The DOI matches its Crossref record.
Exploiting process lifetime distributions for dynamic load balancing
Open accessAbstract
We consider policies for CPU load balancing in networks of workstations. We address the question of whether preemptive migration (migrating active processes) is necessary, or whether remote execution (migrating processes only at the time of birth) is sufficient for load balancing. We show that resolving this issue is strongly tied to understanding the process lifetime distribution. Our measurements indicate that the distribution of lifetimes for a UNIX process is Pareto (heavy-tailed), with a consistent functional form over a variety of workloads. We show how to apply this distribution to derive a preemptive migration policy that requires no hand-tuned parameters. We used a trace-driven simulation to show that our preemptive migration strategy is far more effective than remote execution, even when the memory transfer cost is high.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“(As observed in prior work [7, 8, 2], job size distributions in a number of settings are well-modeled by a Pareto”
From Improving Online Algorithms via ML Predictions (2024) · cites this paper as [8]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
No references could be resolved yet.
Research works printed but not linked: 44
- ABRAHAMS, D. M. AND RIZZARDI, F. 1988. The Berkeley Interactive Statistical System. W. W. Norton.]]
- 10.1109/TSE.1987.233509 · DOI
- 10.1145/125826.126208 · DOI
- 10.1109/2.35213 · DOI
- 10.5555/563048 · DOI
- 10.1109/12.59854 · DOI
- BRYANT, R. M. AND FINKEL, R.A. 1981. A stable distributed scheduling algorithm. In the 2nd International Conference on Distributed Computing Systems. 314-323.]]
- CABRERA, F. 1986. The influence of workload on load balancing strategies. In Proceedings of the Usenix Summer Conference (June). USENIX Assoc., Berkeley, Calif., 446-458.]]
- CASAS, J., CLARK, D. L., KONURU, R., OTTO, S. W., PROUTY, R. M., AND WALPOLE, J. 1995. Mpvm: A migration transparent version of pvm. Comput. Syst. 8, 2 (Spring), 171-216.]]
- CASAVANT, T. L. AND KUHL, J.G. 1987. Analysis of three dynamic distributed load-balancing strategies with varying global information requirements. In the 7th International Conference on Distributed Computing Systems (Sept.). IEEE, New York, 185-192.]]
- 10.1016/0743-7315(90)90117-8 · DOI
- DE PAOLI D. AND GOSCINSKI A. 1995. The rhodos migration facility. Tech. Rep. TR C95-36 School of Computing and Mathematics Deakin Univ. Victoria Australia. Available via http://www.cm.deakin.edu.au/rhodos/rh_tr95.html#C95-36. Submitted to the Journal of Systems and Software.]] 10.1016/S0164-1212(97)00014-9 · DOI
- 10.1002/spe.4380210802 · DOI
- 10.5555/5527.5535 · DOI
- 10.1145/55595.55604 · DOI
- 10.1145/223587.223597 · DOI
- 10.1016/0167-8191(93)90073-T · DOI
- 10.1016/0164-1212(90)90054-P · DOI
- 10.5555/77493 · DOI
- KRUEGER, P. AND LIVNY, M. 1988. A comparison of preemptive and non-preemptive load distributing. In the 8th International Conference on Distributed Computing Systems. IEEE, New York, 123-130.]]
- 10.1109/32.83908 · DOI
- LARSEN, R. g. AND MARX, M. L. 1986. An Introduction to Mathematical Statistics and Its Applications. 2nd ed. Prentice-Hall, Englewood Cliffs, N.J.]]
- 10.1145/317531.317539 · DOI
- LIN, H.-C. AND RAGHAVENDRA, C. 1993. A state-aggregation method for analyzing dynamic load-balancing policies. In the IEEE 13th International Conference on Distributed Computing Systems. IEEE, New York, 482-489.]]
- LITZKOW, M. AND LIVNY, M. 1990. Experience with the Condor distributed batch system. In the IEEE Workshop on Experimental Distributed Systems. IEEE, New York, 97-101.]] · DOI
- LITZKOW, M., LIVNY, M., AND MUTKA, M. 1988. Condor--A hunter of idle workstations. In the 8th International Conference on Distributed Computing Systems. IEEE, New York.]]
- 10.1145/800047.801689 · DOI
- 10.1016/0743-7315(90)90118-9 · DOI
- 10.1145/800217.806619 · DOI
- PULIDAS, S., TOWSLEY, D., AND STANKOVIC, J.A. 1988. Imbedding gradient estimators in load balancing algorithms. In the 8th International Conference on Distributed Computing Systerns (June). IEEE, New York, 482-490.]]
- 10.1109/32.92912 · DOI
- 10.1145/364995.365690 · DOI
- 10.5555/95329 · DOI
- SVENSSON, A. 1990. History, an intelligent load sharing filter. In the IEEE l Oth International Conference on Distributed Computing Systems. IEEE, New York, 546-553.]]
- 10.1145/96267.96281 · DOI
- 10.1145/323647.323629 · DOI
- 10.1016/0140-3664(91)90059-A · DOI
- 10.5555/1267638.1267639 · DOI
- WANG, J., ZHOU, S., K. AHMED, AND LONG, W. 1993. LSBATCH: A distributed load sharing batch system. Tech. Rep. CSRI-286, Computer Systems Research Inst., Univ. of Toronto, Toronto, Canada. April.]]
- WANG, Y.-T. AND MORRIS, R.g. 1985. Load sharing in distributed systems. IEEE Trans. Comput. C-94, 3 (Mar.), 204-217.]] · DOI
- 10.1145/41457.37503 · DOI
- 10.5555/829527.831172 · DOI
- ZHOU, S. AND FERRARI, D. 1987. A measurement study of load balancing performance. In the IEEE 7th International Conference on Distributed Computing Systems. IEEE, New York, 490-497.]]
- 10.1002/spe.4380231203 · DOI
Cited by
Sorted by citations
Improving Online Algorithms via ML Predictions
Kumar, R., Purohit, M., & Svitkina, Z. (2024) · arXiv · doi:10.48550/arxiv.2407.17712 · Cited by 111
Metadata
- Authors
- Harchol-Balter, M., & Downey, A. B.
- Affiliations
- Univ. of California, Berkeley
- University of California, Berkeley (US)
- ORCID
- Downey, Allen B.
- Venue
- ACM Transactions on Computer Systems
- Published
- 1997-08
- Volume
- 15
- Issue
- 3
- Pages
- 253-285
- ISSN
- 0734-2071 (ISSN-L)
- 1557-7333
- OpenAlex
- W2068666958
- Cited by
- 442
- References
- 0
- Citations by year
- 2026: 1 · 2025: 5 · 2024: 4 · 2023: 3 · 2022: 4 · 2021: 6 · 2020: 8 · 2019: 8 · 2018: 13 · 2017: 8 · 2016: 3 · 2015: 4 · 2014: 11 · 2013: 13 · 2012: 24
- FWCI
- 18.89
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- ACM Transactions on Computer Systems (publishedVersion)
- Funders
- National Science Foundation (8919074, 9201092)
- National Physical Science Consortium
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Distributed and Parallel Computing Systems
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Physical Sciences › Computer Science › Information Systems › Cloud Computing and Resource Management
- Keywords
- dynamic load balancing, workstation clusters, task migration, remote execution, Pareto distribution, heavy-tailed distributions, UNIX processes, migration policy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Exploiting process lifetime distributions for dynamic load balancing. https://app.cochat.ai/papers/10.1145/263326.263344
- The paper
- Harchol-Balter, M., & Downey, A. B. (1997). Exploiting process lifetime distributions for dynamic load balancing. ACM Transactions on Computer Systems. https://doi.org/10.1145/263326.263344
