Skip site navigation (1) Skip section navigation (2)

Re: testing HS/SR - 1 vs 2 performance

From: Heikki Linnakangas <heikki(dot)linnakangas(at)enterprisedb(dot)com>
To: Erik Rijkers <er(at)xs4all(dot)nl>
Cc: pgsql-hackers(at)postgresql(dot)org
Subject: Re: testing HS/SR - 1 vs 2 performance
Date: 2010-04-13 18:09:46
Message-ID: 4BC4B36A.3090803@enterprisedb.com (view raw or flat)
Thread:
Lists: pgsql-hackers
Heikki Linnakangas wrote:
> I could reproduce this on my laptop, standby is about 20% slower. I ran
> oprofile, and what stands out as the difference between the master and
> standby is that on standby about 20% of the CPU time is spent in
> hash_seq_search(). The callpath is GetSnapshotDat() ->
> KnownAssignedXidsGetAndSetXmin() -> hash_seq_search(). That explains the
> difference in performance.

The slowdown is proportional to the max_connections setting in the
standby. 20% slowdown might still be acceptable, but if you increase
max_connections to say 1000, things get really slow. I wouldn't
recommend max_connections=1000, of course, but I think we need to do
something about this. Changing the KnownAssignedXids data structure from
hash table into something that's quicker to scan. Preferably something
with O(N), where N is the number of entries in the data structure, not
the maximum number of entries it can hold as it is with the hash table
currently.

A quick fix would be to check if there's any entries in the hash table
before scanning it. That would eliminate the overhead when there's no
in-progress transactions in the master. But as soon as there's even one,
the overhead comes back.

-- 
  Heikki Linnakangas
  EnterpriseDB   http://www.enterprisedb.com

In response to

Responses

pgsql-hackers by date

Next:From: Alvaro HerreraDate: 2010-04-13 19:00:25
Subject: Re: Timezone matching script (win32)
Previous:From: Tom LaneDate: 2010-04-13 17:55:39
Subject: Re: Timezone matching script (win32)

Privacy Policy | About PostgreSQL
Copyright © 1996-2014 The PostgreSQL Global Development Group