Re: [HACKERS] performance tests, initial results - Mailing list pgsql-hackers

From Vadim Mikheev
Subject Re: [HACKERS] performance tests, initial results
Date
Msg-id 3584743E.2A005766@krs.ru
Whole thread Raw
In response to performance tests, initial results  (dg@illustra.com (David Gould))
List pgsql-hackers
First, thanks for fixing runtests.pl, David (I'm not so cool perl
programmer as I would like to be -:)

>  - Assertion checking seems to cost about 7% except for create index where
>    it costs 90%

Wow! This should be discovered!

>  - Something is very wrong with our buffer cache implementation. Going from
>    256 buffers to 2048 buffers costs an average of 25%. In the 8K txn case
>    it costs about 70%. I see looking at the code and profiling that in the 8K
>    txn case this is in BufferSync() which examines all the buffers at commit
                                            ^^^^^^^^^^^^^^^^^^^^^^^^
>    time. I don't quite understand why it is so costly for the single 8K row
>    txn (35%) though.

This one is in my plans for 1 - 1.5 year :)

Vadim

pgsql-hackers by date:

Previous
From: dg@illustra.com (David Gould)
Date:
Subject: performance tests, initial results
Next
From: Vassilis Papadimos
Date:
Subject: subscribe