Oracle Exadata

Database Machine
X11M
The Oracle Exadata Database Machine (Exadata) is engineered to deliver
dramatically better performance, cost-effectiveness, and availability for Oracle
databases. Exadata features a modern cloud-enabled architecture with scale-out Oracle Exadata Database
high-performance database servers, scale-out intelligent storage servers with Machine X11M
state-of-the-art PCIe flash, unique storage caching using RDMA accessible
memory, and cloud-scale RDMA over Converged Ethernet (RoCE) internal fabric
Key Features
that connects all servers and storage. Unique algorithms and protocols in Exadata
implement database intelligence in storage, compute, and networking to deliver  Up to 2,880 CPU cores per
rack for database
higher performance and capacity at lower costs than other database platforms.
processing
Exadata is ideal for all types of modern database workloads, including Online
 Up to 42 TB memory per
Transaction Processing (OLTP), Analytics and Data Warehousing (DW), In-Memory
rack for database
Analytics, Artificial Intelligence (AI), Internet of Things (IoT), financial services, processing
gaming, and compliance data management, as well as efficient consolidation of
 Up to 1,088 CPU cores per
mixed database workloads. rack dedicated to SQL
processing in storage
Exadata Database Machine X11M is the latest generation Exadata hardware and
implements the next-generation intelligent data software architecture. Simple and  Up to 21.25 TB of Exadata
RDMA Memory per rack
fast to implement, Exadata X11M powers and protects your most important
databases. Exadata X11M can be purchased and deployed on-premises as the  2x100 Gb/sec active-active
RoCE Network
ideal foundation for a private database cloud or acquired using a subscription
 Complete redundancy for
model and deployed in the Oracle Cloud Infrastructure, Cloud@Customer in a
high availability
hybrid cloud model, or Multicloud (Azure, Google Cloud, and AWS) with all
 From 2 to 15 database
infrastructure management performed by Oracle. The Oracle Autonomous
servers per rack
Database is available exclusively on Exadata, either in the Oracle Cloud
 From 3 to 17 storage
Infrastructure, Multicloud, or Cloud@Customer.
servers per rack

Engineered For Fast and Reliable Deployment  Up to 462.4 TB of

performance-optimized
The Exadata Database Machine is the most cost-efficient and highest- flash capacity (raw) per rack
performance platform for running Oracle Databases. Exadata is easy to deploy
 Up to 2 PB of capacity-
even for the most mission-critical systems, as the database servers, storage optimized flash capacity
servers, and network are pre-configured, pre-tuned, and pre-tested by Oracle (raw) per rack
experts. Extensive end-to-end testing and validation ensure all components,  Up to 4.4 PB of disk capacity
including database software, operating system, hypervisor, drivers, and firmware (raw) per rack
work seamlessly together, and there are no performance bottlenecks or single
points of failure.

1 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
All Exadata Database Machines are identically configured; therefore, customers Key Benefits
benefit from the experience of thousands of other customers’ Exadata  Pre-configured, pre-tested
deployments. Customer systems are also identical to the systems that Oracle system optimized for all
Support uses for problem identification and resolution, the systems on which database applications

Oracle Development develops and tests the Oracle Database, and the systems that  Uncompressed I/O
run Oracle’s SaaS applications such as Oracle Fusion Applications and NetSuite. bandwidth of up to 8.5
TB/sec per rack from SQL
Exadata is the most thoroughly tested and tuned platform for running Oracle
Database.  Ability to perform up to
25.2M 8K database read I/O
Any Oracle Database on any supported platform can be seamlessly migrated operations, or 13M 8K Flash
write I/O operations per
to the Exadata Database Machine with no changes to the application using that
second in a single rack
database. Likewise, any Oracle Database can also be easily migrated off Exadata,
 Easily add database or
eliminating “lock-in” concerns.
storage servers to meet the

Extreme System Scalability and Growth with Elastic needs of any size
application
Configurations  Extreme scalability by
The Exadata Database Machine uses a scale-out architecture for both database connecting multiple Exadata
Database Machine X11M
and storage servers. As workloads grow, database, storage, and networking
racks or Exadata X11M
resources can be added to an Exadata Database Machine to scale without Storage Expansion Racks.
bottlenecks. The architecture scales from small to extremely large Up to 14 racks can be
configurations to accommodate workloads of any size. In Exadata X11M, a connected by simply adding
RoCE cables and internal
high-bandwidth, low-latency active-active 100 Gb/sec RDMA over Converged switches. Larger
Ethernet (RoCE) Network Fabric connects all the components. Specialized configurations can be built
database networking protocols deliver much lower latency and higher bandwidth with external RoCE switches
than is possible with generic communication protocols, enabling faster response
time for OLTP operations and higher throughput for analytic workloads.
External data center connectivity to the Exadata Database Machine is via standard
10 Gb/sec, 25 Gb/sec, or 100 Gb/sec Ethernet.

Exadata Database Machine is the most versatile database platform with

extreme scalability inherent at every layer in its architecture. Exadata X11M
extends this innovation further with powerful database servers that are equipped
with the latest AMD EPYC two 96-core x86 processors and 512 GB of DDR5
memory (expandable up to 3 TB).

Exadata X11M also introduces the new Database Server-Z equipped with a single
32-core x86 processor and 768 GB of DDR5 memory (expandable up to 1,152 GB)
providing customers with the choice of database servers to match their workload
requirements. For example, customers that require fewer CPU cores, or are
consolidating a few virtual machines or databases.

The CPU scalability within each database server enables superior performance and
utilization efficiency by enabling greater database and VM consolidation with
higher OLTP transaction throughput and significantly more parallelized analytic
workloads to coexist and consume fewer data center resources.

2 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
Exadata also uses scale-out, intelligent storage servers for database I/O Related Products
processing, which are available in three configurations in Exadata X11M – High  Exadata Cloud
Capacity (HC), Extreme Flash (EF), and High Capacity-Z (HC-Z) Infrastructure

• HC Storage Servers have four 6.8 TB performance-optimized Flash  Exadata Cloud@Customer

Accelerator F680 v2 NVMe PCIe 5.0 Flash cards for Exadata Smart Flash  Oracle Exadata Storage
Cache and twelve 22 TB 7,200 RPM SAS disks for a total of 264 TB of raw Expansion Rack X11M

storage.  Oracle Exadata Storage

Server X11M
 Exadata X11M EF Storage Servers have an all-flash configuration. Each server
 Oracle Exadata Database
has four 6.8 TB performance-optimized Flash Accelerator F680 v2 NVMe PCIe Server X11M
5.0 Flash cards for Exadata Smart Flash Cache and four 30.72 TB capacity-
 Oracle Database Enterprise
optimized NVMe PCIe Flash drives totaling 122.88 TB of raw storage. Edition 19c, 21c, and 23ai

 Exadata X11M HC and EF Storage Servers include Exadata RDMA Memory  Exadata Exascale
(XRMEM), further enhancing performance by delivering up to 2.8 million 8K  Exadata Database Service
OLTP Read IOPS. Each server is populated with 1.5 TB of DDR5 memory, 1.25  Oracle Autonomous
TB of which is configured as Exadata RDMA Memory and used as a caching Database
tier between the database buffer cache and Flash Cache, and the remaining  Real Application Clusters
256 GB is used for Exadata System Software. SQL Scan throughput from flash
 Partitioning
is 2.2x faster than the prior generation reaching 100 GB/s per storage server.
 Multitenant
In addition, Smart Scan also reads columnar data in XRMEM accelerating
analytics query throughput up to 500 GB/s. Two 32-core x86 processors are  Database In-Memory
included for Exadata System Software operations in each HC and EF storage  Advanced Compression
server.  Advanced Security
 Exadata X11M HC-Z Storage Servers are ideal for running small to medium  Active Data Guard
workloads with two 6.8 TB performance-optimized Flash Accelerator F680 v2  GoldenGate
NVMe PCIe 5.0 Flash cards for Exadata Smart Flash Cache and six 22 TB 7,200  Real Application Testing
RPM SAS disks. Each server is populated with 768 GB of DDR5 memory, 576
 OLAP
GB of which is configured as Exadata RDMA Memory and used as a caching
 Enterprise Manager
tier between the database buffer cache and Flash Cache, and the remaining
192 GB is used for Exadata System Software. One 32-core x86 processor is  Oracle Linux
included for Exadata System Software operations in each HC-Z storage server.  Oracle Linux Virtualization

The minimal configuration of an Exadata Database Machine consists of two

database servers and three HC, EF, or HC-Z storage servers. This configuration Related Services
can elastically expand by adding more database and/or storage servers within The following services are
the same rack. Elastic configurations provide a flexible and efficient mechanism available from Oracle:
to meet any size business needs. Customers can mix both X11M database server  Advanced Customer
and all three storage server configurations within the same rack enabling even Services
greater control of resources to meet varying performance, high availability,  Oracle Premier Support for
security, and consolidation requirements. Systems

 Oracle Platinum Services

In addition to expanding within a rack, multiple Exadata racks can be
interconnected using the integrated RoCE network fabric to form even larger  Oracle Consulting Services
configurations. These racks can be Exadata X8M, X9M, X10M, or X11M  Oracle University courses
generations. A system composed of four racks of Exadata X11M is simply four
times as powerful as a single rack: it provides four times the I/O throughput, four
times the storage capacity, and four times the processing power. It can be
configured as a single system or logically partitioned for multiple databases and

3 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
clusters. Scaling out is easy, as Oracle Real Application Clusters (RAC) can dynamically add more processing power,
and Exadata Exascale and Automatic Storage Management (ASM) can dynamically add more storage capacity.

Figure 1 Elastic Scale-out to Multi-rack Exadata

For databases and workloads that require extreme storage capacity, the Oracle Exadata X11M Storage Expansion
Rack is used to expand the storage tier of Exadata Database Machine. The Storage Expansion Rack expands the
storage capacity, Flash Cache capacity, OLTP IOPS, and scan throughput of any Exadata Database Machine. It is
designed for database deployments with very large amounts of data, including historical or archive data, backups,
vectors, documents, images, XML, JSON, and LOBs. The Storage Expansion Rack connects to the Exadata Database
Machine using the integrated RoCE network fabric and is configured with a few simple commands, as there are no
LUNs or mount points. The starting configuration of the Oracle Exadata Storage Expansion Rack consists of four HC
or EF storage servers and can be expanded with additional storage servers.

“We have implemented nearly 300 Exadata systems for our customers in
manufacturing, financial services, construction and engineering, and
public and private sector services.”
Dr. WP Hong
CIO
Samsung SDS

Groundbreaking RDMA-Based Network Fabric

The Exadata X11M uses an ultra-fast cloud-scale RDMA over Converged Ethernet (RoCE) networking fabric. RDMA
(Remote Direct Memory Access) allows one computer to directly access data from another without Operating System
or CPU involvement for high bandwidth and low latency. The network card directly reads/writes memory with no
extra copying or buffering and with very low latency. RDMA is an integral part of the Exadata high-performance
architecture and has been tuned and enhanced with each new generation of Exadata, underpinning several Exadata-
only technologies including Exafusion Direct-to-Wire Protocol for faster inter-instance OLTP communication, or to
read undo blocks from other Real Application Clusters (RAC) instances to increase OLTP performance.

Exadata X11M implements a dual port PCIe 5.0 network interface card capable of 2x 100 Gb/sec active-active RoCE
network for a total throughput of 200 Gb/sec. By leveraging the RoCE network, Oracle Database on Exadata can
perform read I/O directly from memory in the shared storage servers.

4 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
Shared Exadata RDMA Memory Acceleration
Exadata RDMA Memory (XRMEM) in the Exadata Storage Servers is leveraged as a shared read accelerator. The
XRMEM Data Accelerator is a memory cache tier in front of Flash Cache, enabling orders of magnitude lower latency
accessing remotely stored data. By utilizing RDMA to access memory remotely, XRMEM Data Accelerator bypasses
the network and I/O stack, eliminating expensive CPU interrupts and context switches, and reducing latency by
more than 17x, from 250 microseconds 1 to as low as 14 microseconds. Smart Exadata System Software also ensures
data is mirrored across storage servers, which provides additional fault tolerance. Exadata’s unique end-to-end
integration between Oracle Database and Exadata Storage Servers automatically caches the hottest data blocks
efficiently between the buffer cache in database servers and XRMEM and Flash Cache in storage servers. XRMEM is a
shared storage tier across all of the storage nodes, which means the aggregate performance of this cache can be
dynamically used by any database instance on any database server. This is a significant advantage over general-
purpose storage architectures, which preclude sharing storage resources across database instances.

Real-world database workloads running on Exadata X11M, utilizing the shared XRMEM Data Accelerator, can achieve
up to 25.2 million OLTP Read IOPS (8K IOs) 2 in a single rack. This represents a 21% improvement over the same
nine database and nine storage server configurations of the Exadata X9M generation at 20.7 million 3 and 430%
higher than Exadata Database Machine X7 4. This performance scales as additional racks are deployed.

Security and management of XRMEM are fully automated. XRMEM is configured automatically, with no user
interaction required, and automatically managed thereafter. Hardware monitoring is pre-configured. Exadata RDMA
Memory is only accessible to databases using database access controls, ensuring end-to-end security of data.
XRMEM is entirely transparent to all applications.

Record-breaking Analytics I/O Performance

Each X11M High Capacity (HC) and Extreme Flash (EF) Storage Server includes four 6.8 TB performance-optimized
flash drives, offering 27.2 TB of Exadata Smart Flash Cache. Exadata delivers ultra-high performance by placing all
the flash devices directly on the high-speed PCIe interface rather than behind slow disk controllers. Exadata HC and
EF Storage Servers include 1.25 TB of DDR5 Exadata RDMA Memory as a data acceleration tier in front of Flash
Cache.

For analytics environments that require the highest performance, Exadata X11M HC and EF storage servers are both
capable of scanning data in flash at up to 100 GB/s with Smart Scan, 2.2x faster than the previous generation. In
addition, Smart Scan can achieve up to 8.5 TB/s scan throughput 5 from a single rack configuration by reading
columnar data cached in Exadata RDMA Memory.

This represents real-world, end-to-end performance measured running SQL workloads with standard 8K database
I/O sizes inside a single rack Exadata system. Exadata’s performance on real Oracle Database workloads is orders of
magnitude faster than traditional storage array architectures and much faster than current all-flash storage arrays.

1
Exadata X7 8K OLTP Read Latencyn from flash in storage servers
2
Elastic configuration with 9x Exadata X11M Database Servers and 9x Exadata X11M Extreme Flash or 9x Exadata X11M High Capacity Storage Servers
3
Elastic configuration with 9x Exadata X9M Database Servers and 9x Exadata X9M Extreme Flash Storage Servers or 9x Exadata X9M High Capacity Storage Servers
4
Exadata X7-2 Full Rack with 8x Exadata X7 Database Servers and 14x Exadata X7 Extreme Flash Storage Servers or 14x High Capacity Storage Servers
5
Elastic configuration with 2x Exadata X11M Database Servers and 17x Exadata X11M High Capacity or 17x Exadata X11M Extreme Flash Storage Servers

5 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
High Capacity Storage Server: Tiered Disk, Flash, and Exadata RDMA
Memory Deliver Lower Cost of Disk Storage with Shared Memory
Performance
The most common Exadata storage option is the High Capacity (HC) Storage Server. This server includes twelve 22
TB disk drives with 264 TB total raw disk capacity. It also has four 6.8 TB performance-optimized flash drives for a
total raw capacity of 27.2 TB of Exadata Smart Flash Cache and 1.25 TB of DDR5 Exadata RDMA Memory (XRMEM) in
front of flash to boost performance further.

Flash in the HC Storage Server can be used directly as flash disks but is almost always configured as a flash cache
(Exadata Smart Flash Cache) in front of disk storage and behind the Exadata RDMA Memory. Exadata Smart Flash
Cache is used with the XRMEM Data Accelerator to automatically cache frequently accessed data while keeping
infrequently accessed data on disk, delivering the high I/O rates and fast response times of flash with the large
capacity and low cost of disk. Exadata uniquely understands database workloads and knows when to avoid caching
data that negatively affects overall performance. For example, if large write I/Os caused by backups or large table
scans are likely to disrupt higher-priority OLTP or scan operations, those large I/Os will bypass the flash cache and go
straight to disk. Otherwise, Exadata System Software will utilize additional spare flash capacity and I/O bandwidth to
optimize performance by caching these I/Os. Administrators can also manually provide SQL directives to ensure that
specific tables, indexes, or partitions are preferentially retained in the flash cache.

It is common for hit rates in the Exadata Smart Flash Cache to be over 95%, or even 99% in real-world database
workloads, yielding an effective flash capacity many times larger than the physical flash.

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 a
single Exadata Database Machine X11M rack reaches 13 million 8K flash write I/O operations per second (IOPS) 6.
The Exadata Write-Back Flash Cache is transparent, persistent, and fully redundant, with performance comparable to
dozens of enterprise disk arrays with thousands of disk drives.

The automatic data tiering between memory, flash, and disk in Exadata provides tremendous advantages over other
flash-based solutions. Many storage vendors have developed flash-only arrays to achieve higher performance than
traditional disk-based arrays. However, due to the need for such arrays to move data to the database servers instead
of processing data in the storage, the network infrastructure becomes a significant performance bottleneck as a
single flash card can overwhelm the network. Therefore, all-flash storage arrays cannot match the cost advantages of
Exadata’s smart data tiering between disk and flash because they lack Exadata’s unique database-aware storage
optimizations. In addition, generic data deduplication provided by some flash arrays may be effective for workloads
such as Virtual Desktop Infrastructure environments but are not for databases. In addition to utilizing its integrated
and optimized hardware architecture, Exadata delivers superior performance by offloading data-intensive processing
to unique algorithms in storage that have been specifically optimized for Oracle Database.

“Our infrastructure needed to keep pace with exponential growth, quality

and availability. The customer is the center of our strategy and one of our
objectives is to always offer the best experience. With Oracle Exadata, we
were able to improve our digital banking applications with 70% better
performance and speed to enhance customer service.”
Everton Sims de Queiroz
Executive Infrastructure Manager
Banco Original

6
Elastic configuration with 6x Exadata X11M Database Servers and 13x Exadata X11M Extreme Flash Storage Servers or 13x Exadata X11M High
Capacity Storage Servers
6 Oracle Exadata Database Machine X11M / Version 1.1
Copyright © 2025, Oracle and/or its affiliates / Public
Extreme Flash Storage Server: Lowest Latency, All Flash
Exadata Extreme Flash (EF) Storage Server is the foundation of a database-optimized all-flash Exadata Database
Machine. Each EF Storage Server contains four capacity-optimized 30.72 TB flash drives for an aggregate, raw
storage capacity of 122.88 TB and increasing the usable storage capacity by 2.4x 7. Exadata EF storage servers deliver
extreme high performance, flash capacity, and low latency for database workloads with the highest performance
demands. In addition, X11M EF storage includes four 6.8 TB performance-optimized flash drives for a total raw
capacity of 27.2 TB, increasing the size of the Smart Flash Cache by 11.5x 8 and is used to satisfy read and write
requests. 1.25 TB of DDR5 Exadata RDMA Memory (XRMEM) is available in front of flash to boost performance
further.

High Capacity-Z Storage Server: High Performance Storage Accelerates

Small to Medium Database Workloads
The third Exadata storage option is the High Capacity-Z (HC-Z) Storage Server. Each HC-Z Storage server includes
six 22 TB disk drives with 132 TB total raw disk capacity. To boost performance further, the HC-Z Storage Server also
includes two 6.8 TB NVMe PCIe Flash Cards for 13.6 TB of Exadata Smart Flash Cache and 576 GB of DDR5 XRMEM
in front of flash.

The High Capacity-Z storage server is ideal for smaller workloads or environments. It delivers Exadata’s extraordinary
performance, scalability, security, and manageability while making Exadata accessible to all organizations.

Accelerate Database Processing with Smart System Software

After implementing the Oracle Exadata system, our client services saw
performance improvements of 300% in data processing and 200% in data
warehousing, while achieving zero downtime and zero data loss.
Chang Rea Han
Vice President and CIO
KCB

As data volumes continue to grow, 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
tens to hundreds of gigabytes a second, far faster than conventional storage arrays can deliver data through their
storage controllers and the storage network.

Exadata System Software enables Exadata’s unparalleled performance by implementing a unique, highly efficient,
database-optimized storage infrastructure on the Exadata Storage Server. Each storage server has CPUs used to
offload database processing. These CPUs in the storage servers do not replace database CPUs. They accelerate
database-intensive workloads similar to how graphics cards accelerate image-intensive workloads.

One of the many unique features of Exadata System Software is Smart Scan technology, which offloads data-
intensive SQL operations from the database servers directly into the storage servers. By pushing SQL processing
to the storage servers, data filtering and processing occur immediately and in parallel across all storage servers, as
data is read from disk and flash. Only the rows and columns directly relevant to a query are sent to the database
servers.

For example, suppose a query is executed to identify the customers who placed sales orders over $1000 in the month
of March. Exadata will offload the scanning of the table to the Exadata Storage Servers, where filters extract only the
relevant customer information for March with a minimum $1000 spend and return this reduced quantity of data to

7
Compared to X9M Extreme Flash Storage Servers
8
Exadata X7 – X9M Extreme Flash Storage Servers allocated 2.32 TB to Flash Cache of the total 51.2 TB raw flash capacity per server.

7 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
the database. Offloading reduces the amount of data transferred to the database servers by orders of magnitude.
Smart Scan greatly accelerates query execution, eliminates bottlenecks, and significantly reduces the CPU usage of
the database servers.

Storage Indexes are another powerful and unique capability of Oracle Exadata that helps avoid unnecessary I/O
operations and improves overall performance. Storage Indexes are maintained automatically in the storage server’s
memory and track minimum and maximum column values for table data contained in a storage region on that
storage server. When a query specifies a WHERE clause, Exadata System Software examines the storage index to
determine where rows with the specified column value exist in a disk region on the storage server. Rather than
reading all the rows to satisfy the query and discarding the rows that do not match the WHERE clause, only the
regions of the disk containing the rows matching the WHERE clause are read, avoiding I/Os for rows that would
otherwise have been discarded. Storage Indexes make many SQL operations run dramatically faster because a few in-
memory lookups automatically replace large numbers of I/O operations. Storage Indexes are automatically persisted
to disk, avoiding the need to rebuild them and the associated consumption of extra I/O while ensuring consistent
performance after planned or unplanned downtime.

The time it takes to commit user transactions or perform critical updates is sensitive to the latency of log writes. To
accelerate OLTP workloads, the Exadata Smart Flash Cache implements unique algorithms to ensure consistent low
latency of database log writes. Exadata Smart Flash Log Write-Back eliminates the storage disks as a potential log
write throughput bottleneck, prevents log write latency outliers, and automatically and transparently stores Oracle
Database Redo Logs in the Smart Flash Cache. Smart Flash Log Write-Back increases log write throughput by up to
2.5x. In addition, Pipelined Log Writes increase redo write throughput by up to 1.4x on Exadata 9 by automatically
using the high-performance RoCE network to execute parallel redo log writes without impacting latency, minimizing
the need to queue redo log writes, and improving OLTP performance. Exadata uniquely prioritizes latency-sensitive
I/O, such as log writes, over other I/O requests in the RoCE network and within the Exadata Storage Servers to further
ensure other workloads do not impact mission-critical OLTP workloads.

The combination of Oracle Database software, Exadata System Software, and Exadata infrastructure enables several
additional unique capabilities that offer unparalleled performance levels for OLTP workloads. For example, Exafusion
Direct-to-Wire Protocol uniquely allows database processes to read and send Oracle Real Applications Cluster
(Oracle RAC) messages directly over the ultra-fast RoCE network using Remote Direct Memory Access (RDMA),
bypassing the OS, kernel, and networking software overhead. Using RDMA improves the response time and scalability
of Oracle RAC OLTP configurations on Oracle Exadata Database Machine, especially for workloads with high-
contention updates.

In some OLTP workloads, more than half of remote reads are for undo blocks to satisfy read consistency. Exadata
uniquely leverages ultra-fast RDMA to read undo blocks from other database instances, further improving OLTP
performance.

Exadata uniquely uses Machine Learning to implement Automatic Indexing with Oracle Database 19c and later
releases. Automatic Indexing continually analyzes SQL execution plans and creates new indexes to accelerate
performance. Exadata also uniquely implements Real-Time Statistics gathering as DML operations insert, update,
or delete data. Real-Time Statistics allows the SQL optimizer to adapt plans dynamically as the distribution of data
changes.

AI Smart Scan Accelerates Artificial Intelligence Workloads

Oracle Database 23ai introduces significant new capabilities, known as AI Vector Search, to enable and accelerate
Artificial Intelligence (AI) workloads, enabling applications to query data based on semantic similarity. With AI Vector
Search, applications can search unstructured data, such as contracts, knowledge management documents, images,
video, audio, etc. – and then combine that unstructured data with data stored in relational or other data types already

9 Available on Exadata X10M and later generations

8 Oracle Exadata Database Machine X11M / Version 1.1
Copyright © 2025, Oracle and/or its affiliates / Public
stored in Oracle Database. This continuation of Oracle's Converged Database strategy helps eliminate data
fragmentation by avoiding the need for a specialized vector database and elevates vector processing into the
enterprise-grade data management domain.

AI Smart Scan accelerates AI Vector Search queries by up to 30x with optimizations that deliver low latency
parallelized scans across large volumes of vector data and enables large concurrent AI user communities. AI Smart
Scan processes vector data at memory speed from ultra-fast Exadata RDMA Memory and Flash Cache in storage
servers and performs vector distance computations and Adaptive Top-K Filtering where the data resides, avoiding
unnecessary network data transfer and database work resulting in up to 4.6x faster queries and up to 4.7x greater
data filtering respectively. Additionally, AI queries are up to 32x faster when using BINARY vector dimension
formats in Oracle Database 23ai.

Exadata Exascale Intelligent Data Architecture for the Cloud Era

Exadata Exascale is the world's only intelligent data architecture for the cloud. Exascale is a revolutionary leap
that combines the best of Exadata and the best of the cloud. This next-generation, hyper-elastic, multi-tenant
software architecture is designed to handle mission-critical OLTP, analytics, AI, JSON, and mixed Oracle Database
workloads.

Exascale reimagines how compute and storage resources are managed on Exadata platforms by decoupling
and simplifying storage management, paving the way for innovative new capabilities. It ensures industry-
leading database performance, availability, and security standards that organizations expect from Exadata.

Exascale features a reimagined approach to database snapshots and clones on Exadata. It enables space-
efficient thin clones from any read/write database or pluggable database, significantly boosting developer
productivity. Exascale seamlessly integrates with development, test, and deployment pipeline requirements while
providing native Exadata performance.

Databases on Exascale are automatically distributed across all available storage in the Exadata storage servers,
providing ultra-low latency RDMA for I/O and database-aware intelligent Smart Scan with up to thousands of
cores available to all workloads. Automatic data replication across multiple storage servers ensures fault tolerance
and reliability.

Energy Efficiency Meets Extreme Performance

Customers are increasingly required to meet specific power consumption reduction targets to align with their
corporate sustainability policies and responsibilities. Exadata X11M is designed to assist customers achieve
environmental and sustainable goals while enabling extreme performance. Exadata X11M reduces energy
consumption, space requirements, and cooling needs, helping customers reduce environmental impact while running
high-performance workloads.

The first step in reducing power consumption is to choose the most appropriate database server for the database
workload. Exadata X11M offers two database server configurations: the two-socket, 96-core CPU Database Server,
and the one-socket, 32-core CPU Database Server-Z. These configurations enable customers to choose the
performance and power consumption profiles to suit their workload and corporate requirements.

Exadata X11M offers new capabilities to limit the power consumption of database server CPUs to a specific power
target or by enabling the database server to automatically and dynamically save power when workload demand is low,
for example, on weekday nights and weekends. Exadata Capacity-on-Demand, which allows customers to choose the
number of active cores at initial deployment, may also be used to conserve energy while enabling customers to
license only the cores their workload requires.

Designed to run AI, OLTP, analytics, and mixed workloads on the same infrastructure, Exadata X11M delivers
industry-leading scalability and performance for all workloads making it the ideal consolidation platform. By
9 Oracle Exadata Database Machine X11M / Version 1.1
Copyright © 2025, Oracle and/or its affiliates / Public
consolidating many databases on Exadata, customers can reduce their data center footprint and consume less power.
Exadata Database Machine is designed to be the ideal platform for Oracle Database. The X11M generation continues
to execute this mission while introducing capabilities to help customers affect tangible power savings and increased
data center efficiency, driving a more sustainable future.

Optimize Storage Consumption and I/O Using Compression

The Exadata Storage Server provides a unique compression capability called Hybrid Columnar Compression (HCC)
that enables dramatic reductions in storage for large databases. Hybrid Columnar Compression technology is an
innovative method of organizing data within a database table that uses a combination of both row and columnar
methods for storing data. This hybrid approach achieves the compression benefits of columnar storage while
avoiding the performance shortfalls of a pure columnar format.

With Hybrid Columnar Compression, Exadata enables the highest levels of data compression possible with Oracle
databases and provides substantial cost-savings and performance improvements due to reduced I/O, especially for
analytic workloads. Storage savings is data-dependent and often range from 5x to 20x. Average storage savings is an
industry-leading 10x. Exadata Database Machine can offload decompression operations to processors in Exadata
storage. As a result, there is reduced I/O because of the high compression achieved. Most analytic workloads,
therefore, run faster using Hybrid Columnar Compression than without it.

Two modes of Hybrid Columnar Compression are available. Warehouse compression mode suits read-intensive
workloads and provides large storage savings and enhanced analytic performance. Archive compression mode
offers the highest degree of compression and targets data that is seldom accessed but must remain online.

OLTP systems can use Hybrid Columnar Compression to compress older, less active data while newer, more active,
and update-intensive data can be compressed using Advanced Row Compression. Oracle Database provides the
ability to change the type of compression used by individual table partitions online (even if there are global indexes
on the table), to ensure seamless tiering across different compression types as data ages and becomes less active.

Exadata 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 Cache 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 I/O and storage server CPU consumption. This accelerates reporting and analytic queries
while maintaining excellent performance for OLTP-style single-row lookups.

Fault Tolerant and Fastest Database In-Memory for Analytics and Mixed
Workloads
Exadata is the ideal platform for running Oracle Database In-Memory. Oracle Database In-Memory on Exadata does
not require all data to reside in memory. Data can be stored across multiple storage tiers, with the hottest data in
memory providing extremely high query performance, active data on flash providing very high I/O throughput, and
less active or older data on disk at very low cost. A single query can access data from all three tiers: memory,
flash, and disk, completely transparently. This allows Exadata to run faster, support higher capacities, and deliver
lower costs than competing products.

Exadata uniquely implements In-Memory columnar formats in Flash Cache. This feature extends the Exadata
Columnar Flash Cache by automatically transforming data into In-Memory columnar formats as it is loaded into Flash
Cache. Smart Scans also process multiple column values with a single instruction by leveraging ultra-fast Single
Instruction Multiple Data (SIMD) Vector instructions. Smart Scan results are passed back to the database server in
Oracle Database In-Memory formats, further reducing the load on database server CPUs. The effect is to seamlessly
extend the In-Memory columnar store size from the in-memory pool in the SGA to flash cache capacity in storage

10 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
servers. An Exadata X11M Database Machine 10 has up to 462 TB of Flash Cache, capable of servicing some of the
largest in-memory workloads. Exadata X11M utilizes a unique new algorithm to increase the compression of data
stored in the In-Memory columnar format by up to 1.25x 11, further increasing the effective Flash Cache capacity.
Databases not using Oracle Database In-Memory still benefit from Exadata Columnar Flash Cache without the vector
processing optimizations.

Exadata uniquely implements Fault Tolerant memory duplication for Oracle Database In-Memory. On a generic
non-Exadata cluster configuration, when a database node fails, the in-memory data on that node is lost. It takes time
to repopulate the in-memory data on a surviving node. During this time, analytic queries will run orders of magnitude
slower. This means generic platforms may fail to meet business SLAs. However, on Exadata, Fault-Tolerant memory
duplication can eliminate this slowdown by duplicating any subset of the in-memory data across the clustered
database servers. If a database server fails, queries will transparently access the duplicate copy on a surviving
database server and continue without interruption.

Exadata uniquely integrates with Active Data Guard to allow customers to run In-Memory analytics on a standby
database, further improving the return on investment of the standby system and enhancing availability and overall
performance.

Oracle Database 19c and later enable the use of Database In-Memory Caching in Storage Servers without allocating
memory to the Database In-Memory Column Store on database servers. By setting the inmemory_force parameter to
‘CELLMEMORY_LEVEL’, databases can continue leveraging the optimizations and vector processing benefits of
Database In-Memory and reaping the processing benefits of the shared storage tier and freeing up database server
memory.

Database Consolidation on Exadata

The Exadata Database Machine can host many databases, enabling database consolidation or a sophisticated
Database as a Service private cloud. Multi-database environments inherently have diverse, complex, and
unpredictable workloads mixing OLTP, analytics, and batch operations with sequential and random-access patterns.
Exadata’s ability to run mixed database workloads with industry-leading scalability and performance makes it an
ideal consolidation platform.

Consolidated environments running on Exadata X11M may also use KVM-based Virtual Machines (Guests) and
Secure RDMA Fabric Isolation for strong isolation between workloads. Isolation is critical in hosted, shared, service
provider, and test/dev environments. When using virtualization, Exadata can safely deploy multiple RAC clusters
running the same or different Exadata software, grid infrastructure, or database versions on the same set of database
servers.

Exadata Database Machine is the world’s fastest virtualized Oracle database platform. Exadata virtual machines
use high-speed networking with Single Root I/O Virtualization (SR-IOV) to ensure that performance within a virtual
machine is similar to Exadata’s excellent raw hardware performance. Exadata Smart Scans significantly decrease
virtualization overhead compared to other platforms by dramatically reducing message traffic between virtual
machines. Exadata virtual machines can dynamically expand or shrink the use of CPUs based on the workload
requirement of the applications running in that virtual machine. Virtual machines on Exadata can utilize RDMA-
enabled Exascale Volumes to increase performance and consolidation density with up to 50 VMs per database server.

Virtual machines on Exadata are considered Trusted Partitions, and therefore, software can be licensed at the virtual
machine level instead of the physical processor level. Without Trusted Partitions, database options and other Oracle
software must be licensed at a server or cluster level, even though not all databases running on that server or cluster
may require a particular option.

10
Elastic rack with 2x Exadata X11M Database Servers and 17x Exadata X11M Extreme Flash Storage Servers or 17x Exadata X11M High Capacity Storage Servers
11
Compared to X9M
11 Oracle Exadata Database Machine X11M / Version 1.1
Copyright © 2025, Oracle and/or its affiliates / Public
Multi-database environments create an inherent risk that one database will consume too many resources and
therefore impact the quality of service of other databases. The Exadata Database Machine uniquely provides end-to-
end prioritization of an application workload’s use of database CPU, memory, network, and storage. Workload
priorities and resource limits can be specified at the physical database, pluggable database, connection, application,
user, or even job level to ensure that each of the consolidated databases or SQL operations receives the necessary
resources and achieves the target response times.

Exadata uniquely implements database and I/O resource management. Fine-grained priorities specified for
operations at the database level are automatically communicated to Exadata Storage Servers and applied to each I/O
operation to ensure that prioritization of database operations applies to both CPU operations and I/O operations. The
same resource management principles are applied when multiple databases and virtual clusters are deployed on one
Exadata rack, as is typical in a consolidated private cloud.

In X11M, Exadata utilizes RDMA over Converged Ethernet protocols to ensure network-intensive workloads such as
reporting, batch, and backups don’t stall latency-sensitive interactive workloads. Latency-sensitive network
operations, such as RAC Cache Fusion communication and log file writes, travel across high-priority network channels
within the converged ethernet fabric. Non-latency-sensitive traffic travels on other channels with their own network
switch buffers.

Due to Exadata’s unique database consolidation and Database-as-a-Service capabilities, Exadata is the only platform
supporting up to 4096 Pluggable Databases within a single Oracle Multitenant Container Database.

“Our investment in Oracle Exadata has exceeded our expectations. Not

only did we address our biggest challenge of increasing performance for
the Siebel CRM platform by an average of 40% and 4-5X on large queries,
we also reaped the benefits of consolidating all of our databases onto
Exadata, reduced our 287 databases by half, lowered administration,
improved uptime, and saved 50% of our legacy costs.”
Greg Ogle
Vice President
Global IT Infrastructure
Equinix

Enterprise-Class Security with Extreme Performance

Exadata Database Machine is the world's most secure database machine. Building on the high-security capabilities in
the Oracle Database, such as Transparent Data Encryption (TDE), Exadata uniquely moves decryption processing
from database server software into the Exadata Storage Server hardware. Exadata storage leverages hardware
decryption and compression together to provide the highest-performance secure databases. Encryption occurs after
data is compressed, so the cost of decryption is decreased by the degree of compression. By leveraging both
technologies, Exadata can query fully encrypted and compressed databases with minimal overhead at hundreds of
gigabytes of (original) user data per second. Oracle Transparent Data Encryption provides a complete key
management solution to keep all data encrypted and secure.

Exadata is designed and delivered as an integrated whole instead of a collection of components. In traditional
database deployments, the customer takes on all the system integration tasks, including ensuring the security of each
software and hardware component and ensuring that security is maintained across the entire stack. Oracle delivers
full stack security in the Exadata Database Machine.

Exadata virtual machines provide an added isolation layer at the operating system level. Additionally, in environments
that leverage virtualization on Exadata, Exadata Secure RDMA Fabric Isolation ensures VM Guests in one cluster
cannot communicate directly with other clusters on the same Exadata while still providing access to shared Exadata
storage. Such isolation is beneficial in consolidated environments where, for example, different organizational
divisions share infrastructure and have various data security requirements.
12 Oracle Exadata Database Machine X11M / Version 1.1
Copyright © 2025, Oracle and/or its affiliates / Public
Exadata systems are designed, manufactured, and delivered to customers using a defense-in-depth approach,
increasing the system's security posture. Exadata systems are built using Oracle-designed database and storage
servers. The in-house design and development of the servers enable the implementation of features unique to
Exadata and enable tight control over the security of the design. This focus on security extends to the global supply
chain of Oracle. Exadata security begins at power-up time with Secure Boot, which ensures that the system UEFI
firmware only allows the execution of cryptographically signed boot loaders that the system recognizes as
trustworthy. Secure Boot can be used for bare metal and virtual machines. These signatures are verified every server
reboot, preventing the execution of malware hidden in embedded code in the boot chain. The operating system
installed on Exadata systems is a pared-down version of the standard Oracle Linux distribution, with Unbreakable
Enterprise Kernel, unique to Exadata systems. This nano-kernel only includes packages required to run the Oracle
Database and eliminates unnecessary packages, minimizing the attack surface and hardening the system's security.
Exadata Live Update on the database servers leverages familiar Linux technologies – Ksplice and RPM – of Oracle
Linux to apply system software and security updates while the OS stays online.

In addition, and complimentary to database encryption provided by Transparent Data Encryption, the disk and flash
technologies used in Exadata X11M enable Instant Secure Erase to eliminate data leakage risk during proactive drive
replacement or machine redeployment. Exadata's Secure Erase feature leverages this on-device capability when an
Exadata is re-purposed or decommissioned to instantly erase all user data present on storage devices by
cryptographically erasing the device, rather than require the device to be overwritten. Because the previous device
cryptographic key is deleted with Secure Erase, there is no need to worry about latent data left on storage devices due
to over-provisioning or sector sparing.

Exadata security has been probed and evaluated by hundreds of leading banks, telecoms, and government
organizations worldwide. The security findings of all these evaluations have been incorporated into the Exadata
standard configuration. Therefore, Exadata benefits from scrutiny by Oracle Security experts and hundreds of
industry security experts worldwide.

Mission Critical High Availability

The Exadata Database Machine is engineered to provide the highest levels of availability. All types of failures are
protected against, from simple failures such as disk, server, or network components to complex site failures and
human errors. Each Exadata Database Machine has completely redundant hardware, including redundant
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.
Oracle’s 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 deployed 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.

Exadata in an MAA configuration is recognized by the analyst firm IDC as a system that delivers at least 5-nines
availability (99.999%) and is categorized in the IDC AL4 fault-tolerant market segment 12.

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 unique capability is Instant Failure
Detection. On non-Exadata platforms, detecting a server failure requires waiting for a long timeout, leading to
extended application brownouts. RoCE-based Exadata Database Machines implement a unique RDMA-based sub-
second node failure detection, leading to the virtual elimination of application brownout conditions.

12
Worldwide AL4 Server Market Shares, 2019: Fault-Tolerant Systems Become Digital Transformation Platforms, IDC, Paul Maguranis Peter Rutten,
July 2020

13 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
Disk and flash devices occasionally exhibit high latency I/O operations due to internal recovery of failed sectors,
internal firmware reboots, or wear leveling. These extended I/O operations can cause stalls in mission-critical OLTP
databases. With Exadata’s unique I/O Latency Capping, Oracle Exadata System software automatically redirects
read I/O operations to a mirrored copy of the data when the latency of a read I/O is much longer than expected.
Similarly, I/O Latency Capping automatically redirects high latency write I/O operations to a healthy flash device,
eliminating outliers during write operations. Exadata System Software uses machine learning techniques to predict
components susceptible to failure and takes proactive action to take such components out of service gracefully. If
disks fail, a rebalance operation is performed for the data resident on the disk, while applications continue to access
the database with no interruption. Exadata allows hot-swapping of disks, fans, power supplies, and PCIe flash cards to
avoid downtime. Exadata System software takes rebalance 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.

Exadata automates the monitoring of CPU, memory, input/output subsystems, file system, and network. This
automation combines machine learning techniques with the lessons learned from thousands of mission-critical real-
world deployments. For example, Exadata can detect anomalous use of system resources that negatively impacts
database performance and automatically identifies the process responsible, and issues an alert – all without any
manual intervention.

As a result 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, web-based retailing, and many more. Exadata’s mission-critical availability capabilities are not restricted
to OLTP workloads; they also apply to data warehousing and analytics.

Ultra-Fast Deployment of Development and Test Databases with Exadata

Exascale
Exadata Exascale features a reimagined approach to database snapshots and clones on Exadata. It enables space-
efficient thin clones from any read/write database or pluggable database, significantly boosting developer
productivity. Exascale seamlessly integrates with development, test, and deployment pipeline requirements while
providing native Exadata performance.

Administrators and users can quickly create read-only database snapshots and read-write thin-provisioned clones
from any 23ai source database, including Data Guard standby databases, for test, development, and many other
purposes. Exascale features a powerful new redirect-on-write design that leverages shared database between the
snapshot or clone source and target and minimizes storage needed for changed data in the clones. The space
efficiency of Exascale empowers development teams by enabling each developer access to their own production-like
database(s) without requiring large investments in storage.

Database clones on Exascale can be created from any read/write or read-only database or Pluggable Database (PDB),
including from Data Guard standby and existing clones without requiring any alteration to the source database. Each
clone is entirely independent of its source database. Source databases can continue to be used for their intended
purpose or even dropped without impacting any clones created, increasing flexibility and operational efficiency.

Exascale is integrated with Oracle Multitenant to provide a simple interface for creating new pluggable database (PDB)
snapshots and clones. Exascale enables flexible cloning workflows by allowing PDBs to be cloned within the same
Container Database (CDB), or between CDBs in the same Exadata Exascale infrastructure. The PDB Snapshot
Carousel capability of Oracle Database automatically creates PDB snapshots at regular intervals for subsequent use
as a point-in-time PDB clone source. Data Guard standby databases can be utilized to create snapshots and thin-
provisioned read-write copies of the source databases. Oracle REST Data Services (ORDS) enables REST API control of

14 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
PDB snapshots, clones and the PDB Snapshot Carousel for easy integration with CI/CD development pipelines and
workflows.

Space-efficient clones of a CDB and all the PDBs it contains can be created using the gDBCLone utility. gDBClone
simplifies the process of cloning CDBs with an easy-to-use command-line interface.

All Exadata-specific features such as Smart Scan, Exadata RDMA Memory Data Accelerator, resource management,
and Smart Flash Cache work seamlessly on database instances created via Exadata snapshots, providing an exact test
and development environment while using a fraction of valuable storage resources. RMAN backups of snapshots on
Exadata are also space efficient, with only the changed blocks included.

Comprehensive System Management

Oracle Enterprise Manager uses a holistic approach to manage the Exadata Database Machine and provides
comprehensive capabilities from monitoring and reporting to active lifecycle management. It enables:

 Unified Monitoring: Oracle Enterprise Manager 24ai uniquely supports a single pane of glass view of all the
hardware and software components, such as database servers, storage servers, and network switches, and
monitors the operations running on them and their resource utilization. DBAs can drill down from database
monitoring screens to the Exadata storage layer to quickly determine the root cause of any performance
bottlenecks.

 Lights-out monitoring within Enterprise Manager is optimized for Exadata with predefined metrics and
thresholds so administrators receive timely notifications when issues arise and manage those exceptions.
Hardware incidents are automatically detected, and service requests are logged to reduce problem resolution
time.

 The Exachk tool, integrated with Enterprise Manager’s powerful compliance framework, provides functionality for
system administrators to automate the assessment of Engineered Systems for known configuration problems
and best practices. Administrators can leverage the Consistency Check functionality to find deviations in
configuration across the racks or among the database servers of a rack. Exachk is a component of the
Autonomous Health Framework (AHF). AHF issues early warnings or automatically solves operational runtime
issues faced by Database and System administrators in availability and performance.

 Exadata’s built-in Management Server (MS) processes constantly monitor the health of hardware and software
components and send alerts to administrators and Oracle support when faulty components are detected.

 Exadata Real-time Insight streams fine-grained performance data directly from the Management Server (MS)
processes on all Exadata servers to power real-time performance dashboards, enabling DBAs to monitor
performance at a fleet level with per-second level accuracy.

Highest Level of Service

Oracle offers a complete set of support services for the Exadata family of products, including 24x7 hardware support,
system monitoring, software installation, and configuration, among other standard and custom offerings.

Oracle Platinum Services is available exclusively for Oracle’s Engineered Systems. Platinum Services provides fault
monitoring, faster response times, and expedited escalation to development. With Platinum Services, Oracle support
engineers perform software maintenance and patching remotely. Platinum Services covers all software and hardware
within an Engineered System, including the Oracle Database – the highest level of support ever for a full-stack
software/hardware platform. Platinum Services is provided at no extra charge to Exadata customers.

IT Agility
Exadata is a complete system for running databases, including storage, servers, and networking. Management of a
traditional database system is typically spread across the teams of each component, such as the database team, the
storage team, and the system administrators. In contrast, an Exadata system is typically managed by a unified
15 Oracle Exadata Database Machine X11M / Version 1.1
Copyright © 2025, Oracle and/or its affiliates / Public
Database Machine Administration (DMA) team. Database Machine Administrators have complete control of all
resources in the Exadata Database Machine, including storage resources. Database Machine Administrators can
implement new database deployments and configuration changes 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 low-level configuration issues.

Dramatically Lower Costs

Due to the extreme performance, high storage capacity, and unique compression capabilities delivered by the
Exadata Database Machine, workloads that would require very large traditional hardware systems can be run on much
smaller Exadata systems. In sizing exercises, it is typical to see a 2x-4x reduction in Exadata system size compared to
a traditional system.

Exadata provides a huge memory, flash, and disk footprint for large data sets. Raw disk storage on an Exadata
system 13 can reach 4.4 PB (Petabytes), while raw flash storage can be up to 2 PB. Hybrid Columnar Compression may
also increase the effective storage and memory capacity by an average of 10x. By intelligently moving active data
across disk, flash, and memory tiers, Exadata simultaneously delivers the highest performance and the lowest cost.

Exadata can uniquely consolidate many databases supporting multiple workloads in a single cloud platform.
High-end OLTP, AI, analytics, batch, reporting, and backups can run simultaneously within and across databases with
extreme performance. Exadata's extreme performance and capacity enable many databases and workloads to be
consolidated on Exadata. Consolidating databases on Exadata reduces system hardware and software costs and
ongoing operations costs.

The uniformity of Exadata Database Machine configurations results in large cost savings. Exadata standardizes not
just technologies but also integration, testing, security, hardening, tuning, and support. Customers deploy
Exadata systems much faster and with less labor than traditional systems. Low-level tuning, integration, and
maintenance is reduced or eliminated. All Exadata users run a configuration that is identical to thousands of other
users and are identical to Oracle’s internal configurations, making it far less likely that issues will be encountered.
When issues occur, the resolution is simpler as customers work with one supplier – Oracle, as the entire system –
hardware, firmware, operating system, hypervisor, and database layers are all owned and supported by Oracle. The
“one-hand-to-shake” support model enables faster problem resolution times and reduces downtime and associated
costs, further increasing economic benefits.

Capacity-on-Demand Software Licensing

An Exadata X11M Database Server has a substantial compute capacity with two 96-core x86 processors (192 cores
per database server). The Capacity-on-Demand feature allows a subset of cores (minimum of 14) in each database
server to be enabled during the hardware installation. As your workload grows and more cores are needed, Capacity-
on-Demand can be used to increase CPU resources in 2-core increments. Since software licenses are only required for
the enabled cores, this pay-as-you-grow approach to software licensing is another way Exadata helps align costs with
business growth.

Exadata in Oracle Cloud

Customers can run Oracle databases on Exadata in the Cloud (Exadata Cloud), with the same extreme performance
and availability experienced by thousands of organizations running Exadata on-premises. Exadata Cloud combines
the world’s #1 database – Oracle, and the most powerful database platform – Exadata, with the simplicity,
automation, operations, and economics of the cloud. Exadata Cloud is available in the Oracle public cloud (Oracle

13
Exadata X11M elastic configuration with 2x X11M Database Servers and 17x X11M High Capacity Storage Servers or 17x X11M Extreme Flash Storage Servers

16 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
Cloud Infrastructure - OCI), within partner public clouds (Azure, Google Cloud and AWS), and as a hybrid cloud
platform (Exadata Cloud@Customer) within customer datacenters.

With Exadata Cloud:

 Compute resources can be online scaled up and down enabling customers to pay only for what they use, starting
with a highly affordable entry-level subscription on OCI

 Customers choose between fully managed Autonomous Database or, for total control, Exadata Database Service,
or run both services on the same Exadata infrastructure

 All Exadata System software and hardware is included with the infrastructure subscription

 Customers can bring their own on-premises Oracle Database licenses or subscribe to an all-inclusive license
containing all Oracle Database options and features

 Oracle Cloud operations manage all infrastructure, eliminating many administration activities previously
performed by customer staff

 Powerful cloud automation exposed through a browser-based UI and REST APIs simplifies common lifecycle
management tasks

 Customers who are unable to migrate their databases to the public cloud because of security, compliance, data
residency or dependencies on other on-premises systems can run Exadata Cloud in their own datacenter with
Exadata Cloud@Customer.

Oracle databases deployed on Exadata Cloud are 100% compatible with those deployed on-premises, ensuring a
smooth transition to the cloud, and a seamless hybrid cloud strategy. For existing Oracle Database customers,
applications and data models do not need to change to include the elasticity and flexibility of Exadata Cloud. They
also do not have to invest in separate database cloud services for different data models or workloads, since Exadata
provides a unified platform for all applications – AI, OLTP, analytics, consolidation and mixed-workloads.

Exadata Cloud is an ideal fit for:

 Business-critical production databases at any scale without incurring the capital expenditure and complexity of
maintaining the underlying IT infrastructure

 Minimizing costs for workloads whose resource requirements vary over time .

 Consolidating a variety of systems, databases and database services on powerful Exadata infrastructure, avoiding
the cost and complexity of multiple database services

 Easy provisioning of Oracle standby or replica databases for disaster recovery and/or query offloading using
Oracle Active Data Guard or Oracle GoldenGate

 Quickly provisioning high-performance ad-hoc Oracle databases for development, functionality testing,
application certification, and proof-of-concept

Uniquely engineered for extreme performance for all workloads, along with fast deployment, simplified
management, low operating costs and reduced risks, Exadata Cloud is simply the best cloud database platform.

Exadata Business Benefits

Beyond the operational benefits of extreme performance, availability, security, and deployment flexibility across on-
premises and cloud, Exadata also directly benefits the business bottom line.

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 risks of
unexpected system issues after go-live are greatly reduced. When a new application is deployed, it is common for

17 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
unanticipated application usage patterns to create performance issues. Exadata’s 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.

Exadata’s extreme performance, large memory, and flash capacity enhance employee productivity and customer
satisfaction by significantly improving user response times. Users spend more time doing valuable work, and less
time waiting for the system to respond.

Exadata’s 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

“It is not an exaggeration to say that Oracle Exadata has been the living
proof and the most important companion in Hyundai Home Shopping’s
digital innovation journey. Sales, revenue, and operating profit margins
have all grown significantly.”
Bae-hyun Kim
Team Leader, Security and Infrastructure
Hyundai Home Information, Hyundai IT&E

Conclusion
Exadata delivers a fully integrated database platform with the latest hardware technologies and unique software to
deliver extreme performance, availability, and security. Coupled with cost savings, ease of management, and
enhanced supportability results in greater business agility and efficiency. Given what can be achieved with Exadata, it
is no surprise it is the new global standard for running Oracle Databases – on-premises or in the cloud.

18 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
Exadata Server Hardware 1
Server Type CPU Memory Disk Flash Standard Network Optional Network
(DDR5) Adapters Adapters

 Client/backup  Client/backup
Database 2 x 96-core Choose: 2 x 3.84 TB NVMe
adapter 1: 2 x 10/25 adapter 3, 4, or 5:
Server2 AMD EPYC™ Flash SSD (hot Gb Ethernet ports  4 x 10 Gb
512 GB3
9J25 swappable), (SFP28) Ethernet ports
4  Client/backup (RJ45), or
processors, 1,536 GB
(upgradeable to adapter 2: 2 x 10/25  2 x 10/25 Gb
2.6 GHz Gb Ethernet ports Ethernet ports
2,304 GB4 4 x 3.84 TB)
(SFP28) (SFP28), or
(up to 4.5 GHz)
 1 x 1 Gb Ethernet port  2 x 100 Gb
3,072 GB5
(RJ45, management) optical
 1 x 1 Gb Ethernet port Ethernet ports
(RJ45, ILOM) (QSFP28)
 2 x 100 Gb QSFP28
RoCE Fabric ports

Database 1 x 32-core  Client/backup  Client/backup

Choose: 2 x 3.84 TB NVMe
Server-Z2 AMD EPYC™ adapter 1: 2 x 10/25 adapter 3:
9J15 processor Flash SSD (hot Gb Ethernet ports
768 GB3  4 x 10 Gb
2.95 GHz swappable), (SFP28)
Ethernet ports
(up to 4.4 GHz)
1,152 GB5  Client/backup (RJ45), or
(upgradeable to
4 x 3.84 TB) adapter 2: 2 x 10/25
 2 x 10/25 Gb
Gb Ethernet ports
Ethernet ports
(SFP28)
(SFP28), or
 1 x 1 Gb Ethernet port
 2 x 100 Gb
(RJ45, management)
optical
 1 x 1 Gb Ethernet port Ethernet ports
(RJ45, ILOM) (QSFP28)
 2 x 100 Gb QSFP28
RoCE Fabric ports

 2 x 100 Gb QSFP28
Storage 2 x 32-core 256 GB 12 x 22 4 x 6.8 TB NVMe PCIe
RoCE Fabric ports
Server High AMD EPYC™ TB 7,200 5.0 performance-  1 x 1 Gb Ethernet port
1,280 GB
Capacity 9J15 processors RPM optimized Flash cards (RJ45, management)
Exadata  1 x 1 Gb Ethernet port
2.95 GHz disks
RDMA (RJ45, ILOM)
(up to 4.4 GHz)
Memory

 2 x 100 Gb QSFP28
Storage 2 x 32-core 256 GB 4 x 6.8 TB NVMe PCIe
RoCE Fabric ports
Server AMD EPYC™ 5.0 performance-  1 x 1 Gb Ethernet port
1,280 GB
Extreme 9J15 processors optimized Flash cards, (RJ45, management)
Exadata  1 x 1 Gb Ethernet port
Flash 2.95 GHz and
RDMA (RJ45, ILOM)
(up to 4.4 GHz)
Memory 4 x 30.72 TB NVMe
PCIe 4.0 capacity-
optimized Flash cards

Storage  2 x 100 Gb QSFP28

1 x 32-core 192 GB 6 x 22 TB 2 x 6.8 TB NVMe PCIe
Server High RoCE Fabric ports
Capacity-Z 2 AMD EPYC™ 7,200 5.0 performance-  1 x 1 Gb Ethernet port
576 GB
9J15 processor RPM optimized Flash cards (RJ45, management)
Exadata  1 x 1 Gb Ethernet port
2.95 GHz disks
RDMA (RJ45, ILOM)
(up to 4.4 GHz)
Memory

19 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
 1 All servers include redundant hot swappable fans and power supplies
2Database Server-Z and High Capacity-Z Storage Servers can be combined with standard servers in the same rack. Minimum server requirements
apply for Normal and High Redundancy
3 Factory only option
4 Factory option and field upgrade
5 Maximum configuration, factory option and field upgrade

Exadata Rack Configurations 1, 2, 5

Rack Size Database Servers Storage Servers and High Capacity Storage Extreme Flash Storage
and Cores Cores Server Capacity (Raw) Server Capacity (Raw)

Quarter Rack 2 x servers, 384 3 x servers, 192 cores  792 TB disk or  368.6 TB capacity-
cores for SQL offload  81.6 TB performance- optimized Flash
optimized Flash  81.6 TB performance-
 3.75 TB Exadata RDMA optimized Flash
Memory  3.75 TB Exadata RDMA
Memory

Quarter Rack 2 x servers, 64 cores 3 x HC-Z servers, 96 Using Storage Server High or  368.6 TB capacity-
(Database Server-Z) cores for SQL offload Capacity-Z optimized Flash
 81.6 TB performance-
 396 TB disk
or optimized Flash
 40.8 TB performance-
 3.75 TB Exadata RDMA
optimized Flash
3 x HC or EF servers, Memory
 1.69 TB Exadata RDMA
192 cores for SQL
Memory
offload

or

Using Storage Server High

Capacity

 792 TB disk
 81.6 TB performance-
optimized Flash
 3.75 TB Exadata RDMA
Memory

Elastic Configuration 9 x servers, 1,728 9 x servers, 576 cores  2,376 TB disk or  1,105.9 TB capacity-
1 cores for SQL offload  244.8 TB performance- optimized Flash
(Example)3 optimized Flash  244.8 TB performance-
 11.25 TB Exadata RDMA optimized Flash
Memory  11.25 TB Exadata RDMA
Memory

Elastic Configuration 2 x servers, 384 17 servers, 1,088  4,488 TB disk or • 2,088 TB capacity-
2(Example)3 cores cores for SQL offload  462.4 TB performance- optimized Flash
optimized Flash
• 462.4 TB performance-
 21.25 TB Exadata RDMA
optimized Flash
Memory
• 21.25 TB Exadata RDMA
Memory

+Database Servers Up to 15x servers4,

2,880 cores max per
rack

+Storage Servers Maximum per rack: Maximum per rack using HC or Maximum per rack:
storage:
Up to 17x HC or EF  2,088 TB capacity-
servers4, 1,088 cores  4,488 TB disk optimized Flash

20 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
 or  462.4 TB performance-  462.4 TB performance-
optimized Flash optimized Flash
Up to 17x HC-Z
 21.25 TB Exadata RDMA  21.25 TB Exadata RDMA
servers4, 544 cores
Memory Memory

or

Maximum per rack using HC-

Z storage
 2,244 TB disk
 231.2 TB performance-
optimized Flash
 9.6 TB Exadata RDMA
Memory
1Each rack is 42 RU (Rack Units) in height, has 2x redundant Power Distribution Units (PDUs), 2x 36-port 100 Gb/s RoCE switches and 1x 48-port
Management Ethernet switch for administration.
2Elastic configurations allow adding database or storage servers to a quarter rack to achieve the exact ratio of compute to storage that the
application needs. An elastic configuration cannot exceed 19 servers and 38 RU (Rack Units) per rack. Database Servers = 2 RU, Storage Servers =
2 RU
3
Elastic Configuration 1 and Elastic Configuration 2 configurations added as examples of elastic configurations.
4
Maximum number of database servers allowed in an elastic configuration is 15. Maximum number of storage servers allowed in an elastic
configuration is 17.
5 Exadata X11M enables significant flexibility by allowing 1 socket (Database Server-Z and High Capacity-Z) and 2 socket database and storage

servers to be mixed in almost any combination. For example, two Database Server-Z and three Extreme Flash (EF) Storage servers can be
configured for workloads that require the extreme low latency of flash while having low database CPU and/or memory requirements. The same
type of storage server must be used when expanding existing storage servers. E.g. Extreme Flash must be used to expand Extreme Flash servers
including disk groups and storage pools. When adding a new storage server type, a minimum of two servers is required for Normal redundancy
and three for High redundancy (recommended).

Other Elastic Expansion Options

Multi-Rack Connect any combination of up to 14 Exadata Database Machine racks or Exadata Storage Expansion Racks via
Connection
the RoCE Network Fabric.

 Larger configurations can be built with external RoCE switches.

 Connected racks must contain Exadata RoCE hardware

21 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
Exadata Capacity and Performance Metrics: Individual Servers
Server Maximum Maximum SQL Maximum Maximum Exadata Performance- Capacity- Disk Data
Type SQL Flash Exadata SQL Read SQL Write RDMA Optimized PCI Optimized Capacity
Bandwidth2
RDMA IOPS1,3 IOPS4 Memory Flash Capacity PCI Flash (Raw) 5
Memory Capacity (Raw) 5 Capacity
Bandwidth2 (Raw)5 (Raw)5

2,800,000 2,500,000 7.68 TB

Database
Server

Database 1,400,000 1,250,000 7.68 TB

Server-Z

100 GB/s 500 GB/s 2,800,000 1,000,000 1,280 GB 27.2 TB 264 TB

Storage
Server
High
Capacity
(HC)1

100 GB/s 500 GB/s 2,800,000 1,000,000 1,280 GB 27.2 TB 122.88 TB

Storage
Server
Extreme
Flash (EF)1

Storage 50 GB/s 250 GB/s 1,400,000 500,000 576 GB 13.6 TB 132 TB

Server
High
Capacity-Z
(HC-Z)
1
Actual system performance varies by application.
2Bandwidth is peak physical scan bandwidth achieved running SQL, assuming no database compression. Effective user data bandwidth is higher
when using database compression.
3Based on 8K I/O requests running SQL. Note that the I/O size greatly affects Flash IOPS. Other products quote IOPS based on smaller I/Os 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 I/Os to maintain redundancy.
5 Raw capacity is measured in standard disk drive terminology with 1 GB = 1 billion bytes.

22 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
Exadata Elastic Rack Configurations: Flash Capacity and Performance
Metrics (HC, EF, and HC-Z)
Flash Metrics Maximum SQL Flash Maximum SQL Maximum SQL Performance-Optimized PCI
and Exadata RDMA XRMEM Read IOPS1,3 Flash Write IOPS4 Flash Capacity (Raw)5
Memory Bandwidth2

Elastic Configuration HC1 4,500 GB/s 25,200,000 9,000,000 244.8 TB

6
1 (Example)
EF1 4,500GB/s 25,200,000 9,000,000 244.8 TB

Elastic Configuration HC1 8,500 GB/s 5,600,000 5,000,000 462.4 TB

2 (Example)6
EF1 8,500 GB/s 5,600,000 5,000,000 462.4 TB

Quarter Rack HC1 1,500 GB/s 5,600,000 3,000,000 81.6 TB

EF1 1,500 GB/s 5,600,000 3,000,000 81.6 TB

Quarter Rack HC-Z1 750 GB/s 2,800,000 1,500,000 40.8 TB

(Database Server-Z)
HC1 1,500 GB/s 2,800,000 2,500,000 81.6 TB

EF1 1,500 GB/s 2,800,000 2,500,000 81.6 TB

1 EF = Extreme Flash; HC = High Capacity, HC-Z = High Capacity-Z
2 Bandwidth is peak physical scan bandwidth achieved running SQL, assuming no database compression. Effective user data bandwidth is higher
when using database compression.
3 Based on 8K IO requests running SQL. Note that the IO size greatly affects Flash IOPS. Others quote IOPS based on smaller IOs and are not

relevant for databases.

4
Based on 8K IO 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
Elastic Configuration 1 and Elastic Configuration 2 configurations added as examples of elastic configurations. Elastic Configuration 1 = 9x DB
and 9x Storage Servers; Elastic Configuration 2 = 2x DB and 17x HC or 17x EF Storage Servers

Exadata Elastic Rack Configurations: Disk Capacity and Performance

Metrics (HC and HC-Z)
Disk Metrics Maximum SQL Disk Bandwidth1 Maximum SQL Disk IOPS2 Data Capacity (Raw)3

Elastic Configuration 1 (Example)4 16 GB/s 23,000 2,376 TB

Elastic Configuration 2 (Example)4 30.5 GB/s 44,000 4,488 TB

Quarter Rack 5.4 GB/s 7,800 792 TB

Quarter Rack 2.7 GB/s 3,900 396 TB

(Database Server-Z)
1Bandwidth is peak physical scan bandwidth achieved running SQL, assuming no database compression. Effective user data bandwidth is higher
when database compression is used.
2Based on 8K IO requests running SQL. Note that the IO size greatly affects Flash IOPS. Others quote IOPS based on smaller IOs and are not
relevant for databases.
3 Raw capacity is measured in standard disk drive terminology with 1 GB = 1 billion bytes.

23 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
 4Elastic Configuration 1 and Elastic Configuration 2 configurations added as examples of elastic configurations. Elastic Configuration 1 = 9x DB
and 9x Storage Servers; Elastic Configuration 2 = 2x DB and 17x HC

Exadata Elastic Rack Configurations: Combined Metrics (HC, EF and HC-Z)

Combined Metrics Data Capacity (Usable) Data Capacity (Usable) High Maximum Data Load
Normal Redundancy1 Redundancy 1 Rate2

Elastic Configuration 1 HC1 983.2 TB 720.3 TB 22.5 TB/hour

(Example)3
EF1 457.6 TB 335.2 TB 22.5 TB/hour

Elastic Configuration 2 HC1 1857.2 TB 1360.6 TB 8.8 TB/hour

(Example)3
EF1 864.2 TB 633.1 TB 8.8 TB/hour

HC-Z1
Quarter Rack 153.1 TB 120 TB 3.8 TB/hour

HC1 306.1 TB 240.1 TB 7.5 TB/hour

EF1 142.5 TB 111.7 TB 7.5 TB/hour

HC-Z1
Quarter Rack 153.1 TB 120 TB 3.8 TB/hour

(Database Server-Z)
HC1
306.1 TB 240.1 TB 7.5 TB/hour

EF1 142.5 TB 111.7 TB 7.5 TB/hour

1
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. Normal redundancy
calculations reflect the use of Grid Infrastructure version 12.2.0.1 or later.
2Load rates are typically limited by database server CPU, not I/O. Rates vary based on load method, indexes, data types, compression, and
partitioning.
3
Elastic Configuration 1 and Elastic Configuration 2 configurations added as examples of elastic configurations. Elastic Configuration 1 = 9x DB
and 9x Storage Servers; Elastic Configuration 2 = 2x DB and 17x HC or 17x EF Storage Servers

24 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
Exadata Database Machine Component Environmental Specifications
Metric Exadata Exadata Exadata Exadata Exadata Exadata Exadata Storage
Database Database Database Database Storage Server Storage Server Server X11M
Server X11M Server-Z Server X11M Server X11M X11M High X11M Extreme High Capacity-Z
X11M (1.5TB (3TB Capacity (HC) Flash (EF) (HC-Z)
Memory) Memory)

Height 3.42” ( 86.9 mm )

Width 17.52 “ ( 445.0 mm )

Depth 30.51” ( 775.0 mm )

Acoustic 8.6 B 8.5 B 8.5 B 9.0 B 8.6 B 8.0 B 8.6 B

Noise
(operating)

Weight 53 lb ( 24 kg ) 53 lb ( 24 kg ) 53 lb ( 24 kg ) 53 lb ( 24 kg ) 74 lb ( 33.6 kg ) 60 lb ( 27.2 kg ) 63 lb ( 28.6 kg )

Maximum 1.2 kW 1.1 kW 1.4 kW 1.4 kW 1 kW 0.9 kW 0.8 kW

Power Usage ( 1.2 kVA ) ( 1.1 kVA ) ( 1.4 kVA ) ( 1.4 kVA ) ( 1 kVA ) ( 0.9 kVA ) ( 0.8 kVA )

Typical Power 0.8 kW 0.8 kW 1 kW 1 kW 0.7 kW 0.6 kW 0.5 kW

Usage1 ( 0.8 kVA ) ( 0.8 kVA ) ( 1 kVA ) ( 1 kVA ) ( 0.7 kVA ) ( 0.6 kVA ) ( 0.5 kVA )

Cooling at 4,054 3,783 4,726 4,705 3,474 BTU/hour 3,037 BTU/hour 2,570 BTU/hour
Maximum BTU/hour BTU/hour BTU/hour BTU/hour
Usage
4,277 3,991 4,986 4,964 3,665 kJ/hour 3,204 kJ/hour 2,712 kJ/hour
kJ/hour kJ/hour kJ/hour kJ/hour

Cooling at 2,838 2,648 3,308 3,294 2,431 BTU/hour 2,126 BTU/hour 1,799 BTU/hour
Typical Usage BTU/hour BTU/hour BTU/hour BTU/hour

2,994 2,794 3,490 3,475 2,565 kJ/hour 2,243 kJ/hour 1,898 kJ/hour
kJ/hour kJ/hour kJ/hour kJ/hour

Airflow at 188 CFM 175 CFM 219 CFM 218 CFM 161 CFM 141 CFM 119 CFM
Maximum
Usage2

Airflow at 131 CFM 123 CFM 153 CFM 152 CFM 113 CFM 98 CFM 83 CFM
Typical
Usage2

Operating temperature/humidity: 5 ºC to 32 ºC (41 ºF to 89.6 ºF), 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.

25 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
Exadata Database Machine Environmental Specifications
Metric Elastic Configuration 1 Elastic Configuration 2 Quarter Rack4 Quarter Rack (Database
(Example)3,4 (Example)3,4 Server-Z and High
Capacity-Z)

Height 78.74 in ( 2000 mm )

Width 23.62 in ( 600 mm )

Depth 47.12 in ( 1197 mm )

High Capacity Storage Servers

Acoustic Noise 9.7 B 9.9 B 9.4 B 9.4 B

(operating)

Weight 1904.7 lb ( 864 kg ) 2145 lb ( 972.9 kg ) 937.8 lb ( 425.4 kg ) 904.8 lb.

( 410.4 kg )

Maximum Power 22.5 kW ( 22.9 kVA ) 20.9 kW ( 21.3 kVA ) 6.7 kW ( 6.8 kVA ) 5.3 kW
Usage ( 5.4 kVA )

Typical Power Usage1 15.7 kW ( 16.1 kVA ) 14.6 kW ( 14.9 kVA ) 4.7 kW ( 4.8 kVA ) 3.7 kW
( 3.8 kVA )

Cooling at Maximum 76,702 BTU/hour 71,409 BTU/hour 22,779 BTU/hour 18,185 BTU/hour
Usage
80,920 kJ/hour 75,337 kJ/hour 24,032 kJ/hour 19,185 kJ/hour

Cooling at Typical 53,691 BTU/hour 49,987 BTU/hour 15,946 BTU/hour 12,730 BTU/hour
Usage
56,644 kJ/hour 52,736 kJ/hour 16,823 kJ/hour 13,430 kJ/hour

Airflow at Maximum 3551 CFM 3306 CFM 1055 CFM 842 CFM
Usage2

Airflow at Typical 2486 CFM 2314 CFM 738 CFM 589 CFM
Usage2

Extreme Flash Storage Servers

Acoustic Noise 9.7 B 9.4 B 9.2 B

(operating)

Weight 1778.7 lb ( 806.8 kg ) 1907 lb ( 865 kg ) 895.8 lb ( 406.3 kg )

Maximum Power 21.3 kW ( 21.8 kVA ) 18.8 kW ( 19.1 kVA ) 6.3 kW ( 6.4 kVA )
Usage

Typical Power Usage1 14.9 kW ( 15.2 kVA ) 13.1 kW ( 13.4 kVA ) 4.4 kW ( 4.5 kVA )

Cooling at Maximum 72,771 BTU/hour 63,984 BTU/hour 21,469 BTU/hour

Usage
76,773 kJ/hour 67,504 kJ/hour 22,650 kJ/hour

Cooling at Typical 50,940 BTU/hour 44,789 BTU/hour 15,028 BTU/hour

Usage
53,741 kJ/hour 47,253 kJ/hour 15,855 kJ/hour

Airflow at Maximum 3369 CFM 2962 CFM 994 CFM

Usage2

Airflow at Typical 2358 CFM 2074 CFM 696 CFM

Usage2

Operating temperature/humidity: 5 ºC to 32 ºC (41 ºF to 89.6 ºF), 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

26 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
 2 Airflow must be front-to-back.
3 Elastic Configuration 1 and Elastic Configuration 2 configurations added as examples of elastic configurations. Elastic Configuration 1 = 9x DB
and 9x Storage Servers ; Elastic Configuration 2 = 2x DB and 17x HC or 17x EF Storage Servers
4 Environmental specifications based on Exadata X11M database server with 1.5 TB memory

Exadata Database Machine Regulations and Certifications

Regulations 1,2,3 Product Safety:
UL/CSA 60950-1, EN 60950-1, IEC 60950-1 CB Scheme with all country differences

UL/CSA 62368-1, EN 62368-1, IEC 62368-1 CB Scheme with all country differences

EMC

Emissions: FCC CFR 47 Part 15, ICES-003, EN55032, KS C 9832, EN61000-3-11, EN61000-3-12

Immunity: EN55035, KS C 9835

Certifications 2,3 North America (NRTL), CE (European Union), International CB Scheme, HSE Exemption (India), BSMI (Taiwan), KC
(Korea), RCM (Australia), VCCI (Japan), UKCA (United Kingdom)

European Union 2014/35/EU Low Voltage Directive, 2014/30/EU EMC Directive, 2011/65/EU RoHS Directive, 2012/19/EU WEEE
Directives 3 Directive
1 All standards and certifications referenced are to the latest official version. For additional detail, please contact your sales representative.
2 Other country regulations/certifications may apply.
3 In some cases, as applicable, regulatory and certification compliance were obtained for the shelf-level systems only.

Exadata Database Machine Support Services

 Hardware Warranty: 1 year with a 4 hr. web/phone response during normal business hours (Mon-Fri 8AM-5PM), with 2 business day on-site
response/Parts Exchange
 Oracle Premier Support for Systems includes Oracle Linux support and 24x7 with 2 hour on-site hardware service response (subject to
proximity to service center)
 Oracle Premier Support for Operating Systems
 Oracle Customer Data and Device Retention
 System Installation Services
 Software Configuration Services
 Oracle Platinum Services
 Business Critical Service for Systems
 Oracle Exadata Start-Up Pack
 System Upgrade Support Services including hardware installation and software configuration
 Oracle Auto Service Request (ASR)

Optional Customer Supplied Ethernet Switch Installation in Exadata

Database Machine X11M
Each Exadata Database Machine X11M rack has 2U available at the top of the rack that can be used by customers to optionally install
their own client network Ethernet switches in the Exadata rack instead of in a separate rack. Some space, power, and cooling restrictions
apply.

27 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
Key Features and Functionality
Exadata and Database Software Features – Analytics
 Unique Automatic Parallelization and Offload of Data Scans to storage
 Unique Filtering of Rows in Storage based on 'where' clause
 Unique Filtering of Rows in Storage based on columns selected
 Unique Storage Offload of JSON and XML Analytic Queries
 Unique Filtering of rows in Storage based on Join with other Table
 Unique Hybrid Columnar Compression
 Unique Storage Index Data Skipping
 Unique I/O Resource Management by User, Query, Service, DB, etc.
 Unique Automatic Transformation to Columnar Format in Flash Cache
 Unique Smart Flash Caching for Table Scans
 Unique Storage Offload of Index Fast Full Scans
 Unique Storage Offloads of Scans on Encrypted Data, with FIPS compliance
 Unique Storage Offload for LOBs and CLOBs
 Unique Storage Offload for min/max operations
 Unique Data Mining Offload to Storage
 Unique Reverse Offload to DB servers if Storage CPUs are Busy
 Unique Automatic Data Columnarization
 Unique Automatic Conversion of Data to In-Memory Formats when Loading into Flash Cache
Exadata and Database Software Features – OLTP
 Unique Exadata RDMA Memory Data Accelerator
 Unique Exadata RDMA Memory Commit Accelerator (X8M and X9M only)
 Unique Database Aware PCI Flash
 Unique Exadata Smart Flash Caching
 Unique Exadata Smart Flash Logging
 Unique Smart Write-back Flash Cache
 Unique I/O Prioritization by cluster, workload, DB or user to ensure QOS
 Unique Exafusion Direct-to-Wire Protocol
 Unique Database Intelligent Network Resource Management
 Unique Exachk full-stack validation
 Unique Full-stack security scanning
 Unique Database scoped security
 Unique Cell-to-Cell Rebalance preserving Flash Cache and Storage Index
 Unique Full-Stack Secure Erase
 Unique Instant Data File Creation
 Unique Control of Flash Cache Size per Database
 Unique In-Memory OLTP Acceleration
 Unique Undo-Block Remote RDMA Read
 Unique Support for 4096 Pluggable Databases per Container Database with Multitenant Option
Exadata and Database Software Features – Artificial Intelligence
• Unique Automatic parallelization and offload of AI Vector Search to storage
• Unique Filtering of rows based on vector distance
• Unique Column Projection of AI Vector Search results including vector distance column from storage
• Unique Vector Distance Computation on Storage Servers
• Unique per-storage server Adaptive Top-K calculation
Exadata and Database Software Features – High Availability
 Unique Instant Detection of Node or Cell Failure
 Unique In-Memory Fault Tolerance
 Unique Sub-second Failover of I/O on stuck disk or Flash
 Unique Offload backups to storage servers
 Unique Exadata Data Validation (extended H.A.R.D.)
 Unique Prioritize Recovery of Critical Database Files
 Unique Automatic Repair of Corrupt Disk Data By Reading Other Storage Servers
 Unique Avoidance of Read I/Os on Predictive failed disks
 Unique Confinement and power cycle of temporarily poor performing drives
 Unique Shutdown Prevention If Mirror Storage Server is Down
 Unique Detection and Disabling of Unreliable Network Links
 Unique Preservation of Storage Index on Rebalance
 Unique Storage Index persistence to avoid rebuild on storage server restart
 Unique Database In-Memory Columnar Cache persistence to avoid rebuild on storage server restart

28 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
 Manageability Features
 Oracle Embedded Integrated Lights Out Manager (ILOM) with upgrade pre-staging optimizations
 Oracle Enterprise Manager Exadata Plug-in
 Unique Active AWR includes storage stats for end-to-end monitoring
 Real-time Insights server metric streaming
 IPv6 Support for Ethernet Connections
 Capacity on Demand
 Cell software transparent restart
 Flash and disk life cycle management alert
 Automatic Disk Scrub and Repair
 Trusted Partitions for Oracle Linux Virtualization
 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
 Automatic Service Request and Patch Manager (patchmgr) support for:
 database servers,
 storage servers
 power distribution units, and
 Cisco RoCE and management switches

Oracle Database Software (available separately):

 For database servers: Oracle Database 19c Enterprise Edition, Oracle Database 21c Enterprise Edition, and Oracle Database 23ai
Enterprise Edition. Oracle Database Options such as Oracle Real Application Clusters, Oracle Partitioning, Oracle Multitenant, Oracle
Active Data Guard. See the release specific documentation for feature support. Oracle Grid Infrastructure 19c or higher is required.
 For storage servers: Oracle Exadata System Software. Licenses are transferable from one system to another, or to a new
system.

Oracle Software (included):

 For database servers: Oracle Linux 8 with the Unbreakable Enterprise Kernel 7. Zero-loss Zero-copy Datagram Protocol (ZDP)
RoCEv2 protocol used to communicate between the Exadata Storage Servers and the Oracle Database which is based on the
Reliable Datagram Sockets (RDS) OpenFabrics Enterprise Distribution (OFED)

29 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public
Connect with us

Call +1.800.ORACLE1 or visit oracle.com. Outside North America, find your local office at: oracle.com/contact.

blogs.oracle.com facebook.com/oracle twitter.com/oracle

Copyright © 2025, Oracle and/or its affiliates. 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 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 means, electronic or mechanical, for any purpose, without our prior written permission.

Oracle, Java, and MySQL are registered trademarks of Oracle and/or its affiliates. Other names may be trademarks of their respective owners.

30 Oracle Exadata Database Machine X11M / Version 1.1

Copyright © 2025, Oracle and/or its affiliates / Public