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

A brief comparison between Compellent and XIV

In these days I’m working on a deal where we are proposing Compellent Storage Center in competition against IBM XIV.

The customer is a fast growing company, Italian leader in its market and the IT department is facing with big strategic projects, one of them is the new SAN infrastructure.

The customer is very disappointed about the old generation SAN (two IBM DS4x00) in place and he has done a brief hardware selection excluding immediately names like HDS and EMC because they are seen as old generation storage vendors!

Only two proposal are on his table now: Compellent Storage Center and IBM XIV…. what a match!

Customers prerequisites for the new SAN are performance, scalability, ease of management, TCO and TCA. (sounds a little bit banal, but it’s true).

Here you are a coarse recap of my thoughts:

A brief introduction on quite different architecture:

Compellent

Compellent is company that makes a product called Storage Center: a next generation storage.

Storage Center is an array of disks based on standard hardware, the difference between Compellent and the rest of the world is called DBA (Dynamic Block Architecure): DBA permits to store some metadata for each data block allowing a full virtualization of the storage.

The most important software feature is called Data Progression (Automated Tiered Storage): the capability to write data on the fastest portion of the speediest disks in RAID 10 and then migrate the data using statistics like number of accesses and block age, in less valuable portions and types of disks at different RAID levels. This feature, coupled with many others, permit to achieve great performance and space utilization rates and lower costs.

You can choose a mix of up to 18 FC/SAS/ethernet ports on each controller (2 controllers per system) and a maximum of 1008 disks per systems (different types and sizes of disks -SAS/SATA/FC/SSD- are supported).

The Storage Center software runs on any hardware generation, this means that you can can upgrade software features without buying new hardware or viceversa. This architecture is very flexible and permits to choose the best mix to match your needs. Storage Center is at its third hardware generation and fifth software revision.

XIV

XIV company was acquired a couple of years ago from IBM. It was founded by a great name of the storage industry: Moshe Yanai (EMC Symmetrix inventor). The XIV is a next generation storage based on standard hardware and uses SATA disk drives to store data.

The architecture is very simple, only RAID-X (RAID 10 derived) widestriped SATA disks, gigabit ethernet backend, each tray of 12 disks (max 15 trays) has processing power and 8GB of local cache. The system is proposed from a minimum of 6 trays (72 disks) to a full rack of 15 trays (180 disk). no further scalability in the single system, if you need more IOPS or TBs you need to buy a whole new system. XIV architecture permits limited configurability: 6 to 15 trays (first step is 6 to 9 trays, then 1 full tray increments are permitted), same type of disk (you cannot mix different sizes of disks. If you buy today 1TB disks you will be forced to buy 1TB tomorrow!).

The Front End connectivity is based on the number of trays installed (each tray adds computational power, cache, and IO ports).

There are a lot of doubts on this architecture/product by analysts, bloggers and customers but IBM is working very hard to convince them about quality, real world performance and availability. XIV is at its second generation but many people are waiting for a third generation soon. try to search about “XIV storage” on google, :-)

Performance: 1-0 for Compellent.

Speaking about XIV performance is very hard:

math says that 180 SATA disks (a full XIV composed by 15 trays) may bring to you, more or less, only 14.400 IOPS for a 100% random workload. IBMers tell you that the huge cache (120GB) makes the difference but I’m not very convinced and some -unofficial- benchmarks that you can find on the internet confirms my point.

Furthermore the backend architecture of XIV is based on 1Gb/sec ethernet and SATA may be a problem.

Another problem is the fact that you have a fixed IOPS/TB for the whole system (180 IOPS/TB with 1TB disks and 90 IOPS/TB with 2TB disks for a DB workload), so, you have two options here: use the system in a “performance configuration”, without allocating a lot of space or use the system in a “space-savvy configuration”, all space allocable but with low performances;

Compellent thinks different due to Data Progression. You can configure the storage with different tiers of disks (SSD/FC/SAS) to achieve the desired IOPS then you add tier 3 (big SATA disks) to achieve your space requirements. The major advantage of this approach is the freedom of choice but I can add automatic tuning and a performance guarantee on top.

Scalabiliy: 2-0 for Compellent.

The two competitors have a software capable to manage many systems from a single point of view (16 for XIV, something like unlimited for Compellent).

IBM thinks XIV scalability in terms of adding more racks! (1 system == 1 rack) Compellent thinks about scalability adding disks on the same rack up to the maximum possible in terms of space/iops. The XIV’s way is to buy a whole new system every 80 (now 160) TB of space or about 14/15K iops!

The Compellent’s way is to buy only disks and backend/frontend ports up to the limit of the single system (in theory up to 1008 disks per system) and then scale out using Enterprise Manager as a single-pane management interface.

Ease of management: 3-0 for Compellent.

XIV has a good management software that helps storage administrator to manage its “bricks” with an attractive GUI but nothing special from my point of view.

Compellent has a feature rich management software called Enterprise Manager tightly integrated with its Replay manager (snapshots management software that simplify a fast recovery from some application data such as, for example, Microsoft exchange or SQL Server) . EM even has some additional modules like chargeback reporting.

Also there’s a very powerful (not to mention completely free) Powershell based script suite and a multiplatform Java one that can be used to completely automate the storage functions, including Volume creation/snapshots/migration, Server creation and Lun Mapping and so on.

TCO:4-0 for Compellent

The primary goal of any IT Manager is to lower TCO, but customers and vendors have different metrics to calculate TCO!

So I will only show some facts, please verify them in your TCO model/metrics:

  • Compellent has a low power consumption if compared to XIV: to obtain 79TB usable space you need only three trays instead of fifteen!!! (less power)
  • Compellent can bring more IOps: a bunch of active SSDs equate the IOps of a XIV! (less costs)
  • Compellent has much better and mature replica features (sync, async, snapshot delivery, deduplication, Qos, portable volumes, FC volumes replicable via iSCSI, 1:N and N:1 replication). XIV have only sync/async replica. (less costs for DR)
  • Compellent has Replay Manager to manage consistent snapshot for a lot of application environments, I haven’t found nothing similar in XIV documentation. (less time to spend in scripting and more secure)
  • Compellent is working hard with Microsoft/Citrix/VMware and many others, there are a lot of free tools/plugins/libs to work better on these environments (less time to provision and mange complex environments)
  • Compellent has a chargeback feature integrated in its management system. (more control and help for budgeting)
  • Compellent has the ability to mix and match all the types of disks, interfaces and protocols on a single system (more freedom of choice and granted upgrades)
  • Compellent has a fully integrated NAS head (a new unified storage), XIV needs a N-series (NetApp) NAS to achieve this result. (you need to learn to manage NetApp.. more training costs)
  • Compellent has a better support: each systems calls home every day and send a lot of informations about usage, configurations, statistics. The support contract is 7×24 with immediate response from a skilled engineer! Engineers can connect directly into the systems to investigate, solve problems, manage upgrades.  IBM support, normally, is delivered via a call center to open the ticket and then you will be called back by some first level technician… (better support means less problems and FASTER RESOLUTION TIMES!)

TCA: 5-0 or 4-1 ?

Finally the Price.

Well, Compellent has competitive prices but I know that IBM slashes them down to unpredictable lows when in competition with other vendors. They are big and they can go down to avoid to lose customers. It’s a well known tactic but how much will it cost a future upgrade?

Conclusion

I know, I’m biased but I firmly believe in what I wrote in this post and I’m here to discuss your point of view.

If you are a XIV customer or an IBM employee/partner let me know your point of view, comments are welcomed.

Related Posts:

A not so successful case and the power of marketing

These days I am competing with IBM XIV in a business negotiation.

I’m gathering as much information as possible to give the customer a document he could find immediately useful and then I’ll publish it on this blog.

During my research I came across this “success case” (just one out of the 11 published): the customer says he bought a XIV (79 TB usable) to feed a 7TB database and now, (guess what?) he finds it outperforms his previous obsolete storage.

WOW! He says that after having piled disks up to 180TB RAW, to mange 7TB of data for a single application, he is satisfied with the performance: it might be but is surely far from being efficient!

Marketing rules!!!!

Related Posts:

How Compellent Storage Center works – Part 2

Here we are again with How Compellent works part 2, I’m writing this post just after a lucullian easter lunch with my whole family so please forgive some of my expressions :-)

In the last post we talked about how data is written into PAGES and progressed using Storage Profiles and Data Progression, this time we’ll focus on how Replay works.

Replays are, in fact, snapshots of your volume data at a certain point in time, to apply this concept to the PAGES that Storage Center uses there’s another metadata on each, which identify the category of the PAGE, the categories are:

  • Accessible Recently Accessed – These are the active pages the volume is using the most
  • Accessible Non-recently accessed – Read-write pages that have not been recently used
  • Historical Accessible – Read-only pages that may be read by a volume, applies to Snapshot Volumes only
  • Historical Non-Accessible – Read-only data pages that are not being currently accessed by a volume, applies to Snapshot Volumes only, Snapshot maintains these pages for recovery purposes and they should be placed on the lowest cost storage possible

(the descriptions are copy/pasted from a Compellent document)

Let’s see with a simple graphic how it works, let’s see how a Volume is represented inside Storage Center when a Replay is taken, each blue block is a 2MB PAGE:


According to this diagram when the C1 PAGE has been written the old C Page change its state to
Historical Non-Accessible, meanwhile C1 is an Accessible Recently Accessed PAGE, all the other PAGES that resides below the Replay separator are Historical Accessible PAGES.So in this case, the C PAGE will be automatically demoted during the first Data Progression Cycle to a lower cost storage.


In this graphic another Replay is taken, as you can see, even with multiple replays only the changed PAGES are allocated as new, in this scenario the C1 PAGE and E PAGE becomes
Historical Non-Accessible PAGES.

Here is the Replay expiration, the expiration could be manually or scheduled, during the replay creation you can choose between a “never expire” Replay or a scheduled expiration, that can be eventually changed on the fly. The grey tinted PAGES are pushed toward the new oldest replay available, meanwhile the orange tinted PAGE is released back into the pool, to be immediately available for other purposes.

But what if we need to access data of a single Replay? maybe map it to another server to replicate the production environment?Here comes the VIEW.Now the graphic is getting complicated, in the following diagram we see the upper part which represent the VIEW created from a Replay which is in purple, and the lower part which represent the Volume with multiple snapshots like the examples above:

Here we have created this VIEW and mapped to another server (every VIEW is R/W) where we decided to create a new development environment based on production data that we snapshotted using a Replay, now every READ operation goes through the Replay like the arrows say, if there’s the need to write a new PAGE it will be written in the VIEW space, consuming in fact only the ∆ changes.Now the development environment has the need to be snapshotted itself, can we do it? OF COURSE we can :-) , let’s see with the usual diagram how it works:


So you can clearly see how this technology is really powerful and space-savvy, it is also applicable recursively so you can create a view made from a replay of a view which is a view of a replay etc… etc…Next time I’ll take care of the replication with QOS and deduplication, as always feedback and comments are very welcomed!.

Fabio Rapposelli

This post originally appeared on my blog: http://p2v.itquid cos a e stato detto?
Inviares la steed

Stessa pi
Ubbli

Related Posts:

     
Latestnews

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