| From: | Mark Wong <markw(at)osdl(dot)org> |
|---|---|
| To: | "Luke Lonergan" <llonergan(at)greenplum(dot)com> |
| Cc: | "Andrew Dunstan" <andrew(at)dunslane(dot)net>, "Alvaro Herrera" <alvherre(at)surnet(dot)cl>, "Bruce Momjian" <pgman(at)candle(dot)pha(dot)pa(dot)us>, "Alon Goldshuv" <agoldshuv(at)greenplum(dot)com>, pgsql-patches(at)postgresql(dot)org, maryedie(at)osdl(dot)org |
| Subject: | Re: COPY FROM performance improvements |
| Date: | 2005-07-21 21:55:07 |
| Message-ID: | 200507212154.j6LLsdjA002847@smtp.osdl.org |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-patches pgsql-performance |
I just ran through a few tests with the v14 patch against 100GB of data
from dbt3 and found a 30% improvement; 3.6 hours vs 5.3 hours. Just to
give a few details, I only loaded data and started a COPY in parallel
for each the data files:
http://www.testing.osdl.org/projects/dbt3testing/results/fast_copy/
Here's a visual of my disk layout, for those familiar with the database schema:
http://www.testing.osdl.org/projects/dbt3testing/results/fast_copy/layout-dev4-010-dbt3.html
I have 6 arrays of fourteen 15k rpm drives in a split-bus configuration
attached to a 4-way itanium2 via 6 compaq smartarray pci-x controllers.
Let me know if you have any questions.
Mark
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Tom Lane | 2005-07-21 22:26:17 | Re: [PATCHES] Roles - SET ROLE Updated |
| Previous Message | Stephen Frost | 2005-07-21 21:45:14 | Re: [PATCHES] Roles - SET ROLE Updated |
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Luke Lonergan | 2005-07-21 23:14:47 | Re: COPY FROM performance improvements |
| Previous Message | Frank Wosczyna | 2005-07-21 18:26:04 | Re: What is best way to stream terabytes of data into |