CRAM is a novel memory compression model for Linux that keeps compressed data directly in RAM, diverging from traditional methods like zswap and ZRAM which function as swap-layer features. This new model aims to significantly improve performance by re-evaluating where the primary performance bottlenecks lie in compressed memory systems.
Conceptualized by Gregory Price and his team at Meta, CRAM's development was driven by the realization that the largest performance hit in compressed memory systems comes from faulting and swap behavior, not the compression process itself. By keeping compressed data entirely in memory, CRAM seeks to eliminate these swap-related overheads.
CRAM utilizes existing Linux mechanisms to achieve higher performance. It employs a private NUMA node, rather than presenting itself as a block device, allowing Linux to manage CRAM using its native memory semantics, including migration and ballooning. This design enables radically faster compressed memory operations, particularly for reads.
A key component, the "Chicken Bit," helps Linux manage CRAM allocations, especially when writes exceed CRAM's capacity. The challenge of dynamically determining logical RAM size with varying data compressibility and predicting memory exhaustion remains an area of ongoing research for CRAM.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
Meta developed CRAM, a new Linux memory compression model that operates entirely within RAM, avoiding the swap layer. This approach yields up to 452 times the performance of ZRAM by addressing performance bottlenecks related to swap behavior rather than compression itself.