UNPKG

@clickup/pg-microsharding

Version:
145 lines (140 loc) 4.5 kB
import mapValues from "lodash/mapValues"; import omit from "lodash/omit"; import { shardFactorFromComment } from "./names"; import { ident, join, sql } from "./quote"; import { runSql } from "./runSql"; import { unindent } from "./unindent"; const FUNC_NAME_WEIGHT = "microsharding_schema_weights_weight_"; const FUNC_NAME_STATS = "microsharding_schema_weights_stats_"; export const WEIGHT_COL_NAME_DEFAULT = "Weight"; // Perf notes: // - pg_relation_size() is fastest, but doesn't include TOASTs // - pg_table_size() is 50% slower (still okay), it includes TOASTs // - pg_total_relation_size() includes indexes and is super-slow const WEIGHT_SQL_DEFAULT = unindent(` SELECT round(sum(pg_table_size(pg_class.oid)) / 1024 / 1024) || ' MB' AS "Size" FROM pg_class WHERE pg_class.relkind = 'r' AND pg_class.relnamespace = current_schema()::regnamespace `); /** * Returns weights for each schema in the list. SQL query in weightSql should * return a numeric value with optional units after it; the units should be the * same in all responses and are ignored while sorting. */ export async function getSchemaWeights({ dsn, schemas, weightSql, verbose, }: { dsn: string; schemas: string[]; weightSql: string | undefined; verbose?: boolean; }): Promise< Map< string, { weightColName: string; weight: number; appliedFactor: number; unit: string | undefined; other: Record<string, string>; } > > { weightSql ||= WEIGHT_SQL_DEFAULT; const statsSql = unindent(` SELECT ${[ 'count(1) AS "Tables"', 'sum(seq_scan)+sum(idx_scan) AS "Reads"', ...(verbose ? [ "sum(seq_scan) AS seq_scan", "sum(idx_scan) AS idx_scan", "sum(vacuum_count) AS vacuum_count", ] : []), 'sum(n_tup_ins)+sum(n_tup_upd)+sum(n_tup_del) AS "Writes"', ...(verbose ? [ "sum(n_tup_ins) AS n_tup_ins", "sum(n_tup_upd) AS n_tup_upd", "sum(n_tup_del) AS n_tup_del", ] : []), ].join(",\n ")} FROM pg_stat_user_tables WHERE schemaname = current_schema() `); const query = join( [ unindent(` CREATE OR REPLACE FUNCTION pg_temp.${FUNC_NAME_WEIGHT}(schema_name text) RETURNS text LANGUAGE plpgsql AS $$ BEGIN EXECUTE format('SET search_path TO %I', schema_name); RETURN (SELECT row_to_json(r) FROM (${weightSql.trim()}) r); EXCEPTION WHEN undefined_table THEN RETURN NULL; END; $$ `), unindent(` CREATE OR REPLACE FUNCTION pg_temp.${FUNC_NAME_STATS}(schema_name text) RETURNS text LANGUAGE plpgsql AS $$ BEGIN EXECUTE format('SET search_path TO %I', schema_name); RETURN (SELECT row_to_json(r) FROM (${statsSql.trim()}) r); END; $$ `), sql` SELECT schema_name, obj_description(schema_name::regnamespace, 'pg_namespace'), pg_temp.${ident(FUNC_NAME_WEIGHT)}(schema_name), pg_temp.${ident(FUNC_NAME_STATS)}(schema_name) FROM json_array_elements_text(${JSON.stringify(schemas)}) AS t(schema_name) `, ], ";\n", ); const resRows = await runSql(dsn, query); return new Map( resRows.map(([schema, schemaComment, weightJson, statsJson]) => { const weightRow: Record<string, unknown> = weightJson ? JSON.parse(weightJson) : {}; const statsRow: Record<string, unknown> = statsJson ? JSON.parse(statsJson) : {}; const row = { ...weightRow, ...statsRow }; const weightColName = Object.keys(row)[0] || undefined; const weightWithUnit = weightColName ? String(row[weightColName] || "") : ""; const [weight, unit] = weightWithUnit.match(/^(\d+)(.*)$/s) ? [parseFloat(RegExp.$1), RegExp.$2.trim()] : [0, undefined]; const appliedFactor = shardFactorFromComment(schemaComment) ?? 1; return [ schema, { weightColName: !weightColName || weightColName.startsWith("?") ? WEIGHT_COL_NAME_DEFAULT : weightColName, weight: weight * appliedFactor, appliedFactor, unit, other: mapValues( weightColName ? omit(row, weightColName) : row, String, ), }, ]; }), ); }