Metraipolis › archive › dc_22467b4bbdbc
No-Restart Elasticity in an Adaptive Runtime System for Cloud-Native HPC — arXiv:2609.32217
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32217
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:12:01.216Z
- SHA-256 of the archived text
4c9f33b434763e043577ff65eef8df3062ce9e4af5ecb6dc339747bf3fcb0290- Stable URL of this page
https://metraipolis.com/documento/dc_22467b4bbdbc
How to cite
No-Restart Elasticity in an Adaptive Runtime System for Cloud-Native HPC — arXiv:2609.32217 — arXiv (en), https://arxiv.org/abs/2609.32217 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_22467b4bbdbc (Metraipolis archive dc_22467b4bbdbc, sha256 4c9f33b434763e043577ff65eef8df3062ce9e4af5ecb6dc339747bf3fcb0290)
BibTeX
@misc{dc22467b4bbdbc,
title = {No-Restart Elasticity in an Adaptive Runtime System for Cloud-Native HPC — arXiv:2609.32217},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32217},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_22467b4bbdbc; sha256 4c9f33b434763e043577ff65eef8df3062ce9e4af5ecb6dc339747bf3fcb0290},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32217. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Exploiting discounted spot instances for HPC requires an application to change its resource allocation at runtime, shrinking ahead of an interruption and expanding onto replacement capacity. Existing elasticity mechanisms implement rescaling as a full process teardown followed by a cold restart at the new processor count, and the restart stage accounts for up to 95% of the total overhead, growing with node count and increasing substantially on GPUs due to CUDA context initialization. In this paper, we present a no-restart rescaling mechanism for the Charm++ runtime system in which surviving processes never exit: a rescaling operation consists of a membership negotiation with a lightweight external coordinator, reconciliation of the UCX communication endpoints with the new cluster view, and a return to the top of the runtime initialization path that preserves live application state. This reduces the cost of a rescaling operation, excluding the load balancing step that any rescaling model requires, from multiple seconds to 8--15ms on CPUs and 7--11ms on GPUs, at 4 to 32 instances. Because processes survive, GPU device state persists in place, eliminating the checkpointing daemons previously required for GPU elasticity, and a launcher-independent bootstrap mechanism removes the dependence on supervised process managers, which are incompatible with spot instance interruptions. Integrated with an existing spot instance management framework, the mechanism cuts the end-to-end overhead of eight simultaneous interruptions to 0.2% of runtime on CPUs and 0.6% on GPUs, and raises the rate at which a job can be rescaled below 1% overhead by a factor of seven. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-29 in cs.DC). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2609.32217 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T21:53:13.645Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).