PostgreSQL Technologies

Display the estimated amount of bloat in your tables and indices in PostgreSQL:

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
;

table_bloat.sql

/* WARNING: executed with a non-superuser role, the query inspect only *tables you are granted to read.
This query is compatible with PostgreSQL 9.0 and more
*/

SELECT current_database(), schemaname, tblname, bstblpages AS real_size,
(tblpages-est_tblpages)*bs AS extra_size,
CASE WHEN tblpages - est_tblpages > 0
THEN 100 * (tblpages - est_tblpages)/tblpages::float
ELSE 0
END AS extra_ratio, fillfactor, (tblpages-est_tblpages_ff)*bs AS bloat_size,
CASE WHEN tblpages - est_tblpages_ff > 0
THEN 100 * (tblpages - est_tblpages_ff)/tblpages::float
ELSE 0
END AS bloat_ratio, is_na
-- , (pst).free_percent + (pst).dead_tuple_percent AS real_frag
FROM (
SELECT ceil( reltuples / ( (bs-page_hdr)/tpl_size ) ) + ceil( toasttuples / 4 ) AS est_tblpages,
ceil( reltuples / ( (bs-page_hdr)
fillfactor/(tpl_size100) ) ) + ceil( toasttuples / 4 ) AS est_tblpages_ff,
tblpages, fillfactor, bs, tblid, schemaname, tblname, heappages, toastpages, is_na
-- , stattuple.pgstattuple(tblid) AS pst
FROM (
SELECT
( 4 + tpl_hdr_size + tpl_data_size + (2
ma) - CASE WHEN tpl_hdr_size%ma = 0 THEN ma ELSE tpl_hdr_size%ma END - CASE WHEN ceil(tpl_data_size)::int%ma = 0 THEN ma ELSE ceil(tpl_data_size)::int%ma END ) AS tpl_size, bs - page_hdr AS size_per_block, (heappages + toastpages) AS tblpages, heappages, toastpages, reltuples, toasttuples, bs, page_hdr, tblid, schemaname, tblname, fillfactor, is_na FROM ( SELECT tbl.oid AS tblid, ns.nspname AS schemaname, tbl.relname AS tblname, tbl.reltuples, tbl.relpages AS heappages, coalesce(toast.relpages, 0) AS toastpages, coalesce(toast.reltuples, 0) AS toasttuples, coalesce(substring( array_to_string(tbl.reloptions, ' ') FROM 'fillfactor=([0-9]+)')::smallint, 100) AS fillfactor, current_setting('block_size')::numeric AS bs, CASE WHEN version()~'mingw32' OR version()~'64-bit|x86_64|ppc64|ia64|amd64' THEN 8 ELSE 4 END AS ma, 24 AS page_hdr, 23 + CASE WHEN MAX(coalesce(null_frac,0)) > 0 THEN ( 7 + count() ) / 8 ELSE 0::int END
+ CASE WHEN tbl.relhasoids THEN 4 ELSE 0 END AS tpl_hdr_size,
sum( (1-coalesce(s.null_frac, 0)) * coalesce(s.avg_width, 1024) ) AS tpl_data_size,
bool_or(att.atttypid = 'pg_catalog.name'::regtype)
OR count(att.attname) <> count(s.attname) AS is_na
FROM pg_attribute AS att
JOIN pg_class AS tbl ON att.attrelid = tbl.oid
JOIN pg_namespace AS ns ON ns.oid = tbl.relnamespace
LEFT JOIN pg_stats AS s ON s.schemaname=ns.nspname
AND s.tablename = tbl.relname AND s.inherited=false AND s.attname=att.attname
LEFT JOIN pg_class AS toast ON tbl.reltoastrelid = toast.oid
WHERE att.attnum > 0 AND NOT att.attisdropped
AND tbl.relkind = 'r'
GROUP BY 1,2,3,4,5,6,7,8,9,10, tbl.relhasoids
ORDER BY 2,3
) AS s
) AS s2
) AS s3
-- WHERE NOT is_na
-- AND tblpages*((pst).free_percent + (pst).dead_tuple_percent)::float4/100 >= 1;

Btree_bloat.sql

— WARNING: executed with a non-superuser role, the query inspect only index on tables you are granted to read.
— WARNING: rows with is_na = ‘t’ are known to have bad statistics (“name” type is not supported).
— This query is compatible with PostgreSQL 8.2 and after

SELECT current_database(), nspname AS schemaname, tblname, idxname, bs(relpages)::bigint AS real_size, bs(relpages-est_pages)::bigint AS extra_size,
100 * (relpages-est_pages)::float / relpages AS extra_ratio,
fillfactor, bs*(relpages-est_pages_ff) AS bloat_size,
100 * (relpages-est_pages_ff)::float / relpages AS bloat_ratio,
is_na
-- , 100-(sub.pst).avg_leaf_density, est_pages, index_tuple_hdr_bm, maxalign, pagehdr, nulldatawidth, nulldatahdrwidth, sub.reltuples, sub.relpages -- (DEBUG INFO)
FROM (
SELECT coalesce(1 +
ceil(reltuples/floor((bs-pageopqdata-pagehdr)/(4+nulldatahdrwidth)::float)), 0 -- ItemIdData size + computed avg size of a tuple (nulldatahdrwidth)
) AS est_pages,
coalesce(1 +
ceil(reltuples/floor((bs-pageopqdata-pagehdr)
fillfactor/(100(4+nulldatahdrwidth)::float))), 0
) AS est_pages_ff,
bs, nspname, table_oid, tblname, idxname, relpages, fillfactor, is_na
-- , stattuple.pgstatindex(quote_ident(nspname)||'.'||quote_ident(idxname)) AS pst, index_tuple_hdr_bm, maxalign, pagehdr, nulldatawidth, nulldatahdrwidth, reltuples -- (DEBUG INFO)
FROM (
SELECT maxalign, bs, nspname, tblname, idxname, reltuples, relpages, relam, table_oid, fillfactor,
( index_tuple_hdr_bm +
maxalign - CASE -- Add padding to the index tuple header to align on MAXALIGN
WHEN index_tuple_hdr_bm%maxalign = 0 THEN maxalign
ELSE index_tuple_hdr_bm%maxalign
END
+ nulldatawidth + maxalign - CASE -- Add padding to the data to align on MAXALIGN
WHEN nulldatawidth = 0 THEN 0
WHEN nulldatawidth::integer%maxalign = 0 THEN maxalign
ELSE nulldatawidth::integer%maxalign
END
)::numeric AS nulldatahdrwidth, pagehdr, pageopqdata, is_na
-- , index_tuple_hdr_bm, nulldatawidth -- (DEBUG INFO)
FROM (
SELECT
i.nspname, i.tblname, i.idxname, i.reltuples, i.relpages, i.relam, a.attrelid AS table_oid,
current_setting('block_size')::numeric AS bs, fillfactor,
CASE -- MAXALIGN: 4 on 32bits, 8 on 64bits (and mingw32 ?)
WHEN version() ~ 'mingw32' OR version() ~ '64-bit|x86_64|ppc64|ia64|amd64' THEN 8
ELSE 4
END AS maxalign,
/* per page header, fixed size: 20 for 7.X, 24 for others
/ 24 AS pagehdr, / per page btree opaque data / 16 AS pageopqdata, / per tuple header: add IndexAttributeBitMapData if some cols are null-able / CASE WHEN max(coalesce(s.null_frac,0)) = 0 THEN 2 -- IndexTupleData size ELSE 2 + (( 32 + 8 - 1 ) / 8) -- IndexTupleData size + IndexAttributeBitMapData size ( max num filed per index + 8 - 1 /8) END AS index_tuple_hdr_bm, / data len: we remove null values save space using it fractionnal part from stats */
sum( (1-coalesce(s.null_frac, 0)) * coalesce(s.avg_width, 1024)) AS nulldatawidth,
max( CASE WHEN a.atttypid = 'pg_catalog.name'::regtype THEN 1 ELSE 0 END ) > 0 AS is_na
FROM pg_attribute AS a
JOIN (
SELECT nspname, tbl.relname AS tblname, idx.relname AS idxname, idx.reltuples, idx.relpages, idx.relam,
indrelid, indexrelid, indkey::smallint[] AS attnum,
coalesce(substring(
array_to_string(idx.reloptions, ' ')
from 'fillfactor=([0-9]+)')::smallint, 90) AS fillfactor
FROM pg_index
JOIN pg_class idx ON idx.oid=pg_index.indexrelid
JOIN pg_class tbl ON tbl.oid=pg_index.indrelid
JOIN pg_namespace ON pg_namespace.oid = idx.relnamespace
WHERE pg_index.indisvalid AND tbl.relkind = 'r' AND idx.relpages > 0
) AS i ON a.attrelid = i.indexrelid
JOIN pg_stats AS s ON s.schemaname = i.nspname
AND ((s.tablename = i.tblname AND s.attname = pg_catalog.pg_get_indexdef(a.attrelid, a.attnum, TRUE)) -- stats from tbl
OR (s.tablename = i.idxname AND s.attname = a.attname))-- stats from functionnal cols
JOIN pg_type AS t ON a.atttypid = t.oid
WHERE a.attnum > 0
GROUP BY 1, 2, 3, 4, 5, 6, 7, 8, 9
) AS s1
) AS s2
JOIN pg_am am ON s2.relam = am.oid WHERE am.amname = 'btree'
) AS sub
-- WHERE NOT is_na
ORDER BY 2,3,4;

Comments Rating 0 (0 reviews)

About the author

BestTechReads

Add Comment

Click here to post a comment

Sending

Categories

Categories