TY - GEN
T1 - Rethinking Tiered Storage
T2 - 20th ACM Workshop on Hot Topics in Operating Systems!
AU - Zhang, Jiyuan
AU - Kim, Jongyul
AU - Alverti, Chloe
AU - Liu, Peizhe
AU - Jia, Weiwei
AU - Xu, Tianyin
N1 - We thank our shepherd Dan Tsafrir for the extensive technical discussion that reshaped the paper. We thank Swaminathan Sundararaman and Nam Sung Kim for their valuable technical discussion. The paper is supported in part by NSF CNS-1956007, CNS-2145295, SHF-2348066, an IIDAI grant, and the Wing Kai Cheng Fellowship.
PY - 2025/6/6
Y1 - 2025/6/6
N2 - Different storage technologies motivate the development of specialized file systems tailored to specific device types. A tiered file system aggregates such device types into a single file system. We argue that the current practice of developing tiered file systems tends to lag behind that of device-specific file systems because, inherently, developers are burdened with addressing multiple device types simultaneously, rather than specializing. We propose to solve this problem using Mux, a new tiered file system that accesses different device types indirectly through device-specific file systems, rather than directly through device drivers. Despite introducing an additional indirection layer, we show that Mux significantly outperforms Strata, a research tiered file system, because it utilizes specialized production-ready file systems. Compared with direct access to per-device file systems (with no tiering), Mux adds a worst-case read latency overhead of 6.6% to 87.3%, and a write throughout overhead of 1.6% to 3.5% across devices. We contend that Mux's separation of tiering and specialization concerns enables progressive evolution and flexible integration of heterogeneous storage devices.
AB - Different storage technologies motivate the development of specialized file systems tailored to specific device types. A tiered file system aggregates such device types into a single file system. We argue that the current practice of developing tiered file systems tends to lag behind that of device-specific file systems because, inherently, developers are burdened with addressing multiple device types simultaneously, rather than specializing. We propose to solve this problem using Mux, a new tiered file system that accesses different device types indirectly through device-specific file systems, rather than directly through device drivers. Despite introducing an additional indirection layer, we show that Mux significantly outperforms Strata, a research tiered file system, because it utilizes specialized production-ready file systems. Compared with direct access to per-device file systems (with no tiering), Mux adds a worst-case read latency overhead of 6.6% to 87.3%, and a write throughout overhead of 1.6% to 3.5% across devices. We contend that Mux's separation of tiering and specialization concerns enables progressive evolution and flexible integration of heterogeneous storage devices.
KW - File System
KW - Operating System
KW - Tiered Storage
UR - https://www.scopus.com/pages/publications/105010237624
UR - https://www.scopus.com/pages/publications/105010237624#tab=citedBy
U2 - 10.1145/3713082.3730383
DO - 10.1145/3713082.3730383
M3 - Conference contribution
AN - SCOPUS:105010237624
T3 - HOTOS 2025 - Proceedings of the 2025 Workshop in Hot Topics in Operating Systems
SP - 67
EP - 73
BT - HOTOS 2025 - Proceedings of the 2025 Workshop in Hot Topics in Operating Systems
PB - Association for Computing Machinery
Y2 - 14 May 2025 through 16 May 2025
ER -