cheaper?;

3) If I'm already a VMware shop, then I get significant value out of using vSphere 5.1 anyways through vCenter Server with HA/DRS and any plug-ins I already own for SAN, backup, monitoring, replication, SRM, etc so it's well worth the added cost;

4) How does the application ecosystem compare between RHEL on x86-64 and RHEL on POWER? Which offers the more robust product catalog?

When you really look at the numbers, it's not really surprising that POWER, even though it may be technically better than x86, isn't as hot as boring old x86 in terms of sales. It goes beyond strictly price/performance.

The yellow stripe looks hot though.

M. B.

Likely...

...they probably want to get this information out before they finish their deliberations. Icahn only thinks the company is worth a mint because he owns shares in it. We'll see how quick he is to retract his proposal after seeing the financial results.

That's where Icahn and Mike Dell are different, Icahn will see the writing on the wall and get as much money out of it as he can (which is what he's trying to do anyways), Dell-the-man will take the business and transform it into what he thinks it needs to be in order to survive and succeed.

M. B.

We're having some concerns right now...

...with continuing to buy Dell hardware until we know for certain what is going to happen with the company. Desktops are desktops and they can be replaced with just about anything but servers, storage? Not so easy. I have a requirement for 6 new servers in the short term, hopefully we see some positive movement on this soon so I can make a decision I'm confident in. With Mikey in charge, more PowerEdges please. Icahn? Maybe it's time to talk to Cisco and HP again.

M. B.

I should hope so...

"We also expect EMC to refresh its VNX line of mid-range arrays in the second half of this year."

It was on stage at EMC World, demonstrating the thread scheduling and performance enhancements of the MCx technology across 16 cores. They didn't mention much about it though, nothing beyond "here we see MCx running on the next generation VNX platform". Can't wait to see what's under the hood, they need to catch up to HP and Dell in the midrange as I'm finding both of them are practically giving away NAS heads with the 3PARs and Compellents, both of which already have refreshed platforms.

As for the new cards, if EMC wants to be the value leader with the weight of their name then this market will heat up, FusionIO will need to either cut costs to compete (how low will EMC go?) or come out with something revolutionary. An "Executive-friendly" brand plus lower costs plus integration with a large ecosystem of products is a sound recipe.

M. B.
Thumb Up

Debian is my choice too...

Still haven't upgraded my home stuff yet but there's no rush, the old installs work fine as expected.

I know of one company currently running Wheezy through it's QA processes with the intention to either migrate almost all of their internal systems to Debian or run them in the cloud. My counterpart in their organization said the endgame over the next two years is to whittle down to nothing more than a pair of Windows domain controllers and a small vSphere cluster running 50-some Debian-based virtual machines, with email/chat/collab pushed out to the cloud and compatible with whatever endpoint the users want to use.

They expect to save two million plus dollars a year in Oracle and Microsoft licensing and due to better resource utilization and in-house development, they also expect their VMware licensing to drop as well. They spent a little more up front hiring a couple Linux admins and a half dozen devs to add to their talent pool, but the projected ROI is outstanding and they are on track as far as project management and testing goes. Best of luck to them.

If there wasn't so little Linux knowledge here and such a resistance to moving services to the cloud, I'd be working on the same.

M. B.

Similar results here...

We still use it here for tape. I upgraded us from 10 to 12.5, then deployed 2010 at another office. Lots of headaches. 2012 looks prettier and more intuitive but my confidence in the quality of our backups is extremely low. I have since convinced my boss that we need to go up to enterprise-level backup products, when slow jobs stream to tape at 500MB/min and nothing else can write to the tape during that time, it's no surprise that our weekend backups run until Wednesday morning.

M. B.

So are they preparing us for...

...a letdown as far as hardware announcements At this EMC World? I still haven't heard anything worth getting excited over this year.

M. B.

Is this supposed to be...

...the Project Bourne-based storage offering? A single management plane for your storage devices?

So far the only news I've heard from EMC World is this and job cuts. Neither are really very interesting.

Hope they're saving the best for last.

M. B.

Hopefully they scrap...

...the Numara garbage so we can finally move off of it.

M. B.

As a dad...

I'd want them hung by their balls (my 5-year-old son recently took part in nationwide assemblies in his school against bullying, this is a Big Deal here in Canada).

As a rational person though, there should be an inquiry into the handling of the case to determine if it should be reopened or not. Suspected rapists should not be walking free if their faces are all over a rape video. Even more so if Anonymous has the names of the people involved.

M. B.

Re: Dual-Core Atom = Home

"The iSCSI, Tandberg says, is for virtualised server environments."

Clearly the intention is to use it more than once every 10 years.

I've been in this boat before with our dev team. "We want more storage for testing". They bought a pair of "high end" QNAP 12-bay NAS boxes, powered by Atom processors. 6 months, a dead motherboard, lost data, and many headaches later, they ended up with a FAS2220 and "just let the ops guys deal with it".

M. B.

Re: the absence of any and all OEM crapware

It's also a contributor to the cost, the crapware vendors often subsidize the cost of the laptop somewhat by having their software preinstalled. In this case, those subsidies look to cover the cost of the Windows license.

Unfortunate. I'd still take a Linux box, myself. Can't get them in Canada yet.

M. B.

Re: AppAssure user chiming in...

It has built-in compression algorithms. Dell themselves sell an AppAssure appliance which combines the AppAssure data efficiency set with the Ocarina-based technology they've built into the DR4000 platform to crank the ratios up even further. I'm looking to get Data Domain on loan for a month or so to see how much space efficiency it can add on top of AppAssures compression algorithm. FYI we're getting 60% space savings already on a wide mix of virtual machines (RHEL, W2K8/R2, W2K3) . Once we start adding multiple W2K8 and RHEL boxes into the mix with dedupe, I would expect some interesting results.

M. B.

AppAssure user chiming in...

...I love it. It's dead simple to use and works really well. I have it deployed on a virtual machine at the moment, backing up a dozen VMs to a CIFS volume on our NetApp. We're getting almost 60% savings on AppAssure compression ratios.

My big problem is our NetApp is the production storage system. Last thing I want to do is stick my backups on my production platform - they should be on separate storage. Throwing Data Domain into the racks to further improve space efficiency just makes sense. Yes, Dell makes the DR4000 or whatever (Ocarina-based) but unless you're buying the AppAssure hardware appliance, I wouldn't bother - Data Domain is the best for a reason.

As soon as Data Domain lands in my racks, we'll be pulling the plug on Backup Exec and using our LTO-4 library for monthly dumps to tape for compliance. AppAssure software pointing to a Data Domain target is the way forward for us.

M. B.
Go

The biggest problem we had...

...when we looked at Oracle storage wasn't the technology so much as it was the software, the packaging and to some extent, the marketing. As far as the marketing, the ZFS Storage Appliance IS a unified storage offering. You can add 8GB FC HBAs to the appliances and connect them to SAN fabric and provision LUNs on top of ZFS. You can provision LUNs through iSCSI, or you can provision network shares through NFS or CIFS. You know, kind of like NetApp with it's FAS heads. Those are pretty good, right? They should be bragging about their protocol support, 8Gb FCP, 1Gb/10Gb iSCSI, IP and RDMA over Infiniband, NFS, CIFS, HTTP, WebDAV, FTP, yeah, it does those.

The packaging problem that I see is the entry system, the 7120, doesn't support a cluster option. It's a single head system. But it supports 177TB of capacity. NetApp's FAS2220 entry system will grow up to 180TB, yet you get HA with the system. Those capacity levels call for HA and make them attractive to businesses who are outgrowing entry networked storage systems (QNAPs and DLINKs and junk). Sure, the FAS2220 doesn't support FC, but the FAS2240 does, and it's still cheaper than the 7120 as of the last series of quotes I received. If the 7120 were built on a shelf unit like the Supermicro two node units built into a chassis for HA with SAS-connected drives out front, I think they'd do better with this product.

In the midrange, the product starts looking a bit better, especially for Oracle shops cashing in on Hybrid Columnar Compression. It also does inline deduplication and compression, snaps and clones, local and remote replication, SSD read/write acceleration, phone home capability, various RAID options along with data/metadata checksum verification, etc. High availability is an option but it's a no-brainer when you're talking about 432TB of data, at least in my opinion. Two nodes should offer enough front end ports and performance to handle that kind of capacity, so this one seems to hit a sweet spot.

In the high end it stumbles again with a packaging problem, as it's peers are scaling up and out it is still stuck at two nodes. 2.6PB is a lot of disk for two nodes to keep up with, especially with all the bells and whistles turned on and slamming the system with heavy workload. It certainly has the capacity for big workloads.

Then there is the software problem. You could do quite well with Linux, Windows, and VMware integration tools for path management on block storage and snapshot/backup utilities with application awareness. But aside from the Oracle Snap Management Utility, I can't find anything else that ties it in to anything else. DTrace looks pretty and the mobile app is neat. If they would open their focus and develop tools for more systems, the appeal would grow.

They have a potentially good product with the ZFS Storage Appliance. This should be their take-aways:

- Rebrand it as an Oracle Unified Storage Appliance built on ZFS technology, make some noise about its protocol support;

- Develop more tools and integration pieces with other OSes and applications (why not at least make a good storage product to sell into the MSSQL and DB2 shops?);

- Re-engineer the low end system to do HA in a single shelf (I'm sure SUN can put together a Supermicro-like two node chassis with SAS-connected disks out front);

- Scale out the high end model to support more controllers;

- Add all- or mostly-SSD options to the mix.

Lots of folks out there think ZFS is the future. Lots of folks want a big name attached to their mission-critical storage when things go pear-shaped as opposed to buying a "validated design" based on whitebox hardware from other, smaller ZFS vendors. Oracle has the opportunity to really build something here if they would simply broaden their horizons and expand their focus. But I don't think they will, they want you to buy engineered systems and they want you to use them to store your data in their database. There's nothing wrong with that, but their storage sales won't be booming anytime soon with that approach. Until they do turn it around, people looking for an all-in-one HA storage array with some space-saving features and broad protocol and application support will continue to buy NetApp.

M. B.
Thumb Up

Re: Tech company condoms

At first I didn't know why I bothered to click on this article.

Now I do.

M. B.

VMAX and VNX hybrid controllers...

Will this be VMAX2 and VNX2? Rumor has it the VNX2 will be a dual-socket family of systems (unlike the current single-socket systems), likely to be able to keep up with large pools of flash. I've been scouring the Internet and grilling account managers over the v2 models for a while, no one wants to spill the beans.

Fingers crossed for a big reveal at EMC World 2013.

M. B.

Larry's ego makes storage...

...it was formerly Pillar Data Systems (majority owned by Larry) and Oracle bought up the company to try and expose it to more customers, I suppose. We have significant investments in Oracle software unfortunately, and they try to sell us the kitchen sink on occasion, but they have never once tried to sell me their storage.

Their ZFS appliances aren't bad, just badly priced. I can do NetApp for a whole lot less, especially in the entry and mid-range configurations, which means tons of good software to integrate the storage into my applications/systems.

M. B.

Re: It strikes at the core of the small enterprise space...

It's biuriful...

But you just got me invited to 2 meetings to discuss Oracle licensing since I dropped the bombshell on my director this morning about Glassfish licensing (also per-core).

I don't know if I'm winning or losing today.

M. B.

Re: It strikes at the core of the small enterprise space...

"You don't need to license every core in the cluster - only every core within each host that will be running Oracle workloads. DRS affinity rules can help you to achieve this goal. If Oracle try to tell you any differently, ask them to point out where in your Oracle License and Services Agreement (OLSA) it states that you have to license hosts that will never run Oracle applications."

They actually have told us differently! I thought it was pretty ridiculous that they would charge us for every host in the cluster, even when only two 6-core hosts would run RAC nodes. They insisted that was the case, even after asking about CPU affinity specifically they offered nothing around configuring host affinity. F@cking b@stards.

M. B.

Re: VMware

Have to agree here. SSO is garbage. Do better, VMware.

Why can't the vCenter Appliance simply scale up to dozens of hosts and hundreds of virtual machines? The whole point of this is that things should be simple and just plug in to each other, like any good relationship. Make it simple, keep it simple. Otherwise, you know, Hyper-V is pretty simple (okay System Center can be a nightmare, but SCVMM isn't required to make a cluster work).

M. B.

It strikes at the core of the small enterprise space...

Things like RAC licensing on a per-core basis kills Oracle on VMware for us. It's not "per vCPU assigned to the VM" but rather for each and every physical core the VM could possibly run on. I have 96 cores in my vSphere cluster. To run RAC on that would be prohibitively expensive. We've been down this road with them before, we can do it all we want but it'll cost us big.

Oracle VM allows you to do hard partitioning of the CPU cores to avoid that. The new Oracle Database Appliances allow you to use Oracle VM to deploy database nodes and use leftover compute resources for middleware or business logic, locking VMs to specific cores and driving up resource utilization, while maintaining licensing compliance with Oracle at the same time.

They've created a value proposition, which is mighty big of them because it'll save us money in the long run. We still run our application servers and core infrastructure bits in VMware and leverage that highly developed ecosystem (virtual appliance support, SRM replication, SAN integration, hardware monitoring plug-ins, etc) but now we have an easy way to consolidate the formerly unconsolidatable Oracle apps on a different platform that allows us to get the most out of the hardware.

That's what will get them market share, offering value. It's a strange thing coming from Oracle but I think it could work to a point for organizations like ours running Oracle software and wanting to get the most out of our new ODAs.

M. B.

Innovate or die.

That's the way it is in storage. The DotHill product is a good performer and doesn't break the bank for the SMB marketplace, but it's a legacy platform. There hasn't been any major innovation on the product for a long time.

The last time I had my folks do a pricing exercise for remote office storage, NetApp FAS2240 came in at several thousand dollars less than an HP P2000. As a result, we now have a FAS2240 in one of our remote offices handling file and block duties.

M. B.
Angel

EMC to world:

"Nom nom nom all your data!"

Hopefully by the time we're ready to look at "converged infrastructures" this vision will be implemented at the vBlock solution level and I can buy myself a rack full of buzzwords. My director will be most pleased.

M. B.

Re: Literally bulletproof storage

I guess Hitachi can too then by default!

Also, the article mentioned the resiliency of the VMware VSA but didn't mention HP's StoreVirtual VSA (running LeftHand OS 10) which I would argue is the best of the bunch. We've been testing it here on some old servers for lab purposes and it works really quite well if you have a couple NICs to spare.

M. B.

Re: Nice but nothing new

Yes, NetApp needs to bring FAS levels of integration and tools to the E-series. They might not, because they won't want to hurt their cash cow, but it would bring the E-series to a whole new level IMO.

M. B.

The only caveat I ran into...

...was SSO. For some reason I was completely oblivious to the database requirement and kept pointing it at the vCenter database my DBA had created for me. Once I pulled me head out of my ass and got him the SSO DB scripts it was very easy to get it running.

Next step is to cut over my ESXi hosts from one vCenter to another, then use Update Manager to bring them all up to 5.1.

M. B.

It's not the hardware itself...

...but rather the support , services, and top tier warranty. The VAR network. The 2 hour onsite response. As well as the R&D/testing and reference designs that go along with purchasing IBM, Dell, HP, Cisco, or Oracle servers. Yes you could duplicate them on Supermicro hardware for much less money, but who is going to stand behind the end result?

My environment is a mix of medium business and small enterprise requirements, and my infrastructure is a mesh of HCL'd hardware and software at correct revisions, a lot of it straight out of vendor whitepapers. There is simply no room for this white box level stuff until it has the same level of R&D and support as the big players.

Unlike some organizations, we can't simply buy the cheapest thing out there, throw any old version of Linux on it, stick it in a rack, and call it done. I suspect that is the way it is for many organizations out there.

In other words, cool, but not for me.

M. B.

Aside from...

...OnCommand System Manager which I give out to new storage guys to help them get used to managing NetApp storage, the OnCommand family is a bit of a mess. Or at least it was last I checked it out about 8 months ago. Installed all the bits and pieces and wasn't very impressed with the inconsistent interfaces and jumping between applications. I promptly went back to SSH and scripts for most of my work.

M. B.

One of the problems around the SAN attach rate and network uptake...

...is that VARs, at least around me, are sticking to what they know best.

On the storage side I'm still getting the EMC and NetApp sales pitches with a few IBM as well. I have to go out and ask repeatedly to see Compellent or 3PAR options. One vendor even has a golden reference on Compellent, 360TB main site with replication and all the cool functionality licensed and used regularly with awesome performance (supporting server and desktop virtualization and a significant Oracle RAC cluster), the client simply adores it.

On the networking side you're looking at Cisco. That's just a fact. One vendor is starting to slot in Brocade where HP ProCurve used to be a good fit (they think A-series is garbage and they think E-series has no future). But if you wanted to hear about them or Force10 or Arista or Juniper you pretty much need to go through the manufacturer itself and have them hook you up with someone locally, and even then they'll probably try to steer you towards what they know best.

I don't want "what they know best", I want the actual "best solution to the problem".

It sucks to see since there's a lot of cool stuff out there, and we aren't seeing very many converged offerings as a result. This has to be impacting the bottom line, at least in smaller markets with smaller VARs with narrower skill sets.

M. B.

Better...

...but not perfect.

Should have made it 1920x1200, you'd be amazed at the difference a little more gives, especially in vertical real estate.

And they should drop the price a couple hundy to make it worthwhile. At $1249, I'd consider it. With 1920x1200 I'd have already asked my Dell rep about one.

M. B.

They probably expect you...

...to shell out the cake for a NetApp FAS with a gateway license to front-end that storage so you can ejaculate your Data ONTAP goodness all over the downstream hardware.

M. B.

Re: Turmoil - Probably just a rant.

I was impressed by the sheer scale of it all when I clicked "maximize comment", I'm sure there's a brilliant post in there somewhere though.

M. B.

Compellent

"The base configuration has one Compellent SC8K array with three storage trays. The storage setup has one 24-bay SC220 tray filled with *****13 SAS drives***** that have 200GB of raw storage capacity mated with two SC200 trays (each with 24 bays) and that have them full with 600GB 10K RPM disk drives.

That gives you 48 disks with 28.8TB of storage and *****13 SSD drives***** with 2.6TB. This ratio of disk to flash meets HANA's stringent appliance guidelines."

One of these things is not like the other. I suspect you meant 13x200GB SSDs in the first paragraph, just sayin'.

M. B.

Gonna miss netbooks...

Lenovo x120e. I have this little AMD Fusion-powered netbook, 4GB RAM, cheapest 64GB SSD I could find running Win 7, and 1366x768 11" display with extended battery. Totally usable as a road warrior. Has been all over North America with me for work and family vacations and works brilliantly for what I need. Charges devices. Long battery life. Plenty of performance for office apps. Usable screen resolution and keyboard to get actual work done, especially when RDP'ing back into work machines. Runs all my tools. Got it for about half the cost of an Air, including extended warranty and the SSD.

They just hit a sweet spot for a lot of people, they have enough performance to play movies on long flights and enough grunt to get "work" done without being tied to a power source for any significant period of time. And they're small enough to go into a laptop bag sideways, saving room for important stuff like my son's LeapPad.

Gonna hang on to this one. My wife has mostly taken it over anyways, such a small footprint it easily fits in chair pockets so she can get the latest celeb gossip and Youtube idiocy without moving too much and her 8-month pregnant belly makes a perfect table for it since it's so small and gives off almost no heat.

M. B.

Decent idea but lean on spec...

That screen is garbage and that CPU is no monster. More RAM and storage needed to be a real all-in-one. Hopefully this is just their first kick at the can, it's on the right track but not what I was really hoping for, certainly not at that price.

M. B.

Probably not NetApp

With all the exciting small storage companies out there I'd look hard at the likes of Nimble. They're even painted to match the UCS servers already.

Nutanix is a cool product but I don't think Cisco would care much about the server side of their offering.

Can't help but think NetApp might be a bit hard to digest.

M. B.

Dell Storage

The title is a bit misleading. There is some interesting things going on in the Dell world, just not ground-breaking stuff.

As an EqualLogic customer (branch offices) looking at Compellent for our head office SAN, we're very much interested in the cross-platform replication and single pane of glass management option (replacing SAN HQ and Enterprise Manager) in the hopper. Storage Center 6.3 is largely re-written and delivers much higher performance, especially with the SC8000 controllers.

AppAssure was a solid buy. It's cheap and I honestly prefer the guest-based VM backup instead of host-based that we've been stuck with for a while. I've had a number of host backup jobs fail due to VSS issues on a single guest, I prefer being able to pause individual jobs and work on specific problem servers without kicking off another round of backups or what have you.

The DR4000 appliance is neat, especially for medium businesses and small enterprises. Based on the Ocarina technology, it gets pretty good storage efficiency and makes a good backup target. A new version is coming with DAS for capacity expansion.

Dell also has clusterable FS-series NAS heads for their block storage, and standalone NAS in the PowerVault NX line.

I think the real problem is one of optics, as this clearly shows. Dell has a lot of storage offerings and things coming down the pipe. If the author had sat down with a Dell rep beforehand this would have been an extremely short article.

Writing off either Dell or HP at this point is foolish, they still have cash and solid products on offer. We're probably not going to see huge groundbreaking things anything soon from either but both are working to provide comprehensive storage solutions. If they've got holes in their storage portfolios, you can bet they're trying to fill them with something that's at least as good as what's out there right now.

M. B.

Re: Slightly off-topic, but...

Single instance storage is no longer a part of Exchange as of the 2010 release.

I generally configure a third-party archiving solution to grab anything over 13 months old, most of them offer deduplication functionality.

It's a bit of a pain in the butt and we still lose capacity/efficiency, but at least it forced an archiving solution on us (execs wanted us to "just use Exchange and tell people not to delete stuff").

M. B.
Stop

Re: I don't often throw my SME storage money around...

Not strictly true, the Compellent SC8000 controllers have double the CPU and double the RAM and since they're based on the PowerEdge R720, they have 6 PCIe slots for expansion. Also much more granular as far as adding storage, disks do not need to be added in fours or eights, I can buy a single drive if I want, which means its very easy to tack a drive here and there into project budgets (which is a problem I face). And controller upgrades are potentially easier since there is no chassis dependency, a problem we're facing with our 4 year old FAS3140.

But I like smart, efficient hardware. Custom ASICs are just that. And as a lower midrange customer, I know I'll never scratch the performance potential of a Compellent pair or quad-node 7400. The thought of a dual-node symmetric active-active 7400 for potential expandability with an extra shelf for block storage is pretty sweet, hits our capacity, performance, and probably pricing requirements perfectly.

Now to see if they'll bring out the starter kits like they had with the F-class.

M. B.

I don't often throw my SME storage money around...

...but when I do I want you to shut up and take it.

I've been holding off on this VMware SAN upgrade project for a few weeks hoping for F-class replacements packing a SAS back-end and 2.5" drives and a controller spec on par with IBM V7000 and Dell SC8000. Touche, HP.

M. B.

Re: enough is enough?

EqualLogic slots in there as well, I've seen some interesting stuff where the back end will consist of EqualLogic branch arrays replicating to centralized Compellent arrays, both using Ocarina and Exanet tech for file storage and dedupe/compression and everything tiered automatically across all systems and disk types as needed. It's pretty cool, but also pretty "big picture". Interesting times ahead.

M. B.
Megaphone

SC8000...

...not SC800. The next generation Storage Center controllers are SC8000's.

M. B.

Re: Not enough...

Dell fluid data tiers across arrays too, so you can buy a SATA array and a SAS array, throw them in the same EqualLogic group, and it will redistribute hot blocks across the faster array.

HP's product suffers from two things, if you want a faster tier of disk you have to go out and buy new LeftHand arrays and manually move the data (AFAIK), and if you buy a starter kit with two arrays, you have to use one of them as a mirror. So a 14.4TB kit with two 7.2TB arrays gives you less than 7.2TB usable (with sparing). If you want network RAID-5 you have to add another array, and it has to be a specific part number to match the other nodes.

14.4TB in a network RAID-5 configuration (1 2-node starter kit and 1 additional array, all SAS) rings in at about $85k. A 14.4TB SAS EqualLogic array will cost me $35k, a 13TB SSD/SAS hybrid array rings in at $45k - I can buy both for less than the LeftHand stuff and get more storage capacity with automatic tiering to a higher performance array. Both quotes are on my desk as I type this (I think Dell wants it more than HP from the discount levels being offered).

HP actually offered up even stronger discounting on 3PAR, which is in a whole other class of performance altogether.

M. B.
Pint

Guys guys guys!

"Our new stuff is faster than our old stuff by THIS HUGE AMOUNT!" - Every storage vendor in the history of data storage

Drop the SPC garbage. Drop the marketing fluff. Storage guys should not be getting excited over statements like this, we've been duped and misled too many times before.

Show us REAL WORLD mixed workload performance with low latency and the ability to deal with huge IO spikes and give us real pricing information with real data resiliency factored in and the licensed features people actually need to make the thing do what it says on the box. Then show us how you do it better than everyone else. THEN maybe I'll care about the marketing spew. Also, tell your fanboys to shut the hell up.

Sorry for the rant, this is not EMC-specific but they're certainly a convenient target right about now. Ask me how my mid-range storage RFI is going. Long day.

Beer because of beer.

M. B.

Re: SVC equivalent

I used the IBM equivalents, two DS4300 arrays with an N6040 front end and it was... subpar. Manageability was fine since I'm quite comfortable with Data OnTAP but there was a weird timing issue between the arrays which would cause the DS4300s to disconnect from the IBM-branded NetApp at random (well not random, but at an unknown interval). We were never able to solve it (read: IBM and NetApp couldn't figure it out, we were forced to buy native N-series shelves to cover the capacity hit) so if I were to be front-ending any of the Engenio stuff at the moment, it wouldn't be with a NetApp unless they've specifically addressed this issue.

M. B.

Corporate evolution

You see this approach a lot more on the enterprise computing side, Dell acquired many companies over the past few years but hasn't really gutted any of them, they simply operate as their own division under the Dell name (Compellent, EqualLogic, Force10, AppAssure, KACE, Sonicwall etc are now rebranded Dell:Compellent, Dell:EqualLogic, etc). I'm sure in traditional business areas (IT, finance, HR) Dell has probably consolidated those companies under their internal processes, but otherwise for the most part the companies seem to retain their identities and benefit from some collaboration with other divisions.

It's not a bad approach, and it looks like the same was done with Alienware.

Page: