skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


This content will become publicly available on August 1, 2026

Title: Disaggregated State Management in Apache Flink® 2.0
We present Apache Flink 2.0, an evolution of the popular stream processing system's architecture that decouples computation from state management. Flink 2.0 relies on a remote distributed file system (DFS) for primary state storage and uses local disks as a secondary cache, with state updates streamed continuously and directly to the DFS. To address the latency implications of remote storage, Flink 2.0 incorporates an asynchronous runtime execution model. Furthermore, Flink 2.0 introduces ForSt, a novel state store featuring a unified file system that enables faster and lightweight checkpointing, recovery, and reconfiguration with minimal intrusion to the existing Flink runtime architecture. Using a comprehensive set of Nexmark benchmarks and a large-scale stateful production workload, we evaluate Flink 2.0's large-state processing, checkpointing, and recovery mechanisms. Our results show significant performance improvements and reduced resource utilization compared to the baseline Flink 1.20 implementation. Specifically, we observe up to 94% reduction in checkpoint duration, up to 49× faster recovery after failures or a rescaling operation, and up to 50% cost savings.  more » « less
Award ID(s):
2440334
PAR ID:
10659062
Author(s) / Creator(s):
; ; ; ; ; ; ; ; ;
Publisher / Repository:
Proceedings of the VLDB Endowment
Date Published:
Journal Name:
Proceedings of the VLDB Endowment
Volume:
18
Issue:
12
ISSN:
2150-8097
Page Range / eLocation ID:
4846 to 4859
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Proceedings of the USENIX Conference on File and Storage Technologies (FAST 2021))
    Aguilera, Marcos; Yadgar, Gala (Ed.)
    Training Deep Neural Networks (DNNs) is a resource-hungry and time-consuming task. During training, the model performs computation at the GPU to learn weights, repeatedly, over several epochs. The learned weights reside in GPU memory, and are occasionally checkpointed (written to persistent storage) for fault-tolerance. Traditionally, model parameters are checkpointed at epoch boundaries; for modern deep networks, an epoch runs for several hours. An interruption to the training job due to preemption, node failure, or process failure, therefore results in the loss of several hours worth of GPU work on recovery. We present CheckFreq, an automatic, fine-grained checkpointing framework that (1) algorithmically determines the checkpointing frequency at the granularity of iterations using systematic online profiling, (2) dynamically tunes checkpointing frequency at runtime to bound the checkpointing overhead using adaptive rate tuning, (3) maintains the training data invariant of using each item in the dataset exactly once per epoch by checkpointing data loader state using a light-weight resumable iterator, and (4) carefully pipelines checkpointing with computation to reduce the checkpoint cost by introducing two-phase checkpointing. Our experiments on a variety of models, storage backends, and GPU generations show that CheckFreq can reduce the recovery time from hours to seconds while bounding the runtime overhead within 3.5%. 
    more » « less
  2. (, File and storage technologies)
    We present FusionFS, a direct-access firmware-level in-storage filesystem that exploits the near-storage computational capability for fast I/O and data processing, consequently reducing I/O bottlenecks. In FusionFS, we introduce a new abstraction, CISCOps, that combines multiple I/O and data processing operations into one fused operation and offloaded for near-storage processing. By offloading, CISCOps significantly reduces dominant I/O overheads such as system calls, data movement, communication, and other software overheads. Further, to enhance the use of CISCOps, we introduce MicroTx for fine-grained crash consistency and fast (automatic) recovery of I/O and data processing operations. We also explore scheduling techniques to ensure fair and efficient use of in-storage compute and memory resources across tenants. Evaluation of FusionFS against the state-of-the-art user-level, kernel-level, and firmware-level file systems using microbenchmarks, macrobenchmarks, and real-world applications shows up to 6.12X, 5.09X and 2.07X performance gains, and 2.65X faster recovery for applications. 
    more » « less
  3. ; ; ; ; (, Proceedings of the 48th International Conference on Parallel Processing (ICPP) 2019)
    Pregel-like systems are popular for iterative graph processing thanks to their user-friendly vertex-centric programming model. However, existing Pregel-like systems only adopt a naïve checkpointing approach for fault tolerance, which saves a large amount of data about the state of computation and signi!cantly degrades the failure-free execution performance. Advanced fault tolerance/recovery techniques are left unexplored in the context of Pregel-like systems. This paper proposes a non-invasive lightweight checkpointing (LWCP) scheme which minimizes the data saved to each checkpoint, and additional data required for recovery are generated online from the saved data. This improvement results in 10x speedup in checkpointing, and an integration of it with a recently proposed log-based recovery approach can further speed up recovery when failure occurs. Extensive experiments veri!ed that our proposed LWCP techniques are able to signi!cantly improve the performance of both checkpointing and recovery in a Pregel-like system. 
    more » « less
  4. ; ; ; ; ; (, ACM)
    We introduce CrossPrefetch, a novel cross-layered I/O prefetching mechanism that operates across the OS and a user-level runtime to achieve optimal performance. Existing OS prefetching mechanisms suffer from rigid interfaces that do not provide information to applications on the prefetch effectiveness, suffer from high concurrency bottlenecks, and are inefficient in utilizing available system memory. CrossPrefetch addresses these limitations by dividing responsibilities between the OS and runtime, minimizing overhead, and achieving low cache misses, lock contentions, and higher I/O performance. CrossPrefetch tackles the limitations of rigid OS prefetching interfaces by maintaining and exporting cache state and prefetch effectiveness to user-level runtimes. It also addresses scalability and concurrency bottlenecks by distinguishing between regular I/O and prefetch operations paths and introduces fine-grained prefetch indexing for shared files. Finally, CrossPrefetch designs low-interference access pattern prediction combined with support for adaptive and aggressive techniques to exploit memory capacity and storage bandwidth. Our evaluation of CrossPrefetch, encompassing microbenchmarks, macrobenchmarks, and real-world workloads, illustrates performance gains of up to 1.22x-3.7x in I/O throughput.We also evaluate CrossPrefetch across different file systems and local and remote storage configurations. 
    more » « less
  5. ; ; ; (, Proc. of IEEE Int. Conf. on Cluster Computing (Cluster'18))
    Unified Virtual Memory (UVM) was recently introduced with CUDA version 8 and the Pascal GPU. The older CUDA programming style is akin to older large-memory UNIX applications which used to directly load and unload memory segments. Newer CUDA programs have started taking advantage of UVM for the same reasons of superior programmability that UNIX applications long ago switched to assuming the presence of virtual memory. Therefore, checkpointing of UVM has become increasing important, especially as NVIDIA CUDA continues to gain wider popularity: 87 of the top 500 supercomputers in the latest listings use NVIDIA GPUs, with a current trend of ten additional NVIDIA-based supercomputers each year. A new scalable checkpointing mechanism, CRUM (Checkpoint-Restart for Unified Memory), is demonstrated for hybrid CUDA/MPI computations across multiple computer nodes. The support for UVM is particularly attractive for programs requiring more memory than resides on the GPU, since the alternative to UVM is for the application to directly copy memory between device and host. Furthermore, CRUM supports a fast, forked checkpointing, which mostly overlaps the CUDA computation with storage of the checkpoint image in stable storage. The runtime overhead of using CRUM is 6% on average, and the time for forked checkpointing is seen to be a factor of up to 40 times less than traditional, synchronous checkpointing. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email