Commit 095c8691 authored by Ahmad Sherif's avatar Ahmad Sherif

Merge branch 'bjk/update_queries' into 'master'

Update bloat queries

See merge request gitlab-org/gitlab-exporter!125
parents 19d86623 f194bb4b
Pipeline #178403 passed with stage
in 2 minutes and 15 seconds
......@@ -12,73 +12,90 @@ SELECT current_database(), nspname AS schemaname, tblname, idxname AS object_nam
END 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)
-- , 100-(pst).avg_leaf_density AS pst_avg_bloat, est_pages, index_tuple_hdr_bm, maxalign, pagehdr, nulldatawidth, nulldatahdrwidth, reltuples, 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)
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, tblname, idxname, relpages, fillfactor, is_na
-- , pgstatindex(idxoid) 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
AND nspname = 'public'
ORDER BY 2,3,4;
SELECT maxalign, bs, nspname, tblname, idxname, reltuples, relpages, idxoid, 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 n.nspname, i.tblname, i.idxname, i.reltuples, i.relpages,
i.idxoid, i.fillfactor, current_setting('block_size')::numeric AS bs,
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 i.atttypid = 'pg_catalog.name'::regtype THEN 1 ELSE 0 END ) > 0 AS is_na
FROM (
SELECT ct.relname AS tblname, ct.relnamespace, ic.idxname, ic.attpos, ic.indkey, ic.indkey[ic.attpos], ic.reltuples, ic.relpages, ic.tbloid, ic.idxoid, ic.fillfactor,
coalesce(a1.attnum, a2.attnum) AS attnum, coalesce(a1.attname, a2.attname) AS attname, coalesce(a1.atttypid, a2.atttypid) AS atttypid,
CASE WHEN a1.attnum IS NULL
THEN ic.idxname
ELSE ct.relname
END AS attrelname
FROM (
SELECT idxname, reltuples, relpages, tbloid, idxoid, fillfactor, indkey,
pg_catalog.generate_series(1,indnatts) AS attpos
FROM (
SELECT ci.relname AS idxname, ci.reltuples, ci.relpages, i.indrelid AS tbloid,
i.indexrelid AS idxoid,
coalesce(substring(
array_to_string(ci.reloptions, ' ')
from 'fillfactor=([0-9]+)')::smallint, 90) AS fillfactor,
i.indnatts,
pg_catalog.string_to_array(pg_catalog.textin(
pg_catalog.int2vectorout(i.indkey)),' ')::int[] AS indkey
FROM pg_catalog.pg_index i
JOIN pg_catalog.pg_class ci ON ci.oid = i.indexrelid
WHERE ci.relam=(SELECT oid FROM pg_am WHERE amname = 'btree')
AND ci.relpages > 0
) AS idx_data
) AS ic
JOIN pg_catalog.pg_class ct ON ct.oid = ic.tbloid
LEFT JOIN pg_catalog.pg_attribute a1 ON
ic.indkey[ic.attpos] <> 0
AND a1.attrelid = ic.tbloid
AND a1.attnum = ic.indkey[ic.attpos]
LEFT JOIN pg_catalog.pg_attribute a2 ON
ic.indkey[ic.attpos] = 0
AND a2.attrelid = ic.idxoid
AND a2.attnum = ic.attpos
) i
JOIN pg_catalog.pg_namespace n ON n.oid = i.relnamespace
JOIN pg_catalog.pg_stats s ON s.schemaname = n.nspname
AND s.tablename = i.attrelname
AND s.attname = i.attname
GROUP BY 1,2,3,4,5,6,7,8,9,10,11
) AS rows_data_stats
) AS rows_hdr_pdg_stats
) AS relation_stats
ORDER BY nspname, tblname, idxname;
-- Originally from: https://github.com/ioguix/pgsql-bloat-estimation/blob/master/table/table_bloat.sql
/* WARNING: executed with a non-superuser role, the query inspect only tables you are granted to read.
/* WARNING: executed with a non-superuser role, the query inspect only tables and materialized view (9.3+) you are granted to read.
* This query is compatible with PostgreSQL 9.0 and more
*/
SELECT current_database(), schemaname, tblname AS object_name, bs*tblpages AS real_size,
......@@ -16,12 +16,12 @@ SELECT current_database(), schemaname, tblname AS object_name, bs*tblpages AS re
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
-- , tpl_hdr_size, tpl_data_size, (pst).free_percent + (pst).dead_tuple_percent AS real_frag -- (DEBUG INFO)
FROM (
SELECT ceil( reltuples / ( (bs-page_hdr)/tpl_size ) ) + ceil( toasttuples / 4 ) AS est_tblpages,
ceil( reltuples / ( (bs-page_hdr)*fillfactor/(tpl_size*100) ) ) + ceil( toasttuples / 4 ) AS est_tblpages_ff,
tblpages, fillfactor, bs, tblid, schemaname, tblname, heappages, toastpages, is_na
-- , stattuple.pgstattuple(tblid) AS pst
-- , tpl_hdr_size, tpl_data_size, pgstattuple(tblid) AS pst -- (DEBUG INFO)
FROM (
SELECT
( 4 + tpl_hdr_size + tpl_data_size + (2*ma)
......@@ -29,6 +29,7 @@ FROM (
- 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
-- , tpl_hdr_size, tpl_data_size
FROM (
SELECT
tbl.oid AS tblid, ns.nspname AS schemaname, tbl.relname AS tblname, tbl.reltuples,
......@@ -40,24 +41,24 @@ FROM (
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,
23 + CASE WHEN MAX(coalesce(s.null_frac,0)) > 0 THEN ( 7 + count(s.attname) ) / 8 ELSE 0::int END
+ CASE WHEN bool_or(att.attname = 'oid' and att.attnum < 0) THEN 4 ELSE 0 END AS tpl_hdr_size,
sum( (1-coalesce(s.null_frac, 0)) * coalesce(s.avg_width, 0) ) AS tpl_data_size,
bool_or(att.atttypid = 'pg_catalog.name'::regtype)
OR count(att.attname) <> count(s.attname) AS is_na
OR sum(CASE WHEN att.attnum > 0 THEN 1 ELSE 0 END) <> 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
WHERE NOT att.attisdropped
AND tbl.relkind in ('r','m')
GROUP BY 1,2,3,4,5,6,7,8,9,10
ORDER BY 2,3
) AS s
) AS s2
) AS s3
WHERE NOT is_na
-- WHERE NOT is_na
-- AND tblpages*((pst).free_percent + (pst).dead_tuple_percent)::float4/100 >= 1
AND schemaname= 'public';
ORDER BY schemaname, tblname;
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment