SMDG: Enhancing In-Memory Dynamic Graph Processing With Storage-Class Memory
IEEE Transactions on Knowledge and Data Engineering · 2026-06 · 38 (6) · 3895-3911
DOI: 10.1109/tkde.2026.3676514 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-06. Verfasst von Tongfeng Weng und 6 weiteren Autor:innen. Die Arbeit nennt 65 Literaturangaben. Gefördert von: Ministry of Education, WBS.
Abstract (Originalsprache)
In-memory dynamic graph processing faces three critical challenges: limited DRAM capacity, inefficient concurrent update/query handling, and vulnerability to crashes. Traditional segment-level systems struggle with write amplification on emerging Storage-Class Memory (SCM), while existing persistent-memory systems suffer from coarse-grained synchronization and high recovery overhead. This study presents the Storage-Class Memory Dynamic Graph (SMDG) processing framework, an architecture-level redesign centered on the block as the atomic unit across storage, concurrency, and recovery. The system addresses these challenges through three key innovations. First, a block-granular storage design organizes adjacency data at fixed-size block granularity on heterogeneous DRAM-SCM architecture, employing buffered batched writes to significantly reduce write amplification while preserving logarithmic update complexity. Second, block-level multi-version concurrency control maintains timestamped block versions under per-vertex read-write synchronization to provide task-ordered snapshot visibility for concurrent queries without copying entire vertices or pages. Third, a block-granular crash recovery protocol with decentralized per-vertex logs enables independent parallel reconstruction, ensuring application-level semantic consistency while achieving substantially faster recovery than sequential approaches. Experimental results validate that this unified block-granular design improves update efficiency, sustains mixed update-query workloads with controlled memory overhead, and accelerates crash recovery compared with prior dynamic graph systems.
Förderung
- Ministry of Education
- WBS
Zitieren
APA
Weng, T., Sha, M., Zhou, X., Lu, J., Huang, W., Li, K., & Tan, K. (2026). SMDG: Enhancing In-Memory Dynamic Graph Processing With Storage-Class Memory. IEEE Transactions on Knowledge and Data Engineering, 38(6), 3895-3911. https://doi.org/10.1109/tkde.2026.3676514
Vancouver
Weng T, Sha M, Zhou X, Lu J, Huang W, Li K, et al. SMDG: Enhancing In-Memory Dynamic Graph Processing With Storage-Class Memory. IEEE Transactions on Knowledge and Data Engineering. 2026;38(6):3895-3911. doi:10.1109/tkde.2026.3676514
BibTeX
@article{Weng2026,
author = {Weng, Tongfeng and Sha, Mo and Zhou, Xu and Lu, Jingjing and Huang, Wentao and Li, Kenli and Tan, Kian-Lee},
title = {SMDG: Enhancing In-Memory Dynamic Graph Processing With Storage-Class Memory},
journal = {IEEE Transactions on Knowledge and Data Engineering},
year = {2026},
volume = {38},
number = {6},
pages = {3895--3911},
doi = {10.1109/tkde.2026.3676514}
}
EUVIMED