README.md

Big Queue

A big, fast, and persistent queue based on a memory-mapped file.

Notice, bigqueue is just a standalone library, for a high-throughput, persistent, distributed, publish-subscribe messaging system, please refer to Luxun, Luxun messaging system uses bigqueue internally as fast and persistent queue.

Feature Highlight

1. Fast: close to the speed of direct memory access, both enqueue and dequeue are close to O(1) memory access.
2. Big: the total size of the queue is only limited by the available disk space.
3. Persistent: all data in the queue is persisted on disk, and is crash-resistant.
4. Reliable: OS will be responsible to persist the produced messages even your process crashes.
5. Realtime: messages produced by producer threads will be immediately visible to consumer threads.
6. Memory-efficient: automatic paging & swapping algorithm, only most-recently accessed data is kept in memory.
7. Thread-safe: multiple threads can concurrently enqueue and dequeue without data corruption.
8. Simple & Light-weight: current number of source files is 12 and the library jar is less than 30K.

The Big Picture

Memory Mapped Sliding Window

Performance Highlight

• In concurrent producing and consuming cases, the average throughput is around 166M bytes per second.
• In sequential producing than consuming case, the average throughput is around 333M bytes per second.

Suppose the average message size is 1KB, then bigqueue can concurrently producing and consuming 166K messages per second. Basically, the throughput is only limited by disk I/O bandwidth.

here is a detailed performance report

How to Use

1. Direct jar or source

Download jar from repository mentioned in the version history section below, the latest stable release is 0.7.0.

Note: bigqueue depends on log4j, please also added log4j jar reference if you use bigqueue.

2. Maven

<dependency>
    <groupId>com.leansoft</groupId>
    <artifactId>bigqueue</artifactId>
    <version>0.7.0</version>
</dependency>

<repository>
    <id>github.release.repo</id>
    <url>https://raw.github.com/bulldog2011/bulldog-repo/master/repo/releases/</url>
</repository>

Docs

1. A Simple Design Document
2. Big Queue Tutorial
3. Fanout Queue Tutorial
4. Big Array Tutorial
5. How to turn big queue into a Thrift based Queue Service
6. Use case: producing and consuming 4TB log daily on one commodity machine
7. Use case: sort and search 100GB data on a single commodity machine
8. The architecture and design of a pub-sub messaging system tailored for big data collecting and analytics
9. A big, fast and persistent queue[ppt]

Version History

0.7.0 - March 24, 2013: repository

• Feature: support fanout queue semantics
• Enhancement: make data file size configurable

0.6.1 — January 29, 2013: repository

• Initial version

Copyright and License

Copyright 2012 Leansoft Technology [email protected]

Licensed under the Apache License, Version 2.0 (the "License"); you may not use this work except in compliance with the License. You may obtain a copy of the License in the LICENSE file, or at:

http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License.