Chronicle Queue

Persisted low-latency messaging framework that handles massive throughput at microsecond latencies for high-performance and critical applications. 

Low-Latency IPC

Chronicle Queue aims to achieve latencies of under 40 microseconds end-to-end across multiple services 99.99% of the time.

High-Resolution Timings Across Machines

Chronicle Queue allows calibrated timings across machines to accurately detect outliers.

Persistence to Disk

Chronicle Queue makes full use of the disk space available, hence is not constrained by the main memory of your machine. As all saved data is stored as memory-mapped files, the on-heap overhead is insignificant, even for 100 TBs of data.

Replays All Input and Output

Chronicle Queue supports several replay strategies to give control of what messages to replay, and when. For example, choose to replay every message, only new messages, only missed messages, or restart from any known point using the index of the entry.

Real-Time Compression

Can be paired with Chronicle Wire Enterprise for real-time compression to reduce message sizes by a factor of 10, with minimal delays. Other less performant options are LZW, Snappy, and GZIP.

Compacting Logs

Chronicle Queue manages storage by cycle. A listener can be added to receive notifications whenever a new file is added, and when it is no longer retained. At that point, the file can be moved, compressed, or deleted, depending on the application. 


Chronicle Queue Benchmarks

Chronicle Queue can be considered to be similar to a low-latency, broker-less durable/persisted JVM topic. It is a distributed, unbounded, persisted queue that:

  • supports asynchronous RMI and pub/sub interfaces with microsecond latencies

  • passes messages between JVMs in under 1 µs*

  • provides stable, soft, real-time latencies into the millions of messages/s for a single thread to one queue

* In optimised examples

Write-to-Read Latency Between 2 Threads

Delivers Value for Companies Worldwide


Chronicle Queue Enterprise

Chronicle Queue Enterprise is the commercially supported version of Chronicle Queue. Beyond being fully supported by our technical experts, the software is also equipped with features that boost performance even more and allow your queues to be replicated across hosts for back-up. Queues can also be encrypted to protect sensitive data, and rollover schedules can be configured with regard to timezones.

<4 µs

Read-to-write latency in async mode 

Expert Support

Get full support by our technical experts

TCP/IP Replication

Real-time back-up of all queue data

Timezone Rolling

Easy timezone rollover scheduling 

Articles about Chronicle Queue

Big Data and Chronicle Queue

The Big Question How is Chronicle Queue being used for Big Data solutions in Java, and how does it work under the covers? What is Chronicle Queue? Chronicle Queue is a persisted journal of messages which supports concurrent writers and readers even across multiple JVMs on the same machine. Every reader sees every message, and…

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 >>

Chronicle Queue storing 1TB in virtual memory on a 128GB machine

If you use a standard JVM like the Oracle JVM or the OpenJDK, you might find that as the heap size grows the performance of your JVM can drop as GC pause time escalates. This tends to be a problem around 32 GB of heap, but it often depends on the application at which point…

Continue Reading >>

Get Started Today

Chronicle Queue is available open source, so why not get started right away? Follow the Quick Start link below to get set up in minutes.