Oracle Exadata X4 (Part 1): Bigger Than It Looks?
December 20, 2013 17 Comments
One of the results of my employment history is that I tend to take particular interest in the goings on at a certain enterprise software (and hardware!) company based in Redwood Shores. I love watching Oracle’s announcements, press releases, product releases and financial statements to see what they are up to – and I am never more intrigued than when they release a new version of one of their Engineered Systems.
In part this is because I used to work with Exadata a lot and still know many people who do. But the main reason I like Engineered Systems releases is because I believe there is no better indicator of Oracle’s future strategy. Sifting through the deluge of marketing clod, product collateral, datasheets and press releases is like reading the tea leaves – and I’ve been doing it for a long time.
A few weeks ago Oracle released the new “fifth-generation” Exadata Database Machine X4-2, along with the usual avalanche of marketing. Over the last couple of weeks I’ve been throwing it all up in the air to see what lands. Part one of this post will look at the changes, while part two will look at the underlying message.
Database as a Service
The first thing to notice about Exadata X4 is that Oracle Marketing has fallen in love with a new term: database as a service. Previous versions of Exadata were described as being suitable for database consolidation, but in the X4 launch this phrase has been superseded:
Personally I see little difference between consolidation and DBaaS, but I assume the latter has more connotations of cloud computing and so is more fitting for a company attempting to build its own cloud empire. The idea is presumably that you buy Exadata for use in private clouds and use Oracle Cloud for your public cloud service. That’s all very well, but what I find somewhat surprising is the claim that X4 is optimized for OLTP, data warehousing and database-as-a-service. Surely those three workloads encompass everything? Claiming that you have built a solution which is optimized for everything is … shall we say bold?
More Processor Cores = More Licenses
As with previous releases, Oracle has frozen the price of both the Exadata hardware and the Exadata Storage Software licenses (see price lists). This seems like a great result for customers given that the X4 contains significantly faster hardware (see comments section). For example, the Exadata compute nodes change from having 8-core Sandy Bridge versions of the Intel Xeon processor to 12-core Ivy Bridge models. What never ceases to amaze me is the number of people who do not immediately see the consequence of this change: 50% more cores means 50% more database software licenses are required to run the equivalent X4 machine. So while the Exadata storage license cost remains unchanged, the cost of running Oracle Database Enterprise Edition increases by 50%, as does the cost of options such as Oracle RAC, Partitioning, Advanced Compression, the Diagnostic and Tuning Packs, etc etc. And it just so happens that the bits which increase by 50% happen to form the majority of the cost (and don’t forget that the 22% annual fee for support and maintenance will also be going up for them):
Prices are estimates – contact Oracle for correct pricing
So far so boring. Nobody expected something for nothing, despite some of the altruistic statements made to the press. But there’s something much more interesting going on if you look at the X4’s use of flash memory…
Ever-Increasing Capacity
The new Exadata X4 model now contains 44.8TB of raw flash in the form of rebranded LSI Nytro PCIe cards placed in the storage cells. The term “raw“, as always in the storage industry, is used to denote the total amount of flash available prior to any overhead such as RAID, formatting, areas kept aside for garbage collection, etc. Once all of these overheads are added, you end up with a new figure known as “usable” – and it is this amount which describes the area where you can store data.
But hold on, what’s this new term “logical flash capacity” in the press release promising “88 TB per full rack”?
That’s twice the raw capacity! This is an incredible statement, because this so-called “logical” capacity is in fact a complete guess based on compression ratios – which are entirely dependant on your data. And it gets worse when you read the datasheet, which makes the following claim: an “effective flash capacity” of “Up to 448TB“! This is now ten times the raw capacity!
But what is an “effective flash capacity”? Let’s read the small print of the datasheet to find out… Apparently this is the size of the data files that can often be stored in Exadata and be accessed at the speed of flash memory. No guarantees then, you just might get that, if you’re lucky. I thought datasheets where supposed to be about facts?
I am very uncomfortable about this sort of claim, partly because it carries no guarantees, but mainly because it often confuses customers. It’s not inconceivable that a potential customer will mistakenly think they are buying more raw flash capacity than they are actually are. You think not? Then take a look at slide 21 of this Oracle presentation and consider the use of the word “raw”:
Maybe someone can explain to me how that statement can possibly be valid, because to me it looks utterly bewildering.
Exadata Smart Flash Cache Compression
The Exadata Smart Flash Cache has been a stalwart of the Exadata machine for many generations, so it is no surprise to see its feature set continually expanding. For the Exadata X4 release, the big feature appears to be Exadata Smart Flash Cache Compression (read more about it here), which allows Oracle to transparently compress data and store it on the PCIe flash cards. It is this feature which Oracle is describing when it claims a “logical flash cache capacity” of 88TB in the press release and the datasheet. Yet according to slide 22 of this Oracle presentation it is a feature which requires the Advanced Compression Option:
As you can see, the author of this slide deck makes the rather brave assumption that most Exadata customers already have licenses for Advanced Compression (something I strongly contest). But either way, does it not seem reasonable that the press release and/or the datasheet should include this statement if they are going to promise such enlarged flash capacities? I’ve looked and looked, but I cannot see this mentioned – even in the infamous small print.
The thing is, right now on the Oracle Store, the Advanced Compression Option is retailing at $11,500 per core. Given that the new Exadata X4 machine now has 192 cores in a full rack (and taking into account the core multiplication factor of 0.5 for Intel Xeon), I calculate the list price of this option as being over $1.1m. Personally, I think that’s a large enough add-on that it ought to be mentioned up front.
Conclusion
As always with Oracle’s Exadata products, there is much to read between the lines. In the second part of this article I’ll be drawing my own conclusions about what the X4 means… stay tuned.
flashdba 
“This seems like a great result for customers given that the X4 contains significantly faster hardware. For example, the Exadata compute nodes change from having 8-core Sandy Bridge versions of the Intel Xeon processor to 12-core Ivy Bridge models. ”
Are you sure E5-2697v2 is “significantly” faster than the E5-2690? I think the world needs a refresher on Turbo Boost 2.0 and core packing. There is only 3% difference in SPECint between the E5-2690 and E5-2697v2… core packing means packing more slower cores… and QPI 1.1 is constant between this CPUs (the one in the X3 and the one in the X4).
DBA’s enjoying an unlimited license situation in their data center might shrug this off. However, the CFOs that pay for their equipment will figure it out in 3yrs time when Oracle audits cores in use and sits down to negotiate that renewal of the ULA. Viola, Oracle has forced a 50% increase in the cores you’re using.
Wise words, Kevin.
Pardon me for being a novice on this situation. But Exadata has HCC build in, so why would you require to buy Advanced Compression licenses. I thought HCC comes bundled in with storage software licenses; doesn’t this make Advanced compression undesirable.
Absolutely, you spend all that money on Exadata Storage licenses – giving you the right to use Hybrid Columnar Compression – so why would you want to then buy Advanced Compression Option licenses too?
But… it seems Oracle’s assumption is that you will, otherwise you cannot use the Exadata Smart Flash Cache Compression feature and you will not see the so-called “Effective” flash capacity of 88TB. In the slide deck Oracle even makes the claim that most customers already have ACO licenses…
We certainly don’t. And at the scale we operate just ACO would run us into millions. I think it’s not fair to charge for storage software licenses and exclude flash cache compression from it. And storage indexes equate to partitioning in some strange ways, which rules out partitioning option. I don’t understand why Oracle sells Exadata as an appliance-engineered system yet has the same old licensing scheme for it. If the appliance analogy holds true imagine buying a refrigerator and paying LG 100$ extra to run it below 10celcius, 50$ for activating the freeZer and 20$ for the defrost option.
sshdba,
And now you’re starting to see why guys like me did not want to continue having our personal brand tarnished by being in the Exadata dev organization. Handling of stuff like HCC and not this host-ACO-to-enable-storage-functionality was just too shameful. The list goes on and on.
I can certainly understand the frustration of someone who was instrumental in developing the product and then let it go down a completely different path.
I think Exadata should be sold something like an Apple model. 50TB , 100TB and 300TB. And then you have the option to choose HCC,Smart Cache etc. No need to license Oracle Database and RAC externally. That is something closer to an appliance model than what is currently being offered by Oracle.
Hi Kevin,
I know you are one of the guys who actually designed Exadata, just out of curiosity, did you envision Exadata to be a shared nothing architecture or it was to be shared disk like Oracle RAC. You work with EMC now and Greenplum is shared nothing 🙂 so just curious.
Hi,
Did you noticed about the 1.2TB SAS disks? 1.2TB 10K rpm will be faster than 600GB 15K rpm (talking about IOPS)? (slide 15)
Correct if I am wrong, but I don’t believe in this. Your V2/X2/X3 will be faster than your X4 (based on disks/IOPS).
I did notice this – and in fact this is the reason why this blog post is called Part 1. In Part 2 I plan to talk about this very subject, because Oracle’s decision to move from 15k RPM to 10k RPM drives is extremely interesting. This move results in a 50% increase of average rotational latency (4ms to 6ms), consequently reducing the number of random IOPS that can be delivered from each disk. Given that Exadata is marketed as a performance solution, this must have been a difficult choice – and one that Oracle only made because they were forced to.
The next post will discuss why. I just need to find the time to write it!
Amazing how people throw around the word of performance. Performance has many dimensions. The majority is focused on the query performance so I will focus on that for now. “A performance issue” to me (24 year DBA) means I need to look at 4 areas: The query, the schema, the configuration of DB(init and objects) and the load. Once I cleared all those hurdles, I would look at the hardware. DBAs can keep throwing larger hardware at the DB but sooner or later they need to look at the other entities of performance. I understand the spot light is on query performance since that is the impact of the day to day business but you also need to look at the performance of other operations like backup, replication for QA, replication for DR, or the most important the performance of recovery. I still have the scars.
Hi, if i have a 8th rack x4-2, what licensing options do i have? is it a must to have 12 Diagnostics licenses, 24 ADG licenses, 24 RAC licenses, 24 Tuning licenses and 24 Database licenses?
You should talk to Oracle for an official answer.
However, an Eighth Rack X4-2 has 12 CPU cores enabled per database server, of which they are two, giving a total of 24 cores. Since they are Intel x86 Xeon processors the core multiplier is 0.5, which means you need 24 * 0.5 = 12 licenses.
You therefore need 12 licenses for any database product and option you want to use. The database licenses are obviously required, but the rest depends on what you want to use. Technically you don’t even need to use RAC, although in my opinion it would be pointless to use Exadata without the RAC option. Other options you may need include the diagnostic pack, tuning pack, partitioning, active data guard, advanced compression, advanced security… there are many. Each would require 12 licenses.
The only exception is the Exadata Storage Software licenses, which are licenses by the disk drive in each storage cell. I believe that there are 18 disks in use in an 1/8th rack so you would need 18 storage software licenses.
Once final thought. You mentioned ADG, by which I assume you mean active data guard. This therefore suggests that you have a standby Exadata 1/8th rack as well. If this is the case, you need to double everything just discussed because that system must be fully licensed too.
Disclaimer: I do not work for Oracle so this is just my estimate of what is required. Always double-check with the vendor or your chosen Oracle partner.
Abi Chapagai / Database Administrators are responsible for mnntnaiaiig and managing the databases of a company and they will have different roles and responsibilites as per the need of the company but most of the DBAs have same kind of role. Some of the traits of good DBA and bad DBA that i know are listed below. Please feel free to add comments on it: Some of the traits of a good DBA are:• Good attitude.• Fast learner• Good at performance tuning.• Good at database backup and restore.• Automate the jobs.• Good at setting up database security.• Continuous education• Good at database design.• Understand the problem domain fast.• Patience• Understand that nature of the data being stored in the database.• Understand the enterprise architecture.• Good at setting up high availability.• Communication• Certifications• Get up to date with the technology.• Do not play with production data.• Understands the Database Engine Architecture• Monitor the database every day.• Maintenance plan expert.• Detail oriented.• Organized• Follows the corporate rules and regulations. Some of the traits of bad DBA:• Do not want to learn.• Not understand the importance of Organization data.• Not interested in latest technology.• Deletes table and data randomly.• Not organized.• Do not follow the corporate policies.
Yes er…thanks for this, I do indeed agree that this would be a bad trait of a DBA: “Deletes table and data randomly”
Based on documents, it seems that the smart scan / query offloading is available on the following basic requirements are met in exadata.
1. There must be full scan of an object
2. The Scan must use Direct Path Read Mechanism
3. The object must be in stored in Exadata storage
So I have question here, For all other access specifically, the index unique scan, index range scans in oracle Exadata machine, is it uses the same algorithm as previous releases ?
And the performance benefit we are getting for these accesses, are only through the hardware ?
That’s correct – at least, that’s my understanding of it. But my days of working with Exadata are long behind me…