Cinetica  
chi siamo soluzioni e servizi successi blog  
Articoli con tag ‘Storage’
CINETICABLOG

Enterprise storage: what does it mean for you?

Yesterday we saw a big tweetstorm about 3Par acquisition from DELL or HP and, of course, the discussion mentioned the possible alternatives for the loser of this fight, but it is clear that Dell and HP are looking for an “enterprise storage” capable to compete with other Tier 1 arrays/vendors in the high end market segment and the only solution seems to be 3Par.

The community, as often happens, breaks up into many parties. In this post I would like to express my point of view and some basic concepts about the meaning of enterprise storage in 2010. Enterprise storage comes in many flavors according to the goals you want to achieve.

Once upon a time was the “Enterpise Storage”

In the last century the concept of enterprise storage was very tightened with the capability to connect to Mainframes and it was very simple to tell enterprise storage from non-enterpise storage. The ES was a monolithic object capable to deliver great performance on proprietary hardware and protocols and connected to a single host at a time.

Things slowly changed with the enterprise adoption of Unix first and Windows later. Moreover, SCSI (small computer system interface) was born and some fades between black and white appeared. In the ’90s the enterprise storage was still a Monolithic storage capable to connect many (for that age) different systems (MF comprised). We saw, for the first time, on unix and windows servers, some interesting features like clones and replicas.

In this age we found the first “non-enterprise” or modular arrays, the first SANs and a first approach to standard hardware (HDDs).

What is “enterprise/T1 array” today?

The capability to connect to MFs is no more important for many companies, they already moved to other platforms  years ago and the enterprise storage array is losing very fast the monolithic form too.

But there is something still of primary importance: the architecture.

The architecture makes the difference: many fast redundant controllers, many connectivity ports and protocols, smart and huge shared caches and switched backplanes are only some of the most important elements in this kind of architectures.

A T1 array is designed to support many different workloads simultaneously, to scale up vertically and linearly, to have no point of failures and a great uptime.

What is T1.5 storage?

The industry has defined the big enterprise arrays T1 but companies have more than primary data to access to, so T2 is what we commonly call mid-size or modular (enterprise) storage. Sometimes little bit of confusion arises because Tiers are often referred to when talking about products and vendors too: EMC/IBM/HDS/NetApp are commonly identified has T1 vendors while 3Par/Compellent/Xiotech/ecc. are often named as T2.

T2 arrays are architected in a simpler way than T1 ones: two controllers, smaller mirrored caches, less scalability and connectivity but (often) easy to use.

T2 arrays are chosen for their lower cost (if compared to the T1s), for specific applications/workloads, for testing or as primary storage in SMBs and many other times when you want to avoid the complexity and costs of T1 arrays.

But there is a new category: 1.5. what is 1.5? sometimes we have 1.5 vendors: we can find here some small but fast growing vendors with T1-arrays comparable features products. (probably it’s a diplomatic way to not diminish too much small vendors with good products).

We can also term 1.5 arrays, the most famous product in this category is XIV: IBM is selling it as a T1 array but the rest of the world consider it as a T2 array… and here you are the the solomonic 1.5!

The evolution of “enterprise” concept: modular, commodity, features, integration and automation.

What IT managers are looking for in 2010? simple: saving money while bringing more to the enterprise in terms of quality and services! (ok, I know, it’s easier to say than to do).

From the infrastructure point of view, virtualization and consolidation are a mainstream way to do this. Enterprises are looking deeper and deeper at features, capabilities and architectures to simplify and automate the management of data stored in their boxes and, on top of all, they need open and integrated solutions to get the best results.

Vendors like Compellent, 3Par, NetApp and others are in the spotlight because they address very well these needs (surely better than T1s) and this is why they are climbing sales charts furiously (also in Fortune 500).

The concept of enterprise storage is evolving quickly because nowdays:

  • virtualization is more important than vertical scalability: you can buy more boxes if you have a simple way to manage them as a whole.
  • automation is more important than big hardware: save and use better resources with automations without spending time to optimize manually.
  • integration is more important than proprietary management tools: a true integration allows big time savings.
  • …and so on.

Here is a few words recap: enterprises are looking more now than in the past at open, easy to use, features rich, virtualized and automated storage!

Bye, bye T1 arrays?

It’s not difficult to preview the next steps: Federation and commoditization.

  • Federation: in a coarse way, the capability of T1.5/T2 arrays to be managed and seen as a whole one to achieve T1 performances, scalability and uptime.
  • Commoditization: the use of standard hardware (and tons of software) to build all the components of the architecture and save a lot of money!

We will have the ability to cluster (federate) a bunch of T2 arrays and use them as a T1 or, in other words, T1 arrays will be clusters of T2 arrays. :-)

What is enterprise storage for you?

Related Posts:

Archeology or Technology?

On friday @plankers sent this Tweet:” 2.5″ 10k disk is as fast as a 3.5″ 15K disk. Did not know that, thanks @Compellent #TechFieldDay“! yes, it sound a little bit strange and it is inaccurate but twitter’s 140 chars limit doesn’t help to fully explain the whole story.

Simply put, this result is achieved positioning most accessed data on the outer tracks of the disks but, after this Tweet, a furious quarrel started about doubts some competing vendors raised. The discussion was closed by the storage anarchist and alextangent with twitts like: “the math (& observed reality) doesn’t support the mktg BS. BTW the BEST data placement is MIDDLE of platter” and   “mid-platter data placement well understood since winchester tech 1st appeared; 1970-80s!” …. But it’s not finished yet!

Well, they tried to do some unrealistic FUD stating that Compellent’s Fast track is based on wrong concepts and it doesn’t work!

A short prologue
Compellent has a software feature called Fast Track. This features is used, with success, by many Compellent customers to get more IOPS per disk! It works and satisfied customers can confirm this.
I wrote a lot on FT in the past and you can find articles in my blog by clicking hereherehere or searching “fast track” for a full list.
You can also find a nice and illuminating video about Fast Track on the Compellent’s website.

How is it possible?
It’ simple Compellent Storage Center is a next generation storage system and was architected less then 10 years ago (not in 80s o even in 70s!).
The Compellent architecture is not comparable to old generation (i.e.: clariion or V-Max) arrays because it redefines the basic concepts about how data blocks are stored and managed!  Comparing Compellent’s storage architecture to the EMC’s arrays architecture equals to compare Technology and Archeology!

When Barry and Alex say that they get the best performance from the array positioning most accessed data blocks on the middle of the disk they speak about technologies of the last century: (winchester disks: 40 years ago!), arrays (designed on archaic raid techniques) and very old algorithms (those you’ll likely find in the base foundation of old generation arrays)… so we must admit we are speaking about archeology surely not about nowdays technology!

The options are two: These guys are biased or they ignore how Compellent works (probably both).

Fast track works because it is integrated with data progression: a true Fully Automated Storage Tiering available since years, not a feature like EMC’s FASTv2 promised more than 1.5 years ago! You can’t expect automatic data placement optimization (like fast track) from companies that can’t offer a true Automtated Tiered Storage.

In vitro Vs. real life
We have studied and tested all the Compellent software features intensively before start to sell these systems in Italy two years ago and I can say that fast track works: we have a lot of documentation on this and we achieved more than 30% improvements after having enabled it on our system.
The world is not perfect and 30%, sometimes, drops down to 20 or even 15: it depends on the number of the hosts and the applications involved but this anyway means that you can buy up to 20% less disks!

Now, if I add my 20% to a 10/12% of 2,5″ Vs. 3,5″ (improvement in IOPS due to the less latency), I get more or less 30/32% improvement. That’s why a 10K/2,5″ disks “equals” a 15K/3,5″ IOPS!

Obviously I’m not telling you a 2.5″ 10k disk is as fast as a 3.5″ 15K disk. But we can say that the fastest tracks of a 10K RPM 2,5″ disk can give you the same average IOPS a 15K RPM 3,5″ disk can offer… If you can use them the right way.

Last, but not least, Barry where do EMC arrays write the most accessed data blocks? I hope automagically in the middle of the disk! Because a Compellent’s array can decide where to put most accessed data but I’m not sure Clariions and VMaxes can!

Related Posts:

Detto fatto.

Nel mio articolo di questa mattina avevo messo in dubbio anche un aggiornamento dello storage 7000 dal punto di vista hardware, invece sono stato smentito subito (in parte visto che si tratta di solo software).

Qui una news sugli aggiornamenti di questi prodotti e qui l’annuncio ufficiale. Per chi non avesse voglia di leggere, dico solo che sono stati rilasciati anche gli HD SATA da 2TB (raddoppiando di fatto la capacità), il supporto del protocollo FC (su HBA da 8gb/sec) e la inline dedupliation.

Sono proprio curioso di capire tre cose:

  1. come si comporta l’FC sui 7000 nella realtà, spero che qualcuno pubblichi presto dei benchmark;
  2. come si comporta la deduplica, che impatto ha sulle performance generali del sistema e soprattutto se funziona (visto che l’hanno rilasciata per la prima volta pochi mesi fa in una versione di sviluppo di OpenSolaris!);
  3. quando ci sarà il supporto da parte dei vendor per le funzionalità del prodotto su protocollo FC (SRM di VMware, software vari di cluster, snapshot consistenti da windows, ecc., ecc. )… sempre che ad Oracle interessi qualcosa.

E adesso che abbiamo hanno l’FC in casa quanto durerà il contratto OEM con LSI?

Related Posts:

     
Latestnews

Cinetica è sponsor di CLOUDscene (a Bologna il 30 settembre 2010 c/o Hotel Royal Carlton). Evento dedicato al cloud computing pubblico e privato riservato a CEO,CIO/CTO e CFO.

Se sei interessato a ricevere un invito, contattaci.

Related Posts:

  • No Related Posts
 
Perchè rivolgersi a noi
Soluzioni hardware/software complete e pienamente integrate.
Progettazione realizzazione di infrastrutture Virtualizzate.

Consulenze specializzate per l'implementazione e il mantenimeto di infrastrutture HW e SW in ambiente enterprise.

Qualità e innovazione nelle soluzioni offerte, allineate con le esigenze dei clienti.
 
Blog
Uno dei fattori di successo di cinetica è l'entusiasmo per quello che facciamo, è per questo che abbiamo deciso di pubblicare un Blog dove condividere le nostre idee e le esperienze con chi lo desidera...CONTINUA
     
         
 
CONTACT
World Trade Center (Torre B)
via Consiglio dei sessanta, 99 Dogana
47891 Repubblica di San Marino (RSM)
  +39 0549 908 096  |  +39 0549 908 054
 
 
RSS Articoli | RSS Commenti
Copyright © 2009 Cinetica. All Rights Reserved.

site design: openspace soluzioni creative
powered by WordPress