Bibliographic record
Abstract
Cloud computing is an integral part of modern life, which became increasingly apparent during the COVID-19 pandemic. Applications that run on the cloud facilitate many of our daily activities, including education, retail, and high quality video calls that keep us connected. These applications run on one or more Virtual Machines (VM), where networked cloud applications can benefit from inter-VM network bandwidth guarantees. For example, an entire class of network-intensive big-data processing applications run more quickly with sufficient network bandwidth guarantees. However, offering inter-VM bandwidth guarantees creates challenges both for resource allocation latency and datacenter utilization, because the resource scheduler must satisfy per-VM resource demands and inter-VM bandwidth requirements. This dissertation demonstrates that it is feasible to offer inter-VM bandwidth guarantees as a first class cloud service. We develop several algorithms that allow efficient sharing of datacenter network bandwidth across tenants. These algorithms maintain high datacenter utilization while offering low allocation latency. Specifically, we propose constraint-solver-based algorithms that scale well to datacenters with hundreds of servers and heuristic-based algorithms that scale well to large-scale datacenters with thousands of servers. We demonstrate the practicality of these algorithms by integrating them into the OpenStack cloud management framework. We also construct a realistic cloud workload with bandwidth requirements, which we use to evaluate the efficiency of our resource scheduling algorithms. We demonstrate that selling inter-VM network bandwidth guarantees as a service increases cloud provider revenue. Furthermore, it is possible to do so without changing cloud affordability for the tenants due to shortened job completion times for the tenant applications. Savings from the shortened VM lifetimes can be used to cover the network bandwidth guarantees service cost, which allows tenants to complete their job faster without paying extra. For example, we show that cloud providers can generate up to 63% extra revenue compared to the case when they do not offer network bandwidth guarantees.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".