Voir le 'gonflement des tables , la requête provient de la sonde nagios / icinga check_postgres de bucardo.org.

requête complexe triée (tables non bloatée n'apparaissent pas):

WITH constants AS (
    -- definition de constantes pour les tailles
    -- pour référence dans la requête et avoir un entretien facilité
    SELECT current_setting('block_size')::numeric AS bs, 23 AS hdr, 8 AS ma
),
no_stats AS (
    -- exclusion des tables qui ont des attributs
    -- qui n'ont pas de statistiques, telles que 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 (
    -- trouver les en-têtes nulles 
    -- omission des tables qui n'ont pas de statistiques complètes
    -- et des attributs qui ne sont pas visibles
    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 (
    -- estimation de la taille de l'en-tête et de la ligne
    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 (
    -- estimations de la taille des tables
    -- en fonctionde la taille de la ligne et de la page
    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 (
    -- ajouter les tailles estimées des tables 'TOAST'
    -- estimation basée sur 4 toast tuples par page car on a rien de mieux
    -- ajout également des tables no_data
    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 (
-- ajout des métadonnées supplémentaire aux données de la table
-- et aux calculs à réutiliser
-- y compris si nous ne pouvons pas l'estimer
-- ou si nous pensons qu'elles pourraient être compressées
    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 (
    -- calculs finaux et formatage du résultat
    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
)
-- sortie de filtre pour les tables bloatées
SELECT databasename, schemaname, tablename,
    can_estimate,
    est_rows,
    pct_bloat, mb_bloat,
    table_mb
FROM bloat_data
-- ce where définit les tables qui apparaissent réellement
-- dans le qraphique des bloat
-- exemple ci-dessous les filtres pour les tables qui sont à 50%
-- bloatée avec plus de 20mb , ou plus de 25%
-- bloatée avec plus 1GB
WHERE ( pct_bloat >= 1 AND mb_bloat >= 20 )
    OR ( pct_bloat >= 1 AND mb_bloat >= 20 )
ORDER BY pct_bloat DESC;

 

requête plus simple non triée

SELECT
  current_database(), schemaname, tablename, /*reltuples::bigint, relpages::bigint, otta,*/
  ROUND((CASE WHEN otta=0 THEN 0.0 ELSE sml.relpages::FLOAT/otta END)::NUMERIC,1) AS tbloat,
  CASE WHEN relpages < otta THEN 0 ELSE bs*(sml.relpages-otta)::BIGINT END AS wastedbytes,
  iname, /*ituples::bigint, ipages::bigint, iotta,*/
  ROUND((CASE WHEN iotta=0 OR ipages=0 THEN 0.0 ELSE ipages::FLOAT/iotta END)::NUMERIC,1) AS ibloat,
  CASE WHEN ipages < iotta THEN 0 ELSE bs*(ipages-iotta) END AS wastedibytes
FROM (
  SELECT
    schemaname, tablename, cc.reltuples, cc.relpages, bs,
    CEIL((cc.reltuples*((datahdr+ma-
      (CASE WHEN datahdr%ma=0 THEN ma ELSE datahdr%ma END))+nullhdr2+4))/(bs-20::FLOAT)) AS otta,
    COALESCE(c2.relname,'?') AS iname, COALESCE(c2.reltuples,0) AS ituples, COALESCE(c2.relpages,0) AS ipages,
    COALESCE(CEIL((c2.reltuples*(datahdr-12))/(bs-20::FLOAT)),0) AS iotta -- very rough approximation, assumes all cols
  FROM (
    SELECT
      ma,bs,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 (
      SELECT
        schemaname, tablename, hdr, ma, bs,
        SUM((1-null_frac)*avg_width) AS datawidth,
        MAX(null_frac) AS maxfracsum,
        hdr+(
          SELECT 1+COUNT(*)/8
          FROM pg_stats s2
          WHERE null_frac<>0 AND s2.schemaname = s.schemaname AND s2.tablename = s.tablename
        ) AS nullhdr
      FROM pg_stats s, (
        SELECT
          (SELECT current_setting('block_size')::NUMERIC) AS bs,
          CASE WHEN SUBSTRING(v,12,3) IN ('8.0','8.1','8.2') THEN 27 ELSE 23 END AS hdr,
          CASE WHEN v ~ 'mingw32' THEN 8 ELSE 4 END AS ma
        FROM (SELECT version() AS v) AS foo
      ) AS constants
      GROUP BY 1,2,3,4,5
    ) AS foo
  ) AS rs
  JOIN pg_class cc ON cc.relname = rs.tablename
  JOIN pg_namespace nn ON cc.relnamespace = nn.oid AND nn.nspname = rs.schemaname AND nn.nspname <> 'information_schema'
  LEFT JOIN pg_index i ON indrelid = cc.oid
  LEFT JOIN pg_class c2 ON c2.oid = i.indexrelid
) AS sml
ORDER BY wastedbytes DESC