摘要
广电视频点播(Video on Demand,VOD)系统包含图片、视频等海量应用数据,需要强大的存储系统和灵活的调度策略来支撑超级数据量的存储、调度和使用。对此,提出一种基于智能网格推流系统的云分布式存储策略,具备负载均衡与平滑扩容机制,可扩大本地缓存容量,提高存储抗干扰性能,保障系统资源调度速率,维护VOD系统缓存稳定;采用分层缓存管理机制,对存储数据包进行时序特征分割,减少服务器缓存时延;针对异常故障数据,利用哈希校验方式对缓存文件进行替换,保证存储数据集群的完整性,并利用读写旁路与懒惰存储解决缓存数据缺失问题。该方法可有效提高VOD系统存储效率,具有一定的参考价值。
The Video on Demand(VOD)system contains a large amount of application data,such as pictures and videos,and requires a powerful storage system and flexible scheduling policies to support the storage,scheduling,and use of a large amount of data.Therefore,this paper proposes a cloud distributed storage strategy based on intelligent grid flow pushing system,which has load balancing and smooth expansion mechanism,can expand local cache capacity,improve storage anti-interference performance,ensure system resource scheduling rate,and maintain the cache stability of VOD system.The hierarchical cache management mechanism is used to partition the time sequence features of the stored data packets to reduce the cache delay of the server.For abnormal data,the cache file is replaced by hash check to ensure the integrity of the storage data cluster,and the read-write bypass and lazy storage are used to solve the problem of cache data loss.This method can effectively improve the storage efficiency of VOD system and has certain reference value.
作者
毛红卫
陈海明
周忠瑞
MAO Hongwei;CHEN Haiming;ZHOU Zhongrui(Zhuji city Media Convergence Center,Shaoxing 311800,China)
出处
《电视技术》
2023年第11期219-222,共4页
Video Engineering
