pith. sign in

arxiv: 2607.01486 · v1 · pith:4NA4LTFInew · submitted 2026-07-01 · 💻 cs.DC

SLFS: a Flexible, Low-Cost Distributed File System Using Serverless Designs

Cheng Hao (Ryan) Yang , Paola Alsharabaty , Soufiane Jounaid , Cristina Nita-Rotaru , Ji-Yong Shin This is my paper

Pith reviewed 2026-07-03 18:16 UTC · model grok-4.3

classification 💻 cs.DC
keywords serverless computingdistributed file systemscold start mitigationelastic scalingkey-value storesmetadata operationscost efficiency
0
0 comments X

The pith

SLFS builds a distributed file system using serverless functions for both data and metadata operations.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Traditional distributed file systems must provision resources for peak demand, yet file access patterns fluctuate and leave capacity idle because scaling entire servers takes minutes or hours. Serverless computing supplies millisecond elasticity and pay-per-use billing, but cold starts have blocked its use for file-system workloads. SLFS places file services on key-value stores so that individual function operations stay simple and short, then adds a multi-threaded short-lived server design to eliminate cold-start delays without inflating cost. A policy-enforcing coordinator maps files to instances, performs elastic scaling, and tunes function lifetimes to balance speed and expense. The same architecture runs on backends from S3 to user-managed stores, letting operators trade cost against performance.

Core claim

SLFS implements file services on top of key-value stores, keeping function operations simple and short, and introduces a novel multi-threaded, short-lived server design that overcomes the cold-start problem while maintaining low cost. A policy-enforcing coordinator efficiently maps files to function instances, scales the system elastically, and controls function lifetimes to balance performance and cost. SLFS can flexibly run on diverse storage backends -- from cloud-native services like S3 to user-managed key-value stores -- enabling configurable cost-performance trade-offs.

What carries the argument

Multi-threaded short-lived server design that overcomes cold starts at low cost, together with a policy-enforcing coordinator that maps files, scales instances, and controls lifetimes.

If this is right

  • File-system scaling can occur at millisecond granularity instead of minutes or hours.
  • Cost can be reduced by up to 68 percent relative to EFS while preserving or improving performance.
  • Cold starts can be lowered by a factor of 580 compared with a plain serverless implementation.
  • The same code base can be deployed against S3 or against a local key-value store to obtain different cost-performance points.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The coordinator's mapping and lifetime policies could be reused as a general pattern for other stateful serverless services that need fine-grained elasticity.
  • Because the design decouples the file-system logic from any single storage backend, it may simplify hybrid deployments that span public cloud and on-premise stores.
  • Extending the short-lived server pattern to metadata-heavy workloads beyond files could reduce cold-start penalties in other distributed systems.

Load-bearing premise

The multi-threaded short-lived server design can eliminate cold starts without raising overall operating cost.

What would settle it

Measure cold-start frequency and total cost when running SLFS on a fluctuating real-world workload and compare those numbers directly to an otherwise identical serverless implementation that lacks the multi-threaded short-lived design.

Figures

Figures reproduced from arXiv: 2607.01486 by Cheng Hao (Ryan) Yang, Cristina Nita-Rotaru, Ji-Yong Shin, Paola Alsharabaty, Soufiane Jounaid.

Figure 1
Figure 1. Figure 1: Cost comparison [13] of SLFS under different con￾figurations and a cloud native file system, EFS. resource usage in serverless functions than in VMs. Thus, using serverless functions non-stop is not cost-effective and only the applications with some idle periods could benefit from serverless designs. Storage accesses in the cloud exhibit such idle patterns and we conduct a cost analysis [PITH_FULL_IMAGE:f… view at source ↗
Figure 3
Figure 3. Figure 3: Separation of control and data flows. function instance design was proposed by LambdaObject [61], but SLFS further extends the idea. First, read-only files can be mapped to multiple functions for concurrent reads. Second, SLFS maps multiple files to one function instance, since operations are the same across all files/directories. This facilitates function instance reuse to avoid cold start and improves fu… view at source ↗
Figure 4
Figure 4. Figure 4: Relationship between SLFS components and de￾tailed designs. Dynamic policy designs are in blue. While open source serverless frameworks allow inbound connec￾tion to function instances, some commercial platforms prohibit this. As a workaround, one can use TCP/NAT hole punching [41, 45]. 3.5 Storage Backend SLFS is designed to work with key-value storage backends. The condition for safety (see Section 4.3) i… view at source ↗
Figure 5
Figure 5. Figure 5: SLFS cache design and cache migration (dotted ar￾rows) to replacement function instances. 6 Caching We implement a write-through least recently used (LRU) block cache inside each function to increase the performance and mem￾ory utilization ( [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 7
Figure 7. Figure 7: Scaling of function instances depending on the load. [PITH_FULL_IMAGE:figures/full_fig_p009_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Performance under a fixed number of coordinators [PITH_FULL_IMAGE:figures/full_fig_p009_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: SLFS cache and InfiniCache. SLFS cache performs comparably at a cheaper cost. The SLFS cache hit rate is comparable to InfiniCache. However, because SLFS passes the recently accessed data information to new instances, it exhibits a better hit rate when InfiniCache loses a chunk of cached data due to an instance termination (i.e., “b1”). Because InfiniCache requires running separate cache instances, the cos… view at source ↗
Figure 1
Figure 1. Figure 1: However, 𝜆FS which yields comparable hot start results to SLFS costs significantly more than SLFS as its function instance always runs until the maximum allowed duration: on average 𝜆FS costs 21 times higher than SLFS. This clearly shows the need and effectiveness of the function lifetime management of SLFS. 8.5 Metadata Operations under 𝜆FS Benchmark We use 𝜆FS benchmark [26] to saturate the throughput to… view at source ↗
Figure 12
Figure 12. Figure 12: End-to-end runtime comparison against EFS and [PITH_FULL_IMAGE:figures/full_fig_p011_12.png] view at source ↗
read the original abstract

Large-scale distributed file systems must provision resources for peak demand, yet file access patterns fluctuate significantly, leaving substantial capacity idle during off-peak periods. Existing scaling mechanisms operate at the granularity of entire servers and take minutes to hours, making them unable to track the rapid, fine-grained load variations that file systems commonly experience. Serverless computing, with its millisecond-granularity elasticity and pay-per-use pricing, offers a compelling alternative. We present SLFS, the first distributed file system built with serverless functions for both data and metadata operations. SLFS implements file services on top of key-value stores, keeping function operations simple and short, and introduces a novel multi-threaded, short-lived server design that overcomes the cold-start problem while maintaining low cost. A policy-enforcing coordinator efficiently maps files to function instances, scales the system elastically, and controls function lifetimes to balance performance and cost. SLFS can flexibly run on diverse storage backends -- from cloud-native services like S3 to user-managed key-value stores -- enabling configurable cost-performance trade-offs. Our evaluation shows that SLFS mitigates cold starts by 580$\times$ compared to the base serverless design and outperforms $\lambda$FS, EFS, and Ceph at up to 63%, 68%, and 63% lower cost, respectively.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper presents SLFS as the first distributed file system using serverless functions for both data and metadata operations. It builds file services atop key-value stores with short, simple operations, introduces a multi-threaded short-lived server design plus a policy-enforcing coordinator to map files, scale elastically, and control lifetimes, and supports configurable backends from S3 to user-managed KV stores. Evaluation claims include 580× cold-start mitigation versus base serverless and up to 63%, 68%, and 63% lower cost than λFS, EFS, and Ceph respectively.

Significance. If the reported performance and cost results hold under scrutiny, the work would demonstrate a practical path to millisecond-granularity elasticity for distributed file systems, directly addressing the mismatch between peak-provisioned servers and variable file-access patterns. The KV-backend abstraction and coordinator lifetime policy are concrete strengths that could influence future serverless storage designs.

major comments (1)
  1. [Evaluation] Evaluation section: the central claims of 580× cold-start reduction and the specific cost savings (63–68% lower than the three baselines) are stated without visible experimental setup, workload definitions, trial counts, or error bars. These details are load-bearing for the primary contribution and must be supplied to allow verification.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their review and constructive comment on the evaluation. We address the concern below and will revise the manuscript accordingly.

read point-by-point responses

  1. Referee: [Evaluation] Evaluation section: the central claims of 580× cold-start reduction and the specific cost savings (63–68% lower than the three baselines) are stated without visible experimental setup, workload definitions, trial counts, or error bars. These details are load-bearing for the primary contribution and must be supplied to allow verification.

    Authors: We agree that the current evaluation section lacks sufficient methodological detail to allow independent verification of the reported 580× cold-start mitigation and cost savings. In the revised manuscript we will expand the Evaluation section to explicitly describe: (1) the experimental setup and hardware/cloud configuration, (2) the workloads and access patterns used (including file sizes, operation mixes, and concurrency levels), (3) the number of trials/repetitions performed for each measurement, and (4) error bars or variance statistics for all reported figures. These additions will directly support the primary claims without altering the experimental results themselves. revision: yes

Circularity Check

0 steps flagged

No significant circularity identified

full rationale

The paper describes an implemented distributed file system (SLFS) using serverless functions for data and metadata, a multi-threaded short-lived server design, and a coordinator for mapping and scaling. All central claims rest on empirical measurements from the running system (e.g., 580× cold-start mitigation and cost comparisons) rather than any equations, fitted parameters renamed as predictions, or self-referential definitions. No derivation chain exists that reduces to its own inputs by construction, and the evaluation is externally falsifiable via the reported implementation and benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The design rests on the domain assumption that serverless functions can support file-system semantics when paired with a multi-threaded short-lived server and coordinator; no free parameters or invented entities are stated in the abstract.

axioms (1)
  • domain assumption Serverless functions can be used for file system operations with appropriate design to mitigate cold starts.
    This assumption underpins the entire SLFS architecture and the claimed 580× cold-start improvement.

pith-pipeline@v0.9.1-grok · 5788 in / 1264 out tokens · 26427 ms · 2026-07-03T18:16:05.665277+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

95 extracted references · 33 canonical work pages

  1. [1]

    Amazon DynamoDB Transactions

    2018. Amazon DynamoDB Transactions. https://aws.amazon.com/blogs/aws/ new-amazon-dynamodb-transactions/. SLFS: a Flexible, Low-Cost Distributed File System Using Serverless Designs arXiv.org, July 2026, Boston, MA, USA

    2018

  2. [2]

    Reducing Java Cold Starts on AWS Lambda Functions with SnapStart | AWS Compute Blog

    2022. Reducing Java Cold Starts on AWS Lambda Functions with SnapStart | AWS Compute Blog. https://aws.amazon.com/blogs/compute/reducing-java- cold-starts-on-aws-lambda-functions-with-snapstart/

    2022

  3. [3]

    Apache OpenWhisk Is a Serverless, Open Source Cloud Platform

    2023. Apache OpenWhisk Is a Serverless, Open Source Cloud Platform. https://openwhisk.apache.org/

    2023

  4. [4]

    Apache ZooKeeper

    2023. Apache ZooKeeper. https://zookeeper.apache.org/

    2023

  5. [5]

    AWS Fargate Enables Faster Container Startup using Seekable OCI

    2023. AWS Fargate Enables Faster Container Startup using Seekable OCI. https://aws.amazon.com/blogs/aws/aws-fargate-enables-faster-container- startup-using-seekable-oci/

    2023

  6. [6]

    AWS Lambda Pricing

    2023. AWS Lambda Pricing. https://aws.amazon.com/lambda/pricing/

    2023

  7. [7]

    HDFS Architecture Guide

    2023. HDFS Architecture Guide. https://hadoop.apache.org/docs/r1.2.1/hdfso_ design.html

    2023

  8. [8]

    Why is my EFS file system performance slow? https://repost.aws/ knowledge-center/efs-troubleshoot-slow-performance

    2024. Why is my EFS file system performance slow? https://repost.aws/ knowledge-center/efs-troubleshoot-slow-performance

    2024

  9. [9]

    Amazon EFS

    2025. Amazon EFS. https://aws.amazon.com/efs/

    2025

  10. [10]

    Amazon S3 | Strong Consistency | Amazon Web Services

    2025. Amazon S3 | Strong Consistency | Amazon Web Services. https://aws. amazon.com/s3/consistency/

    2025

  11. [11]

    AWS Batch on AWS Fargate

    2025. AWS Batch on AWS Fargate. https://docs.aws.amazon.com/batch/latest/ userguide/fargate.html

    2025

  12. [12]

    AWS EC2 Instance lifecycle

    2025. AWS EC2 Instance lifecycle. https://docs.aws.amazon.com/AWSEC2/latest/ UserGuide/ec2-instance-lifecycle.html

    2025

  13. [13]

    AWS Price Calculator

    2025. AWS Price Calculator. https://calculator.aws

    2025

  14. [14]

    Azure Blob Storage | Microsoft Azure

    2025. Azure Blob Storage | Microsoft Azure. https://azure.microsoft.com/en- us/services/storage/blobs/

    2025

  15. [15]

    Azure Disk Storage – Block Storage | Microsoft Azure

    2025. Azure Disk Storage – Block Storage | Microsoft Azure. https://azure. microsoft.com/en-us/services/storage/disks/

    2025

  16. [16]

    Azure Durable Functions

    2025. Azure Durable Functions. https://learn.microsoft.com/en-us/azure/azure- functions/durable/

    2025

  17. [17]

    Azure Files - Managed File Shares and Storage | Microsoft Azure

    2025. Azure Files - Managed File Shares and Storage | Microsoft Azure. https: //azure.microsoft.com/en-us/services/storage/files/

    2025

  18. [18]

    Cloud Object Storage – Amazon S3 – Amazon Web Services

    2025. Cloud Object Storage – Amazon S3 – Amazon Web Services. https: //aws.amazon.com/s3/

    2025

  19. [19]

    Docker: Accelerated, Containerized Application Development

    2025. Docker: Accelerated, Containerized Application Development. https: //www.docker.com/

    2025

  20. [20]

    Filestore: Fully Managed Cloud File Storage | Google Cloud

    2025. Filestore: Fully Managed Cloud File Storage | Google Cloud. https://cloud. google.com/filestore

    2025

  21. [21]

    2025. GCSFS. https://gcsfs.readthedocs.io/en/latest/

    2025

  22. [22]

    Google Cloud Storage

    2025. Google Cloud Storage. https://cloud.google.com/storage

    2025

  23. [23]

    High-Performance Block Storage – Amazon EBS – Amazon Web Services

    2025. High-Performance Block Storage – Amazon EBS – Amazon Web Services. https://aws.amazon.com/ebs/

    2025

  24. [24]

    IOzone Filesystem Benchmark

    2025. IOzone Filesystem Benchmark. https://www.iozone.org/

    2025

  25. [25]

    LambdaFS

    2025. LambdaFS. https://github.com/ds2-lab/LambdaFS

    2025

  26. [26]

    LambdaFS-Benchmarking

    2025. LambdaFS-Benchmarking. https://github.com/ds2-lab/LambdaFS- Benchmarking

    2025

  27. [27]

    2025. LevelDB. https://github.com/google/leveldb

    2025

  28. [28]

    Microsoft Azure Traces

    2025. Microsoft Azure Traces. https://github.com/Azure/AzurePublicDataset

    2025

  29. [29]

    MySQL NDB Cluster Carrier Grade Edition

    2025. MySQL NDB Cluster Carrier Grade Edition. https://www.mysql.com/ products/cluster/

    2025

  30. [30]

    Persistent Disk: durable block storage | Google Cloud

    2025. Persistent Disk: durable block storage | Google Cloud. https://cloud.google. com/persistent-disk

    2025

  31. [31]

    2025. S3Fs. https://s3fs.readthedocs.io/en/latest/

    2025

  32. [32]

    Bolosky, Miguel Castro, Gerald Cermak, Ronnie Chaiken, John R

    Atul Adya, William J. Bolosky, Miguel Castro, Gerald Cermak, Ronnie Chaiken, John R. Douceur, Jon Howell, Jacob R. Lorch, Marvin Theimer, and Roger P. Wattenhofer. 2002. {FARSITE}: Federated, Available, and Reliable Storage for an Incompletely Trusted Environment. In5th Symposium on Operating Systems Design and Implementation (OSDI 02)

    2002

  33. [33]

    Alexandru Agache, Marc Brooker, Alexandra Iordache, Anthony Liguori, Rolf Neugebauer, Phil Piwonka, and Diana-Maria Popa. 2020. Firecracker: Light- weight Virtualization for Serverless Applications. In17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). 419–434. https: //www.usenix.org/conference/nsdi20/presentation/agache

    2020

  34. [34]

    Aguilera, Arif Merchant, Mehul Shah, Alistair Veitch, and Christos Karamanolis

    Marcos K. Aguilera, Arif Merchant, Mehul Shah, Alistair Veitch, and Christos Karamanolis. 2007. Sinfonia: a new paradigm for building scalable distributed systems. InProceedings of Twenty-First ACM SIGOPS Symposium on Operating Systems Principles(Stevenson, Washington, USA)(SOSP ’07). Association for Com- puting Machinery, New York, NY, USA, 159–174. doi:...

    work page doi:10.1145/1294261.1294278 2007

  35. [35]

    Arpaci-Dusseau, Andrea C

    Remzi H. Arpaci-Dusseau, Andrea C. Arpaci-Dusseau, and Venkateshwaran Venkataramani. 2018. Cloud-Native File Systems. In10th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud ’18). USENIX Association, Boston, MA. https://www.usenix.org/conference/hotcloud18/presentation/arpaci-dusseau

    2018

  36. [36]

    Mahesh Balakrishnan, Dahlia Malkhi, Vijayan Prabhakaran, Ted Wobber, Michael Wei, and John D. Davis. 2012. CORFU: A Shared Log Design for Flash Clusters. InProceedings of the 9th USENIX Conference on Networked Systems Design and Implementation (NSDI’12). USENIX Association, 1

    2012

  37. [37]

    Bernstein, Vassos Hadzilacos, and Nathan Goodman

    Philip A. Bernstein, Vassos Hadzilacos, and Nathan Goodman. 1987.Concurrency Control and Recovery in Database Systems. Addison-Wesley

    1987

  38. [38]

    James Cadden, Thomas Unger, Yara Awad, Han Dong, Orran Krieger, and Jonathan Appavoo. 2020. SEUSS: skip redundant paths to make serverless fast. InProceedings of the Fifteenth European Conference on Computer Systems (Eu- roSys ’20). Association for Computing Machinery, New York, NY, USA, 1–15. doi:10.1145/3342195.3392698

    work page doi:10.1145/3342195.3392698 2020

  39. [40]

    Benjamin Carver, Runzhou Han, Jingyuan Zhang, Mai Zheng, and Yue Cheng

  40. [41]

    InProceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 4(Vancouver, BC, Canada)(ASPLOS ’23)

    𝜆FS: A Scalable and Elastic Distributed File System Metadata Service using Serverless Functions. InProceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 4(Vancouver, BC, Canada)(ASPLOS ’23). Association for Computing Machinery, New York, NY, USA, 394–411. doi:10.1145/3623278.3624765

    work page doi:10.1145/3623278.3624765

  41. [42]

    Benjamin Carver, Jingyuan Zhang, Ao Wang, Ali Anwar, Panruo Wu, and Yue Cheng. 2020. Wukong: a scalable and locality-enhanced framework for serverless parallel computing. InProceedings of the 11th ACM Symposium on Cloud Comput- ing (SoCC ’20). Association for Computing Machinery, New York, NY, USA, 1–15. doi:10.1145/3419111.3421286

    work page doi:10.1145/3419111.3421286 2020

  42. [43]

    Paul Castro, Vatche Ishakian, Vinod Muthusamy, and Aleksander Slominski

  43. [44]

    ACM62, 12 (Nov

    The rise of serverless computing.Commun. ACM62, 12 (Nov. 2019), 44–54. doi:10.1145/3368454

    work page doi:10.1145/3368454 2019

  44. [45]

    Cooper, Adam Silberstein, Erwin Tam, Raghu Ramakrishnan, and Russell Sears

    Brian F. Cooper, Adam Silberstein, Erwin Tam, Raghu Ramakrishnan, and Russell Sears. 2010. Benchmarking Cloud Serving Systems with YCSB. InProceedings of the 1st ACM Symposium on Cloud Computing (SoCC ’10). Association for Computing Machinery, 143–154. doi:10.1145/1807128.1807152

    work page doi:10.1145/1807128.1807152 2010

  45. [46]

    Dong Du, Tianyi Yu, Yubin Xia, Binyu Zang, Guanglu Yan, Chenggang Qin, Qix- uan Wu, and Haibo Chen. 2020. Catalyzer: Sub-millisecond Startup for Serverless Computing with Initialization-less Booting. InProceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS ’20). Association...

    work page doi:10.1145/3373376.3378512 2020

  46. [47]

    Bryan Ford, Pyda Srisuresh, and Dan Kegel. 2005. Peer-to-Peer Communication Across Network Address Translators. In2005 USENIX Annual Technical Conference (USENIX ATC 05). https://www.usenix.org/conference/2005-usenix-annual- technical-conference/peer-peer-communication-across-network-address

    2005

  47. [48]

    Wahby, Brennan Shacklett, Karthikeyan Vasuki Bal- asubramaniam, William Zeng, Rahul Bhalerao, Anirudh Sivaraman, George Porter, and Keith Winstein

    Sadjad Fouladi, Riad S. Wahby, Brennan Shacklett, Karthikeyan Vasuki Bal- asubramaniam, William Zeng, Rahul Bhalerao, Anirudh Sivaraman, George Porter, and Keith Winstein. 2017. Encoding, Fast and Slow: Low-Latency Video Processing Using Thousands of Tiny Threads. In14th USENIX Sympo- sium on Networked Systems Design and Implementation (NSDI 17). 363–376....

    2017

  48. [49]

    Alexander Fuerst and Prateek Sharma. 2021. FaasCache: keeping serverless computing alive with greedy-dual caching. InProceedings of the 26th ACM In- ternational Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2021). Association for Computing Machinery, New York, NY, USA, 386–400. doi:10.1145/3445814.3446757

    work page doi:10.1145/3445814.3446757 2021

  49. [50]

    Ganger and Yale N

    Gregory R. Ganger and Yale N. Patt. 1994. Metadata update performance in file systems. InProceedings of the 1st USENIX Conference on Operating Systems Design and Implementation(Monterey, California)(OSDI ’94). USENIX Association, USA, 5–es

    1994

  50. [51]

    Sanjay Ghemawat, Howard Gobioff, and Shun-Tak Leung. 2003. The Google File System.ACM SIGOPS Operating Systems Review37, 5 (Oct. 2003), 29–43. doi:10.1145/1165389.945450

    work page doi:10.1145/1165389.945450 2003

  51. [52]

    Kuszmaul, and Donald E

    William Jannen, Jun Yuan, Yang Zhan, Amogh Akshintala, John Esmet, Yizheng Jiao, Ankur Mittal, Prashant Pandey, Phaneendra Reddy, Leif Walsh, Michael Bender, Martin Farach-Colton, Rob Johnson, Bradley C. Kuszmaul, and Donald E. Porter. 2015. BetrFS: A Right-Optimized Write-Optimized File System. InPro- ceedings of the 13th USENIX Conference on File and St...

    2015

  52. [53]

    Zhipeng Jia and Emmett Witchel. 2021. Boki: Stateful Serverless Computing with Shared Logs. InProceedings of the ACM SIGOPS 28th Symposium on Operating Systems Principles (SOSP ’21). Association for Computing Machinery, New York, NY, USA, 691–707. doi:10.1145/3477132.3483541

    work page doi:10.1145/3477132.3483541 2021

  53. [54]

    Jiawei Jiang, Shaoduo Gan, Yue Liu, Fanlin Wang, Gustavo Alonso, Ana Klimovic, Ankit Singla, Wentao Wu, and Ce Zhang. 2021. Towards Demystifying Serverless Machine Learning Training. InProceedings of the 2021 International Conference on Management of Data (SIGMOD ’21). Association for Computing Machinery, New York, NY, USA, 857–871. doi:10.1145/3448016.3459240

    work page doi:10.1145/3448016.3459240 2021

  54. [55]

    David Karger, Eric Lehman, Tom Leighton, Rina Panigrahy, Matthew Levine, and Daniel Lewin. 1997. Consistent Hashing and Random Trees: Distributed Caching Protocols for Relieving Hot Spots on the World Wide Web. InProceedings of the Twenty-Ninth Annual ACM Symposium on Theory of Computing (STOC ’97). Association for Computing Machinery, 654–663. doi:10.114...

    work page doi:10.1145/258533.258660 1997

  55. [56]

    Anurag Khandelwal, Arun Kejariwal, and Karthikeyan Ramasamy. 2020. Le Taureau: Deconstructing the Serverless Landscape & A Look Forward. InPro- ceedings of the 2020 ACM SIGMOD International Conference on Management of Data (SIGMOD ’20). Association for Computing Machinery, New York, NY, USA, arXiv.org, July 2026, Boston, MA, USA Cheng Hao (Ryan) Yang, Pao...

    work page doi:10.1145/3318464.3383130 2020

  56. [57]

    Ana Klimovic, Yawen Wang, Patrick Stuedi, Animesh Trivedi, Jonas Pfefferle, and Christos Kozyrakis. 2018. Pocket: Elastic Ephemeral Storage for Server- less Analytics. In13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 427–444. https://www.usenix.org/conference/osdi18/ presentation/klimovic

    2018

  57. [58]

    Jinhyung Koo, Junsu Im, Jooyoung Song, Juhyung Park, Eunji Lee, Bryan S Kim, and Sungjin Lee. 2021. Modernizing file system through in-storage indexing. In15th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI}21). 75–92

    2021

  58. [59]

    John Kubiatowicz, David Bindel, Yan Chen, Steven Czerwinski, Patrick Eaton, Dennis Geels, Ramakrishan Gummadi, Sean Rhea, Hakim Weatherspoon, Westley Weimer, Chris Wells, and Ben Zhao. 2000. OceanStore: An Architecture for Global- Scale Persistent Storage.ACM SIGPLAN Notices35, 11 (Nov. 2000), 190–201. doi:10.1145/356989.357007

    work page doi:10.1145/356989.357007 2000

  59. [60]

    Avinash Lakshman and Prashant Malik. 2010. Cassandra: A Decentralized Struc- tured Storage System.ACM SIGOPS Operating Systems Review44, 2 (April 2010), 35–40. doi:10.1145/1773912.1773922

    work page doi:10.1145/1773912.1773922 2010

  60. [61]

    Leslie Lamport. 2001. Paxos Made Simple.ACM SIGACT News (Distributed Computing Column) 32, 4 (Whole Number 121, December 2001)(Dec. 2001), 51–58. https://www.microsoft.com/en-us/research/publication/paxos-made-simple/

    2001

  61. [62]

    Kunal Lillaney, Vasily Tarasov, David Pease, and Randal Burns. 2019. Agni: An Efficient Dual-Access File System over Object Storage. InProceedings of the ACM Symposium on Cloud Computing(Santa Cruz, CA, USA)(SoCC ’19). Association for Computing Machinery, New York, NY, USA, 390–402. doi:10.1145/3357223. 3362703

    work page doi:10.1145/3357223 2019

  62. [63]

    Arpaci-Dusseau, and Remzi H

    Kai Mast, Andrea C. Arpaci-Dusseau, and Remzi H. Arpaci-Dusseau. 2022. Lamb- daObjects: Re-aggregating storage and execution for cloud computing. InProceed- ings of the 14th ACM Workshop on Hot Topics in Storage and File Systems(Virtual Event)(HotStorage ’22). Association for Computing Machinery, New York, NY, USA, 15–22. doi:10.1145/3538643.3539751

    work page doi:10.1145/3538643.3539751 2022

  63. [64]

    Marshall Kirk McKusick and Gregory R. Ganger. 1999. Soft updates: a technique for eliminating most synchronous writes in the fast filesystem. InProceedings of the Annual Conference on USENIX Annual Technical Conference(Monterey, California)(ATEC ’99). USENIX Association, USA, 24

    1999

  64. [65]

    Salman Niazi, Mahmoud Ismail, Seif Haridi, Jim Dowling, Steffen Grohsschmiedt, and Mikael Ronström. 2017. HopsFS: scaling hierarchical file system metadata using newSQL databases. InProceedings of the 15th Usenix Conference on File and Storage Technologies(Santa clara, CA, USA)(FAST’17). USENIX Association, USA, 89–103

    2017

  65. [66]

    Kai Ren and Garth Gibson. 2013. TABLEFS: Enhancing Metadata Efficiency in the Local File System. InProceedings of the 2013 USENIX Conference on Annual Technical Conference (USENIX ATC’13). USENIX Association, 145–156

    2013

  66. [67]

    Sean Rhea, Patrick Eaton, Dennis Geels, Hakim Weatherspoon, Ben Zhao, and John Kubiatowicz. 2003. Pond: The {OceanStore} Prototype. In2nd USENIX Conference on File and Storage Technologies (FAST 03)

    2003

  67. [68]

    Yadwadkar, Rodrigo Fonseca, Christos Kozyrakis, and Ricardo Bianchini

    Francisco Romero, Gohar Irfan Chaudhry, Íñigo Goiri, Pragna Gopa, Paul Ba- tum, Neeraja J. Yadwadkar, Rodrigo Fonseca, Christos Kozyrakis, and Ricardo Bianchini. 2021. Faa$T: A Transparent Auto-Scaling Cache for Serverless Ap- plications. InProceedings of the ACM Symposium on Cloud Computing (SoCC ’21). Association for Computing Machinery, New York, NY, U...

    work page doi:10.1145/3472883.3486974 2021

  68. [69]

    Yadwadkar, and Christos Kozyrakis

    Francisco Romero, Mark Zhao, Neeraja J. Yadwadkar, and Christos Kozyrakis

  69. [70]

    Yadwadkar, Rodrigo Fonseca, Christos Kozyrakis, and Ricardo Bianchini

    Llama: A Heterogeneous & Serverless Framework for Auto-Tuning Video Analytics Pipelines. InProceedings of the ACM Symposium on Cloud Computing (SoCC ’21). Association for Computing Machinery, New York, NY, USA, 1–17. doi:10.1145/3472883.3486972

    work page doi:10.1145/3472883.3486972

  70. [71]

    Rohan Basu Roy, Tirthak Patel, and Devesh Tiwari. 2022. IceBreaker: warming serverless functions better with heterogeneity. InProceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2022). Association for Computing Machinery, New York, NY, USA, 753–767. doi:10.1145/3503222.3507750

    work page doi:10.1145/3503222.3507750 2022

  71. [72]

    Hellerstein

    Johann Schleier-Smith, Leonhard Holz, Nathan Pemberton, and Joseph M. Hellerstein. 2020. A FaaS File System for Serverless Computing. arXiv:2009.09845 [cs.DC]

    work page arXiv 2020

  72. [73]

    Yadwadkar, Raluca Ada Popa, Joseph E

    Johann Schleier-Smith, Vikram Sreekanti, Anurag Khandelwal, Joao Carreira, Neeraja J. Yadwadkar, Raluca Ada Popa, Joseph E. Gonzalez, Ion Stoica, and David A. Patterson. 2021. What serverless computing is and should become: the next phase of cloud computing.Commun. ACM64, 5 (April 2021), 76–84. doi:10.1145/3406011

    work page doi:10.1145/3406011 2021

  73. [74]

    Mohammad Shahrad, Rodrigo Fonseca, Íñigo Goiri, Gohar Chaudhry, Paul Batum, Jason Cooke, Eduardo Laureano, Colby Tresness, Mark Russinovich, and Ricardo Bianchini. 2020. Serverless in the Wild: Characterizing and Optimizing the Serverless Workload at a Large Cloud Provider. In2020 USENIX Annual Technical Conference (USENIX ATC 20). 205–218. https://www.us...

    2020

  74. [75]

    Pradeep Shetty, Richard Spillane, Ravikant Malpani, Binesh Andrews, Justin Seyster, and Erez Zadok. 2013. Building Workload-Independent Storage with VT- trees. InProceedings of the 11th USENIX Conference on File and Storage Technologies (FAST’13). USENIX Association, 17–30

    2013

  75. [76]

    Gonzalez, Joseph M

    Vikram Sreekanti, Chenggang Wu, Saurav Chhatrapati, Joseph E. Gonzalez, Joseph M. Hellerstein, and Jose M. Faleiro. 2020. A fault-tolerance shim for serverless computing. InProceedings of the Fifteenth European Conference on Computer Systems (EuroSys ’20). Association for Computing Machinery, New York, NY, USA, 1–15. doi:10.1145/3342195.3387535

    work page doi:10.1145/3342195.3387535 2020

  76. [77]

    Gonzalez, Joseph M

    Vikram Sreekanti, Chenggang Wu, Xiayue Charles Lin, Johann Schleier-Smith, Joseph E. Gonzalez, Joseph M. Hellerstein, and Alexey Tumanov. 2020. Cloudburst: stateful functions-as-a-service.Proceedings of the VLDB Endowment13, 12 (July 2020), 2438–2452. doi:10.14778/3407790.3407836

    work page doi:10.14778/3407790.3407836 2020

  77. [78]

    Frans Kaashoek, and Hari Balakr- ishnan

    Ion Stoica, Robert Morris, David Karger, M. Frans Kaashoek, and Hari Balakr- ishnan. 2001. Chord: A Scalable Peer-to-Peer Lookup Service for Internet Ap- plications.ACM SIGCOMM Computer Communication Review31, 4 (Aug. 2001), 149–160. doi:10.1145/964723.383071

    work page doi:10.1145/964723.383071 2001

  78. [79]

    Terry, A.J

    D.B. Terry, A.J. Demers, K. Petersen, M.J. Spreitzer, M.M. Theimer, and B.B. Welch

  79. [80]

    InProceedings of 3rd International Conference on Parallel and Distributed Information Systems

    Session guarantees for weakly consistent replicated data. InProceedings of 3rd International Conference on Parallel and Distributed Information Systems. 140–149. doi:10.1109/PDIS.1994.331722

    work page doi:10.1109/pdis.1994.331722 1994

  80. [81]

    Terry, Vijayan Prabhakaran, Ramakrishna Kotla, Mahesh Balakrish- nan, Marcos K

    Douglas B. Terry, Vijayan Prabhakaran, Ramakrishna Kotla, Mahesh Balakrish- nan, Marcos K. Aguilera, and Hussam Abu-Libdeh. 2013. Consistency-Based Service Level Agreements for Cloud Storage. InProceedings of the Twenty-Fourth ACM Symposium on Operating Systems Principles (SOSP ’13). Association for Computing Machinery, 309–324. doi:10.1145/2517349.2522731

    work page doi:10.1145/2517349.2522731 2013

Showing first 80 references.