Multi-Tiered Storage Adaptive Video Streaming
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Adaptive HTTP streaming systems face challenges in ensuring quality of service for video delivery due to reliance on large resource provisioning, leading to high costs and power consumption, especially with traditional HDDs, while SSDs offer lower power consumption but have high costs and limited lifetime.
Innovation Solution
A multi-tiered storage system is implemented, utilizing RAM, SSDs, and HDDs, with an optimal block size determination method for SSDs to minimize write amplification and prioritize read operations, incorporating an evict-ahead policy and metadata embedding for efficient video streaming.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If traditional HDDs are used for storage capacity and bandwidth, then storage capacity is improved, but power consumption and cooling costs increase significantly
Solution Approach 1:
The patent divides the storage system into multiple tiers: SSD tier for hot content (frequently accessed videos) and HDD tier for cold content (less frequently accessed videos). This segmentation allows the system to use energy-efficient SSDs for only the necessary portion of storage, reducing overall power consumption while maintaining adequate total storage capacity.
Solution Approach 2:
The patent applies different storage media with different energy characteristics to different portions of the video library based on access patterns. Hot content stored on SSDs receives high-performance, low-power treatment, while cold content on HDDs uses cost-effective, higher-power storage only when necessary, optimizing the local energy efficiency of each storage region.
2Use of energy by moving object
If SSDs are used for storage, then power consumption is reduced, but cost per gigabyte increases
Solution Approach 1:
The system segments the video library into hot and cold content, allocating expensive SSD storage only to hot content that requires low power consumption and high performance. Cold content remains on cheaper HDDs, optimizing the cost-to-capacity ratio while still achieving energy efficiency for the actively used portion of the library.
Solution Approach 2:
The patent changes the parameter of storage media selection based on content access patterns. By dynamically determining which content is hot versus cold and allocating storage resources accordingly, the system adapts the cost and power consumption parameters to match actual usage requirements.
3Productivity
If large resource provisioning is used for CDN infrastructure, then video delivery performance is improved, but cost and resource over-provisioning increase
Solution Approach 1:
The patent segments the video library by access frequency and provisions storage resources accordingly. By using SSDs for hot content and HDDs for cold content, the system achieves high delivery performance for frequently accessed videos without needing to over-provision expensive SSD capacity for the entire library.
Solution Approach 2:
The system implements adaptive caching that automatically identifies hot content and caches it on SSDs based on access patterns. This self-service mechanism allows the system to optimize performance and resource utilization without manual intervention, delivering high performance only when and where needed.
Data Source
AI summary
The disclosed technology includes techniques for efficiently streaming media content from a multi-tiered storage system. An example implementation may be used for adaptive HTTP streaming of video segments and other content. In some implementations, flash memory SSDs (SLC or MLC) may form an intermediate cache layer between a first layer of DRAM cache and third layer of HDDs. Significant architectural elements of various implementations include optimal write granularity to overcome the write amplification effect of flash memory SSDs and a QoS-sensitive caching strategy that monitors the activity of the flash memory SSDs to ensure that video streaming performance is not hampered by the caching activity.