Horton

Re: PostgreSQL pre-fork speedup

James Robinson <jlrobins@socialserve.com>

View thread View on postgr.es
From: James Robinson <jlrobins@socialserve.com>
To: Tom Lane <tgl@sss.pgh.pa.us>
Cc: PostgreSQL Development <pgsql-hackers@postgresql.org>, sdv mailer <sdvmailer@yahoo.com>, Tatsuo Ishii <t-ishii@sra.co.jp>
Date: 2004-05-06T19:06:56Z
Lists: pgsql-hackers 
Tom Lane writes:
	... too much flushing ...

I agree. I'll bet replacing the pool_write_and_flush() calls in 
BinaryRow()
and AsciiRow() with just pool_write(), followed by removing the
fflush() calls at the bottom of those two methods should go a long
way towards fixing things, since the CompleteCommandResponse
handler method ends with a call to pool_write_and_flush(), and
you've pretty much gotta get a CompleteCommand message
trailing all of those rows.

----
James Robinson
Socialserve.com