← 返回项目详情
此成果详情页已在新标签打开。查看完成后，可关闭当前标签返回原项目页，也可以点击“返回项目详情”。网页不会强制关闭浏览器标签。
成果详情 / 项目说明与报告
云实验公开报告
原始文件名report-public.md
- 内容说明
- 把 canonical 聚合数值、公开图表与排除项连接起来，说明这是 packaging operation 而不是新的云端访问或 benchmark。
- 能够证明
- 支持公开报告所引用的网络、存储、PostgreSQL 聚合结果及其适用条件。
- 不能证明
- 不证明所有区域和规格的普遍性能，不形成完整性能审计或单一根因结论。
- 许可说明
- CC BY 4.0 国际署名许可（自行编写的公开报告）
- 来源和脱敏说明
- 根据 DigitalOcean canonical local aggregate results 形成的公开报告；本 Goal 不重新运行实验。
预览
站内查看方式
使用 HTML 安全转义的 Markdown 文本预览。
# Public report
The public package is derived from canonical local aggregate results and the existing public-portfolio chart set. It is a packaging operation only; no benchmark, cloud access, account access, or provider API call was performed.
Published aggregates: VPC throughput approximately 1.98–2.03 Gbit/s; sequential block storage up to approximately 452 MiB/s; selected random read/write approximately 6994 / 3006 IOPS; PostgreSQL at 32 clients approximately 10272 TPS and 3.055 ms; PostgreSQL at 64 clients approximately 9937 TPS and 6.249 ms; failed transactions 0.
The package excludes the resource ledger, raw network/storage/database logs, SSH incident raw material, provider portal captures, original PDF/DOCX, and files carrying address, host, account, connection, or local-path identity. The architecture figure is redrawn with generic labels because the source diagram exposed those fields.
The points apply only to recorded test conditions. They do not represent every region or size, do not form a complete performance audit, and do not create a production SLA. Evidence archive gaps remain. The package does not claim a single proven causal explanation for the relationship among CPU, load, queueing, throughput, and latency.
公开包完整性
SHA-256 摘要
9858834aec5e5d4282b5d59b5aac25289c6487a12f681f718456d3e7547d3d2d