Re: [HACKERS] Clock with Adaptive Replacement
| От | Vladimir Sitnikov |
|---|---|
| Тема | Re: [HACKERS] Clock with Adaptive Replacement |
| Дата | |
| Msg-id | CAB=Je-F_BhGfBu1sO1H7u_XMtvak=BQtuJFyv8cfjGBRp7Q_yA@mail.gmail.com обсуждение исходный текст |
| Ответ на | Re: [HACKERS] Clock with Adaptive Replacement (Robert Haas <robertmhaas@gmail.com>) |
| Ответы |
Re: [HACKERS] Clock with Adaptive Replacement
|
| Список | pgsql-hackers |
>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?
Sample output can be seen here: https://github.com/vlsi/pgsqlstat/tree/pgsqlio#pgsqlio
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 1If DTrace is acceptable, trace format might be adjusted for easier consumption by https://github.com/ben-manes/caffeine/wiki/Simulator
Vladimir
В списке pgsql-hackers по дате отправления: