Blog

  1. RDMA+NVM remote persistence

    Problem Due to RDMA NIC implementation, RNIC doesn't have remote persistent flush primitives. So one-sided write data from clients will write to the volatile cache on RNIC first and then ...

  2. (SC '21) LogECMem: Coupling Erasure-Coded In-memory Key-Value Stores with Parity Logging

    LogECMem uses a hybrid method of in-place update and Parity logging (PL) for parity updates.

  3. (VLDB '22) PM + Learned Index

    learned index + PM. APEX: A High-Performance Learned Index on Persistent Memory[1]

  4. (ATC '21, SDC' 20) Use PM as cache in industry

    Some industry works about how to utilize DRAM+PM archi as cache (from facebook and twitter).

  5. (ATC '21) One-sided RDMA-Conscious Extendible Hashing for Disaggregated Memory

    RDMA+KVS. Different with local hashing, insertion, deletion and update are expensive in RDMA environments. So a carefully index design based on one-sided RDMA ops is crucial.

  6. (ATC '21) Characterizing and Optimizing Remote Persistent Memory with RDMA and NVM

    An experiment-driven work from SJTU-IPADS shows some methods to achieve better performance in NVM+RDMA systems.

  7. Some eADR related works

    Some eADR related works

  8. (ICDCS '21) StripeMerge: Efficient Wide-Stripe Generation for Large-Scale Erasure-Coded Storage

    StripeMerge shows a method to merge narrow stripes to wide stripes.

  9. Erasure Coding in DRAM -- part 1

    Background EC is mainly for cold storage, providing low redundancy costs and availability. While hot storage need to keep QoS, so expensive replication is more common.

  10. (FAST '21) Exploiting Combined Locality for Wide-Stripe Erasure Coding in Distributed Storage

    ECWide uses wide stripe to decrease redundancy while avoid repairing bandwidth waste.

Search

Search articles, notes and pages.

Type to search · Esc to close