IN-MEMORY, KEY VALUE STORE

Chronicle Map Enterprise

Chronicle Map behaves like a drop-in replacement to a standard Java Map, but is faster and does not generate garbage. It uses off-heap memory and can share data between processes on the same machine, or use replication to share across the LAN or WAN.

"Chronicle Map is a really great project. I use it for off-heap storage, it incredibly increases performance"

-Dr Khalil El Mazouari, AbnomX

Trusted by Top-Tier Financial Institutions

UOB logo
RBC Royal Bank logo
MUFG Logo

How Does It Work?

You define the structure of the entries you wish to store and set the maximum number of entries. Chronicle Map will create an appropriately sized memory mapped file. 

Data is transferred directly using shared memory to other processes on the same server. Unlike some competing products, we do not use TCP/IP loopback, which introduces latency and failure modes.

This approach gives you outstanding performance, we have measured data being transferred between processes in a staggering 40 nanoseconds.

 
map enterprise diagram

Chronicle Map and Scalability

Chronicle Map Enterprise has been tested to do 30 million updates per second with 500 million key-values on a 16 core machine, with a 64 MB heap and no minor collections.

Another test is a ping-pong between processes - one process set a flag from false to true, the other from true to false. Data is not lost even if the JVM crashes on the next line after setting the value.

30 Million

Updates per second on a 16 core machine, with a 64 MB heap.

25 million

Updates per second in a ping-pong test between processes.

1.6 Million

Updates per second across low bandwidth between two laptops.

Low-Latency

performance icon

High throughput, low latency, cross process, replicated key-value store with microsecond latency

Low Resource Consumption

routing icon

Better utilise existing hardware due to optimised implementation and low use of CPU and memory resources

Support Huge Datasets

tick icon

Customers have production Maps with billions of entries. Our memory-mapping technology means that the size of the Map is constrained only by available disk space

Supported by Our Experts

handshake icon

Get full support from our technical experts, with decades of experience building low-latency software for some of the largest players in the financial sector

Robust and Resilient

configurable icon

Equipped with full HA/DR capabilities via multi-node replication and hot-hot configurations

Protects Sensitive Data

padlock secure icon

Persistent data can be encrypted at rest

Low-Latency

performance icon

High throughput, low latency, cross process, replicated key-value store with microsecond latency

Low Resource Consumption

routing icon

Better utilise existing hardware due to optimised implementation and low use of CPU and memory resources

Supported by Our Experts

handshake icon

Get full support from our technical experts, with decades of experience building low-latency software for some of the largest players in the financial sector

Support Huge Datasets

tick icon

Customers have production Maps with billions of entries. Our memory-mapping technology means that the size of the Map is constrained only by available disk space

Robust and Resilient

configurable icon

Equipped with full HA/DR capabilities via multi-node replication and hot-hot configurations

Protects Sensitive Data

padlock secure icon

Persistent data can be encrypted at rest

routing icon

Low Resource Consumption

Better utilise existing hardware due to optimised implementation and low use of CPU and memory resources

performance icon

Low-Latency

High throughput, low latency, cross process, replicated key-value store with microsecond latency

handshake icon

Supported by Our Experts

Get full support from our technical experts, with decades of experience building low-latency software for some of the largest players in the financial sector

tick icon

Support Huge Datasets

Customers have production Maps with billions of entries. Our memory-mapping technology means that the size of the Map is constrained only by available disk space

padlock secure icon

Protects Sensitive Data

Persistent data can be encrypted at rest

configurable icon

Robust and Resilient

Equipped with full HA/DR capabilities via multi-node replication and hot-hot configurations

Licensing and support

At Chronicle we pride ourselves on the stability and knowledge of our development and support team. With decades of experience from the financial industry, you can trust us with your toughest challenges.

Get expert help

Our expert consultants are ready to support you with any issues that may arise. We understand that the Chronicle Map is usually only a small part of a system, and our experienced developers can help with architecture and latency issues in other areas if needed.

 

Simple licensing model

Our simple and transparent licensing model provides certainty and ensures that Chronicle Map Enterprise is available to businesses of all sizes, from the largest bank to the smallest hedge fund.

What's Next?

Get Started Today

If you want to learn more about how Chronicle Map Enterprise works, why not see a demo? 

Contact us today:

Articles about Chronicle Map

Efficient Memory Mapping for Terabyte Sparse Files in Java

On Linux, you can create sparse files, where only the pages (of 4 KiB) that are touched utilise either memory or disk space. This allows you to memory map large virtual regions without worrying about wasted memory or disk In this program, you can see it reserves 8 TiB (8,192 GiB) Figure 1. Test 1:…

Continue Reading >>

Did You Know You Can Create Mappers Without Creating Underlying Objects in Java?

As most Java developers know, putting values in a Java Map (like a HashMap) involves creating a large number of auxiliary objects under the covers. For example, a HashMap with int keys and long values might, for each entry, create a wrapped Integer, a wrapped Long object and a Node that holds the former values…

Continue Reading >>

Improving Percentile Latencies in Chronicle Queue

Compared to a year ago, we have significantly improved the throughput at which we can achieve the 99%ile (worst one in 100). What tools and tricks did we use to achieve that? What are we testing? Chronicle Queue appends messages to a file while another thread or process can be reading it. This gives you…

Continue Reading >>