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

Re: measuring lwlock-related latency spikes

From: Simon Riggs <simon(at)2ndQuadrant(dot)com>
To: Greg Stark <stark(at)mit(dot)edu>
Cc: Robert Haas <robertmhaas(at)gmail(dot)com>, pgsql-hackers(at)postgresql(dot)org
Subject: Re: measuring lwlock-related latency spikes
Date: 2012-03-31 14:21:48
Message-ID: CA+U5nMLAFGe5PEm79uRBrPFQvorKbkVPyfhAHbRGyAOg7MX=2Q@mail.gmail.com (view raw or flat)
Thread:
Lists: pgsql-hackers
On Sat, Mar 31, 2012 at 1:58 PM, Greg Stark <stark(at)mit(dot)edu> wrote:
> On Sat, Mar 31, 2012 at 4:41 AM, Robert Haas <robertmhaas(at)gmail(dot)com> wrote:
>> But I didn't think we were ever supposed to hold content
>> locks for that long.
>
> Isn't that lock held while doing visibility checks? What about I/O
> waiting for a clog page to be read?

So what we should be logging is the list of lwlocks held when the lock
wait occurred.

That would differentiate call paths somewhat better than just looking
at the current lock request.

-- 
 Simon Riggs                   http://www.2ndQuadrant.com/
 PostgreSQL Development, 24x7 Support, Training & Services

In response to

pgsql-hackers by date

Next:From: Tom LaneDate: 2012-03-31 14:56:36
Subject: pgsql: Add PGDLLIMPORT to ScanKeywords and NumScanKeywords.
Previous:From: Dobes VandermeerDate: 2012-03-31 13:37:14
Subject: Re: HTTP Frontend? (and a brief thought on materialized views)

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