THE SQL Server Blog Spot on the Web

Welcome to - The SQL Server blog spot on the web Sign in | |
in Search

Joe Chang

New SQL Server 2012 per core licensing – Thank you Microsoft

Many of us have probably seen the new SQL Server 2012 per core licensing, with Enterprise Edition at $6,874 per core super ceding the $27,495 per socket of SQL Server 2008 R2 (discounted to $19,188 for 4-way and $23,370 for 2-way in TPC benchmark reports) with Software Assurance at $6,874 per processor? Datacenter was $57,498 per processor, so the new per-core licensing puts 2012 EE on par with 2008R2 DC, at 8-cores per socket.

This is a significant increase for EE licensing on Intel Xeon 5600 6-core systems (6x$6,874 = $41,244 per socket) and a huge increase for Xeon E7 10-cores systems, now $68,740 per socket. I do not intend to discuss justification of the new model. I will say that SQL Server licensing had gotten out of balance with the growing performance capability of server systems over time. So perhaps the more correct perspective is that SQL Server had become underpriced in recent years. (Consider that there was a 30%+ increase in the hardware cost structure in the transition from Core 2 architectures systems to Nehalem systems for both 2-way and 4-way to accommodate the vastly increased memory and IO channels.)

Previously, I had discussed that the default choice for SQL Server used to be a 4-way system. In the really old days, server sizing and capacity planning was an important job category. From 1995/6 on, the better strategy for most people was to buy the 4-way Intel standard high-volume platform rather than risk the temperamental nature of big-iron NUMA systems (and even worse, the consultant to get SQL Server to run correctly by steering the execution plan around operations that were broken on NUMA). With the compute, memory and IO capabilities of Intel Xeon 5500 (Nehalem-EP), the 2-way became the better default system choice from mid-2009 on.

By “default choice”, I mean in the absence of detailed technical sizing analysis. I am not suggesting that ignorance is good policy (in addition to bliss), but rather the cost of knowledge was typically more than the value of said knowledge. Recall that in the past, there were companies that made load testing tools. I think they are mostly gone now. An unrestricted license for the load test product might be $100K. The effort to build scripts might equal or exceed that. All to find out whether a $25K or $50K server is the correct choice?

So now there will also be a huge incentive on software licensing to step down from a 4-way 10-core system with 40 cores total to a 2-way system with perhaps 8-12 cores total (going forward, this cost structure essentially kills the new AMD Bulldozer 16-core processor, which had just recently achieved price performance competitiveness with the Intel 6-core Westmere-EP in 2-way systems).

In the world of database performance consulting, for several years I had been advocating a careful balance between performance tuning effort (billed at consultant rates) with hardware. The price difference between a fully configured 2-way and 4-way system might be $25,000. For a two-node cluster, this is $50K difference in hardware, with perhaps another $50K in SQL Server licensing cost, with consideration that blindly stepping up to bigger hardware does not necessarily improve the critical aspect of performance proportionately, sometimes not at all, and may even have negative impact.

With performance tuning, it is frequently possible to achieve significant performance gains in the first few weeks. But after that, additional gains become either progressively smaller, limited in scope, or involve major re-architecture. In the long ago past, when hardware was so very expensive, not mention the hard upper limits on performance, it was not uncommon for a consultant to get a long term contract to do performance work exclusively.

More recently, performance consulting work tended to be shorter-term. Just clean up the long hanging fruit, and crush moderate inefficiencies with cheap powerful hardware. While this is perfectly viable work, it also precludes the justification for the deep skills necessary to resolve complex problems, which also calls into question the need to endure an intolerably arrogant, exorbitantly expensive consultant.

It had gotten to the point that I had given thought to retiring, and go fishing in some remote corner of the world. But now with the new SQL Server per core licensing, Microsoft has restored the indispensable (though still intolerable) status to arrogant, exorbitantly expensive, performance consultant. So, thank you Microsoft.

Edit 16 Dec 2011
VR-Zone mentions a Windows 7/Server 2008 R2 hot-fix that treats the 8-core AMD Bulldozer die as 4 cores with HT, as opposed to AMD's positioning as 8-cores. AMD should hope that this is Microsoft's position for SQL Server 2012 or no one should consider the AMD in light of the per core licensing, given that Intel physical cores are much more powerful than the Bulldozer "core"

Edit 20 Feb 2012
I might add that the new per core licensing would be well worth the extra money if SQL Server would give us:
1) Parallel Execution plans for Insert, Update and Delete
2) Improve Loop Join parallel scaling - I believe today there is content between thread in latching the inner source index root
3) Fix parallel merge join - If the parallel merge join code is broken, why can we not use the parallel hash join code with the existing index?

The basis for this if we going to pay the cores, then SQL Server should not let the core sit idle in time consuming operations.

Published Wednesday, November 16, 2011 4:19 PM by jchang

Comment Notification

If you would like to receive an email when updates are made to this post, please register here

Subscribe to this post's comments using RSS



Jason said:

Joe,  aren't the per-core licenses being sold in two packs?  So that means that a 6 core machine would require 3 packs @ $6,874, only a 50% premium over current per socket licenses.  It also means that a 4 core machine would be a wash in cost to a single socket license.

November 16, 2011 3:43 PM

Chris said:

While an increase in license cost may help consultants, it's killing the tight budgets of many clients. OSS is looking more useful by the day to much of the marketplace...

November 16, 2011 3:44 PM

jchang said:

Jason: the way I read it is $6,874 per core, with licenses sold in 2-core packs. I am interpreting this to mean you need 3 2-core packs per 6-core at $6,874. Per above, it is not a huge step for 6-core processor, it is huge for 10-core processor, and lethal for weak 16-core processors.

Chris: I am not here to save the world, only to do what I do, and let the world take care of itself. I am not convinced of a large move to OSS. For a main line-of-business database + application, SQL Server licensing is a small part. Effective management of the IT department is still more important.

But it probably does mean that Microsoft needs to deliver really effective problem resolution to justify value. I have seen huge "costs" expended in the back and forth with tech support to resolve problems that render the bare licensing cost irrelevent, and this is true with any vendor. I am thinking that utility databases should not be on EE, but Std.

November 16, 2011 3:55 PM

alen said:

we bought 4 servers this year with 12 cores total in 2 CPU's. looking at the prices it's cheaper for us to buy new servers with 8 cores each. even if we move to SQL 2012 standard because we don't need BI in all system it's still cheaper to buy less cores

November 16, 2011 4:03 PM

Jason said:

You're right, 2 core packs are $6780 per pack... with a minimum of 2 packs per socket :)  So it also a push to get everyone off 2 core processors.  

You're absolutely right, it's going to push DBA's planning purchasing hardware towards more powerful and faster frequency chips with low core density... and that means Intel.

Glenn Barry has a great blog post on Intel / AMD and the new licensing for SQL 2012.

November 16, 2011 4:04 PM

jchang said:

ps. In the Westmere generation, the EP line was for 2-way systems, 6-cores at up to 3.46GHz with a less interesting 4-core version up to 3.60GHz. The EX line was for 4 & 8-way systems, 10-cores at 2.4GHz and 8-core models to 2.66GHz. By less interesting, I mean that for SQL Server, the higher frequency per core does not outweigh having fewer cores.

For Sandy-Bridge, the EP will be for 2 & 4-way systems, with models at 6 and 8 cores? and no EX version until Ivy Bridge?

I am thinking the strategy might now be to include a 4-core model going for max frequency.

November 16, 2011 4:29 PM

a.m. said:

I love your conclusion. Happy New Year!!!

November 16, 2011 5:12 PM

Rente Vergelijk said:

yeah thank you microsoft !:)

November 17, 2011 11:47 AM

Dan said:

So, if I have a SQL Standard with dual 6 cores & HT (2x6x2) I'll have 24 threads.  Does SQL/MS know this is only 12 cores, not 24?  And will this bypass SQL Standard's 16 core limitiation, or will it force me to only use 16 of the available 24 threads?

November 17, 2011 3:44 PM

jchang said:

the doc clearly states only the physical core needs a license (excluding nuances for VM not on EE), but it is unclear whether SE is limited to 16 physical cores or threads. The system DMVs are capable of distinguishing physical and logical cores.

I am also unclear as to the parallel execution limitations of SE. Once in the past, SE was limited to DOP 2 or 4?, but the SQL 2K8R2 edition comparison sheet does not mention this. Has the DOP limitation of SE been dropped?

November 17, 2011 4:30 PM

noeld said:

Oh boy M$ M$$$ M$$$$$$$$ M$$$$$$$$$$$$$

When pushing too hard ... just remember what happened to NetFlix

November 18, 2011 6:44 PM

dremspider said:

Here is my thought....  Hardware decreases in price over time or gets faster, why shouldn't software expect to do the same as well.  Hardware has rapidly become a commodity, no one cares about it other then nerds.  Just give me something that works and I am happy, I don't care who it is from.  With the push towards cloud computing, NOSQL, Application APIs and more, people aren't going to care what is in the back end, just as long as it works.  Software vendors need to understand that the either the value of their software is going to decrease or they are going to need to enable you to do a lot more for the same price (which is what allowing more cores on the hardware does).  Some vendors will understand it, otherwise will fall behind.

March 12, 2012 9:04 AM

Matt said:


The available licensing documentation for SQL Server 2012 indicates that v-cores map to hardware threads, so don't get caught up in semantics of cores vs threads.

Also, regardless of how many cores/threads/processors SQL Server is limited to run on technically, you still have to license the full amount on that machine, even if that number if higher.


March 26, 2012 9:53 PM

Eduardo Pin said:

This overpriced SQL Server will help the consultants? Are you sure? In short, may be, but for how long?

Many people that I talked about this issue are considering to move their systems to another DBMS. I believe that the number of SQL Server instalations will decrease drastically.

January 28, 2013 1:29 PM

Charles W said:

It is amazing to me that customers have allowed the S/W industry to get away with per core licesing, oro r that matter per socket. S/W is the only product in this world that is based on how much you MIGHT use a product. Additionally, how much I use a product has no coorlation to the manufactoring or development costs of that software.

Imagine if cars were priced this way."Well Mr Smith, how fast do you intend to drive your car"

February 22, 2013 4:15 PM

AaronLS said:

Note that MS has adjusted per core licensing for some chips which have many small cores such as opteron 6200 and 4200.  It only counts 75% of the cores for pricing:

March 23, 2013 8:54 PM

Joe said:

@AaronLS... so if I have a single quad core Opteron 4000, I legally only need 3 cores, but still have to buy 4 since they're sold in multiples of two?

December 11, 2013 8:12 AM

Leave a Comment


About jchang

Reverse engineering the SQL Server Cost Based Optimizer (Query Optimizer), NUMA System Architecture, performance tools developer - SQL ExecStats, mucking with the data distribution statistics histogram - decoding STATS_STREAM, Parallel Execution plans, microprocessors, SSD, HDD, SAN, storage performance, performance modeling and prediction, database architecture, SQL Server engine

This Blog


Privacy Statement