Bloated 테이블을 조회하는 쿼리

코로나 이슈로 트래픽이 급증한 K사의 데이터베이스 구조를 OLTP와 OLAP으로 명확히 구분하여 나누는 작업을 진행하는 과정에서 모처럼 얻은 다운타임 시간 동안 vacuum full을 수행할 일이 있었다. 그룹사 지원 차원에서 온 K사의 ICT 계열사 소속 엔지니어와 함께 진행을 해나갔는데 이 엔지니어가 오픈소스 DB팀에서는 vacuum full를 돌리기 전에 current_size와 actual_size의 현황을 조사한다면서 어떤 SQL 스크립트를 실행하는 것이었다. 그 모습을 보면서 예전에 citus data 블로그에서 읽은 Monitoring your bloat in Postgres라는 글이 생각나서 이번 기회에 정리해두려고 한다.

WITH constants AS (
    -- define some constants for sizes of things
    -- for reference down the query and easy maintenance
    SELECT current_setting('block_size')::numeric AS bs, 23 AS hdr, 8 AS ma
),
no_stats AS (
    -- screen out table who have attributes
    -- which dont have stats, such as JSON
    SELECT table_schema, table_name, 
        n_live_tup::numeric as est_rows,
        pg_table_size(relid)::numeric as table_size
    FROM information_schema.columns
        JOIN pg_stat_user_tables as psut
           ON table_schema = psut.schemaname
           AND table_name = psut.relname
        LEFT OUTER JOIN pg_stats
        ON table_schema = pg_stats.schemaname
            AND table_name = pg_stats.tablename
            AND column_name = attname 
    WHERE attname IS NULL
        AND table_schema NOT IN ('pg_catalog', 'information_schema')
    GROUP BY table_schema, table_name, relid, n_live_tup
),
null_headers AS (
    -- calculate null header sizes
    -- omitting tables which dont have complete stats
    -- and attributes which aren't visible
    SELECT
        hdr+1+(sum(case when null_frac <> 0 THEN 1 else 0 END)/8) as nullhdr,
        SUM((1-null_frac)*avg_width) as datawidth,
        MAX(null_frac) as maxfracsum,
        schemaname,
        tablename,
        hdr, ma, bs
    FROM pg_stats CROSS JOIN constants
        LEFT OUTER JOIN no_stats
            ON schemaname = no_stats.table_schema
            AND tablename = no_stats.table_name
    WHERE schemaname NOT IN ('pg_catalog', 'information_schema')
        AND no_stats.table_name IS NULL
        AND EXISTS ( SELECT 1
            FROM information_schema.columns
                WHERE schemaname = columns.table_schema
                    AND tablename = columns.table_name )
    GROUP BY schemaname, tablename, hdr, ma, bs
),
data_headers AS (
    -- estimate header and row size
    SELECT
        ma, bs, hdr, schemaname, tablename,
        (datawidth+(hdr+ma-(case when hdr%ma=0 THEN ma ELSE hdr%ma END)))::numeric AS datahdr,
        (maxfracsum*(nullhdr+ma-(case when nullhdr%ma=0 THEN ma ELSE nullhdr%ma END))) AS nullhdr2
    FROM null_headers
),
table_estimates AS (
    -- make estimates of how large the table should be
    -- based on row and page size
    SELECT schemaname, tablename, bs,
        reltuples::numeric as est_rows, relpages * bs as table_bytes,
    CEIL((reltuples*
            (datahdr + nullhdr2 + 4 + ma -
                (CASE WHEN datahdr%ma=0
                    THEN ma ELSE datahdr%ma END)
                )/(bs-20))) * bs AS expected_bytes,
        reltoastrelid
    FROM data_headers
        JOIN pg_class ON tablename = relname
        JOIN pg_namespace ON relnamespace = pg_namespace.oid
            AND schemaname = nspname
    WHERE pg_class.relkind = 'r'
),
estimates_with_toast AS (
    -- add in estimated TOAST table sizes
    -- estimate based on 4 toast tuples per page because we dont have 
    -- anything better.  also append the no_data tables
    SELECT schemaname, tablename, 
        TRUE as can_estimate,
        est_rows,
        table_bytes + ( coalesce(toast.relpages, 0) * bs ) as table_bytes,
        expected_bytes + ( ceil( coalesce(toast.reltuples, 0) / 4 ) * bs ) as expected_bytes
    FROM table_estimates LEFT OUTER JOIN pg_class as toast
        ON table_estimates.reltoastrelid = toast.oid
            AND toast.relkind = 't'
),
table_estimates_plus AS (
-- add some extra metadata to the table data
-- and calculations to be reused
-- including whether we cant estimate it
-- or whether we think it might be compressed
    SELECT current_database() as databasename,
            schemaname, tablename, can_estimate, 
            est_rows,
            CASE WHEN table_bytes > 0
                THEN table_bytes::NUMERIC
                ELSE NULL::NUMERIC END
                AS table_bytes,
            CASE WHEN expected_bytes > 0 
                THEN expected_bytes::NUMERIC
                ELSE NULL::NUMERIC END
                    AS expected_bytes,
            CASE WHEN expected_bytes > 0 AND table_bytes > 0
                AND expected_bytes <= table_bytes
                THEN (table_bytes - expected_bytes)::NUMERIC
                ELSE 0::NUMERIC END AS bloat_bytes
    FROM estimates_with_toast
    UNION ALL
    SELECT current_database() as databasename, 
        table_schema, table_name, FALSE, 
        est_rows, table_size,
        NULL::NUMERIC, NULL::NUMERIC
    FROM no_stats
),
bloat_data AS (
    -- do final math calculations and formatting
    select current_database() as databasename,
        schemaname, tablename, can_estimate, 
        table_bytes, round(table_bytes/(1024^2)::NUMERIC,3) as table_mb,
        expected_bytes, round(expected_bytes/(1024^2)::NUMERIC,3) as expected_mb,
        round(bloat_bytes*100/table_bytes) as pct_bloat,
        round(bloat_bytes/(1024::NUMERIC^2),2) as mb_bloat,
        table_bytes, expected_bytes, est_rows
    FROM table_estimates_plus
)
-- filter output for bloated tables
SELECT databasename, schemaname, tablename,
    can_estimate,
    est_rows,
    pct_bloat, mb_bloat,
    table_mb
FROM bloat_data
-- this where clause defines which tables actually appear
-- in the bloat chart
-- example below filters for tables which are either 50%
-- bloated and more than 20mb in size, or more than 25%
-- bloated and more than 1GB in size
WHERE ( pct_bloat >= 50 AND mb_bloat >= 20 )
    OR ( pct_bloat >= 25 AND mb_bloat >= 1000 )
ORDER BY pct_bloat DESC;

CTE 방식으로 파생 테이블에서 파생 테이블을 만들다가 bloat_data라는 CTE 테이블에서 최종적으로 bloating과 관련된 값들을 조회한다. where 조건을 줘서 bloat 퍼센트와 양 값으로 필터링을 할 수도 있다.