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

High IOWAIT times, low iops? Can't figure out what the bottleneck is...

From: "Evan Reiser" <evan(dot)reiser(at)gmail(dot)com>
To: pgsql-admin(at)postgresql(dot)org
Subject: High IOWAIT times, low iops? Can't figure out what the bottleneck is...
Date: 2007-07-03 17:19:43
Message-ID: (view raw, whole thread or download thread mbox)
Lists: pgsql-admin
I was wondering if you guys have some suggested settings for our server, i
think we are not hardware limited but the configureation is set up
incorrectly.  For some reason our database seems to have trouble handling
5-10+ inserts per second which seems to be a pretty trivial load for this
hardware, we're seeing very high %iowait, this is a pretty typical output
for #iostat -m 5

avg-cpu:  %user   %nice %system %iowait  %steal   %idle
                0.97      0.00    0.82         89.69     0.00      8.52

Device:            tps    MB_read/s    MB_wrtn/s    MB_read    MB_wrtn
sda              85.40         0.18         0.72                 0
sdb               0.00         0.00         0.00                  0
sdc              30.43         0.00         0.76                 0
sdd              93.91         0.71         0.12                 3

sda = 2x320GB 7200rpm in RAID1 (operating system)
sdc = 2x150GB 10krpm in RAID1    (transaction log is on this array)
sdd = 6x150GB 10krpm in RAID 10 (database is on the array)

we're using ReiserFS on each of the arrays as the file system
OS is debian Etch x64

raid controller = 3ware 9650 12port - 256MB cache

8GB RAM, core 2 duo - quad core 2.4ghz 8MB L2 Cache

it would seem like the io subsystem is the limiting factor, but i feel like
we should be barely hitting a wall, you can see from the example its writing
< 2MB/s to the array.  If i try to copy a big file (1-2GB) over to the
array, the array hits 300MB/s sustained, it can burst write files < 256mb AT

Here's some of our settings

shared_buffers = 1024MB
temp_buffers = 32MB
max_prepared_transactions = 50
work_mem = 64MB
maintenance_work_mem = 256MB
max_stack_depth = 7MB
max_fsm_pages = 512000

vacuum_cost_delay = 20ms

fsync = on
wal_buffers = 1MB
checkpoint_segments = 32

effective_cache_size = 4128MB

If you guys have any suggestions it would be greatly appreciated

-Evan Reiser


pgsql-admin by date

Next:From: Evan ReiserDate: 2007-07-03 17:44:49
Subject: Re: High IOWAIT times, low iops? Can't figure out what the bottleneck is...
Previous:From: Jayakumar_MukundarajuDate: 2007-07-03 09:16:22
Subject: Re: pg_hba.conf issue

Privacy Policy | About PostgreSQL
Copyright © 1996-2017 The PostgreSQL Global Development Group