Lists: | pgsql-performance |
---|
From: | André Volpato <andre(dot)volpato(at)ecomtecnologia(dot)com(dot)br> |
---|---|
To: | pgsql-performance(at)postgresql(dot)org |
Subject: | Postgres not using array |
Date: | 2008-08-20 18:30:25 |
Message-ID: | 48AC62C1.9070209@ecomtecnologia.com.br |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Lists: | pgsql-performance |
Folks,
In a fresh Pg8.3.3 box, we created a 3-stripe RAID0 array.
The write speed is about 180MB/s, as shown by dd :
# dd if=/dev/zero of=/postgres/base/teste2 bs=1024 count=5000000
5000000+0 records in
5000000+0 records out
5120000000 bytes (5,1 GB) copied, 28,035 seconds, 183 MB/s
BTW, /postgres is $PGDATA ...
Unfortunely, we cant figure out why Postgres is not using the disks at all.
Right now, there are 3 heavy queryes running, and the disks are almost
sleeping...
The CPU is 100% used since a few hours ago. Can anyone tell why?
# dstat
----total-cpu-usage---- -dsk/total- -net/total- ---paging-- ---system--
usr sys idl wai hiq siq|_read _writ|_recv _send|__in_ _out_|_int_ _csw_
99 1 0 0 0 0| 0 0 | 574B 1710B| 0 0 | 6 55
99 1 0 0 0 0| 0 0 | 290B 770B| 0 0 | 8 48
99 1 0 0 0 0| 0 0 | 220B 540B| 0 0 | 6 44
99 1 0 0 0 0| 0 0 | 354B 818B| 0 0 | 10 50
98 2 0 0 0 0| 0 0 |1894B 4857B| 0 0 | 27 78
100 0 0 0 0 1| 0 0 | 348B 1096B| 0 0 | 12 45
The specs:
Intel(R) Pentium(R) Dual CPU E2160 @ 1.80GHz
Linux dbserver4 2.6.24-etchnhalf.1-686-bigmem #1 SMP Mon Jul 21 11:59:12
UTC 2008 i686 GNU/Linux
4GB RAM
--
[]´s, ACV
From: | "David Wilson" <david(dot)t(dot)wilson(at)gmail(dot)com> |
---|---|
To: | André Volpato <andre(dot)volpato(at)ecomtecnologia(dot)com(dot)br> |
Cc: | pgsql-performance(at)postgresql(dot)org |
Subject: | Re: Postgres not using array |
Date: | 2008-08-20 20:02:01 |
Message-ID: | e7f9235d0808201302v1ebe732fjbb6bbf17cf69eed3@mail.gmail.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Lists: | pgsql-performance |
On Wed, Aug 20, 2008 at 2:30 PM, André Volpato
<andre(dot)volpato(at)ecomtecnologia(dot)com(dot)br> wrote:
> The CPU is 100% used since a few hours ago. Can anyone tell why?
Sounds like you've just got a CPU bound query. The data may even all
be in cache.
Some information on database size, along with EXPLAIN results for your
queries, would help here.
--
- David T. Wilson
david(dot)t(dot)wilson(at)gmail(dot)com