DARQ Matter Binds Everything: Performant and Composable Cloud Programming via Resilient Steps
Providing strong fault-tolerant guarantees for the modern cloud is difficult, as application developers must coordinate between independent stateful services and ephemeral compute, and handle various failure-induced anomalies. We propose Composable Resilient Steps (CReSt), a new abstraction for re...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
ACM
2023
|
| Online Access: | https://hdl.handle.net/1721.1/151085 |
| _version_ | 1826191194900660224 |
|---|---|
| author | Li, Tianyu Chandramouli, Badrish Burckhardt, Sebastian Madden, Samuel |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Li, Tianyu Chandramouli, Badrish Burckhardt, Sebastian Madden, Samuel |
| author_sort | Li, Tianyu |
| collection | MIT |
| description | Providing strong fault-tolerant guarantees for the modern cloud is difficult, as application developers must
coordinate between independent stateful services and ephemeral compute, and handle various failure-induced
anomalies. We propose Composable Resilient Steps (CReSt), a new abstraction for resilient cloud applications.
CReSt uses fault-tolerant steps as its core building block, which allows participants receive, process, and send
messages as a single uninterruptible atomic unit. Composability and reliability are orthogonally achieved by
reusable CReSt implementations, for example, leveraging reliable message queues. Thus, CReSt application
builders focus solely on translating application logic into steps, and infrastructure builders focus on efficient
CReSt implementations. We propose one such implementation, called DARQ (for Deduplicated Asynchronously
Recoverable Queues). At its core, DARQ is a storage service that encapsulates CReSt participant state and
enforces CReSt semantics; developers attach ephemeral compute nodes to DARQ instances to implement
stateful distributed components. Services built with DARQ are resilient by construction, and CReSt-compatible
services naturally compose without loss of resilience. For performance, we propose a novel speculative
execution scheme to execute CReSt steps without waiting for message persistence in DARQ, effectively eliding
cloud persistence overheads; our scheme maintains CReSt’s fault-tolerance guarantees and automatically
restores consistent system state upon failure. We showcase the generality of CReSt and DARQ using two
applications: cloud streaming and workflow processing. Experiments show that DARQ is able to achieve
extremely low latency and high throughput across these use cases, often beating state-of-the-art customized
solutions. |
| first_indexed | 2024-09-23T08:51:56Z |
| format | Article |
| id | mit-1721.1/151085 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T08:51:56Z |
| publishDate | 2023 |
| publisher | ACM |
| record_format | dspace |
| spelling | mit-1721.1/1510852024-01-23T18:48:29Z DARQ Matter Binds Everything: Performant and Composable Cloud Programming via Resilient Steps Li, Tianyu Chandramouli, Badrish Burckhardt, Sebastian Madden, Samuel Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Providing strong fault-tolerant guarantees for the modern cloud is difficult, as application developers must coordinate between independent stateful services and ephemeral compute, and handle various failure-induced anomalies. We propose Composable Resilient Steps (CReSt), a new abstraction for resilient cloud applications. CReSt uses fault-tolerant steps as its core building block, which allows participants receive, process, and send messages as a single uninterruptible atomic unit. Composability and reliability are orthogonally achieved by reusable CReSt implementations, for example, leveraging reliable message queues. Thus, CReSt application builders focus solely on translating application logic into steps, and infrastructure builders focus on efficient CReSt implementations. We propose one such implementation, called DARQ (for Deduplicated Asynchronously Recoverable Queues). At its core, DARQ is a storage service that encapsulates CReSt participant state and enforces CReSt semantics; developers attach ephemeral compute nodes to DARQ instances to implement stateful distributed components. Services built with DARQ are resilient by construction, and CReSt-compatible services naturally compose without loss of resilience. For performance, we propose a novel speculative execution scheme to execute CReSt steps without waiting for message persistence in DARQ, effectively eliding cloud persistence overheads; our scheme maintains CReSt’s fault-tolerance guarantees and automatically restores consistent system state upon failure. We showcase the generality of CReSt and DARQ using two applications: cloud streaming and workflow processing. Experiments show that DARQ is able to achieve extremely low latency and high throughput across these use cases, often beating state-of-the-art customized solutions. 2023-07-11T17:36:59Z 2023-07-11T17:36:59Z 2023-06-20 2023-07-01T08:00:03Z Article http://purl.org/eprint/type/JournalArticle 2836-6573 https://hdl.handle.net/1721.1/151085 Li, Tianyu, Chandramouli, Badrish, Burckhardt, Sebastian and Madden, Samuel. 2023. "DARQ Matter Binds Everything: Performant and Composable Cloud Programming via Resilient Steps." Proceedings of the ACM on Management of Data, 1 (2). PUBLISHER_POLICY en https://doi.org/10.1145/3589262 Proceedings of the ACM on Management of Data Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. The author(s) application/pdf ACM Association for Computing Machinery |
| spellingShingle | Li, Tianyu Chandramouli, Badrish Burckhardt, Sebastian Madden, Samuel DARQ Matter Binds Everything: Performant and Composable Cloud Programming via Resilient Steps |
| title | DARQ Matter Binds Everything: Performant and Composable Cloud Programming via Resilient Steps |
| title_full | DARQ Matter Binds Everything: Performant and Composable Cloud Programming via Resilient Steps |
| title_fullStr | DARQ Matter Binds Everything: Performant and Composable Cloud Programming via Resilient Steps |
| title_full_unstemmed | DARQ Matter Binds Everything: Performant and Composable Cloud Programming via Resilient Steps |
| title_short | DARQ Matter Binds Everything: Performant and Composable Cloud Programming via Resilient Steps |
| title_sort | darq matter binds everything performant and composable cloud programming via resilient steps |
| url | https://hdl.handle.net/1721.1/151085 |
| work_keys_str_mv | AT litianyu darqmatterbindseverythingperformantandcomposablecloudprogrammingviaresilientsteps AT chandramoulibadrish darqmatterbindseverythingperformantandcomposablecloudprogrammingviaresilientsteps AT burckhardtsebastian darqmatterbindseverythingperformantandcomposablecloudprogrammingviaresilientsteps AT maddensamuel darqmatterbindseverythingperformantandcomposablecloudprogrammingviaresilientsteps |