From: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
---|---|
To: | Jaime Casanova <jcasanov(at)systemguards(dot)com(dot)ec> |
Cc: | Robert Haas <robertmhaas(at)gmail(dot)com>, decibel <decibel(at)decibel(dot)org>, psql performance list <pgsql-performance(at)postgresql(dot)org> |
Subject: | Re: [PERFORMANCE] work_mem vs temp files issue |
Date: | 2010-01-11 20:18:40 |
Message-ID: | 18803.1263241120@sss.pgh.pa.us |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-performance |
Jaime Casanova <jcasanov(at)systemguards(dot)com(dot)ec> writes:
> LOG: begin tuple sort: nkeys = 1, workMem = 1024, randomAccess = f
> LOG: switching to bounded heapsort at 641 tuples: CPU 0.08s/0.13u sec elapsed 0.25 sec
> LOG: temporary file: path "base/pgsql_tmp/pgsql_tmp8507.5", size 471010
> LOG: temporary file: path "base/pgsql_tmp/pgsql_tmp8507.10", size 81096
> LOG: temporary file: path "base/pgsql_tmp/pgsql_tmp8507.0", size 467373
> LOG: temporary file: path "base/pgsql_tmp/pgsql_tmp8507.9", size 110200
> LOG: temporary file: path "base/pgsql_tmp/pgsql_tmp8507.3", size 470011
> LOG: temporary file: path "base/pgsql_tmp/pgsql_tmp8507.8", size 157192
> LOG: temporary file: path "base/pgsql_tmp/pgsql_tmp8507.4", size 468681
> LOG: temporary file: path "base/pgsql_tmp/pgsql_tmp8507.12", size 101624
> LOG: temporary file: path "base/pgsql_tmp/pgsql_tmp8507.1", size 472285
> LOG: temporary file: path "base/pgsql_tmp/pgsql_tmp8507.11", size 100744
> LOG: temporary file: path "base/pgsql_tmp/pgsql_tmp8507.6", size 467173
> LOG: temporary file: path "base/pgsql_tmp/pgsql_tmp8507.7", size 141888
> LOG: temporary file: path "base/pgsql_tmp/pgsql_tmp8507.2", size 476227
> LOG: temporary file: path "base/pgsql_tmp/pgsql_tmp8507.13", size 89072
> LOG: performsort starting: CPU 0.10s/0.19u sec elapsed 0.33 sec
> LOG: performsort done: CPU 0.10s/0.19u sec elapsed 0.33 sec
> LOG: internal sort ended, 118 KB used: CPU 0.10s/0.19u sec elapsed 0.33 sec
Hmm. Not clear where the temp files are coming from, but it's *not* the
sort --- the "internal sort ended" line shows that that sort never went
to disk. What kind of plan is feeding the sort node?
regards, tom lane
From | Date | Subject | |
---|---|---|---|
Next Message | Tom Lane | 2010-01-11 20:25:57 | Re: performance config help |
Previous Message | Scott Marlowe | 2010-01-11 20:16:45 | Re: performance config help |