Ellison Pits Oracle Cloud Against AWS, Azure

Oracle co-founder and now chief technology officer Larry Ellison may have come late to the term cloud computing, but the database giant that expanded into middleware and applications over his tenure was not – definitely not – late to understanding the transformational aspects of compute utilities hosting application software.

The message that Ellison conveyed, with his wry humor, during his opening keynote at the OpenWorld extravaganza in San Francisco, was that contrary to what many have said, Oracle was not late to the cloud but rather started out a decade ago to transform itself and its code to be a participant in the software as a service, or SaaS cloud, which was about the same time that online retailer Amazon decided to start from the bottom up and sell raw compute and storage capacity to startups as a side business.

“We are in the middle – and I really do mean in the middle – of a generational shift in computing that is no less important than our shift to personal computing when mainframes and minicomputers dominated our industry,” Ellison explained. And he knows because he was there. “It seems like early days. The biggest cloud companies are $6 billion in size, they are not $100 billion, in terms of their cloud business.”

To be sure, the cloud transformation has been going on for fifteen years, and there are some very big players like Amazon, Google, Microsoft, IBM, and Rackspace Hosting that are in the field and some others like Hewlett-Packard and Dell who have left the public cloud and are focusing on selling wares to enterprises to build private clouds. Amazon doesn’t believe in private clouds and says straight up that cloud means public cloud because this is the only way to get scale, and yet it has had to concede that companies will want, at least for some time, a transitional period where they run some of their applications on their own gear in their own datacenters. Google has not let its opinion be known, but we presume it is similar to Amazon’s. Rackspace tries to sell on both sides of the firewall, and so does IBM with its SoftLayer cloud on the public side and now its Power machines and mainframes on the private side. (Most clouds are X86-based, so this is problematic, and due to IBM’s selling off its System x division to Lenovo last October.) HP and Dell partner with the big three cloud providers – and notably they both also sell lots of gear to Microsoft as it builds up Azure – and are also focusing on hybrid scenarios to make their bucks. Dell will inherit yet another public cloud, VMware’s vCloud Air, if its $67 billion acquisition of EMC goes through next year, and it will be interesting to see what Michael Dell does with that. Or doesn’t.

(If you are looking for Ellison to sweep in and try to buy EMC or Dell or both, don’t hold your breath, although that would be a fun fight to watch from the sidelines.)

When Oracle started in the cloud business, it was really seeking to blunt the attack of Salesforce.com, the online CRM application founded by Marc Benioff, a former top Oracle executive, and a slew of other companies that were seeking to get into the application service provider, or ASP, business as it was called back then. The difference between ASP and SaaS, in concept, is negligible, but the underpinnings are wildly different and the need for cheaper hardware and software infrastructure than was available during the dot-com boom is why ASPs, with the exception of Salesforce.com, NetSuite, and a few others from that time fifteen years ago, largely failed. Since that time, hyperscale servers and storage, scalable databases, and multitenant capabilities. Having developed and acquired its middleware and application stacks and more than a few databases as well as its flagship relational database, a decade ago Oracle started down the road of rewriting its middleware and applications from scratch in Java, which it referred to as Fusion.

Oracle did not really intend to get into the PaaS or IaaS markets, Ellison conceded, but the need to deliver SaaS applications made PaaS necessary, and then once you are doing PaaS, you need to create IaaS, too. By this same logic, AWS is moving up the value chain from IaaS to PaaS and we can expect that, at some point, AWS will offer applications of its own too, although you could be generous and count the applications available in the AWS Marketplace right now.

“In this new world of cloud computing, everything has changed, and almost all of our competitors are new,” Ellison continued. “We now compete with Salesforce.com and Workday in applications. These are the companies we see most frequently when we are selling applications in the marketplace, and we virtually never, ever see SAP. This is a stunning change. The largest application company in the world is still SAP, but we never see them in the cloud – and we sell a lot of application in the cloud. One of the companies that has been an historic competitor of ours is Microsoft, and Microsoft is the only one of our traditional competitors that has crossed the chasm and is now competing aggressively in the cloud business at all three layers – infrastructure, platform, and applications. The same applications they offered on premises they offer on the cloud, and they also offer infrastructure plus database and their programming languages. In infrastructure, again, a stunning change. We compete with Amazon.com, primarily, in infrastructure. We see Google occasionally but not all that often. And we never, ever see IBM. So this is how much our world has changed: The two competitors we watched most closely over the last two decades have been IBM and SAP, and we no longer pay any attention to either one of them. It is quite a shock. I can make the case that IBM was the greatest company in the history of companies. They are nowhere in the cloud. SAP is the largest application company that has ever existed. They are nowhere in the cloud.”

In fact, the way Ellison sees Microsoft and Oracle are the only two companies that have taken on all three layers of the cloud, and you get the sense that he believes that a certain amount of scale is necessary to make that happen – scale that a small SaaS provider running on top of Amazon Web Service or Microsoft Azure or Google Compute Engine won’t be able to match.

As for the basic infrastructure underlying the Oracle Cloud, Ellison said that the design goal is to create its systems such that it has the lowest acquisition price and the lowest total cost of ownership for its compute and storage infrastructure. And to be specific, the goal is to meet or beat AWS on compute and storage, although it is tough for Oracle to beat AWS on these factors except in archival storage, said Ellison, where Oracle is one of the three major suppliers of tape libraries in the industry. The other goal was to offer the fastest database, middleware, and analytics software on the cloud, and that performance is just another aspect of price because if you can finish a job faster on a cloud, that is a kind of savings, too. (Hence the TCO argument, not just the raw price per unit of compute or storage.) Peak performance is sometimes a requirement anyway, so this is a kind of positive by-product of that need. And like the hyperscalers, Oracle has learned to add more automation to its software stack to not only make software installation easier and quicker, but to eliminate human error – both of which further reduce costs.


But Oracle has one other big advantage, said Ellison. “As we got into this cloud business and started build SaaS applications, it dawned on us that this is not going to work unless we provide a platform whereby you can extend those applications and integrate those applications with on premises applications and other cloud applications. We have done that, and by the way, Salesforce.com has done that. But most cloud companies are pretty small startups, and it is very difficult for a small startup company to tackle building their SaaS application and a comprehensive platform that they make available to their customers. So this is a huge advantage that Oracle has competing in the SaaS world that we have an underlying platform that makes our applications extensible.”

So what precisely is on the Oracle Cloud today? At the SaaS level, Fusion applications for enterprise resource planning, enterprise performance management, supply chain management, marketing and sales, service and support, human capital management, and talent management. There are also special modules aimed at the banking, telecommunications, utilities, pharmaceuticals, retail, and hospitality industry sectors. With the latest update to the Fusion stack this week, Oracle is adding manufacturing and e-commerce to this stack. Ellison said that Oracle has about 1,300 Fusion ERP customers on the cloud, more than ten times that WorkDay has, and over 5,000 HCM customers and about 1,000 of them using Fusion HCM and around 4,000 using the Taleo SaaS tools Oracle acquired. (The 1,000 customers for Fusion HCM was more customers than WorkDay has for its HCM SaaS tools as well.)


As for SaaS CRM, Oracle has around 5,000 customers today, making it the number two provider behind Salesforce.com. It will take Oracle a while to catch Salesforce.com, which had $5.37 billion in sales in its fiscal 2015 ended this past February and which has orders of magnitude more customers. But, Ellison said that Salesforce.com had a plan to boost its revenues in CRM by $1 billion in new business this year, and Oracle is on track to do an incremental $1.5 billion, so momentum is shifting Oracle’s way thanks to its large enterprise customers. Salesforce.com has been growing, but it has also been losing hundreds of millions of dollars per year to do so. Oracle now has 2,259 customers using its Database Cloud Service, up from 87 a year ago.

As part of the OpenWorld conference, Ellison trotted out a bunch of new features and functions for parts of the Oracle stack. In addition to supporting in-memory columnar storage and query processing with Oracle 12c, the database is also given multitenancy capabilities. The database is split into a container database, or CDB, that containers the data, control, redo log, and other files associated with a database – most of the working parts of the database. On top of the CDB rides what Oracle calls pluggable databases, or PDBs, and this contains data that is relevant to a specific database instance; as far as an application is concerned, a PDB looks like a whole database, even though it is isolated from others around it and sharing certain aspects of the underlying database management system through the CDB. With the Oracle 12c 12.2 update, Oracle now supports 4,096 PDBs per CDB, up from 252 PDBs with Oracle 12c 12.1. The 12.2 update also supports hot cloning and refresh of PDBs and online tenant relocation through movement of PDBs.


Oracle has not said what iron it is using to build the Oracle Cloud, but it has not been very interested in peddling bare bones machines and has largely removed itself from the HPC market that Sun Microsystems, which it bought in 2010, used to play in. But Ellison did say that it was now parking Exadata parallel database clusters in the cloud so that customers could use them on premises or in the Oracle Cloud. The cloudy Exadata machines scale in increments of 28 to 68 cores, 512 GB of main memory, 19.2 TB of PCI-Express flash, and 42 TB of disk capacity. Pricing was not available at press time.

All Exadata machines, cloud or on premises, are now also able to store columnar data in the PCI-Express flash cards in the Exadata machines as well as in DRAM main memory, effectively boosting their columnar storage by a factor of 10X to 100X. Ellison said this would allow these machines to store all but the largest databases in the world in memory. (He was using flash plus main memory as “memory,” something we had better get used to as 3D XPoint comes to market next year.) Oracle is now also allowing for Oracle Real Application Clustering to be used across whatever iron it does use in its cloud; presumably this means not just on Exadata iron, but on virtual machine and bare metal instances on Oracle Cloud.

The other interesting feature is called Multitenant Java Server, which is a pluggable variant of the WebLogic application server that will allow the live migration of applications between on premises and the Oracle Cloud while also offering some of the same multitenancy security that has been added to the 12c database. Importantly, Oracle will be a big user of this feature since it allows for 3X compression of Java instances on servers. As a cloud provider, Oracle has to get its iron to do as much work as it can. Oracle is also simplifying and automating its Coherence Java server replication and caching software to make it easier to create fault tolerant Java applications that can span multiple datacenters, something that Ellison said would take some “hotshot engineers” to set up before all of this automation.

Sign up to our Newsletter

Featuring highlights, analysis, and stories from the week directly from us to your inbox with nothing in between.
Subscribe now


  1. You have to have been living in a cave the last 10 years to buy ANYTHING from Oracle, let alone cloud. Abusive sales force pressuring customers into forking over more money, random audits, or how about Oracle’s latest game – buy some cloud from us and we’ll back off the latest audit…

  2. @JM – you may have that impression – but let me tell you that contrary to what you might think there are many of us within Oracle who are genuinely working hard to provide the very best public cloud solutions for Oracle customers. I know that’s true because I work with the teams. Oracle’s Public Cloud is real and delivering real benefit for our customers. The Cloud space is competitive, as you know.

  3. Dear Larry,

    You seriously screwed up and lost most of your customers when:

    1. you allowed OpenSolaris to die
    2. you didn’t drop the SPARC hardware prices down to be cheaper than intel-based servers
    3. you allowed that horrible image packaging system to replace SVR4 packaging in Solaris. That was the final nail in the coffin.

    Meanwhile, you core Solaris engineers, the best of the best, have left Snoracle and are now thriving developing illumos at other companies, and illumos-based SmartOS is eating everyone else’s lunch in terms of cloud virtualisation, customer support, and capabilities (lx- and KVM-brnaded zones anyone)?

Leave a Reply

Your email address will not be published.


This site uses Akismet to reduce spam. Learn how your comment data is processed.