Presenta completaoow2013

  • 549 views
Uploaded on

Presentation systems Oracle Open world 2013

Presentation systems Oracle Open world 2013

More in: Technology , Business
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Be the first to comment
    Be the first to like this
No Downloads

Views

Total Views
549
On Slideshare
0
From Embeds
0
Number of Embeds
0

Actions

Shares
Downloads
37
Comments
0
Likes
0

Embeds 0

No embeds

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
    No notes for slide
  • Oracle produced a world record single-server SPECjEnterprise2010 benchmark result of 27,843.57 SPECjEnterprise2010 EjOPS using one of Oracle's SPARC T5-8s for both the application and the database tier. This result directly compares the 8-chip SPARC T5-8 (8 SPARC T5s) to the 8-chip IBM Power 780 (8 POWER7+). The 8-chip SPARC T5 is 2.6x faster than the 8-chip IBM POWER7+ server.Both Oracle &IBM used virtualization to provide 4-chips for application and 4-chips for DB.The server cost/performance for the SPARC T5 server was 7.1x better than the IBM POWER7+. The cost/performance of the SPARC T5-8 is $10.72 compared to the IBM Power 780 at $76.64.The total configuration cost/performance (hardware+software) for the SPARC T5 was 3.6x better than the IBM POWER7+. The cost/performance of the SPARC T5-8 is $56.21 compared to the IBM Power 780 at $199.43. The IBM system had 1.6x better performance per core, but this did not reduce the total SW+HW. This shows performance-per-core is a poor predictor of characteristics relevant to customers.IBM has a non-virtualized result (1server for application &1server for database). The IBM PowerLinux 7R2 achieved 13,161.07 SPECjEnterprise2010 EjOPS which means it was 2.1x slower than the SPARC T5-8 server. The total configuration cost/performance (HW+SW) for the SPARC T5 server was 11% better than the IBM POWER7+ server. The cost/performance of the SPARC T5-8 is $56.21 compared to the IBM PowerLinux 7R2 at $62.26. The total IBM hardware plus software cost was $2,174,152 versus the total HW+SW cost of $1,565,092. IBM could only provide 768 GB of memory while Oracle was able to deliver 2 TB in the SPARC T5-8.The SPARC T5-8 requires only 8 rack units, the same as the space of the IBM Power 780. IBM had a hardware core density of 4 cores per rack unit which contrasts with the 16 cores per rack unit for the SPARC T5-8. Again performance-per-core is a poor predictor of characteristics relevant to customers.The virtualized SPARC T5 server ran the application tier servers on 4 chips using Oracle Solaris Zones and the database tier in a 4-chip Oracle Solaris Zone. The virtualized IBM POWER7+ server ran the application in a 4-chip LPAR and the database in a 4-chip LPAR.The SPARC T5-8 ran the Oracle Solaris 11.1 operating system and used Oracle Solaris Zones to consolidate eight Oracle WebLogic application server instances and one database server instance to achieve this result. The IBM system used LPARS and AIX V7.1.This result demonstrated less than 1 second average response times for all SPECjEnterprise2010 transactions and represents JEE 5.0 transactions generated by 227,500 users.
  • Oracle's SPARC T5-4 server delivered world record single server performance of 409,721 QphH@3000GB with price performance of $3.94/QphH@3000GB on the TPC-H @3000GB benchmark. The 4-chip SPARC T5 is significantly faster than both 8-chip IBM POWER7 processor and 8-chip HP Intel x86 processor-based servers.This result demonstrates a complete Data warehouse solution that shows the performance both of individual and concurrent query processing streams, faster loading, and refresh of the data during business operations. The SPARC T5-4 server delivers superior performance and cost efficiency when compared to IBM's POWER7 solution.The SPARC T5-4with four SPARC T5 processors is 2.1 times faster than the IBM Power 780 server with eight POWER7 processors and 2.5 times faster than the HP ProLiant DL980 G7 server with eight x86 processors on the TPC-H @3000GB benchmark. The SPARC T5-4also delivered better performance per core than these eight processor systems from IBM and HP. The SPARC T5-4with four SPARC T5 processors is 2.1 times faster than the IBM Power 780 server with eight POWER7 processors on the TPC-H @3000GB benchmark. The SPARC T5-4is 38% better in price performance compared to the IBM Power 780 server on the TPC-H @3000GB benchmark. SPARC T5-4is 2.8 times faster than the IBM Power 780 for data loading. SPARC T5-4is up to 7.6 times faster than the IBM Power 780 server for the Refresh Function. The SPARC T5-4with four SPARC T5 processors is 2.5 times faster than the HP ProLiant DL980 G7 server with the same number of cores on the TPC-H @3000GB benchmark. SPARC T5-4is 4.1 times faster than the HP ProLiant DL980 G7 server for data loading. SPARC T5-4is up to 8.9 times faster than the HP ProLiant DL980 G7 for the Refresh Function. The SPARC T5-4delivered 6% better performance than the SPARC Enterprise M9000-64 server and 2.1 times better than the SPARC Enterprise M9000-32 server on the TPC-H @3000GB benchmark.
  • Oracle's SPARC T5-8 server equipped with eight 3.6 GHz SPARC T5 processors obtained a result of 8,552,523 tpmC on the TPC-C benchmark. This result is a world record for single servers. Oracle demonstrated this world record database performance running Oracle Database 11g Release 2 Enterprise Edition with Partitioning. The SPARC T5-8 delivered a single system TPC-C world record of 8,552,523 tpmC with a price performance of $0.55/tpmC using Oracle Database 11g Release 2. This configuration is available 09/25/13. The SPARC T5-8 has 2.8x times better performance than the 4-processor IBM x3850 X5 system equipped with Intel Xeon processors. The SPARC T5-8 delivers 1.7x the performance compared to the next best 8 chip result. The SPARC T5-8 delivers 2.4x the performance per chip vs. IBM Power 780 3-node cluster result. The SPARC T5-8 delivers 1.8x the performance per chip vs. IBM Power 780 non-clustered. The SPARC T5-8 delivers 1.4x the performance per chip compared to the IBM Flex x240 Xeon result. The SPARC T5-8 delivers 1.7x the performance per chip compared to the Sun Server X2-8 system equipped with Intel Xeon processors. The SPARC T5-8 demonstrated over 3.1 Million 4KB IOP/s with 76% idle, demonstrating its ability process a large IO workload with lots of processing headroom. This result showed Oracle's integrated hardware and software stacks provide industry leading performance. The Oracle solution utilized Oracle Solaris 11.1 with Oracle Database 11g Enterprise Edition with Partitioning and demonstrates stability and performance with this highly secure operating environment to produce the world record TPC-C benchmark performance.
  • Oracle, using Oracle Solaris and Oracle JDK, delivered a two socket server world record result on the SPECjbb2013 benchmark, Multi-JVM metric. This benchmark was y to showcase Java performance. SPECjbb2013 is the replacement for SPECjbb2005 (SPECjbb2005 will soon be retired by SPEC). Oracle's SPARC T5-2 server achieved 75,658 SPECjbb2013-MultiJVM max-jOPS and 23,268 SPECjbb2013-MultiJVM critical-jOPS on the SPECjbb2013 benchmark. This result is a two chip world record. (Oracle has submitted this result for review by SPEC.) There are no IBM POWER7 or POWER7+ based server results on the SPECjbb2013 benchmark. IBM has published IBM POWER7+ based servers on the SPECjbb2005 which will soon be retired by SPEC. The SPARC T5-2 server running is 1.9x faster than the 2-chip HP ProLiant ML350p server (2.9 GHz E5-2690 Sandy Bridge-based) based on SPECjbb2013-MultiJVM max-jOPS. The 2-chip SPARC T5-2 server is 15% faster than the 4-chip HP ProLiant DL560p server (2.7 GHz E5-4650 Sandy Bridge-based) based on SPECjbb2013-MultiJVM max-jOPS. The Sun Server X3-2 system running Oracle Solaris 11 is 5% faster than the HP ProLiant ML350p Gen8 server running Windows Server 2008 based on SPECjbb2013-MultiJVM max-jOPS. Oracle's SPARC T4-2 server achieved 34,804 SPECjbb2013-MultiJVM max-jOPS and 10,101 SPECjbb2013-MultiJVM critical-jOPS on the SPECjbb2013 benchmark. (Oracle has submitted this result for review by SPEC.) Oracle's Sun Server X3-2 system achieved 41,954 SPECjbb2013-MultiJVM max-jOPS and 13,305 SPECjbb2013-MultiJVM critical-jOPS on the SPECjbb2013 benchmark. (Oracle has submitted this result for review by SPEC.) Oracle's Sun Server X2-4 system achieved 65,211 SPECjbb2013-MultiJVM max-jOPS and 22,057 SPECjbb2013-MultiJVM critical-jOPS on the SPECjbb2013 benchmark. (Oracle has submitted this result for review by SPEC.) These results were obtained using Oracle Solaris 11 along with Java Platform, Standard Edition, JDK 7 Update 17 on the SPARC T5-2 server, SPARC T4-2 server, Sun Server X3-2 and Sun Server X2-4. From SPEC's press release, "SPECjbb2013 replaces SPECjbb2005. The new benchmark has been developed from the ground up to measure performance based on the latest Java application features. It is expected to be used widely by all those interested in Java server performance, including JVM vendors, hardware developers, Java application developers, researchers and members of the academic community."
  • The cryptography benchmark suite was internally developed by Oracle to measure the maximum throughput of in-memory, on-chip encryption operations that a system can perform. Multiple threads are used to achieve the maximum throughput. Systems powered by Oracle's SPARC T5 processor show outstanding performance on the tested encryption operations, beating Intel processor based systems. A SPARC T5 processor running Oracle Solaris 11.1 runs from 2.4x to 4.4x faster on AES 256-bit key encryption than the Intel E5-2690 processor running Oracle Linux 6.3 for in-memory encryption of 32 KB blocks using CFB128, CBC, CCM and GCM modes fully hardware subscribed. AES CFB mode is used by the Oracle Database 11g for Transparent Data Encryption (TDE) which provides security to database storage. Performance LandscapePresented below are results for running encryption using the AES cipher with the CFB, CBC, CCM and GCM modes for key sizes of 128, 192 and 256. Decryption performance was similar and is not presented. Results are presented as MB/sec (10**6). Encryption Performance – AES-CFBAES-CFB is the mode used in the Oracle Database for tablespaceencryptionPerformance is presented for in-memory AES-CFB128 mode encryption. Multiple key sizes of 256-bit, 192-bit and 128-bit are presented. The encryption was performance on 32 KB of pseudo-random data (same data for each run).
  • With Oracle Solaris 10, we raised the bar in terms of the innovation included in the operating system. Oracle Solaris is a trusted platform for enterprise deployments among our customer base for providing a highly available and mission critical foundation that they can rely on. Larry Ellison has often said “If it must work, it runs on Solaris”. With features such as our predictive self healing capability (through the Service Management Facility and Fault Management Architecture) we can continue to run in the event of any software and hardware failures either by restarting services, or isolating hardware components until they can be replaced some time later. ZFS, the next generation file system, provides us tremendous scale and data integrity when managing the high volumes of data in today’s computing industry. Built in data services like snapshot and cloning, encryption, RAID and others mean that customers no longer need to purchase additional expensive software to secure their data. With Oracle Solaris Cluster, customers could benefit from the unique integration with the fastest levels of fail over for application clustering. Through technologies like Oracle Solaris auditing and Role Based Authentication Control, customers could ensure they met compliance requirements while having unprecedented observability of live production systems through the DTrace dynamic tracing framework in a safe way.Oracle Solaris 11 brings all of the attributes of a mission critical enterprise operating system together but with a focus on also being an agile and flexible environment for cloud computing at a large scale. With built-in server, storage and network virtualization, no other operating system provides the complete virtualized solution to deal with the demands of cloud computing in a scalable way. We’ve done a lot of work to ensure we can provision the operating system quickly and consistency, and manage it for the complete lifecycle in a fail safe environment. One of the technology foundations of this approach is Oracle Solaris Zones, which provide OS virtualization at extremely low overhead – the perfect vehicle in deploying applications within a multi-tenant cloud environment.
  • What it could beKey elements of an optimized datacenterIn order to have an optimized data center that can become a platform for innovation you need to work through 3 steps.Performance: Improve overall application performance, not just individual componentsSimplicity: Simple to deploy, manage, support, and upgradeRisk: Reduce deployment risk, downtime risk, security risk, vendor lock-in risk
  • The Oracle Real Application Clusters (RAC) distributed database product includes the Lock Management System (LMS), a user-level distributed lock protocol which mediates requests for database blocks between processes on the nodes of a database cluster. Fulfilling a request requires traversing and copying data across the user/kernel boundary on the requesting and serving nodes, even for the significant number of requests for blocks with uncontended locks. We have created a kernel accelerator (KA), which filters database block requests destined for LMS processes and directly grants requests for blocks with uncontended locks, thereby eliminating user-kernel context switches, the associated data copying, and LMS application-level processing for those requests.The KA exports shared memory in which the LMS locking daemon places its lock table. The KA intercepts DBMS block requests over the RDSv3 communications protocol used between cluster nodes and calls into a DBMS-provided kernel accelerator run-time (KA RT) module, which consults the shared-memory lock table. If the lock is available, the KA replies from the kernel, granting the request directly to the requesting node; if the lock is not available, the KA passes the request up to the LMS user process, which handles the request in the same fashion as when no KA is present.This not only speeds up the process of granting locks, but it also frees up CPU cycles, thus allowing for better throughput in the order of 30-40% depending on the workload.Note: The next generation Oracle Database technology plans to include Oracle RAC Kernel Mode Acceleration. The kernel accelerator is available for Oracle Solaris 11 and Oracle Linux.
  • As industry trends have driven memory prices down it is now feasible to deliver very large memory systems with more than 64 TB of memory. This unprecedented availability of memory leads to new opportunities such as running enterprise applications entirely in memory. Large memory systems introduce problems for current operating systems because most operating systems virtual memory subsystems were designed in the 1980s or best case the 1990s and are not designed to deal with the capacity or unique problems that very large memory configurations introduce.Oracle engineers foresaw this opportunity and by working with hardware designers designed a new virtual memory system for Solaris that could not only scale but also optimized the placement of resources near heavily used components. The result is a high performance virtual memory system that scales with the size of the system memory.Very large memory pages are now possible with Solaris 11.1 virtual memory system to better match application needs such as the database. Many database records can now be easily stored in these large memory pages improving overall database performance by reducing multi-step memory operationsAnother innovation is the new built-in memory predictor which monitors large memory page use and adjusts the size of the memory pages to better match the demand for those pages. The predictor is looking at memory demand across the system. For the database, this means that the predictor will try to ensure that the large pages that the database requests at start up are kept available if at all possible. This optimization also helps smaller memory systems by more closely matching the size of the memory pages with the application needs.Note: This feature is only available in Oracle Solaris 11.
  • The System Global Area (SGA) is a group of shared memory areas that are dedicated to an Oracle “instance” (an instance is your database programs and RAM). All Oracle processes use the SGA to hold information. The SGA is used to store incoming data (the data buffers as defined by the db_cache_size parameter), and internal control information that is needed by the database. You control the amount of memory to be allocated to the SGA by setting some of the Oracle “initialization parameters”.  Optimized Shared Memory (OSM) - a new shared memory interface in Solaris - allows dynamic resizing of SGA without having to reserve memory and reboot the database like Linux or AIX. This also helps to improve the start up and shutdown of database instances. Using one (or fewer) OSM segments will be faster and simpler than using many Intimate Shared Memory (ISM) segments.OSM has the advantages of Dynamic Intimate Shared Memory (DISM) but has resolved the issues of DISM. With OSM memory can be allocated as needed (rather than all at once), and the traditional memcntl() interface can be used to adjust allocation policy. The new interfaces are "optimized" for real world usage – they offer flexibility without compromising performance, and functionality without onerous user requirements. The interfaces are based on the concept of a "granule size", which is set once as part of creating the segment This approach was adopted because it reflects an important real-world usage pattern, and it allows the application to communicate a very relevant bit of usage information (the granule size) to the operating system.Note: The next generation Oracle Database technology will use OSM. This feature is only available in Oracle Solaris (S11.1, S11 and S10U10) The next generation Oracle Database will also have fast instance startup of about 2x faster depending on SGA size. Fast instance startup doesn't allocate the entire SGA at startup. Parts of the SGA are allocated and the rest is allocated over time. With OSM, this will simply lock the granules that you need.
  • 11.2.0.3 as well as 12.1.0.1 instance can use 30 TB SGA !!12c DB instance with 30 TB SGA can start in 130 sec !!Solaris optimizations for fast DB startup : Scalable kernel memory allocator for SGABenefits 11g Database more than 12c Directly affects no-mount time during startupParallelized metadata initialization in kernel for ISM : Benefits both 11g and 12c Database instancesImproves 'open' phase of startup Database optimizations for fast DB startup :Faster spawning of background processes (use of posix_spawn( ) interface) Available in 11g and 12c both Deferred SGA allocation (only available in 12c)Deferred creation of selected background processes like PQ slaves, until required (only available in 12c) 
  • Since the acquisition of Sun, Oracle Solaris engineering teams have been working closely with the Oracle Database team and how innovations in the OS could help database deployments. Oracle Solaris DTrace is a dynamic tracing capability in the operating system that allows administrators to observe what’s happening in real time on live production systems safely. This technology has powered the ZFS Storage Appliance analytics, and administrators can use it to ask questions about application performance right across a system. With Oracle’s next generation database we can look for outlier I/O events through integration with DTrace. We can check the v$kernel_io_outlier table to extract information about time spent in the kernel for I/O's whose end to end latency exceeds a given threshold (500ms be default but tunable via the '_io_outlier_threshold' tunable - the example below was on an instance with this set to 200ms): SQL> desc v$kernel_io_outlier  Name                                      Null?    Type  ----------------------------------------- -------- ----------------------------  TIMESTAMP                                        NUMBER  IO_SIZE                                            NUMBER  IO_OFFSET                                         NUMBER  DEVICE_NAME VARCHAR2(513)  PROCESS_NAME VARCHAR2(64)  TOTAL_LATENCY                                NUMBER  SETUP_LATENCY                               NUMBER  QUEUE_TO_HBA_LATENCY              NUMBER  TRANSFER_LATENCY                        NUMBER  CLEANUP_LATENCY                          NUMBER  PID                                                NUMBER  CON_ID                                             NUMBER SQL> select IO_SIZE,PID,TOTAL_LATENCY,SETUP_LATENCY,QUEUE_TO_HBA_LATENCY,TRANSFER_LATENCY,CLEANUP_LATENCY from v$kernel_io_outlier; DEVICE_NAME -------------------------------------------------------------------------------- IO_SIZE PID TOTAL_LATENCY SETUP_LATENCY QUEUE_TO_HBA_LATENCY TRANSFER_LATENCY CLEANUP_LATENCY ----------- ----- ------------------------- ------------------------- ---------------------------------------- ------------------------------- ----------------------------- 64 0 402554 2020 107 400361 64sd@3,0:a,rawThis example shows that this single 64k write to a SCSI target had an end to end latency of just over 400 milliseconds and the breakdown is: SETUP_LATENCY –Time in microseconds spent during initial I/O setup before sending to scsi target device driver (2020 microseconds)QUEUE_TO_HBA_LATENCY – Time in microseconds spent in the scsi target device driver before being sent to the Host Bus Adaptor (107 microseconds)TRANSFER_LATENCY – Time spent transferring (DMA) to the physical device (~400 milliseconds)CLEANUP_LATENCY – Time in microseconds spent freeing resources used by the completed I/O (64 microseconds)Note: The next generation Oracle Database technology uses DTrace to provide I/O observability. This feature is only available on Oracle Solaris.
  • Other databases have row and column formats but you must choose ONE format for a given table.Therefore you get either fast OLTP or fast Analytics on that table but not both. Oracle’s unique dual format architecture allows data to be stored in both row and column format simultaneously. This eliminates the tradeoffs required by others.Up until now, this could only be achieved by having a second copy of the table (Data Mart, Reporting DB, Operational Data Store), which adds cost and complexity to the environment, requires additional ETL processing and incurs time delays.With Oracle’s unique approach, there is a single copy of the table on storage. So there are no additional storage costs, synchronization issues, etc.The Oracle optimizer is In-Memory aware. It has been optimized to automatically route analytic queries to the column store, and OLTP queries to the row store.
  • The Oracle SPARC SuperCluster is a general purposed engineered system that combines the computing power of the SPARC T4 processor, the performance and scalability of Oracle Solaris 11, the optimized database performance of the Oracle Exadata storage, and the accelerated middleware processing of the Oracle Exalogic Elastic Cloud. One of the limitations of the Exadata Database Machine was the inability to host virtualized environments and carve up the system. With SPARC SuperCluster, Oracle Solaris Zones are supported and all the protocols to accelerate network performance on the InfiniBand backplane of the system have been implemented in non-global zones. This provides an additional level of consolidation opportunities for administrators wanting the benefits of Exadata Database Machine, but some of the flexibility of virtualization.Oracle's Transparent Data Encryption (TDE) feature simplifies the encryption of data within datafiles, preventing unauthorized access to it from the operating system. Tablespace encryption, allows encryption of the entire contents of a tablespace.Data is transparently encrypted when written to disk and transparently decrypted after an application user has successfully authenticated and passed all authorization checks. Authorization checks include verifying the user has the necessary select and update privileges on the application table and checking Database Vault, Label Security and Virtual Private Database enforcement policies.Oracle's SPARC T4 processor with hardware cryptography acceleration can greatly improve performance over software implementations. This should greatly expand the use of TDE for many customers.Performance on Oracle TDE (Transparent Data Encryption)SPARC T4 44% faster secure queries than x86 Westmere (AES/NI)Combination of fast query processing and TDETests 8 different queries on 2-socket serversConsistent SPARC T4 query time 128-bit to 256-bit ciphersOracle Advanced Security TDE column encryption was introduced in Oracle Database 10g Release 2, enabling encryption of application table columns, containing credit card or social security numbers. Oracle Advanced Security TDE tablespace encryption and support for hardware security modules (HSM) were introduced with Oracle Database 11gR1. Hardware Security Module (HSM) - A device used to secure keys and perform cryptographic operations. These devices can be standalone network based appliances or plug-able PCI cards. In the context of TDE, these devices can create and store the TDE master key. Advanced Encryption Standard (AES) – A symmetric cipher algorithm defined in the Federal Information Processing (FIPS) standard no. 197. AES provides 3 approved key lengths: 256, 192, and 128 bits. PKCS#11 – A standard developed by RSA for communicating with cryptographic devices. Transparent Data Encryption is one of the three components of the Oracle Advanced Security option for Oracle Database 11g Release 2 Enterprise Edition; it provides transparent encryption of stored data to support your compliance efforts. Applications do not have to be modified and will continue to work seamlessly as before. Data is automatically encrypted when it is written to disk and automatically decrypted when accessed by the application. Key management is built-in, eliminating the complex task of creating, managing and securing encryption keys.
  • Oracle Solaris DTrace is a comprehensive dynamic tracing facility that is built into Oracle Solaris that can be safely used by administrators and developers on live production systems to examine the behavior of both user programs and of the operating system itself. Oracle Solaris DTrace enables you to explore your system to understand how it works, track down performance problems across many layers of software, or locate the cause of aberrant behavior. The following Oracle Solaris DTrace probes have been added to Java Hotspot VMVM Lifecycle ProbesThread Lifecycle ProbesClass Loading ProbesGarbage CollectionProbes, Monitor Probes This instrumentation available with Java Mission Control allows users to closely monitor their Java applications, uncover performance bottlenecks and troubleshoot runtime issues.
  • Organizations worldwide are scrambling to secure sensitive information in response to regulatory pressure for protecting data privacy and integrity, as well as protect from increasingly sophisticated attacks targeting this data. Encrypting data in applications, however, requires costly and complex code changes, often with disastrous performance consequences. Fortunately these pitfalls can be avoided.Oracle Advanced Security is an option for Oracle Database Enterprise Edition providing three main features – Transparent Data Encryption (TDE), Network encryption, and strong authentication. Transparent Data Eencryption (TDE) provides the ability to encrypt sensitive application data on storage media completely transparent to the application itself and no application modifications are needed. Applications do not have to be modified and will continue to work seamlessly as before. Data is automatically encrypted when it is written to disk and automatically decrypted when accessed by the application. Key management is built-in, eliminating the complex task of creating, managing and securing encryption keys. TDE addresses encryption requirements associated with public and private privacy and security mandates such as PCI and California SB1386. Oracle's Transparent Data Encryption (TDE) feature simplifies the encryption of data within data files, preventing unauthorized access to it from the operating system. Tablespace encryption, allows encryption of the entire contents of a tablespace. Data is transparently encrypted when written to disk and transparently decrypted after an application user has successfully authenticated and passed all authorization checks. Authorization checks include verifying the user has the necessary select and update privileges on the application table and checking Database Vault, Label Security and Virtual Private Database enforcement policies.Through integration with Oracle's SPARC T4 processor, hardware cryptography acceleration can greatly improve performance over software implementations. This should greatly expand the use of TDE for many customers.Note: Oracle Advanced Security TDE column encryption was introduced in Oracle Database 10g Release 2, enabling encryption of application table columns, containing credit card or social security numbers. Oracle Advanced Security TDE tablespace encryption and support for hardware security modules (HSM) were introduced with Oracle Database 11gR1. Hardware Security Module (HSM) is a device used to secure keys and perform cryptographic operations. These devices can be standalone network based appliances or plug-able PCI cards. In the context of TDE, these devices can create and store the TDE master key. Advanced Encryption Standard (AES) – A symmetric cipher algorithm defined in the Federal Information Processing (FIPS) standard no. 197. AES provides 3 approved key lengths: 256, 192, and 128 bits. PKCS#11 – A standard developed by RSA for communicating with cryptographic devices.
  • Let’s take a closer look now at clouds and some of the features that we’ve integrated into the operating system to provide huge value for cloud environments
  • Oracle Solaris 11 is the first fully-virtualized OS in the industry delivering full service, storage and networking virtualization. This gives Oracle Solaris the unique ability of being able to provide a full solution for an Infrastructure-as-a-Service offering.As we’ve mentioned before, Oracle Solaris Zones is the cornerstone of our server virtualization, offering application environments with extremely low overhead. This provides the ability to consolidate multiple services onto a single server – whether it’s your web tier, application tier, or database tier. Oracle Solaris Zones scales due to the fact that only a single kernel instance is being used.Our next generation file system, ZFS, is the cornerstone of our storage virtualization. With today’s demands for storing larger amounts of data, ZFS provides an integrated file system and volume manager with extreme data integrity, scalability, and nearly zero administrative overhead. ZFS takes advantage of traditional disk storage and solid-state disk storage with a hybrid storage pool approach, providing extremely efficient read and write caches to make accessing and writing data fast. With ZFS, volumes can be created on remote storage and shared out through iSCSI and Fibre Channel as a block device. This gives the ability to host Oracle Solaris Zones on shared storage in the cloud.And now with Oracle Solaris 11, administrators can create a fully virtualized network for more efficient sharing of network resources. This previously missing functionality now completes the virtualization solution, allowing administrators to create virtualized network interfaces allowing isolated and dedicated network stacks between an application and the physical network interfaces. Network resource management allows organizations to meet quality of service goals for networking, by specifying specific CPU resources or bandwidth limits. Network virtualization is integrated in Oracle Solaris Zones.All of these technologies bring significant cost reduction through consolidation, but increased agility and flexibility allowing you to quickly deploy new services in the cloud, respond to increased workloads and ensure necessary service level agreements are met.
  • This large European city required a highly available online services platform for city residents. Oracle Solaris 11 packaging and update technology has greatly shortened the time they spend updating systems. Each week the customer automatically pulls any new packages from the Oracle support repository to their local IPS repository. About once a month administrators review the READMEs for the updates and initiate the update process. They no longer have to assemble the latest patches and run the new configuration through several days of testing before updating the systems. It was not uncommon for these systems to be updated once or twice a year. With this new model the customer is able to keep the systems in tighter compliance with the latest updates and spend much less time updating the systems.Solaris Zones allow to securely stack both the SAP services and the Oracle Database on the same nodes while restricting access to the respective environments to only those who need itZone Cluster gives a flexible high availability solutions layered on top of the virtualization layer, giving the application administrators control over the high availability. Zone Cluster met all the ease of use needs they were used to with Solaris 10 and Solaris Cluster 3.3Rapid deployment of new Zones and the appropriate Cluster agent brings new services online quicklyDelegated administration allows the SAP and database administrators to safely control the state of their own Zones without endangering the other Zones and services on the systems
  • Software defined networking is an emerging architecture in today’s data center designs separating out the control plane from the data plane of typical switches and routers. This gives increased agility in cloud environments for being able to model or optimize network topologies, and provides a level of management control that was previously proprietary within switches and routers. Through a variety of IEEE network standards, Oracle Solaris 11.1 has kept up with the pace and provided support for Edge Virtual Bridging and Data Center Bridging.Edge Virtual Bridging offloads the decisions and control from virtual switching (using network virtualization in Oracle Solaris 11) to the physical switch network as a standard protocol. This may be done for a variety of reasons includingManagement – Virtual switches are normally set up and controlled by server administrators. In this case, you may want to make sure the network administrators have control over all your network, both physical and virtualMonitoring – A common network monitoring tool will be able to see all the traffic and give a centralized view (as opposed to traffic hidden away through virtual switching)Security – The physical switches may have better functionality to ensure an improved security modelData Center Bridging provides converged storage and network through Ethernet, by implementing lossless Ethernet (critically important for storage when enabling Fibre Channel or RDMA over Ethernet and when trying to avoid implementing over TCP due to performance degradation) and allocate bandwidth control on links.
  • New to Oracle Solaris 11 is the addition of Federated File System support. Oracle Solaris 11.1 is one of the first commercially available operating systems to provide this. Essentially this allows administrators to seamlessly provide a unified namespace through a series of NFSv4 namespace referrals. NFS referrals are a way for an NFSv4 server to point to file systems located on other NFSv4 servers, as a way of connecting multiple NFSv4 servers into a uniform namespace. NFSv2, NFSv3 and other clients can follow a referral because it appears to them to be a symbolic link. NFS referrals are useful when you want to create what appears to be a single set of filenames across multiple servers, and you prefer not to use autofs to do this. Note that only NFSv4 servers may be used, and that the servers must be running the Oracle Solaris 11 release or later to host a referral.
  • As customers deploy more and more virtual environments, the complexity of managing them increases. With the new packaging system, IPS, zones can now be updated in parallel leading to significant performance gains. For customers with 100’s if not 1000’s of systems to manage, this can be a significant cost saving. In this example we can see nearly 30 minutes difference when updating a SPARC T4 based system with 20 Oracle Solaris Zones. Package updates are cached in the global zone meaning that each zone does not need to re-download these packages over the wire. With IPS, we also ensure that all zones installed on the system are consistent with the global zone, and each have their own respective Zone ZFS Boot Environments to allow an unprecedented level of flexibility and control when updating a system.
  • While customers could have placed zones in shared storage (SAN) themselves the configuration is tricky and the various steps are all left to the customer. This resulted in differing implementations, and often customers were not taking advantage of ZFS as their backend storage file system. With Oracle Solaris Zones on Shared Storage, we reduce the complexity of this commonly asked functionality, so customers can easily leverage their backend storage environment. This has become more important now as customers look for mobility of their virtualization. With Oracle Solaris Zones on shared storage the move becomes the time to shutdown/detach/attach/boot the zone – this can be a very fast operation depending on the applications within the zone.Note: Zones on NFS are still not supported.
  • Oracle Solaris Cluster is an additional solution that helps provide further layers of high availability to Oracle Solaris 11. Oracle Solaris Cluster is engineered in lock step to Oracle Solaris 11, and through integration at the kernel layer, provides consistently faster failover times than any other3rd party product. The latest release of Oracle Solaris Cluster 4.1 is required for Oracle Solaris 11.1. It includes a number of new features that help you protect your application investments and take advantage of some of the new features of Oracle Solaris 11.1.Oracle Solaris 10 Zone ClustersOracle Solaris 10 can now be deployed inside an Oracle Solaris Zone cluster in addition to Oracle Solaris 11. This new feature enables the deployment of Oracle Solaris 10 applications in a protective clustering environment within an Oracle Solaris 11 based system. Customers can thus leverage Oracle Solaris 11 best of breed features such as network virtualization and enhanced installation tools while minimizing the risk to new application environments by deploying tested and mature Oracle Solaris 10 solutions. The resulting benefits are protected customer investments and lower TCO. Integrated network virtualizationOracle Solaris Zone clusters can now be configured with “Exclusive IP” which is the Oracle Solaris 11 default. This enables the use of all advantages of the Oracle Solaris network virtualization within a Zone cluster. Added to this, Oracle Solaris Cluster can also take advantage of some of the network resource and priority management features of network virtualization.Configuration WizardsThe configuration wizards guide the users through the resource configuration step-by-step. It automatically discovers default values and auto-selects them to minimize manual interaction. It also presents possible options for multiple choices, allows manual entry of values and verifies the validity of the choices. The wizards help avoid configuration errors, lower the need for training for beginners and save time for advanced users.
  • So what we exactly we mean by a complete, integrated and business-driven cloud management solution?There are three key aspects of Oracle Enterprise Manager 12c that help accomplish this: Complete Cloud Lifecycle Solution To start with, Oracle Enterprise Manager 12c contains solutions to manage all phases of the building, managing, and consuming an enterprise cloud. Using Oracle Enterprise manager 12c you can build and manage a rich catalog of cloud services – whether it is Infrastructure-as-a-Service, Database-as-a-Service, or Platform-as-a-Service , all from a single product. Integrated Cloud Stack ManagementSecondly, Oracle Enterprise Manager 12c enables integrated management of the entire cloud stack – all the way from application to disk. Oracle Enterprise Manager 12c therefore eliminates much of the integration pains and costs that customers would have to otherwise incur by trying to create a cloud environment by integrating multiple point solutions.   Business-Driven Clouds Finally, Oracle Enterprise Manager 12c enables creation of application-aware and business-driven clouds that has deep insight into applications, business services and transactions. Applications – whether they are packaged or home grown – power your businesses and therefore it is critical that an enterprise Cloud platform is not only able to run these applications but also has deep business insight and visibility. As the leading providers of business applications and the middleware that many of your custom applications are built on top of, we are able to offer you a cloud solution that is optimized for business services.
  • And finally, let’s take a look at Oracle Solaris 11 in action at some of our customer sites.
  • The guarantee debuted in May 2000 and covers applications that ran on Solaris 2.6 and forward (1997) We guarantee any app that runs successfully on Solaris 2.6 (released 1997) -- but, apps built as far back as 1992 may qualify for that!Source code compatibility says that your SPARC Solaris application can be recompiled for Solaris on x86 platforms and vice versa. We guarantee that as well.For customers who want to quickly move their older environments to the latest Solaris release to take advantage of the latest hardware (think consolidation play) we offer zones for older Solaris environments. Use physical to virtual tools to easily move those environments forward.
  • Oracle's SPARC T5-1B server module with Oracle VM for SPARC running Oracle Solaris 11 shows that the SPARC T5 processor is 3.1x faster than an x86 system running Sandy Bridge processors when run in a popular virtualized environment. The test showed this performance difference with only two VMs. The test was a heavy OLTP workload based on a customer workload. On a per processor basis, the SPARC T5 processor running the iGen OLTP workload on two Oracle Solaris VM for SPARC Domains is 3.1x faster than an Intel Xeon E5-2690 processor running the same workload on two virtual machines with Red Hat Linux. An Intel Xeon E5-2690 processor based server using a popular virtualization software lost 23% of its performance in a virtualized environment with only two VMs. The SPARC T5 processor only lost 0.4% of its performance in a virtualized environment. The SPARC T5 processor offers better native performance than the x86 system. On a per processor basis, the SPARC T5 processor running the iGen OLTP workload is 2.5x faster than an Intel Xeon E5-2690 processor running the same workload with Red Hat Linux. Increasing the number of Logical Domains on the SPARC T5 processor system, the Oracle Database 11g shows no loss in stability and performance. Oracle VM for SPARC has the lowest overhead of any virtualization technology available. Paravirtualized IO (virtio) was used on both the SPARC T5 processor and the Intel Xeon E5-2690 processor servers.
  • Oracle Solaris and Oracle VM for SPARC leads the industry on high-performance and efficient virtualization. This test measures the effect of virtualization on performance of cpu-intensive enterprise workloads. Virtualization also effects network and storage performance and those are measured in other tests. A Java enterprise workload showed a 13% performance loss on an x86 server running two Red Hat VMs using a leading virtualization software product. The same workload on Oracle's SPARC T4-2 server running two Oracle Solaris 11 VMs using Oracle VM for SPARC showed no performance loss. The performance loss for the Java enterprise workload grew bigger to 26% on the x86 server when the number of Red Hat VMs running was increased to four using the same leading virtualization software product. Performance LandscapeOverheads of different virtualization methods were measured using a compute and memory intensive Java workload distributed evenly to measure maximum Java throughput performance of the hardware.Performance loss is presented as the percentage difference between running without virtualization (native) to running with virtualization. The Java workload is modeled based on a real world Java application, namely a supply chain, but it has many elements generally found in many enterprise applications and Java SE applications. The Java workload allows for the capability to easily take advantage of additional hardware threads for compute intensive operations. The workload is architected in a way that it can be run fairly on a wider range of chips and systems architectures to distribute the Java workload.
  • Oracle's SPARC T5-2 server using Oracle VM Server for SPARC exhibits dramatically lower network latency under virtualization than a popular virtualization solution. The network latency was measured using the Netperf benchmark. The results for Oracle VM Server for SPARC compared to a popular virtualization solution on TCP network latencies are very similar to the TCP network latencies: TCP network latency between 2 Oracle VM Server for SPARC guests running on separate SPARC T5-2 servers each using paravirtualized I/O is 27% faster than between two Red Hat 6.1 guests hosted with a popular virtualization solution on separate x86 based servers each through a paravirtual I/O interface. TCP network latency between two Oracle VM Server for SPARC guests running on separate SPARC T5-2 servers each using direct I/O is 53% faster than between two Red Hat 6.1 guests hosted by a popular virtualization soltuion on separate x86 based servers each using direct I/O. The results for Oracle VM Server for SPARC compared to a popular virutalization solution on UDP network latencies are very similar to the TCP network latencies: UDP network latency between two Oracle VM Server for SPARC guests running on separate SPARC T5-2 servers each using paravirtual I/O is 20% faster than between two Red Hat 6.1 guests hosted with a popular virtualization solution on separate x86 based servers each using paravirtual I/O. UDP network latency between two Oracle VM Server for SPARC guests running on separate SPARC T5-2 servers each using direct I/O is 45% faster than between two Red Hat 6.1 guests hosted with a popular virtualization solution on separate x86 based servers each using direct I/O. TCP and UDP network latencies between two Oracle VM Server for SPARC guests running on separate SPARC T5-2 servers each using SR-IOV were significantly less than when using paravirtual I/O *. Terminology notes: VM – virtual machineguest – encapsulated operating system instance, typically running in a VM.direct I/O – network hardware driven directly and exclusively by guestsparavirtual I/O – network hardware driven by hosts, indirectly by guests via paravirtualized driversSR-IOV – single root i/o virtualization; virtualized network interfaces provided by network hardware, driven directly by guests. LDom – logical domain (previous name for Oracle VM Server for SPARC)
  • Oracle's SPARC T5-2 server using Oracle VM Server for SPARC exhibits dramatically lower network latency under virtualization than a popular virtualization solution. The network latency was measured using the Netperf benchmark. The results for Oracle VM Server for SPARC compared to a popular virtualization solution on TCP network latencies are very similar to the TCP network latencies: TCP network latency between 2 Oracle VM Server for SPARC guests running on separate SPARC T5-2 servers each using paravirtualized I/O is 27% faster than between two Red Hat 6.1 guests hosted with a popular virtualization solution on separate x86 based servers each through a paravirtual I/O interface. TCP network latency between two Oracle VM Server for SPARC guests running on separate SPARC T5-2 servers each using direct I/O is 53% faster than between two Red Hat 6.1 guests hosted by a popular virtualization soltuion on separate x86 based servers each using direct I/O. The results for Oracle VM Server for SPARC compared to a popular virutalization solution on UDP network latencies are very similar to the TCP network latencies: UDP network latency between two Oracle VM Server for SPARC guests running on separate SPARC T5-2 servers each using paravirtual I/O is 20% faster than between two Red Hat 6.1 guests hosted with a popular virtualization solution on separate x86 based servers each using paravirtual I/O. UDP network latency between two Oracle VM Server for SPARC guests running on separate SPARC T5-2 servers each using direct I/O is 45% faster than between two Red Hat 6.1 guests hosted with a popular virtualization solution on separate x86 based servers each using direct I/O. TCP and UDP network latencies between two Oracle VM Server for SPARC guests running on separate SPARC T5-2 servers each using SR-IOV were significantly less than when using paravirtual I/O *. Terminology notes: VM – virtual machineguest – encapsulated operating system instance, typically running in a VM.direct I/O – network hardware driven directly and exclusively by guestsparavirtual I/O – network hardware driven by hosts, indirectly by guests via paravirtualized driversSR-IOV – single root i/o virtualization; virtualized network interfaces provided by network hardware, driven directly by guests. LDom – logical domain (previous name for Oracle VM Server for SPARC)
  • 4 new products have joined Exadata and Exalogic in the Engineered Systems family. These new products adhere to the same technology principles as Exadata and Exalogic, and extend the Engineered Systems’ value proposition. We have been in this business delivering Engineered Systems since 2008 with the introduction of Exadata followed closely by Exalogic. The success of these products has been trulyamazing – outpacing even our goals for adoption. We have over 1200 systems sold to date and expect that number to be 4000 later this year. Exalogic has already surpassed Exadata as the fastest growing product in Oracle’s history and the demand for our new products leads us to believe we will see even greater adoption of our products as they were designed to be “Better Together”.With all of our products the deployment time is minimized, manageability is maximized, the lowest total cost of ownership in comparison to our competitors is delivered to you, implementation risk is minimized, and as always you have one single point of contact for support. These core principles apply to our existing products, our new products, and will certainly apply to the innovation we continue to deliver.
  • As a simple and high-level overview, SuperCluster can be thought of as a combination of Exadata and Exalogic.
  • SC datasheet is at http://www.oracle.com/us/products/servers-storage/servers/sparc-enterprise/t-series/sparc-supercluster-ds-496616.pdf
  • Dynamic Domains isolate the hardware.OVM for SPARC isolates the OS.Zones isolate the process.
  • The new release of Oracle SuperCluster software features several significant enhancements: Greater configuration flexibility, including the ability to configure multiple domains of any type Full support for Solaris zones in all domains, including Database domains. This allows multiple RAC clusters to be configured in a single Database domain Greater flexibility around CPU and memory configuration More useable disk space for zone root file systems
  • Multiple domains of any type can be configured in each T5-8 node, including multiple Database domains. If no domain types other than Database Domains are present, the SuperCluster will operate much like a SPARC version of Exadata. The control domain must boot Solaris 11, so up to 7 Solaris 10 domains are possible per T5-8 node.The Exadata Storage Servers are managed directly from the Database Domains. The disks and flash storage associated with Exadata Storage Servers are available only to Database Domain database instances – they can not be used for general-purpose storage.The ZFS Storage Appliance offers shared storage to all domains on a SuperCluster. The way it is configured depends on the type of domain.Exalogic software runs in a Solaris 11 Application Domain, and the ZFS Storage Appliance is appropriately configured in Solaris 11 Application Domains to run Exalogic software.Fiber Channel HBAs can be added to any type of domain. SAN support on SuperCluster is the same as for T5 servers generally.
  • Key points to highlight:Initial products offered will have full configs – later in 2013 will allow lower mem densitiesNew hot plug IO carriers – different than EMs in T5-4 – allow use of standard LP cards and F40 flash acceleration
  • Comparable to 10,000 disks on 100 array frames20X more writes than previous Exadata version
  • Comparable to 10,000 disks on 100 array frames20X more writes than previous Exadata version
  • While not high in IOPS due to a single tray, it is redundant with dual controllers.
  • Manageability through Ops CenterTransforming Complexity Into SimplicityOracle handles it; doesn’t become your problemIncluded with Oracle Premier supportNo financial barrier to effective managementAlways there, allows Oracle to leverage it to deliver simplicitySimple and Flexible ManagementManages all Oracle SuperCluster componentsSupports multiple levels of virtualizationDomains based on Oracle VM Server for SPARCOracle Solaris Zones and Oracle Solaris ContainersOps Center is included with every SuperCluster. Ops Center simplifies monitoring of SuperCluster and provides Oracle with a foundation to build upon for future manageability enhancements.
  • Oracle hardware and software are not only engineered to work together, they are engineered to be maintained, updated, and supported together. We are uniquely qualified to provide optimized performance at every level of the integrated stack,delivering the essential services and resources your business needs to maintain high availability, increase operational efficiency, and gain competitive advantage.Oracle Premier Support provides fully integrated system support with a single point of accountability… 24/7 support with access to Engineered Systems experts 2 hour onsite response Updates, upgrades and support for the Oracle operating system, database and integrated server and storage hardware. Access to My Oracle Support portal which contains a 1 million article database and many, many proactive tools to help you keep systems running at peak performance Oracle Automated Service Request – where your system phones home to Oracle to let us know if there is a problem with the hardware…and now, qualifying customers can also receive the enhanced coverage of Oracle Platinum Services for no additional cost.Oracle Platinum Services is a special entitlement under Oracle Premier Support, delivered at no additional cost.It’s exclusively available on Oracle Exadata, Exalogic and SuperCluster based on certified configurations.It provides 24/7 Oracle remote fault monitoring Backed by extremely fast response times:5 Minute Fault Notification15 Minute Restoration or Escalation to Development30 Minute Joint Debugging with Development And, quarterly patching deployed by OracleOracle Platinum Services takes standard support to a whole new level with additional, no cost services targeted to delivering high availability.To learn more about Oracle Platinum Services go to: www.oracle.com/goto/platinumservices
  • Data Sheet – http://www.oracle.com/us/products/servers-storage/servers/sparc/supercluster/supercluster-t5-8/oracle-supercluster-t5-8-ds-1964480.pdf
  • This is the FIRST slide must be shown with each presentation that show benchmark results!
  • This is the SECOND slide must be shown with each presentation that show benchmark results!

Transcript

  • 1. Hardware and Software Engineered to Work Together Fran Navarro Principal Sales Consultant What’s New with Systems
  • 2. Agenda “What’s New”
  • 3. Agenda “What’s New”  Servidores Oracle  Solaris 11 y Virtualización  Almacenamiento  Sistemas de Ingeniería  SuperCluster
  • 4. SPARC/Solaris at OOW  50+ SPARC, Solaris and SuperCluster Sessions  30+ demos running on SPARC Solaris  New this year: – Dedicated „Systems Venue‟ at Westin Market St. – „Meet the Experts‟ discussions following sessions – Lunches and „Recharging Stations‟ on premise for charging laptops and mobile devices – Latest products on display  For all the details: Focus on Oracle Servers New Systems Venue
  • 5. SPARC/Solaris at OOW  Larry Ellison‟s Welcoming Keynote, Sunday night  John Fowler/Thomas Kurian Keynote, Tues. 8am  John Fowler on Engineered Systems (SuperCluster), Tues., 10:30 am  Masood Heydari, SPARC Systems Roadmap and Update, Mon., 1;45 pm  Markus Flierl, Solaris Strategy and Update, Mon. 12:15 pm Executive Session Highlights
  • 6. 6 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle Servers Built with the world’s fastest processor with 17+ world record benchmarks Millions of hours of end-to- end testing with Oracle software Most scalable systems in the world Best Performance. Best Value. Cloud Built in. SPARC
  • 7. 7 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Investing in Silicon Innovation An Accelerated Pace of Engineering Execution March 26, 2013 March 26, 2013 This Week
  • 8. 8 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. WorseBetter Historical Economics of SMP Near Linear Pricing $/UnitofPerformance T5-4 $147,992 T5-8 $268,314 M6-32 $1,209,943 T5-2 $67,042 IBM Power 750 POWER7+ $204,982 IBM Power 780 POWER7+ $2,101,370 IBM Power 795 POWER7 $6,491,183 IBM Power 740 POWER7+ $101,571 2 Socket 4 Socket 8 Socket 32 Socket
  • 9. 9 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. WorseBetter Near Linear Pricing $/UnitofPerformance T5-4 $147,992 T5-8 $268,314 M6-32 $1,209,943 T5-2 $67,042 IBM Power 750 POWER7+ $204,982 IBM Power 780 POWER7+ $2,101,370 IBM Power 795 POWER7 $6,491,183 IBM Power 740 POWER7+ $101,571 2 Socket 4 Socket 8 Socket 32 Socket Oracle: Re-engineering the Economics of SMP
  • 10. 10 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Worse Near Linear Pricing $/UnitofPerformance 2 Socket 4 Socket 8 Socket 32 Socket T5-4 $147,992 T5-8 $268,314 M6-32 $1,209,943 T5-2 $67,042 2 Socket 4 Socket 8 Socket 32 Socket
  • 11. 11 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. ACQUIRE 2010 FOCUS 2011 COMPETE 2012 ACCELERATE 2013 IBM SPARC SPARC T-Series SPARC SPARC x86 Investing in Silicon Leadership Oracle 100% performance each generation IBM Power & x86 30–50% performance each generation Next Generation Oracle SPARC Processors X86 & IBM: incremental improvements OPTIMIZE FUTURE
  • 12. 12 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. ACQUIRE 2010 FOCUS 2011 COMPETE 2012 ACCELERATE 2013 Investing in Silicon Leadership IBM SPARC SPARC T-Series SPARC SPARC x86 IBM Power & x86 30–50% performance each generation Oracle 100% performance each generation IBM Power & x86 30–50% performance each generation OPTIMIZE FUTURE M7/T7 M8/T8  M7/T7 – Running in lab now – Deep Software in Silicon – Step function in performance  M8/T8 – New core
  • 13. 13 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. The Ultimate Software Optimization: Hardware Moving Oracle Database & Java Software Functions into Hardware Software in Silicon  Database query acceleration  Java acceleration  Application data protection  Data decompression
  • 14. SPARC T5-2 SPARC T5-4 SPARC T4-1B SPARC T4-1 SPARC T4-2 SPARC T4-4 SPARC T5-2 SPARC T5-8 Best Enterprise Portfolio Entry Level Mid-Range High-End SPARC M5-32 New – M6 SPARC M6-32
  • 15. 15 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle Systems Execution Strategy Focused and Leveraged: Building a Complete Portfolio T4: 8 Cores, 4MB$ 2.85-3.0Ghz T5: 16 cores, 8MB$ 3.6Ghz M5/M6: 6/12 Cores, 48M$ 3.6Ghz SINGLE INNOVATIVE CORE HIGH PERFORMANCE PROCESSORS HIGHLY RELIABLE AND SCALABLE SYSTEMS THE MOST RELIABLE, SCALABLE AND SECURE OPERATING ENVIRONMENT INTEGRATED, TESTED, AND OPTIMIZED FOR ORACLE ENTERPRISE SOFTWARE M5-32 T4-1 T4-2T4-1B T5-2 T5-4 T5-8T5-1B T4-4 S3 Core 8 threads  Enterprise Manager 12c  Enterprise Manager OpsCenter  Oracle Solaris  Zero Overhead Virtualization - Oracle VM Server for SPARC - Oracle Solaris Zones  ILOM M6-32
  • 16. 16 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. T5-8 SPECjEnterprise: Enterprise Java Leadership World Record virtualized (1 server: 1VM for App & 1VM for DB 12c) 3.4x 4.4x 8.8x 2.6x 3.2x 6.9x 1 1 1 Perf HW+SW $/perf server $/perf T5-8 8ch 5:3 new T5-8 8ch 4:4 Power7+ 8ch 4:4 Oracle’s Advantage App + DB Server Processor EjOPs Chip App:DB Oracle T5-8, LDoms 3.6 SPARC T5 36,571.36 5 App : 3 DB Oracle T5-8, Zones 3.6 SPARC T5 27,843.57 4 App : 4 DB IBM Power 780, LPAR 4.42 Power7+ 10,902.30 4 App : 4 DB  SPARC T5-8 Oracle VM for SPARC (LDoms 5 App:3 DB) 3.4x faster than IBM Power7+ Power 780 (4 App:4 DB) – SPARC T5-8 achieved 35,571.36 EjOPS – Virtualization used to balance #chips for Application & Oracle Database 12c  Oracle Database 12c & Weblogic Application New!
  • 17. 17 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. 3TB TPC-H T5-4: Data Warehouse Leadership • 3TB TPC-H: SPARC T5-4 is 2.1x faster than 8-chip Power7 • SPARC T5: 4.3x faster per chip, 1.6x better $/perf, & faster per core than IBM • SPARC T5-4 6% faster M9000-64, Over 4x better price/performance World Record Data Warehouse single-system performance 3TB TPC-H chip,core Database QphH $/QphH Avail SPARC T5-4 4, 64 Oracle 11g 409,722 $3.94 09/24/13 Oracle M9000 64, 256 Oracle 11g 386,478 $18.19 09/22/11 SPARC T4-4 4, 32 Oracle 11g 205,792 $4.10 05/31/12 IBM Power7 780 8, 32 Sybase 192,001 $6.37 11/30/11 10TB TPC-H chip,core Database QphH $/QphH Avail HP DL980 G7 8, 80 SQLserver 158,108 $6.49 4/12/13 See benchmark disclosure slide Recently published 10TB on HP x86 (TPC does not compare different size databases)
  • 18. 18 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. T5-8 TPC-C Benchmark: OLTP DB Leadership • World record single-system TPC-C 8,552,523 tpmC • SPARC T5-8 delivers 3.1M IOPS from storage • SPARC T5 2.4x faster per chip performance than IBM configuration • IBM 3-node p780 (10.3M on 24 total chips), Oracle has 2.5x better $/tpmC • SPARC T5 5x better response time than IBM p780 3-node (New Order 90%) World Record OLTP single-system performance Server so,core Processor SW tpmC $/tpmC Oracle SSC 27n x 4ch SPARC T3 Oracle 11g 30.2M $1.01 IBM Power 780 3n x 8ch 3.86 Power7 DB2 9.7 10.3M $1.38 Oracle T5-8 8, 128 3.6 SPARC T5 Oracle 11g 8.55M $0.55 IBM p595 32, 64 5.0 Power6 DB2 9.5 6.0M $2.81 Oracle X2-8 (X4800) 8, 80 2.4 Xeon E7 Oracle 11g 5.0M $0.94 Cisco UCS 2, 16 2.9 E5-2690 Oracle 11g 1.6M $0.47 IBM Power 780 2, 8 4.14 Power7 DB2 9.5 1.2M $0.69 See benchmark disclosure slide
  • 19. 19 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. SPARC T5-2 SPECjbb2013 MultiJVM  SPARC T5 81,084 Max jOPS 39,088 Crit jOPS – SPARC T5 1.3x faster than Cisco E5-2697 v2 – SPARC T5 1.9x faster than HP E5-2690  IBM Power7+ only publishes SPECjbb2005, SPEC retiring old benchmark in Oct 1, 2013 World Record 2-chip on new realistic enterprise Java benchmark 0 10,000 20,000 30,000 40,000 SPARC T5-2 Cisco B200 M3 UCS C220M3 HP DL980 XeonE7 Westmere XeonE5-2697v2 SPECjbb2013 per-chip SPARCT5 Server MultiJVM Processor # chip Max jOPS Crit jOPS HP DL980 G7 2.4GHz E7-4870 8 106,141 23,268 SPARC T5-2 3.6GHz SPARC T5 2 81,084 39,088 Cisco B200M3 2.7GHz E5-2697 v2 2 62,393 23,505 X4-2 2.7GHz E5-2697 v2 2 52,664 20,553 Cisco C220M3 2.9GHz E5-2690 2 41,954 16,545 XeonE5-2690 SandyBridge New! IvyBridgeDDR3-1866
  • 20. 20 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. SPARC T5 Leading Security Performance Dramatically faster for widest variety of security modes  No published Power7+ security performance, Power7+ lacks AES-CFB mode ?!? See benchmark disclosure slide Server GHz #chip Crypto Uses Perf Advantage SPARC T5-2 3.6 2-chip AES-CFB-128 Oracle DB, block data 68,694 MB/s 3.9x faster X86 E5-2690 2.9 2-chip AES-CFB-128 Oracle DB, block data 17,823 MB/s - SPARC T5 3.6 1-chip SHA256-1024 Banking, block data 24,699 MB/s 29.9x faster X86 E5-2640 2.5 1-chip SHA256-1024 Banking, block data 827 MB/s - SPARC T5 3.6 1-chip RSA-2048 Handshake for Banking, network,… 25,614 op/s 8.4x faster X86 E5-2640 2.5 1-chip RSA-2048 Handshake for Banking, network,… 3,053 op/s -
  • 21. 21 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Unprecedented Performance and Scalability Oracle M6: Terabyte Scale Computing 384 cores, 3,072 threads Hardware Optimized Virtualization 32 Terabytes Memory 3TERABYTES PER SECOND SYSTEM BANDWIDTH 1.4TERABYTES PER SECOND MEMORY BANDWIDTH 1TERABYTE PER SECOND I/O BANDWIDTH
  • 22. 22 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle Solaris and Oracle Linux The World‟s Best UNIX and the World‟s Best Linux Designed for the Cloud Built for Scale Runs Oracle Software Best
  • 23. 23 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle Solaris 11 Mission Critical Meets Cloud Solaris 11 Highly Available, Secure Platform for Enterprise Apps  Predictive self healing  ZFS data integrity  Low overhead snapshots  End to end encryption  Application Clustering  Compliance reporting  DTrace observability Large-scale Cloud Management  Zero overhead Server, Storage, Network virtualization  Immutable zones  Fast, fail safe life cycle management  Comprehensive cloud management solution
  • 24. Availability End to End Security Performance Oracle Solaris 11. Oracle Database. Oracle Java. Engineered to Work Together Compliance
  • 25.  New Solaris/RAC Kernel Mode Acceleration  Allows Solaris to respond directly to lock requests  Saves lock state in memory shared by database and kernel Best UNIX for Oracle RAC New with Solaris 11.1 30-40% lower latency lock grants Up to 20% higher throughput Consistent, predictable RAC performance Solaris RAC Database Solaris RAC Database
  • 26. 26 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. New Virtual Memory System The Predictor  Page Requests over 30 seconds  Analyzer evaluates information and determines action to take  Action Engine creates internal threads to do the work Sampler Analyzer Action Engine Befor e Afte r More scalable applications – especially memory intensive apps
  • 27.  New Optimized Shared Memory interface (OSM)  Works with Oracle DB Automatic Memory Management (AMM)  Dynamic, NUMA- aware granule based shared memory Increased Availability New Database Technology Dynamically resize your Database SGA online without a reboot Bring Oracle Database instances up 2x faster Oracle DB SGA
  • 28. 28 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Solaris Large Memory Database Startup • 21.5x faster upgrading to Solaris 11.1 and Oracle 12c • 21.5x faster for 30 TB SGA and 8x faster for 3TB SGA • 4.3x faster upgrading Solaris only: Solaris11.1 from Solaris11.1 SRU10 • 5.3x faster upgrading Database only: Oracle Database12c from Oracle Database 11g One of the many Solaris optimizations for the Oracle Database 0 5 10 15 20 S11.1+11g S11.1 SRU10+11g S11.1 SRU10+12c Speedup 2800 sec 650 sec 130 sec
  • 29.  Added DTrace I/O Event Tracing  Tracing info loaded in V$ views for queries  Enables DBAs and Oracle support to quickly resolve I/O related escalations Unique Oracle Database I/O Observability New Database Technology v$kernel_io_outlier TIMESTAMP IO_SIZE IO_OFFSET DEVICE_NAME VARCHAR2(513) PROCESS_NAME VARCHAR2(64) TOTAL_LATENCY SETUP_LATENCY … Quickly resolve I/O issues Optimize your Database I/O performance
  • 30. 30 Copyright © 2013, Oracle and/or its affiliates. All rights reserved.  BOTH row and column in-memory formats for same data/table  Simultaneously active and transactionally consistent  100X Faster Analytics & reporting: column format  2X Faster OLTP: row format Oracle Database 12c Breakthrough In-Memory Database Technology Column Format Memory Row Format Memory AnalyticsOLTP Sales Sales
  • 31.  Zones support for Exadata stack on SPARC SuperCluster  RDSv3 Exclusive IP-typed Zones  Advanced IPoIB packet security  InfiniBand Limited membership  Pkey support  High speed, secure low latency database deployments Secure Multitenant Database Consolidation New in Solaris 11.1 Simplify and consolidate databases platforms Domain Architecture Optimized for Application W orkloads T4-4 Node 1 Oracle Solaris 10 Oracle Solaris 11 DB Domain GP Domain Zones Solaris Zone Solaris Zone Solaris Zone Solaris Zone Zones Zones InfiniBand Network EXADATA STORAGE EXADATA STORAGE EXADATA STORAGE ZFS STORAGE APPLIANCE T4-4 Node 1 Oracle Solaris 10 Oracle Solaris 11 DB Domain GP Domain Zones Solaris Zone Solaris Zone Solaris Zone Solaris Zone Zones Zones
  • 32. 32 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. CPU Full MT-hot kernel, scales to 100s of cores and 10,000s of HW threads Support for Critical Threads features in T4 chip 5x performance improvement of high-resolution timer Multi-processing and multi-threading support for next gen database Memory Large Page support Optimized Shared Memory (OSM) NUMA I/O Framework Fast DB Restart Latency-aware kernel memory allocator (x86, SPARC) Re-architecture of Virtual Memory sub-system Userland Fast-Memory Registration and Shared Protection Domain File System Userland file system for DB, Oracle File Server support I/O uDAPL, RDSv1, RDSv3, SDP: Support for low-latency Infiniband protocols Direct I/O with concurrent writes Exclusive-IP zone support for RDSv3 to support DBaaS Dynamic reconfiguration for IB HCAs Solaris Optimizations for Oracle RDBMS The Tip of the Iceberg Key: In Solaris 11 New in Solaris 11.1
  • 33. 33 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Observability Enhanced observability for segmentation faults Read-out of libdtrace by next gen database Reliability and Availability Dynamic reconfiguration notifications for DB for resources rebalancing FMA callback for bad hardware Performance Improved PGA performance Kernel lock acceleration for Oracle RAC Message Passing Co-processor Remote Memory Access (RMA) Multi-tenancy Zones: Secure isolation, lowest latency virtualization Security Transparent crypto off-load More Solaris Optimizations for Oracle RDBMS The Tip of the Iceberg Key: In Solaris 11 New in Solaris 11.1
  • 34. 34 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Java Mission Control Visualizing DTrace data
  • 35. 35 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. CPU User-level high resolution timer support WLS scalability, Single-thread mode smt pause() to optimize busy waits in the JVM Java-optimized Solaris scheduling class Fused compare-and-branch with no delay slot New block initializing store (BIS instruction) Memory Large Page support by JVM T4 2GB pages for Java performance I/O SDP: Support for low-latency Infiniband protocol HA for SDP Security Integration with Solaris crypto offload engines (Java 7u4) Zones support for SDP Zones: Secure isolation, lowest latency virtualization Observability DTrace plugin in Java Mission Control Solaris Optimizations for Java The Tip of the Iceberg Key: In Solaris 11 New in S11.1
  • 36.  Auto-offloading of CPU-intensive security functions onto T4 crypto accelerator  Hardware acceleration for Oracle DB Advanced Security Transparent Data Encryption (TDE)  Turbo charged JRE security End to End Data Encryption Solaris 11 and SPARC T4 No compromise, No tradeoffs No additional costs Use encryption pervasively to reduce risk Storage Solaris ZFS File System Oracle Fusion Middleware Weblogic SOAP SSL Oracle Database Storage Tablespace Encrypt SSL Unified Key Management IPsec (VPN) SSL SSLSSL SSL  ZFS Filesystem Crypto 4x faster vs. x86  10Gb/s SSL T4 uses 50% less threads to saturate 10GbE  OpenSSL 4.3x faster single-thread security vs Power7
  • 37. 37 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Powering Oracle Engineered Systems, Appliances Exadata Exalogic SPARC SuperCluster ZFS Storage Appliance Oracle Solaris 11
  • 38. Oracle Solaris 11 Built for Cloud Infrastructures
  • 39. Oracle Solaris 11: First Fully Virtualized OS Reduce costs. Increase agility. Infrastructure as a Service. Server Web Tier Application Tier Database Tier Network Storage Finance Dataset Finance Zone HR Dataset HR Zone Sales Dataset Sales Zone
  • 40. 40 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Simplified Cloud Deployments Engineering Out Complexity Fool-proof updates with Boot Environments and IPS Packaging Active BE Active BE New BE Old BE Updated BE Rapid provisioning with Automated Installer AI Server DHCP Server Net config AI address Rapid development, test and deployment of Zones
  • 41. 41 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Fast and Fail Safe Lifecycle Management 6:00 Start UpdateMaintenance window 6-7pm 6:04 reboot up and running again New Security Patch 6:01-6:02 New boot environment created, updates downloaded and applied Never brick your system again. Fail safe rollback: Automatically boots last environment Back in Service in 6 Minutes!X 4 6:00-6:01 Dependency checks, patch/update planning
  • 42. 42 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Simple, risk-free updates with Solaris 11  Multi-tenant cloud environment – Delegated administration allows SAP and database administrators to safely control their own Zones without access to other Zones and services on the systems – Database and Applications per zone – HA SAP and Oracle Database Zone Clusters  Automated repository updates – Both Solaris 11 and Solaris Cluster 4.0 local repositories are automatically updated every week Public Sector Customer example “Because acquiring new updates with Solaris 11 is so easy it’s now automatically done on a weekly basis” Local IPS repo updated weekly
  • 43.  Edge Virtual Bridging – Making the network “virtualization aware” – Offload bandwidth control on switches  Data Center Bridging – Convergence of storage and networking – Enabler for low latency RDMA over Ethernet – Multiple lanes of traffic on the same link Software Defined Networking New with Solaris 11.1 Save cost by leveraging Ethernet for storage Prioritize bandwidth for key applications
  • 44. 44 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Software Defined Networking Cloud Networking. Built-in. New with Solaris 11.1  Edge Virtual Bridging - Making the network virtualization- aware - Offload bandwidth control on the switches - Centralized management of virtual NIC profiles  Simplify network management  Better bandwidth isolation  Lower CPU overhead on your server  Drive up utilization of network resources Your Advantage
  • 45.  Federated File System support for a single unified namespace  A collection of machines can be bound into a FedFS unified namespace using a private location database  Clients are seamlessly redirected when looking up or modifying (NFS) data. Cloud-Scale Data Management New with Solaris 11.1 Share data easily across cloud clients
  • 46.  Zone updates now execute in parallel  Time savings exponential across datacenter Fast Zone Updates New with Solaris 11.1 4x less downtime during maintenance windows 0 10 20 30 40 Solaris 11.1 Solaris 11 Minutes Updating a T4 System with 20 Zones Increase consolidation ratios without increasing maintenance windows
  • 47.  Zones on shared storage  Zones framework automatically manages • Configuration/un-configuration of storage services • Attach/detach of storage devices • zpool creation, import, export • For SAN and iSCSI Easy Mobility for Zones New with Solaris 11.1 Move zones around between systems quickly and easily Z o n e B Z o n e A Z o n e C
  • 48.  Safe deployment of mission critical Solaris 10 applications in Solaris 10 Zone Clusters  More control and flexibility with support of exclusive IP  Improved resource and priority management for zone clusters  Simplified Zone cluster set-up through configuration wizard Zone Clusters for Solaris 10 Applications New with Solaris Cluster 4.1 Solaris 11 Zone Solaris 11 Zone Solaris 10 Zone Solaris 10 Zone Solaris 11 Zone Solaris 11 Zone Web Tier Application Tier Database Tier Protect application investment Take advantage of the latest server platforms
  • 49. 49 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Driving Cloud Infrastructure Innovation Security Immutable Zones Deployment Linked Images, Parallel Zone Updates, AI Integration, IPS integration, Package minimization Network Virtual NICS (VNICS), Automatic VNICs, Bandwidth Control, Exclusive IP by Default, Network Observability, Infiniband Enhancements, Data Center Bridging, Edge Virtual Bridging Storage Zone Boot Environments, ZFS Datasets, Recursive ZFS send, NFS Server in a Zone, Zones on Shared Storage, Lofi improvements Migration Pre-flight Checker, Solaris 10 Zones on Solaris 11, Zones install update for V2V archives Management System Configuration, Clean Shutdown, Hung Zones, Zones “unavailable” state, Zonestat, Per Zone fsstat, Zones RAD Module Web Tier Application Tier Database Tier Finance Dataset Financ eZone HR Dataset HR Zone Sales Dataset Sales Zone Solaris 11, Solaris 11.1
  • 50. Total Cloud Control: Solaris IaaS with Complete Lifecycle Management Integrated Cloud Stack Management Business-Driven Application Management Self-Service IT | Simple and Automated | Business Driven
  • 51. Oracle Solaris 11 In Action
  • 52. 52 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Why Oracle Customers Choose Solaris 1. More Reliable: If it must run, it‟s on Solaris 2. Faster: World record leader for enterprise applications 3. More Scalable: Engineered for next generation systems. Invest for the future 4. More Secure: Deeply integrated security. Trusted labeled configurations 5. Built-in Virtualization: Maximum resource utilization. Faster time to market 6. Engineered for Oracle: Best performance. Fastest deployments 7. SPARC and x86: Choice of industry‟s leading enterprise architectures 8. More Applications: 11,000+ applications. 5x more than AIX. 9. Engineering out Complexity: Self managing systems. Simplified operations 10. More Compatible: Preserves your investments. Avoids costly migrations 11. Trusted Vendor: One phone call Top Reasons for Investing in Oracle Solaris Systems
  • 53. 57 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Built In, Zero Cost The Oracle Virtualization Advantage Enterprise Class Virtualization for SPARC and x86 Systems Oracle App Support Rapid App Deployment
  • 54. 58 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. SPARC Solaris Investment Protection  Preserve existing investment – Move older Oracle Solaris environments forward – P2V and V2V tools make it easy  Applications since 1997 guaranteed to work – Plus source code compatibility for developers Safe, Easy Consolidation On SPARC T5 and SPARC T4 Servers Oracle VM Server for SPARC Oracle Solaris 10Oracle Solaris 11 Solaris 11 Zone Solaris 10 Zone Solaris 8 Zone Solaris 9 Zone Solaris 10 Zone
  • 55. 59 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle VM Server for SPARC The Virtualization Platform combining the best of Oracle Solaris and SPARC for Your Enterprise Server Workloads Isolated OS and applications in each logical (or virtual) domain Firmware-based hypervisor Each logical domain runs in dedicated CPU thread(s) Oracle SPARC Server Oracle Solaris 10 Oracle Solaris 11 Database Domain Oracle Solaris 10 Oracle Solaris 11 Database Domain Oracle Solaris 10 Oracle Solaris 11 Database Domain Oracle Solaris 10 Oracle Solaris 11 Database Domain GP Domain GP DomainGP Domain GP Domain SPARC Hypervisor
  • 56. 60 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. SPARC T5 Virtualized OLTP Database – 2VMs Cloud: T5 & Oracle VM for SPARC 3.2x faster than virtualized x86 0 100 200 300 400 500 600 700 800 900 1,000 SPARC T5 Xeon 2.9GHz E5-2690Xeon 3.3GHz X5680 PerchipOLTPKTransactions Virt 23% Loss Virt only 0.4% loss Native 29% Loss Virtualized OLTP DB vs. native performance per chip See benchmark disclosure slide Native Linux Popular Virt SW 2.9GHz Xeon E5-2690 Linux 11g R2 11g R2 11g R2 11g R2 VM for SPARC SPARC T5 Solaris Solaris vs. 3.2x FASTER OLTP workload based on a real customer database – many 8K IOs Performance continues to decrease as more VMs added New!
  • 57. 62 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle Solaris 11: Efficient CPU Virtualization  Oracle Solaris has insignificant overhead for Oracle VM for SPARC – Oracle Solaris efficiencies lead to better consolidation ratios – Popular x86 virtualization software: 45% performance loss with 4 VMs and 18% performance loss with 2 VMs vs. native RedHat 6.1 – Result on SPARC T5, SPARC T4 uses same software Java application: processor and memory-intensive workload 0 10 20 30 40 Solaris11 Oracle VM (SPARC) 2VMs Popular virtualization (x86) 2VMs Popular virtualization (x86) 4VMs % perf loss Results vs. native 18% loss with only 2VMs LDoms much less than 0.1% 45% loss with only 4VMs See benchmark disclosure slide
  • 58. 64 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle Solaris 11: Efficient Network Virtualization  Efficient Oracle virtualization allows applications to meet response time SLAs  Direct IO Network Latency of Oracle Solaris11/SPARC T5 2x better than a popular virtualization software and RedHat6.1 on x86 – Oracle Solaris Zones, Oracle VM for SPARC, & SR-IOV provide near-native latency Oracle has less network latency than popular x86 virtualization 0 40 80 120 160 x86 native Solaris11 Oracle VM SPARC, direct-io Popular virt x86, direct-io Solaris11 Oracle VM SPARC, virt-io Popular virt x86, virt-io TCP usec UDP is similar to TCP Popular virtualization software has long latencies for direct IO & Virt IO (x86 in grey)
  • 59. 65 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle best on Oracle  Oracle Java SPECjbb2013 1.9x faster than Xeon E5  Oracle TimesTen 2.4x faster than 2.9GHz Xeon E5  Oracle OLAP 1.6x faster than 2.4GHz Xeon E7  Oracle JD Edwards EnterpriseOne batch 2.7x faster than Power7  Oracle JD Edwards EnterpriseOne online+batch 6.1x faster than Power7  Oracle Siebel CRM 1.9x faster than Power7  Oracle Internet Directory 1.9x faster than Xeon  Oracle Financial Services FLEXCUBE 4x faster than SPARC T4  Oracle Communications ASAP 2.4x faster than SPARC T4  Oracle ZFS Filesystem Cryptography 3.4x faster than Xeon E5  Oracle Cryptographic Framework 3.9x faster than Xeon E5  Oracle Database 30x scaling on M5-32 Oracle‟s hardware co-designed to be best with Oracle‟s software See benchmark disclosure slide
  • 60. 66 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Investing in Building the Best Hardware in the World Engineered Together at Every Layer For Your Success Storage Networking Servers
  • 61. 67 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle ZS3 Storage Application Engineered Storage Integrated Analytics Real-time visualizations cuts troubleshooting times by 50% Optimized for Oracle Software OISP cuts database tuning times by 65%; HCC delivers 10-50X compression World-record performance and leading price performance Extreme Performance
  • 62. 68 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. ZS3: World Record Performance 4X Better Price-performance for Financial Processing, Database Queries, and Video Streaming Applications IBM DS8870 15,423 SPC-2 MBPS TM $134.2 SPC-2 Price Performance TM VSP 13,147 SPC-2 MBPS TM $95.3 SPC-2 Price Performance TM P9500 XP 13,147 SPC-2 MBPS TM $131.2 SPC-2 Price Performance TM 17,224 SPC-2 MBPS TM $22.5 SPC-2 Price Performance TM ZS3-4 Results as of September 10, 2013, for more information go to www.storageperformance.org/results SPC-2. Results for Oracle ZFS Storage ZS3-4 are 17,244.22 SPC-2 MBPS™, $22.53 SPC-2 Price-Performance. Full results at www.storageperformance.org/results/benchmark_results_spc2#b00067. Results for IBM DS8870 are 15,423.66 SPC-2 MBPS, $131.21 SPC-2 Price-Performance. Full results at ww.storageperformance.org/results/benchmark_results_spc2#b00062. Results for Hitachi VSP are 13,147 SPC-2 MBPS, $95.38 SPC-2 Price-Performance. Full results at www.storageperformance.org/results/benchmark_results_spc2#b000600. Results for HP P9500 XP Disk Array are 13,147.87 SPC-2 MBPS, $88.34 SPC-2 Price-Performance. Full results at www.storageperformance.org/results/benchmark_results_spc2#b00056.
  • 63. 69 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Hybrid Columnar Compression (HCC) Store Less Data AND Run Faster  Up to 50x space reduction  Average 5x faster queries  Only available on Oracle storage  Increases performance for most data warehouse and data protection Retail Data Warehouse Example 735GB Uncompressed With HCC 38GB94% Less 8x Faster 2 Hours, 22 Min, 44 Sec 16 Min, 50 Sec
  • 64. Without OISP With OISP Two shares: logfile and datafile NFS Server OISP Tunes Logfile share Datafile share NFS Server Multiple shares, each with its own Record Size and LogBias setting /mnt/dbname/redo (Record Size, LogBias) /mnt/dbname/control (Record Size, LogBias) /mnt/dbname/pfile (Record Size, LogBias) /mnt/dbname/datafile (Record Size, LogBias) /mnt/dbname/tempfile (Record Size, LogBias) /mnt/dbname/chgtrack (Record Size, LogBias) /mnt/dbname/backup (Record Size, LogBias) /mnt/dbname/logfile (OISP sets Record Size, LogBias) redo /mnt/dbname/datafile (OISP sets Record Xize, LogBias) control pfile datafile tempfile chgtrack backup OS8 | OISP: Auto Tuning of Record Size, LogBias
  • 65. 71 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle Virtual Networking Wire Once Infrastructure for the Software Defined Data Center Oracle Fabric Interconnect 100X faster server management, 70% fewer cables and cards Oracle Virtual Compute Appliance Power-to-production in under an hour Reduces network infrastructure complexity by over 70% Software Defined Networking
  • 66. 72 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle Engineered Systems Mission: Simplify Your Environment Extreme Performance Low Risk Deployment Breakthrough Efficiency
  • 67. 73 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. ENGINEERED SYSTEMS: HARDWARE & SOFTWARE Exadata Database Machine Exalogic Elastic Cloud Exalytics Database Backup Logging and recovery Appliance Big Data Appliance SPARC SuperCluster Oracle Virtual Compute Appliance RDBMS storage compression and database parallelization via “Exadata Storage Servers” Extreme - performance I/O connecting large amount of compute power and memory Huge amount (1TB/4TB) of contiguous memory for large data sets Massively scalable database backup, Assured protection from disk to tape, replica and cloud Massive disk storage array with high- bandwidth I/O for loading „big‟ data SPARC servers, high-performance I/O and Exadata storage servers in one rack “Wire once”, software-defined infrastructure system designed for rapid deployment IaaS NEW!NEW! NEW! Adding In memory database
  • 68. 74 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle Exadata Database Machine The Best Machine for OLTP, Data Warehouse, and Consolidation Exadata Smart Scan Improve query performance by 10X Hybrid Columnar Compression Reduce the size of database storage requirements by up-to 3-5X Smart Flash Cache Improve query response times by 40%
  • 69. 75 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. The New Exalytics In-Memory Machine T5-8 The world’s fastest processor and the world’s best analytics software  Massive scalability  Tens-of-thousands of BI users  Sub-second response times  Extreme analytics infrastructure consolidation 4TB Memory
  • 70. 76 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. The New Oracle Database Backup, Logging, Recovery Appliance  Real time log shipping: near zero data loss  Fast restore to any time point  Delta-only architecture: minimizes network load  End-to-end visibility: cloud & replica, disk to tape option  Scalable appliance: backs up 1000s databases
  • 71. 77 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. The New Virtual Compute Appliance X3-2  Pre-built system, ready to use with minimal setup  Removes the integration risk for deploying infrastructure  Integrated application provisioning with pre-built templates  Fully virtualized system with built in software defined networking for ultimate flexibility
  • 72. 78 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Compute Appliances Have a Role Within Gartner's Fabric Continuum OVCA Exa-Systems
  • 73. Copyright © 2012, Oracle and/or its affiliates. All rights reserved. Oracle Virtual Compute Appliance X3-2 Hardware Specifications Overview Fabric Interconnect Fabric Interconnect Compute Nodes Compute Nodes Mgmt Nodes Management Storage InfiniBand expansion InfiniBand expansion Ethernet switch Oracle Sun X3-2 Servers • 2 to 25 nodes • CPU: Up to 400 cores / 800 threads aggregate • Memory: Up to 6.4TB aggregate • Only 3 cables per server, fully redundant • Oracle Sun X3-2 Servers • Oracle Sun X3-2 Servers Oracle Sun ZFS Storage Appliance 7320 • Redundant controllers, RAID storage • Oracle Fabric Interconnect F1-15 • Oracle Fabric Interconnect F1-15 • Oracle Switch ES1-24 • Oracle Sun Data Center InfiniBand Switch 36 • Oracle Sun Data Center InfiniBand Switch 36 NetworkingManagement Four 4x10GbE 40Gb/sServer-to-Server Network Storage
  • 74. Copyright © 2012, Oracle and/or its affiliates. All rights reserved. Oracle Virtual Compute Appliance X3-2 Software Overview Server Virtualization and Guest OSes Server Virtualization Oracle VM Server Virtualization •All major x86 operating systems •Oracle Linux •Oracle Solaris •Microsoft Windows Oracle Virtual Compute Appliance controller • Oracle VM Manager • Oracle SDN Networking Automation & Management• Oracle Fabric Manager
  • 75. 81 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. The New Oracle SuperCluster M6-32 The Ultimate Engineered System:  Highest performance  Most scalable  Extreme consolidation Most flexible: Grow compute and storage independently Designed for the age of in-memory computing
  • 76. 82 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. The New Oracle SuperCluster M6-32  Exadata and Exalogic acceleration  Oracle‟s most flexible virtualization  384 high-performance cores  32 TB industry standard memory  Expandable Exadata Storage Servers
  • 77. 83 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Conceptual View of Oracle SuperCluster Exadata + Exalogic Heritage Exadata Oracle SuperCluster Exalogic Exadata Storage Database Servers ZFS NAS Storage Application Servers
  • 78. 84 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle SuperCluster  Most scalable engineered system  In-memory applications using big memory capacity – Oracle Database12c and applications optimized  Highest consolidation ratios  Best RAS in compute  Modularly grow compute, memory and storage Extending the Product Family  Best Price / performance  High consolidation ratios  Vertical and horizontal scaling  Run database and applications on a single rack  Half Rack and Full Rack SuperCluster M6-32 SuperCluster T5-8
  • 79. 85 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle SuperCluster T5-8  The best system for running databases and applications  Ideal for consolidation and cloud  Best for IBM/HP and SPARC refreshes and new deployments Oracle‟s Fastest Engineered System COMPLETE Servers Storage Software Networking + +
  • 80. 86 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle SuperCluster T5-8 Half Rack - 2 x SPARC T5-8 compute nodes  4 x T5 Processors @ 3.6 GHz  1 TB of memory (64 x 16GB)  8 x 900 GB internal drive (SAS)  4 x Sun Dual 10 GbE SFP+ PCIe 2.0 Low Profile Adapter (2 port)  4 x Sun Quad Data Rate (QDR) InfiniBand PCIe Low Profile HCA (2 port) – 4 x Exadata Storage Servers, either  High Performance (28.8 TB capacity total)  High Capacity (144 TB capacity total) - 1 x Sun ZFS Storage 7320 Appliance - 3 x Sun Data Center InfiniBand Switch 36 - 1 x GbE Management Switch T5-8 Node 2 Solaris 11 DB Domain T5-8 Node 1 Solaris 11 Solaris 11 DB Domain • Valid configuration, but requires custom installation. Exa data Exa data Exa data Exa data InfiniBand Network ZFSSA Solaris 11 Solaris 11 Solaris 11 Solaris 10Solaris 10
  • 81. 87 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. SPARC Virtualization Server Hypervisor Solaris OSSolaris OS Process Process Process HardwareHardware Levels of Isolation Dynamic Domains OVM for SPARC Solaris Zones SuperCluster
  • 82. 88 Copyright © 2013, Oracle and/or its affiliates. All rights reserved.  Layer 1 Virtualization – Domains with zero performance overhead – Any mix of Database Domains and Application Domains  Oracle Solaris 11 or Oracle Solaris 10 for Application Domains  Layer 2 Virtualization – Both Database Domains and Application Domains support Oracle Solaris Zones T5-8 Compute Node T5-8 Compute Node Oracle SuperCluster Virtualization Layered Optimized Virtualization Database Domain 1 Database Domain 2 Application Domain 1 Database Domain 1 Database Domain 2 Application Domain 1 Application Domain 2 DB Zone DB Zone DB Zone Zone Zone DB Zone DB Zone Zone Zone Zone Solaris Cluster or Load Balancer Clusterware
  • 83. 89 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Configuring Oracle SuperCluster Configuration Flexibility • A broad set of configurations – Complete configuration flexibility – Up to 8 LDoms based on the supported domain types – Simply choose the configuration you need • Multiple domains of any type supported in a single node • Zones supported in all domains, including Database Domains – Multiple RAC and/or Single-Instance databases supported per Database Domain • Fine-grained CPU/Memory allocation now supported – 4 cores of CPU, 64GB memory (half rack) or 128GB memory (full rack) • Zone root file systems can now be stored on iSCSI LUNs – Located on the included Sun ZFS Storage 7320 Appliance
  • 84. 91 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. SPARC T5-8 Server  Compute – 4x or 8x SPARC T5 16-core CPU (1024 threads max) – 64x or 128x 16 GB DDR3 DIMMs  I/O and Storage – 16x PCIe 3.0 x8 slots, with PCIe carriers – 4x 10GbE ports – 8x 2.5” SAS 3.0 drives  Availability and Management – RAID 0/1, Hot-swap fans & PSUs – Oracle Integrated Lights Out Manager Service Processor – Oracle Enterprise Manager Ops Center The Industry‟s First Multithreaded Enterprise Datacenter Server for Mission Critical Workloads
  • 85. SPARC T5 Processor • Features • 16 S3 cores, 16-128 Strands @ 3.6Ghz • Single or multi-threaded operation per core • System scalability to 8 sockets • SPARC Core S3 • 1-8 Strand Dynamically Threaded Pipeline • ISA-based Crypto-acceleration • 8MB Shared L3$ • Integrated I/O • Double I/O bandwidth over T5 • 2 x8 Lane PCIe 3.0 @ 8GT/s • System Scalability • 7 Coherence Ports for scalability to 8S • Power Management • Dynamic Voltage Frequency Scaling • Downclock, Overclock
  • 86. 93 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Exadata Storage Servers  Exadata Storage Servers run Oracle Enterprise Linux and Exadata Storage software. They currently consist of the following hardware: – X3-2 with: - 2 sockets Xeon E5-2630L 6 cores @ 2.0 GHz 15 MB L3$ - 64 GB Memory (16 x 4 GB LV 1333Mhz DDR3 DIMMs) - SAS-2 RAID HBA - 12 disks, either 600 GB@15Krpm (High Performance) or 3 TB@7200rpm (High Capacity) - 4 * Sun Flash Accelerator F40 PCIe Cards, total 1.6TB - 1 QDR IB HCA (2 ports)  They can only be used by Database Domains  Four are installed in the half rack config; eight are installed in the full rack config They are the EXACT same storage servers as the Exadata Storage Server X3-2
  • 87. 94 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Key Exadata Innovations + ++ • Hybrid Columnar Compression – 10x compression for warehouses – 15x compression for archives Data remains compressed for scans and in Flash Space Savings Cascade to Copies compress primary DB standby test dev backup uncompressed • Smart Scale-Out Storage – InfiniBand connected servers – Smart Scan query offload • Smart PCI Flash Cache – Transparent cache in front of disk – Accelerates random I/O up to 30x – Quadruples data scan rate
  • 88. 95 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Improved Exadata Storage Server X3-2 Enhanced Smart Flash Cache • New software caches write I/Os in flash memory −20x write improvement −10x write improvement from previous storage servers • Cache is transparent, persistent, and fully redundant 1 Million 8K flash write IOPs from SQL
  • 89. 96 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Improved Exadata Storage Server X3-2 Enhanced X3 Database Machine Over X2 20X More Write Performance 4X Larger Flash Memory 10% to 30% Lower Power 33% More Data Throughput Exadata Smart Flash Write Caching 22 TB of Flash Memory per Rack Up to 3 Kilowatt Reduction per Rack 100 GB/sec running SQL
  • 90. 97 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Exadata Smart Flash Log Accelerate Transaction Response Times using Flash  Uses Flash for Database Logs in a clever way – Flash is fast but has slow outliers – Erase cycles, wear leveling, etc.  Smart Flash Log feature transparently uses Flash as a parallel write cache to disk controller cache – Whichever write completes first wins (disk or flash)  Better response time and more throughput  Uses almost no flash capacity (0.1% of capacity) Default (on left) - Choppy response - High Outliers Smart Flash Log - 3x faster response - Much lower outliers Transaction Response Times Smart Flash Log Enabled Automatic and Transparent
  • 91. 98 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. ZFS Storage Appliance 7320  Provides shared storage for all Logical Domains – Not mounted by default in the Database Domain. Active mounts are established to all other Domains.  Data can only be accessed inside the SC rack. Only external access is via built-in GbE ports used exclusively for DR and data replication.  Two controllers for high-availability  Single disk shelf with 24 drive bays – 60 TB Storage (20x 3 TB SAS disks) – 4x 73 GB of SSD (for write-optimized SSDs Logzillas)  Integrated Flash and Infiniband  Stores quorum device for Solaris Cluster  An additional IB-enabled ZFS SA device can be attached via additional rack with IB ports connected to both IB Leaf switches in the SC rack  Accessible from Database Domain after manual mount – Can be used for RMAN backups or flat file staging
  • 92.  Discover Oracle SuperCluster as a single system  Hardware event interface view of Oracle SuperCluster as a single system  Monitoring and active management tasks separated by role Total Systems Management Oracle Enterprise Manager Ops Center 12c
  • 93. 100 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle SuperCluster Ops Center  Unified management of Servers, Storage, and Network Fabric  Simplified management of virtual infrastructure for easy application consolidation  Instant Network and Storage provisioning  Automated update of all firmware and software components  Direct connection to Oracle knowledge-base speeds problem resolution
  • 94. 101 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. No Single Point of Failure  Real-time fault notification and resolution  Risk-free, simplified patching of the integrated stack with no service interruption  Up to 10x reduction in time for patching, minimizing downtime Maximum Service Level for All Applications ARCHITECTED FOR THE HIGHEST DATABASE AND APPLICATION AVAILABILITY
  • 95. 102 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle SuperCluster Deployment Simple and Efficient All ApplicationsHardware, Software and Install Service • System Installation and Configuration Services • Starter Pack, Install and Configuration, etc. • Automated Service Requests • Deploy Oracle, 3rd Party, Java, and Custom Applications • My Oracle Support Integration • One-Patch Packaging “Phone Home” Typical 4X Deployment Speed Up
  • 96. 103 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle Support for Performance and Availability Oracle engineers perform patching services up to four times per year Complete. Integrated. Proactive.  24/7 support coverage  Specialized Engineered Systems Support Team  2-hour onsite response to hardware issues1  New updates and upgrades for Database, Server, Storage, and OS software High Availability Services. No Additional Cost.  Better support for the complete Oracle stack – Includes higher support levels for Database software  24/7 Oracle remote fault monitoring  Industry-leading response times: – 5 Minute Fault Notification – 15 Minute Restoration or Escalation to Development – 30 Minute Joint Debugging with Development  Patch deployment by Oracle engineers Available now for certified configurations on Oracle SuperCluster ORACLE PLATINUM SERVICES 1 Covered system must be within an Oracle two-hour service area to receive two-hour response as a standard service.
  • 97. 104 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle Infrastructure as a Service (IaaS) On Premise with Capacity on Demand  Engineered Systems hardware & hardware support for a monthly fee – No upfront capital expenditure, often OPEX not CAPEX – Usually lower total cost than purchasing system  On Premise – Deploys behind customer‟s firewall – Control and visibility over the system  Elastic Compute Capacity on Demand1 – For peak workloads and high availability – Pay only when needed  Oracle Platinum and PlatinumPlus Services2 – Higher level of support including patching services – Quarterly advisory services for system security, performance, and availability 1. Eligible systems include Oracle Exadata, Exalogic, Exalytics and SPARC SuperCluster. 2. Eligible systems include Oracle Exadata, Exalogic, and SPARC SuperCluster.
  • 98. 105 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle SuperCluster T5-8  2 x SPARC T5-8 (128 cores, 2TB memory) – Each T5-8 configured with:  4 x SPARC T5 processors, 64 cores  1 TB memory  4 x InfiniBand HCAs (dual port)  4 x 10GbE NICs (dual port)  8 x 900GB SAS disks  Optional Fiber channel cards  1-4 Domains  Storage – 4 Exadata Storage Servers (144TB HC or 28.8TB HP) – ZFS Storage Appliance (60TB disk and 4 x 73GB Logzillas)  Switches – 3 x InfiniBand 36 port switches – GbE Management switch Half Rack Configuration
  • 99. 106 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Get Better Results with Oracle HARDWARE AND SOFTWARE ENGINEERED TO WORK TOGETHER
  • 100. 108 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. ONE ENGINEERING TEAM
  • 101. 109 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Oracle Software Runs Best on Oracle Hardware
  • 102. 110 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Required Benchmark Disclosure Statement  Copyright 2013, Oracle &/or its affiliates. All rights reserved. Oracle & Java are registered trademarks of Oracle &/or its affiliates.Other names may be trademarks of their respective owners..  TPC Benchmark C, tpmC, and TPC-C are trademarks of the Transaction Processing Performance Council (TPC). SPARC T5-8 (8/128/1024) with Oracle Database 11g Release 2 Enterprise Edition with Partitioning, 8,552,523 tpmC, $0.55 USD/tpmC, available 9/25/2013, New Order 90th% Response Time 0.410sec. IBM Power 780 Cluster (24/192/768) with DB2 ESE 9.7, 10,366,254 tpmC, $1.38 USD/tpmC, available 10/13/2010, New Order 90th% Response Time 2.10 sec. IBM x3850 X5 (4/40/80) with DB2 ESE 9.7, 3,014,684 tpmC, $0.59 USD/tpmC, available 7/11/2011. IBM x3850 X5 (4/32/64) with DB2 ESE 9.7, 2,308,099 tpmC, $0.60 USD/tpmC, available 5/20/2011. IBM Flex x240 (2/16/32) with DB2 ESE 9.7, 1,503,544 tpmC, $0.53 USD/tpmC, available 8/16/2012. IBM Power 780 (2/8/32) with IBM DB2 9.5, 1,200,011 tpmC, $0.69 USD/tpmC, available 10/13/2010. Source: http://www.tpc.org/tpcc, results as of 3/26/2013.  SPEC and the benchmark name SPECjEnterprise are registered trademarks of the Standard Performance Evaluation Corporation. Results from www.spec.org as of 3/26/2013. SPARC T5-8, 57,422.17 SPECjEnterprise2010 EjOPS; SPARC T4-4, 40,104.86 SPECjEnterprise2010 EjOPS; Sun Server X2-8, 27,150.05 SPECjEnterprise2010 EjOPS; Cisco UCS B440 M2, 26,118.67 SPECjEnterprise2010 EjOPS; IBM Power 780, 16,646.34 SPECjEnterprise2010 EjOPS. IBM PowerLinux 7R2, 13,161.07 SPECjEnterprise2010 EjOPS. Sun Server X4-2, 11,259.88 SPECjEnterprise2010 EjOPS. SPARC T5-8 (SPARC T5-8 Server base package, 8xSPARC T5 16-core processors, 128x16GB-1066 DIMMS, 2x600GB 10K RPM 2.5. SAS-2 HDD, 4x Power Cables) List Price $268,742. IBM Power 780 (IBM Power 780:9179 Model MHB, 8x3.86GHz 16-core, 64x one processor activation, 4xCEC Enclosure with IBM Bezel, I/O Backplane and System Midplane,16x 0/32GB DDR3 Memory (4x8GB) DIMMS-1066MHz Power7 CoD Memory, 12x Activation of 1 GB DDR3 Power7 Memory, 5x Activation of 100GB DDR3 Power7 Memory, 1x Disk/Media Backplane. 2x 146.8GB SAS 15K RPM 2.5. HDD (AIX/Linux only), 4x AC Power Supply 1725W) List Price $992,023. Source: Oracle.com and IBM.com, collected 03/18/2013. SPEC and the benchmark name SPECjEnterprise are registered trademarks of the Standard Performance Evaluation Corporation. Results from www.spec.org as of 5/1/2013. SPARC T5-8, 27,843.57 SPECjEnterprise2010 EjOPS; IBM Power 780, 10,902.30 SPECjEnterprise2010 EjOPS. Oracle server(4 app: 4db) only hardware list price is $298,494, and total hardware plus software list price is $1,565,092. Oracle server(5 app: 3db) only hardware list price is $304,914, and total hardware plus software list price is $1,487,792. http://www.oracle.com as of 9/20/2013. IBM server only HW list price is $803,613 and HW+SW cost of $1,943,162.00 and IBM PowerLinux 7R2 server total hardware plus software cost of $819,451.00 based on public pricing from http://www.ibm.com as of 9/20/2013.  SPEC and the benchmark name SPECjbb are registered trademarks of Standard Performance Evaluation Corporation (SPEC). Results from www.spec.org as of 9/22/2013 unless cited below. SPARC T5-2 81,084 SPECjbb2013-MultiJVM max-jOPS, 39,129 SPECjbb2013-MultiJVM critical-jOPS; Sun Server X2-4 65,211 SPECjbb2013-MultiJVM max-jOPS, 22,057 SPECjbb2013-MultiJVM critical-jOPS; Cisco UCS B200 M3 62,393 SPECjbb2013-MultiJVM max-jOPS, 23,505 SPECjbb2013-MultiJVM critical-jOPS, result from www.cisco.com/en/US/prod/collateral/ps10265/le_41704_pb_specjbb2013b200.pdf; Sun Server X4-2 52,664 SPECjbb2013-MultiJVM max-jOPS, 20,553 SPECjbb2013- MultiJVM critical-jOPS, result from www.oracle.com/benchmarks; Sun Server X3-2 41,954 SPECjbb2013-MultiJVM max-jOPS, 13,305 SPECjbb2013-MultiJVM critical-jOPS; HP ProLiant DL560p Gen8 66,007 SPECjbb2013-MultiJVM max-jOPS, 16,577 SPECjbb2013-MultiJVM critical-jOPS; HP ProLiant ML350p Gen8 40,047 SPECjbb2013- MultiJVM max-jOPS, 12,308 SPECjbb2013-MultiJVM critical-jOPS.
  • 103. 111 Copyright © 2013, Oracle and/or its affiliates. All rights reserved. Required Benchmark Disclosure Statement  Copyright 2013, Oracle &/or its affiliates. All rights reserved. Oracle & Java are registered trademarks of Oracle &/or its affiliates.Other names may be trademarks of their respective owners..  Two-tier SAP Sales and Distribution (SD) Standard Application benchmarks SAP Enhancement package 5 for SAP ERP 6.0 as of 3/26/13:SPARC M5-32 (32 processors, 192 cores, 1536 threads) 85,050 SAP SD users, 32 x 3.6 GHz SPARC M5, 4 TB memory, Oracle Database 11g, Oracle Solaris 11, Cert# 2013009. SPARC T5-8 (8 processors, 128 cores, 1024 threads) 40,000 SAP SD users, 8 x 3.6 GHz SPARC T5, 2 TB memory, Oracle Database 11g, Oracle Solaris 11, Cert# 2013008. IBM Power 760 (8 processors, 48 cores, 192 threads) 25,488 SAP SD users, 8 x 3.41 GHz IBM POWER7+, 1024 GB memory, DB2 10, AIX 7.1, Cert#2013004. Two-tier SAP Sales and Distribution (SD) Standard Application benchmarks SAP Enhancement package 4 for SAP ERP 6.0 as of 4/30/12:IBM Power 795 (32 processors, 256 cores, 1024 threads) 126,063 SAP SD users, 32 x 4 GHz IBM POWER7, 4 TB memory, DB2 9.7, AIX7.1, Cert#2010046. SPARC Enterprise Server M9000 (64 processors, 256 cores, 512 threads) 32,000 SAP SD users, 64 x 2.88 GHz SPARC64 VII, 1152 GB memory, Oracle Database 10g, Oracle Solaris 10, Cert# 2009046. SAP, R/3, reg TM of SAP AG in Germany and other countries. More info www.sap.com/benchmark  SPEC & benchmark names SPECfp, SPECint are registered trademarks of the Standard Performance Evaluation Corporation. Results as of March 26, 2013 from www.spec.org and this report. SPARC T5-8: 3750 SPECint_rate2006, 3490 SPECint_rate_base2006, 3020 SPECfp_rate2006, 2770 SPECfp_rate_base2006; SPARC T5- 1B: 489 SPECint_rate2006, 441 SPECint_rate_base2006, 369 SPECfp_rate2006, 350 SPECfp_rate_base2006. IBM Power 780 8-chip 3.92GHz: 2640 SPECint_rate2006. IBM Power 710 Express 1-chip 3.556GHz: 289 SPECint_rate2006.  TPC Benchmark, TPC-H, QphH, QthH, QppH are trademarks of the Transaction Processing Performance Council (TPC). Results as of 6/7/13, prices are in USD. SPARC T5- 4 www.tpc.org/3288; SPARC T4-4 www.tpc.org/3278; SPARC Enterprise M9000 www.tpc.org/3262; SPARC Enterprise M9000 www.tpc.org/3258; IBM Power 780 www.tpc.org/3277; HP ProLiant DL980 www.tpc.org/3285.  SPC Results as of September 10, 2013, for more information go to http://www.storageperformance.org/results SPC-2. Results for Oracle ZFS Storage ZS3-4 are 17,244.22 SPC-2 MBPS™, $22.53 SPC-2 Price-Performance. Full results at http://www.storageperformance.org/results/benchmark_results_spc2#b00067. Results for IBM DS8870 are 15,423.66 SPC-2 MBPS, $131.21 SPC-2 Price-Performance. Full results at http://www.storageperformance.org/results/benchmark_results_spc2#b00062. Results for HP P9500 XP Disk Array are 13,147.87 SPC-2 MBPS, $88.34 SPC-2 Price-Performance. Full results at http://www.storageperformance.org/results/benchmark_results_spc2#b00056.  SPEC SFS SPEC & benchmark names SPECfp, SPECint are registered trademarks of the Standard Performance Evaluation Corporation. Results as of September 10, 2013, for more information see www.spec.org. For details on performance and price comparisons see http://www.oracle.com/us/solutions/performance-scalability/sun- storage-gateway-160373.html
  • 104. 112 Copyright © 2013, Oracle and/or its affiliates. All rights reserved.