Milvus 3.0 的 Loon 存储引擎把对象存储上的点读取量降到原来的六分之一，做向量检索时不用再读一堆无关数据了。
Milvus 3.0 推出 Storage v3，代号 Loon，专为对象存储的 serving-style 访问设计。Loon 引入 ColumnGroups 和对齐行 ID 来组织数据，减少 ANN 搜索后获取字段时的读放大。在内部基准测试中，点读取从 Parquet 格式的 0.4 MB 降至 0.07 MB，降幅超过 80%。该引擎将标量字段、向量和索引分离布局，匹配不同的访问模式，并通过不可变清单追踪数据集版本。
𝗠𝗶𝗹𝘃𝘂𝘀 𝟯.𝟬 𝗶𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗲𝘀 𝗦𝘁𝗼𝗿𝗮𝗴𝗲 𝘃𝟯, 𝗮𝗹𝘀𝗼 𝗸𝗻𝗼𝘄𝗻 𝗮𝘀 𝗟𝗼𝗼𝗻, 𝗮 ...
𝗠𝗶𝗹𝘃𝘂𝘀 𝟯.𝟬 𝗶𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗲𝘀 𝗦𝘁𝗼𝗿𝗮𝗴𝗲 𝘃𝟯, 𝗮𝗹𝘀𝗼 𝗸𝗻𝗼𝘄𝗻 𝗮𝘀 𝗟𝗼𝗼𝗻, 𝗮 𝘀𝘁𝗼𝗿𝗮𝗴𝗲 𝗲𝗻𝗴𝗶𝗻𝗲 𝗯𝘂𝗶𝗹𝘁 𝗳𝗼𝗿 𝘀𝗲𝗿𝘃𝗶𝗻𝗴-𝘀𝘁𝘆𝗹𝗲 𝗮𝗰𝗰𝗲𝘀𝘀 𝗼𝗻 𝗼𝗯𝗷𝗲𝗰𝘁 𝘀𝘁𝗼𝗿𝗮𝗴𝗲. Loon handles a specific problem: after ANN search returns candidate IDs, Milvus still has to fetch the fields for those rows. On object storage, that fetch can become expensive. Analytical file formats are optimized for scans, not serving-style point reads. A query may only need a few vectors or metadata fields, but the layout can force the engine to read much more. 𝗟𝗼𝗼𝗻 𝗿𝗲𝗱𝘂𝗰𝗲𝘀 𝘁𝗵𝗶𝘀 𝗿𝗲𝗮𝗱 𝗮𝗺𝗽𝗹𝗶𝗳𝗶𝗰𝗮𝘁𝗶𝗼𝗻 𝗯𝘆 𝗼𝗿𝗴𝗮𝗻𝗶𝘇𝗶𝗻𝗴 𝗱𝗮𝘁𝗮 𝗶𝗻𝘁𝗼 𝗖𝗼𝗹𝘂𝗺𝗻𝗚𝗿𝗼𝘂𝗽𝘀 𝘄𝗶𝘁𝗵 𝗮𝗹𝗶𝗴𝗻𝗲𝗱 𝗿𝗼𝘄 𝗜𝗗𝘀. Different fields can then use layouts that match how they are actually accessed: • Scalar fields can be laid out for filtering. • Vectors and point-read-heavy fields can use layouts for narrow lookups. • Vector and inverted indexes stay separate from the file format. • Each dataset version is tracked by an immutable manifest. In one internal benchmark, point-read I milvus.io/blog/why-we-bu… .4 MB with Parquet to 0.07 MB with Vortex and Loon. This matters because zero-copy search still needs a storage path built for retrieval workloads. Blog: https://t.co/d4Fgu31EfN 💬 0 🔄 0 ❤️ 0 ⚡