Postgres Pro
Downloads
Home   >   mailing lists

Re: [HACKERS] Clock with Adaptive Replacement - Mailing list pgsql-hackers

From Vladimir Sitnikov
Subject Re: [HACKERS] Clock with Adaptive Replacement
Date
Msg-id CAB=Je-F_BhGfBu1sO1H7u_XMtvak=BQtuJFyv8cfjGBRp7Q_yA@mail.gmail.com
Whole thread Raw
In response to Re: [HACKERS] Clock with Adaptive Replacement  (Robert Haas <robertmhaas@gmail.com>)
Responses Re: [HACKERS] Clock with Adaptive Replacement  (Robert Haas <robertmhaas@gmail.com>)
List pgsql-hackers
Tree view
>If somebody produced a trace showing the buffer lookups in order

To get things moving, I've created a DTrace script that captures buffer reads:

Is it something that can be used to capture live traces?


For instance (time units are nano-seconds):

     Timestamp  Elapsed  ForkNum BlockNum  TableSp DataBase Relation Cached3271837060212     1563        0        1     1663    16385     1259      13271838881374    88205        0        0     1663    16385    16604      03271840973321     4368        0        0     1663    16385    16604      1
If DTrace is acceptable, trace format might be adjusted for easier consumption by https://github.com/ben-manes/caffeine/wiki/Simulator

Vladimir

pgsql-hackers by date:

Previous
From: Peter Geoghegan
Date:
Subject: Re: Sort performance cliff with small work_mem
Next
From: Andrew Dunstan
Date:
Subject: Re: stats_ext test fails with -DCATCACHE_FORCE_RELEASE