Oracle Exadata Database Machine Sl6: All The Benefits of Exadata Combined With Ultra-Fast SPARC Processors Running Linux
Oracle Exadata Database Machine Sl6: All The Benefits of Exadata Combined With Ultra-Fast SPARC Processors Running Linux
Oracle Exadata Database Machine Sl6: All The Benefits of Exadata Combined With Ultra-Fast SPARC Processors Running Linux
Since the 2008 debut of Exadata, Intel x86 processors have powered
Exadata database servers. The Exadata Database Machine SL6 is nearly
identical to the Intel based Exadata, except it uses Oracle SPARC T7-2
database servers based on the SPARC M7 processor. SPARC M7 is the
worlds most advanced processor to run Oracle databases, and the first to
use a revolutionary technology from Oracle referred to as Software in
Silicon. Software in Silicon technology is a breakthrough in microprocessor
and server design, enabling databases to run faster and with unprecedented
security and reliability. Even though the database servers are based on
SPARC processors, Exadata SL6 runs the exact same Linux Operating
System as x86-based Exadata systems.
independently searching and filtering columns of data while the normal processor cores
KEY FEATURES
Up to 640 CPU cores and 10TB memory per
run other functions. Using Capacity in Silicon processors perform data decompression
rack for database processing at full memory speeds, allowing large volumes of data to be kept in compressed format
Up to 320 CPU cores per rack dedicated to
without incurring processing overhead.
SQL processing in storage
From 2 to 10 Database Servers per rack The Security in Silicon functions of SPARC M7 continuously perform validity checks
From 3 to 16 Storage Servers per rack
on every memory reference made by the processor without incurring performance
Up to 410 TB of flash capacity (raw) per rack
overhead. Security in Silicon helps detect buffer overflow attacks made by malicious
Up to 1.54 PB of disk capacity (raw) per rack
Hybrid Columnar Compression often delivers software, and enable applications such as the Oracle Database to identify and prevent
10X-15X compression ratios erroneous memory accesses. The Security in Silicon technologies also encompass the
40 Gb/second (QDR) InfiniBand Network
cryptographic instruction accelerators, which are integrated into each processor core of
Complete redundancy for high availability
the SPARC M7 processor. These accelerators enable high-speed encryption for more
than a dozen industry-standard ciphers.
The Oracle Exadata Database Machine runs the standard Oracle Database. Therefore,
any application that uses the Oracle Database today can be easily and
seamlessly migrated to use the Exadata Database Machine with no changes to
the application. Databases can also be easily migrated off of Exadata eliminating any
fear of lock-in.
Customers thinking of deploying databases on the Public Cloud, now or in the future,
can be confident that Exadata provides 100% compatibility between on-premises
and public cloud enabling easy migration to the public cloud and simple hybrid cloud
deployments.
without bottlenecks.
RELATED PRODUCTS
Oracle Database Exadata Cloud Service The scale-out architecture accommodates any size workload and allows seamless
Oracle Database Exadata Cloud Machine expansion from small to extremely large configurations while avoiding performance
Oracle Exadata Database Machine X6-2 bottlenecks and single points of failure.
Oracle Exadata Database Server X6-2 Plus
InfiniBand Infrastructure A high-bandwidth low-latency 40 Gb/second InfiniBand network connects all the
Oracle Exadata Storage Expansion Rack X6-2 components inside an Exadata Database Machine. Specialized database networking
Oracle Exadata Storage Server X6-2 Plus protocols run over the InfiniBand network and provide much lower latency and higher
InfiniBand Infrastructure bandwidth communication than is possible using generic communication protocols.
Oracle SuperCluster
This enables both faster response time for OLTP operations, and higher throughput for
Oracle Database 12c
analytic workloads. External connectivity to the Exadata Database Machine is provided
Real Application Clusters
using standard 10 Gigabit Ethernet.
Partitioning
Multitenant Exadata Database Machine is the most versatile database platform. The Exadata
Database In-Memory SL6 Database Machine uses powerful database servers, each with two 32-core
Advanced Compression
SPARC M7 processors and 256 GB of memory (expandable up to 1TB). Exadata also
Advanced Security
uses scale-out, intelligent storage servers that appear in two configurations High
Active Data Guard
Capacity (HC) or Extreme Flash (EF). HC Storage Servers have four PCI Flash cards
GoldenGate
each with 3.2 TB (raw) Exadata Smart Flash Cache and twelve 8 TB 7,200 RPM disks.
Real Application Testing
EF Storage Servers have an all-Flash configuration with eight PCI Flash drives, each
OLAP
Advanced Analytics
with 3.2 TB (raw) storage capacity. The starting configuration of an Exadata Database
Business Intelligence Machine consists of two database servers and three storage servers, which can be
Enterprise Manager elastically expanded by adding more database and/or storage severs as requirements
Oracle Linux grow. Elastic configurations provide an extremely flexible and efficient mechanism to
expand computing power and/or storage capacity to meet any business need.
RELATED SERVICES In addition to upgrading within a rack, multiple racks can be connected using the
The following services are available from Oracle: integrated InfiniBand fabric to form even larger configurations. For example, a
Advanced Customer Services
system composed of four racks is simply four times as powerful as a single rack system
Oracle Premier Support for Systems
- providing quadruple the I/O throughput, quadruple the storage capacity, and
Oracle Platinum Services
quadruple the processing power. It can be configured as a large single system or
Consulting Services
logically partitioned for consolidation of multiple databases. Scaling out is easy with
Oracle University courses
Exadata Database Machine. Oracle Real Application Clusters (RAC) can dynamically
add more processing power, and Automatic Storage Management (ASM) can
dynamically add more storage capacity.
When even larger storage capacity is required, the Oracle Exadata Storage
Expansion Rack is available. The Exadata Storage Expansion Rack enables you to
grow the storage capacity and bandwidth of any Exadata Database Machine. It is
designed for database deployments that require very large amounts of data, including
historical or archive data, backups, documents, images, XML, JSON and LOBs. The
storage expansion rack connects to the Exadata Database Machine using the
integrated InfiniBand fabric and is extremely simple to configure, as there are no LUNs
I would recommend Exadata as a platform or mount points. Storage is configured and added to a database online with a few
for performance, reliability and ease of
simple commands. The starting configuration of the Oracle Exadata Storage Expansion
support. Those three things mean very
much to me in my daily life. Rack consists of four storage servers and can be further expanded by adding additional
- Richard Ewald storage servers.
Senior Technical Architect
Sprint Exadata Database Machines protect your investment by allowing newer generation
servers and storage to be deployed seamlessly into existing Exadata Database
Machines. Similarly, new software releases are compatible with most previous
Exadatas Smart Flash Cache is designed to deliver flash-level I/O rates and response
times for data that is many times larger than the physical flash capacity in the machine
by moving active data into flash, while leaving cold data on disk. It is common for hit
rates in the Exadata Smart Flash Cache to be over 90%, or even 98% in real-world
database workloads even though flash capacity is more than 7 times smaller than disk
None of the reports takes more than 10 capacity. Such high flash cache hit rates mean that Exadata Smart Flash Cache
minutes. It was taking 3-4 hours before, now
it completes in 3 minutes. It sounds like un- provides an effective flash capacity that is many times larger than the physical flash.
real but it is real. For example, an elastic configuration of Exadata Database Machine SL6 with 8
- Finance User database servers and 14 High Capacity Storage Servers often has an effective flash
Turkcell
capacity equal to the usable disk capacity of 508 TB.
The Exadata Smart Flash cache also caches database block writes using Exadata
Write Back Flash Cache technology. Write caching eliminates disk bottlenecks in large
scale OLTP and batch workloads. The flash write capacity of an elastic configuration of
Exadata Database Machine SL6 with 8 database servers and 14 High Capacity
Storage Servers exceeds 5.74 Million 8K write I/Os per second. The Exadata write
cache is transparent, persistent, and fully redundant. The I/O performance of the
Exadata Smart Flash Cache is comparable to dozens of enterprise disk arrays with
thousands of disk drives.
The automatic data tiering between RAM, flash and disk implemented in Exadata
provides tremendous advantages over other flash-based solutions. Many storage
vendors have recognized that the architecture of their traditional storage arrays
inherently bottlenecks the performance of flash and therefore have developed new
flash-only arrays. These flash-only arrays deliver higher performance than traditional
arrays but give up the cost advantages of smart tiering of data between disk and flash.
Therefore the overall size of data that benefits from flash is limited to the size of
expensive flash. These flash arrays also do not benefit from any of Exadatas unique
storage optimization technologies. Data deduplication provided by some flash arrays is
very effective for VDI (Virtual Desktop Infrastructure) environments but is ineffective for
databases.
Exadata not only delivers much more capacity than generic all-flash arrays, it also
delivers better performance. Flash-only storage arrays cannot match the throughput of
The heart and soul of our stack right now is Exadata's integrated and optimized architecture with full InfiniBand based scale-out,
Oracle Exadata Database Machine. With fast PCI flash, offload of data intensive operations to storage, and algorithms that are
Oracle Exadata, weve been able to reduce specifically optimized for databases.
queries from days to minutes, and those
that used to take minutes to seconds.
- Chris Wones Accelerating Database Processing with Smart System
Enterprise Architect Software
dunnhumby
As data volumes grow exponentially, conventional storage arrays struggle to quickly
transfer data from disk and flash to database servers at a rate that keeps the CPUs
busy. Modern servers with dozens of CPU cores can consume data at many tens to
hundreds of gigabytes a second. This is far faster than conventional storage arrays can
deliver data through their storage controllers and the storage network.
The technology that enables Exadatas unparalleled performance without any of the
bottlenecks of traditional storage arrays is Exadata Storage Server Software. This
software powers the Exadata storage servers, providing a highly efficient database-
optimized storage infrastructure. Each Exadata Storage Server has two 10-core x86
processors that are used to offload database processing. A rack of Exadata Database
Machine SL6 can have a total of up to 320 processor cores in the storage servers that
can be used to offload the database servers. The CPUs in the storage servers do not
replace database CPUs. Instead they accelerate data intensive workloads similar to
how graphics cards accelerate image intensive workloads.
One of the many unique features of Exadata Storage Server software is Smart Scan
[With Exadata] We can more quickly
process 65 billion daily transactions for data technology, which offloads data intensive SQL operations from the database
charging, while providing real-time servers directly into the storage servers. By pushing SQL processing to the storage
information for customer inquiries,
servers, data filtering and processing occur immediately and in parallel across all
increasing customer satisfaction, and
reducing costs. storage servers, as data is read from disk and flash. Only the rows and columns that
- Jin Hyung Lee are directly relevant to a query are sent to the database servers.
ICT Team Manager, Networking
Engineering For example, if a query is executed to identify the customers who placed sales orders
SK Telecom over $1000 in the month of March, an Exadata system will offload the scanning of the
table to the Exadata storage, filter out all sales orders that are less than $1000, filter out
sales orders not in March, and extract just the relevant customer names. The result is
that the data transferred to the database servers is reduced by orders of magnitude.
This greatly accelerates query execution, eliminates bottlenecks, and significantly
reduces the CPU usage of the database servers.
index using a bloom filter to determine if rows with the specified column value might
exist in a region of disk on the storage server. If the column value doesnt exist in the
bloom filter, then scan I/O in that region for that query is avoided. Storage Indexes
make many SQL operations run dramatically faster because large numbers of I/O
operations are automatically replaced by a few in-memory lookups.
Besides the intrinsic capabilities of Exadata Storage Server software, the combination
of Oracle Database software, Exadata Storage Server software and Exadata
Exadata is the heart of the booking engine,
and we cannot operate as a business, we infrastructure enables several additional capabilities that offer unparalleled
cannot sell tickets without it. performance levels for todays complex enterprise databases. For example, Exafusion
- James Callaghan
Direct-to-Wire Protocol allows database processes to read and send Oracle Real
Chief Technologist
Westjet Application Clusters (Oracle RAC) messages directly over the InfiniBand network,
bypassing the OS kernel and networking software overhead. This improves the
response time and scalability of Oracle RAC configurations on Oracle Exadata
Database Machine.
To further accelerate OLTP workloads, the Exadata Smart Flash Cache implements a
special algorithm to ensure low latency of database log writes called Exadata Smart
Flash Logging. The time to commit user transactions or perform critical updates is
very sensitive to the latency of log writes. Smart Flash Logging takes advantage of the
flash memory in Exadata storage combined with the high speed RAM memory in the
Exadata disk controllers to reduce the average latency of log writes and avoid the
latency spikes that occur in other flash solutions. The Exadata Smart Flash Logging
algorithms are unique to Exadata.
With Hybrid Columnar Compression, Exadata enables the highest levels of data
compression possible with Oracle databases, and provides tremendous cost-savings
and performance improvements due to reduced I/O, especially for analytic workloads.
Storage savings is data dependent and often ranges from 5x to 20x. Average storage
savings is an industry leading 10x. On conventional systems, enabling high data
compression has the drawback of reducing performance by consuming CPU for
decompression. Because the Exadata Database Machine is able to offload
decompression overhead into large numbers of processors in Exadata storage, and in
addition there is reduced I/O because of the high compression achieved, most analytic
workloads run faster using Hybrid Columnar Compression than they do without it.
Hybrid Columnar Compression delivers the compression and analytic performance
benefits of columnar storage while avoiding the dramatic slowdown that columnar-only
data stores experience for drilldown operations that often involve single row access.
For data analytics which benefits from pure columnar access, Exadata Smart Flash
Cache implements a unique algorithm to accelerate reporting and analytical queries
called Exadata Columnar Flash Cache. Columnar Flash Caching implements a dual
format architecture in Exadata flash by automatically transforming frequently scanned
Hybrid Columnar Compressed data into a pure columnar format as it is loaded into the
flash cache. Smart scans on pure columnar data in flash run faster because they read
only the selected columns, reducing flash I/Os and storage server CPU consumption.
This accelerates reporting and analytic queries while maintaining excellent
performance for OLTP style single row lookups.
In-memory databases leverage vector instructions built into processors to process large
amounts of data using relatively few instructions. But vector processing instructions in
general purpose processors such as x86 processors were designed for graphic
operations, not for database processing. SPARC M7 with its unique SQL in Silicon
technology has specialized Database Accelerators (DAX) that are engineered for in-
memory database processing. The 32 DAX engines on each M7 chip are like 32
additional processor cores that accelerate analytic scanning and filtering of in-memory
data for free.
The Exadata system is designed and delivered as an integrated whole, and not a
collection of components. In traditional database deployments, the customer takes on
all the integration tasks for the system including the task of ensuring the security of
each individual software and hardware component, and ensuring that security is
maintained across the full product stack. Oracle delivers full stack security in the
Exadata Database Machine. Additionally, Exadata systems use minimal Linux
distributions to ensure that just the RPMs needed to run Oracle Database are installed
and enabled. With this approach, system security is stronger than default installations
and common security vulnerabilities are avoided.
Exadata security has been probed and evaluated by hundreds of leading banks,
telcoms, and government organizations worldwide. The security findings of all these
evaluations have been incorporated into the Exadata standard configuration, making it
a highly secure database platform.
as disk, server, or network, as well as complex site failures and human errors. Each
Exadata Database Machine has completely redundant hardware, including
redundant InfiniBand networking, redundant Power Distribution Units (PDU), redundant
power supplies, and redundant database and storage servers. Oracle RAC protects
against database server failure. Oracle ASM provides data mirroring to protect against
disk or storage server failures. Oracle RMAN provides extremely fast and efficient
backups to disk or tape. Oracles Flashback technology allows backing out user errors
at the database, table or even row level. Using Oracle Data Guard, a second Exadata
Database Machine can be configured in a Maximum Availability Architecture (MAA)
configuration to transparently maintain a real-time copy of the database at a remote site
and provide full protection against primary database failures and site disasters.
I dont get the calls in the middle of the
night anymore that we have a system down. Exadata in an MAA configuration is recognized by the analyst firm IDC as a system that
Exadata is taken as always being available.
delivers at least 5-nines availability and is categorized in the IDC AL4 fault-tolerant
- James Callaghan 1
Chief Technologist market segment, along with HP Integrity NonStop and IBM z Systems .
Westjet
The Exadata principle of deep hardware and software integration is also evident in the
many ways Exadata uniquely assures high availability across several different failure
conditions. One such capability is Instant Detection of Compute and Storage Server
Failures. On non-Exadata platforms, detecting a server failure requires waiting for a
long timeout, leading to extended application brownouts. Exadata leverages InfiniBand
integration to very quickly determine that the suspect server is not reachable through
any network path and can immediately initiate eviction of the failed server from the
cluster. This entire operation can be completed in less than 2 seconds, leading to
virtual elimination of application brownout conditions.
Disk and flash devices occasionally exhibit very long latency IO operations due to
internal recovery of failed sectors, internal firmware reboots, or wear leveling. These
long IO operations can cause stalls in mission critical OLTP databases. With Exadata
I/O Latency Capping, Oracle Exadata Storage Server software automatically redirects
read I/O operations to an ASM-mirrored copy of the data when the latency of a read I/O
is much longer than expected. Similarly, it automatically redirects high latency write I/O
operations to a healthy flash device, eliminating write outliers. If disks do fail, ASM
performs a rebalance operation for the data that was resident on the disk. Exadata
Storage Server software takes rebalance one step further by preserving the flash cache
population and storage indexes when moving data between storage servers to maintain
consistent application performance. On rare occasions when there are outliers within
the networking subsystem, Exadata redirects the I/O issued by the database server to
another storage server.
Because of its industry leading availability, the Exadata Database Machine has been
deployed by leading companies for their most critical applications including interbank
fund transfers, online securities trading, real-time call tracking, and web-based retailing.
Exadatas Mission Critical availability capabilities are not restricted to OLTP workloads;
they also apply to warehousing and analytics.
1
Worldwide Fault-Tolerant Servers Market Shares, 2014: Vendors Are Hearing the Customer More Bold Moves Needed to Grow the Segment, IDC, Peter
Rutten, Lloyd Cohen, October 2015
Snapshots start with a shared read-only copy of the production database (or PDB) that
has been cleansed of sensitive information. A hierarchy of read-write snapshots can be
created from this shared copy. As changes are made, each snapshot writes the
changed blocks to a sparse disk group. Since multiple users can create independent
snapshots from the same base database copy, multiple test and development
environments can share space while maintaining independent databases for each task.
All Exadata specific features such as Smart Scan, resource management and Smart
Flash Cache work seamlessly on database instances created via Exadata snapshots,
hence providing an exact test and development environment while using a fraction of
valuable storage resources. Backups of snapshots on Exadata are also space efficient
as only the changed information is backed up.
without coordination across different component management teams that are often
overloaded and have differing priorities. Database Machine Administrators can focus
on application and business specific enhancements rather than coordinating across
component teams, or tuning and triaging of low level configuration issues.
Exadata provides a huge RAM, flash, and disk footprint for large data sets. Raw disk
storage on an Exadata full rack can exceed 1.5 Petabytes while raw flash storage can
be up to 409.6 TB. In addition, Hybrid Columnar Compression often expands storage
and memory capacity 10X. By intelligently moving active data across disk, flash, and
memory tiers, Exadata simultaneously delivers the highest performance and the lowest
cost.
Exadata has the unique ability to consolidate many databases supporting multiple
workloads in a single cloud platform. High-end OLTP, analytics, batch, reporting, and
backups can all run simultaneously within and across databases with extreme
performance. The extreme performance and capacity of Exadata enables very
large numbers of databases and workloads to be consolidated on Exadata.
Consolidating databases on Exadata reduces system hardware cost, software cost,
and greatly reduces ongoing operations cost.
the business.
Exadata accelerates time to market for new business applications since the time
needed for system configuration, tuning, and testing is largely eliminated. Deployment
times are reduced from months to days, and the risk of unexpected system level issues
after go-live is greatly reduced. When a new application is deployed, it is common for
unanticipated application usage patterns to create performance issues. Exadatas huge
I/O, network, and compute throughput can absorb spikes created by unanticipated
workloads without slowing response times of mission critical workloads. Overall
Exadata speeds application deployment and reduces risk, allowing businesses to
innovate faster.
Exadatas extreme performance and large memory and flash capacity enhance
employee productivity and customer satisfaction by greatly improving user response
times. Users spend more time doing useful work, and less time waiting for the
system to respond.
Exadatas extreme performance does not just improve business efficiency, it also
enables business users to make smarter decisions, discover growth
opportunities, and reduce costs. Users can analyze data in real-time, explore
different possibilities, and perform rapid iteration to find better solutions. Exadata
enables:
Real-time business data analysis
Faster financial closes
Better planning and budgeting
More effective and faster projections
Conclusion
Exadata delivers a fully integrated database platform with the latest hardware
technologies and unique software to deliver extreme performance, availability, and
security. This coupled with cost savings, ease of management, and enhanced
supportability result in greater business agility and efficiency. The Exadata SL6
features industry leading SPARC M7 processors with unique Software in Silicon
capabilities making SL6 the fastest and most secure Exadata Database Machine ever.
1
EXADATA SERVER HARDWARE
Server Type CPU Memory Disk Flash Network
Database Server 2x 32-core SPARC M7 256 GB 6x 600 GB None
processors (default) to 10,000 RPM disks 3x 1/10 Gb copper Ethernet ports (client)
1 TB(max) (Hot-Swappable) 1x 1/10 Gb copper Ethernet port (mgmt)
Expandable to 8 2x 10 Gb optical Ethernet ports (client)
4x QDR (40 Gb) InfiniBand ports
1x ILOM Ethernet port
2
EXADATA TYPICAL RACK CONFIGURATIONS
Rack Size Database Servers and Cores Storage Servers and Cores HC Storage Capacity (raw) EF Storage Capacity (raw)
3
Eighth Rack 2x servers, 64 cores 3x servers, 30 cores for SQL 144 TB disk, 19.2 TB flash 38.4 TB flash
offload or
Quarter Rack 2x servers, 128 cores 3x servers, 60 cores for SQL 288 TB disk, 38.4 TB flash 76.8 TB flash
offload
2
Each rack is 42 RU (Rack Units) in height, has 2x redundant Power Distribution Units (PDUs), 2x 36-port QDR (40 Gb/s) InfiniBand switches and 1x 48-port Cisco
Ethernet switch for administration. Included Spare Parts Kit Contains:
1 x 3.2 TB NVMe PCI Flash card and 1 x 8 TB High Capacity disk, or
1 x 3.2 TB NVMe PCI flash drive
3
Eighth Rack is the minimum Exadata configuration. Eighth Rack compute servers have half the cores enabled. Eighth Rack EF storage servers have half the cores and
flash drives enabled. Eighth Rack HC storage servers have half the cores enabled and half the disks and flash cards removed.
4
EXADATA ELASTIC CONFIGURATIONS
Rack Size Database Servers and Cores Storage Servers and Cores HC Storage Capacity (raw) EF Storage Capacity (raw)
Base Rack (Quarter 2x servers, 128 cores 3x servers, 60 cores for SQL 288 TB disk, 38.4 TB flash 76.8 TB flash
Rack) offload
+ Database Servers
5
Up to 10 servers , 640 cores n/a n/a or n/a
max per rack
5
+ Storage Servers n/a Up to 16x servers , 320 cores 1,536 TB disk, 204.8 TB flash 409.6 TB flash max per rack
max per rack max per rack
4
A full rack elastic configuration cannot exceed 18 servers and 39 RU (Rack Units). Database Servers = 3 RU, Storage Servers = 2 RU
5
Maximum number of database servers allowed in an elastic configuration is 10. Maximum number of storage servers allowed in an elastic configuration is 16.
Eighth Rack to Quarter Upgradability: Field upgrade from Eighth Rack to Quarter Rack. Expand just compute or just storage or both. Additional Hardware
Rack Upgrade Components are enabled/installed with the Upgrade:
For each Database Server: Thirty two additional cores are enabled,
For each EF Storage Server: Ten additional cores and four PCI Flash drives are enabled
For each HC Storage Server: Ten additional cores are enabled, six disks and two PCI Flash Cache cards are installed.
Server Type Maximum SQL Flash Maximum SQL Read Maximum SQL Write PCI Flash Disk Data
Bandwidth2 IOPS3 IOPS4 Capacity (raw)5 Capacity(raw)
EXADATA SL6 TYPICAL RACK CONFIGURATIONS: FLASH METRICS (HC & EF)
Maximum SQL Flash Maximum SQL Flash Maximum SQL Flash PCI Flash Capacity (raw)
Flash Metrics
Bandwidth Read IOPS Write IOPS
Full Rack HC 252 GB/s 6,650,000 5,740,000 179.2 TB
Equivalent*
EF 280 GB/s 6,930,000 6,300,000 358.4 TB
Half Rack HC 126 GB/s 3,325,000 2,870,000 89.6 TB
EF 140 GB/s 3,465,000 3,150,000 179.2 TB
Quarter Rack HC 54 GB/s 1,425,000 1,230,000 38.4 TB
EF 60 GB/s 1,485,000 1,350,000 76.8 TB
Eighth Rack HC 70 GB/s 712,500 615,000 19.2 TB
EF 30 GB/s 742,500 675,000 38.4 TB
Disk Metrics Maximum SQL Disk Bandwidth Maximum SQL Disk IOPS Data Capacity (raw)
Full Rack Equivalent* 25 GB/s 36,000 1,344 TB
Half Rack 12.5 GB/s 18,000 672 TB
Quarter Rack 5.4 GB/s 7,800 288 TB
Eighth Rack 2.7 GB/s 3,900 144 TB
EXADATA SL6 TYPICAL RACK CONFIGURATIONS: COMBINED METRICS (HC & EF)
Combined Metrics Data Capacity (Usable) Normal Redundancy 6 Data Capacity (Usable) High Redundancy 6 Maximum Data Load Rate7
Full Rack HC 508 TB 399 TB 21 TB/hour
EF 130 TB 102 TB 21 TB/hour
Half Rack HC 254 TB 199 TB 11 TB/hour
EF 65 TB 51 TB 11 TB/hour
Quarter Rack HC 109 TB 85 TB 5 TB/hour
EF 28 TB 22 TB 5 TB/hour
Eighth Rack HC 54 TB 43 TB 2.5 TB/hour
EF 14 TB 11 TB 3 TB/hour
.
HC = High Capacity EF = Extreme Flash. Actual system performance varies by application.
1
2
Bandwidth is peak physical scan bandwidth achieved running SQL, assuming no database compression. Effective user data bandwidth is higher when database
compression is used.
3
Based on 8K I/O requests running SQL. Note that the I/O size greatly affects Flash IOPS. Other products quote IOPS based on smaller IOs that are not relevant
for databases.
4
Based on 8K I/O requests running SQL. Flash write I/Os measured at the storage servers after ASM mirroring, which usually issues multiple storage IOs to
maintain redundancy.
5
Raw capacity is measured in standard disk drive terminology with 1 GB = 1 billion bytes.
6
Usable capacity is measured using normal powers of 2 space terminology with 1 TB = 1024 * 1024 * 1024 * 1024 bytes. It is the actual space available to create
a database after taking into account space needed for ASM redundancy, recovering from a drive failure, DBFS disk group, and OS images and binaries.
7
Load rates are typically limited by database server CPU, not IO. Rates vary based on load method, indexes, data types, compression, and partitioning.
8
Full Rack equivalent represents a configuration with 8 SL6 Database Servers and 14 Storage Servers
SL6 Database Server Plus X6-2 High Capacity X6-2 Extreme Flash
Metric InfiniBand Infrastructure Storage Server Plus Storage Server Plus
InfiniBand Infrastructure InfiniBand Infrastructure
Weight 80.0 lbs (36.3 kgs) 73.0 lbs (33.1 kgs) 62.0 lbs (28.1 kgs)
Maximum power usage 1.8 kW (1.8 kVA) 0.588 kW (0.600 kVA) 0.547 kW ( 0.558 kVA)
Typical power usage 1 1.3 kW (1.3 kVA) 0.412 kW (0.420 kVA) 0.383 kW ( 0.391 kVA)
Operating temperature/humidity: 5 C to 32 C (41 F to 89.6 F), as measured by an industry grade temperature measurement device
directed at the front bezel of the servers, 10% to 90% relative humidity, non-condensing
Altitude Operating: Up to 3,048 m, max. ambient temperature is de-rated by 1 C per 300 m above 900 m
1
Typical power usage varies by application load
2
Airflow must be front-to-back.
ORACL E DA TA SH EET
Height
78.66 - 1998 mm
Width 23.62 600 mm
Depth 47.24 1200 mm
Weight 1353.5 lbs (613.9 kg) 910.5 lb (413.0 kg) 880.3 lbs (399.3 kg)
Maximum power usage 12.2 kW (12.5 kVA) 6.3 kW (6.4 kVA) 5.1 kW (5.2 kVA)
1
Typical power usage 8.6 kW (8.7 kVA) 4.4 kW (4.5 kVA) 3.6 kW (3.6 kVA)
Weight 1276.5 lbs (590.0 kg) 877.5 lbs (398.0 kg) 877.5 lbs (398.0 kg)
Maximum power usage 11.9 kW (12.2 kVA) 6.2 kW (6.3 kVA) 5.0 kW (5.1 kVA)
1
Typical power usage 8.4 kW (8.5 kVA) 4.3 kW (4.3 kVA) 3.5 kW (3.6 kVA)
Operating temperature/humidity: 5 C to 32 C (41 F to 89.6 F), as measured by an industry grade temperature measurement device directed at the front bezel of
the servers 10% to 90% relative humidity, non-condensing
Altitude Operating: Up to 3,048 m, max. ambient temperature is de-rated by 1 C per 300 m above 900 m
1
Typical power usage varies by application load.
2
Airflow must be front-to-back.
Regulations 1 Safety: UL/CSA 60950-1, EN 60950-1, IEC 60950-1 CB Scheme with all country differences
Immunity: EN 55024
Manageability Features
Oracle Embedded Integrated Lights Out Manager (ILOM)
Oracle Enterprise Manager Exadata Plug-in
Active AWR includes storage stats for end to end monitoring
IPv6 Support for Ethernet Connections
Capacity on Demand
Trusted Partitions for Oracle Virtual Machine
Automated VLAN Creation
Oracle Exadata Deployment Assistant
Separate Management Switch and Connectivity
Exacli command line management from remote servers
Cellcli command line management of Storage Servers
DCLI distributed command line automation tool
CONTACT US
For more information about Oracle Exadata, visit oracle.com/exadata or call +1.800.ORACLE1 to speak
to an Oracle representative.
CONNECT WITH US
blogs.oracle.com/oracle Copyright 2017, Oracle and/or its affiliates. All rights reserved. This document is provided for information purposes only, and the
contents hereof are subject to change without notice. This document is not warranted to be error-free, nor subject to any other
warranties or conditions, whether expressed orally or implied in law, including implied warranties and conditions of merchantability or
facebook.com/oracle fitness for a particular purpose. We specifically disclaim any liability with respect to this document, and no contractual obligations are
formed either directly or indirectly by this document. This document may not be reproduced or transmitted in any form or by any
twitter.com/oracle means, electronic or mechanical, for any purpose, without our prior written permission.
Oracle and Java are registered trademarks of Oracle and/or its affiliates. Other names may be trademarks of their respective owners.
oracle.com
Intel and Intel Xeon are trademarks or registered trademarks of Intel Corporation. All SPARC trademarks are used under license and
are trademarks or registered trademarks of SPARC International, Inc. AMD, Opteron, the AMD logo, and the AMD Opteron logo are
trademarks or registered trademarks of Advanced Micro Devices. UNIX is a registered trademark of The Open Group. 0217