From: | "Luke Lonergan" <llonergan(at)greenplum(dot)com> |
---|---|
To: | "Stefan Kaltenbrunner" <stefan(at)kaltenbrunner(dot)cc> |
Cc: | "Spiegelberg, Greg" <gspiegelberg(at)cranel(dot)com>, "Worky Workerson" <worky(dot)workerson(at)gmail(dot)com>, "Merlin Moncure" <mmoncure(at)gmail(dot)com>, pgsql-performance(at)postgresql(dot)org |
Subject: | Re: Best COPY Performance |
Date: | 2006-10-30 15:03:41 |
Message-ID: | C16B625D.5708%llonergan@greenplum.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-performance |
Stefan,
On 10/30/06 8:57 AM, "Stefan Kaltenbrunner" <stefan(at)kaltenbrunner(dot)cc> wrote:
>> We've found that there is an ultimate bottleneck at about 12-14MB/s despite
>> having sequential write to disk speeds of 100s of MB/s. I forget what the
>> latest bottleneck was.
>
> I have personally managed to load a bit less then 400k/s (5 int columns
> no indexes) - on very fast disk hardware - at that point postgresql is
> completely CPU bottlenecked (2,6Ghz Opteron).
400,000 rows/s x 4 bytes/column x 5 columns/row = 8MB/s
> Using multiple processes to load the data will help to scale up to about
> 900k/s (4 processes on 4 cores).
18MB/s? Have you done this? I've not seen this much of an improvement
before by using multiple COPY processes to the same table.
Another question: how to measure MB/s - based on the input text file? On
the DBMS storage size? We usually consider the input text file in the
calculation of COPY rate.
- Luke
From | Date | Subject | |
---|---|---|---|
Next Message | Tom Lane | 2006-10-30 15:09:29 | Re: Strange plan in pg 8.1.0 |
Previous Message | Mattias Kregert | 2006-10-30 14:26:09 | Re: Strange plan in pg 8.1.0 |