[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-09-03。"],[[["\u003cp\u003eThe \u003ccode\u003epg_stat_ann_indexes\u003c/code\u003e view provides metrics for vector indexes generated in AlloyDB Omni, accessible after installing the \u003ccode\u003ealloydb_scann\u003c/code\u003e extension.\u003c/p\u003e\n"],["\u003cp\u003eUsability metrics, such as \u003ccode\u003eindexconfig\u003c/code\u003e and \u003ccode\u003eindexscan\u003c/code\u003e, help to understand the current state of index utilization, including index configuration and scan frequency.\u003c/p\u003e\n"],["\u003cp\u003eTuning metrics, including \u003ccode\u003einsertcount\u003c/code\u003e, \u003ccode\u003eupdatecount\u003c/code\u003e, \u003ccode\u003edeletecount\u003c/code\u003e, and \u003ccode\u003edistribution\u003c/code\u003e, offer insights into index optimization and potential performance issues.\u003c/p\u003e\n"],["\u003cp\u003eHigh mutation rates, indicated by \u003ccode\u003einsertcount\u003c/code\u003e, \u003ccode\u003eupdatecount\u003c/code\u003e, and \u003ccode\u003edeletecount\u003c/code\u003e, or significant vector distribution variance, shown by the \u003ccode\u003edistribution\u003c/code\u003e metric, may suggest a need to reindex to improve query performance.\u003c/p\u003e\n"]]],[],null,["# Vector index metrics\n\nSelect a documentation version: 15.7.1keyboard_arrow_down\n\n- [Current (16.8.0)](/alloydb/omni/current/docs/reference/vector-index-metrics)\n- [16.8.0](/alloydb/omni/16.8.0/docs/reference/vector-index-metrics)\n- [16.3.0](/alloydb/omni/16.3.0/docs/reference/vector-index-metrics)\n- [15.12.0](/alloydb/omni/15.12.0/docs/reference/vector-index-metrics)\n- [15.7.1](/alloydb/omni/15.7.1/docs/reference/vector-index-metrics)\n- [15.7.0](/alloydb/omni/15.7.0/docs/reference/vector-index-metrics)\n\n\u003cbr /\u003e\n\nThis page lists the metrics related to the vector indexes that you generate in AlloyDB Omni. You can view these metrics using the `pg_stat_ann_indexes` view that is available when you install [the `alloydb_scann` extension](/alloydb/omni/15.7.1/docs/ai/store-index-query-vectors).\n\n\u003cbr /\u003e\n\nFor more information about viewing the metrics, see [View vector index metrics](/alloydb/omni/15.7.1/docs/ai/tune-indexes#vector-index-metrics).\n\nUsability metrics\n-----------------\n\nThe usability metrics include metrics that help you understand the state of\nindex utilization with metrics, such as index configuration and number of index\nscans.\n\nTuning metrics\n--------------\n\nTuning metrics provide insights into your current index optimization, allowing you to apply recommendations for faster query performance.\n\n### Tuning recommendation based on the metrics\n\nMutation\n: The `insertcount`, `updatecount`,\n and `deletecount` metrics together show the changes or mutations in\n the vector for the index.\n: The index is created with a specific number of vectors and partitions. When operations such as insert, update, or delete are performed on the vector index, it only affects the initial set of partitions where the vectors reside. Consequently, the number of vectors in each partition fluctuates over time, potentially impacting recall, QPS, or both.\n: If you encounter slowness or accuracy issues such as low QPS or poor recall, in your ANN search queries over time, then consider reviewing these metrics. A high number of mutations relative to the total number of vectors could indicate the need for reindexing.\n\nDistribution\n: The `distribution` metric shows the vector distributions across all partitions.\n: When you create an index, it is created with a specific number of vectors and fixed partitions. The partitioning process and subsequent distribution occurs based on this consideration. If additional vectors are added, they are partitioned among the existing partitions, resulting in a different distribution compared to the distribution when the index was created. Since the final distribution does not consider all vectors simultaneously, the recall, QPS, or both might be affected.\n: If you observe a gradual decline in the performance of your ANN search queries, such as slower response times or reduced accuracy in the results (measured by QPS or recall), then consider checking this metric and reindexing.\n\nDistribution percentile\n: The `distributionpercentile` metric, is a vector index distribution in the `pg_stat_ann_indexes` view that helps you understand the distribution of vectors between partitions of your ScaNN index. The partitions are created based on `num_leaves` value defined during index creation.\n: When you create an `alloydb_scann` index on the initial set of rows by setting `num_leaves`, the index can change the distribution of vectors across the partitions due to data operations (skew mutations), or the number of vectors might increase significantly. These changes can lead to degradation of QPS, recall, or both. The vector index distribution can give you signals if the mutation causes a change in the index distribution. This information can help you determine if a reindex is required, or if a change in search time configurations can help improve query performance.\n: In a vector index, the distribution of vectors across partitions is rarely perfectly even. Such imbalance is referred to as a *non-uniform distribution* . A certain degree of non-uniformity is often expected and doesn't mean you need to reindex. A non-uniform distribution has the following characteristics: \n\n - The variance of the number of vectors is low. Variance can be calculated as \n $(P100(num\\\\_vectors) - p10(num\\\\_vectors))\\*(\\\\frac{num\\\\_leaves}{total\\\\_num\\\\_row})$\n - The number of partitions with 0 vectors is low, and might be less than 30% of partitions.\n - The variance of the number of partitions is low. \n $ variance _{p} = abs(p_{num\\\\_partitions} - num\\\\_leaves \\* (p_{percentile} - p-1_{percentile})) $ where \"p\" is a vector index distribution bucket.\n - The number of vectors at any percentile is \n $\\\u003c 8 x (\\\\frac{num\\\\_rows\\\\ during\\\\ index\\\\ creation\\\\ time}{ num\\\\_leaves})$\n\n When these conditions aren't satisfied, `REINDEX` might be required based on how much QPS and recall are affected.\n: The following scenarios, while less common than non-uniform distribution, can occur: \n\n - **Approximate Uniform Index:** When most of the partitions have the same number of non-zero vectors and the variance of the number of vectors is low, it is an approximate uniform index. `REINDEX` is required if the number vectors in each partition are $\\\u003e 8 \\* average vector$ at `index_creation_time`.\n - **Sparse Index:** A sparse index also occurs where \\\u003e 50% of the partitions are empty. For example, sparse index is created when multiple deletions occur on a table. This scenario causes the vectors to be concentrated in a small number of partitions, which increases the number of vectors in each partition. When this happens, drop the index and recreate it."]]