| From: | "Luke Lonergan" <llonergan(at)greenplum(dot)com> |
|---|---|
| To: | "Mark Woodward" <pgsql(at)mohawksoft(dot)com>, pg(at)mohawksoft(dot)com, pgsql-hackers(at)postgresql(dot)org |
| Subject: | Re: Netflix Prize data |
| Date: | 2006-10-04 21:00:00 |
| Message-ID: | C1496EE0.372A%llonergan@greenplum.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
Mark,
On 10/4/06 1:43 PM, "Mark Woodward" <pgsql(at)mohawksoft(dot)com> wrote:
> markw(at)snoopy:~/netflix$ time psql netflix -c "select count(*) from ratings"
> count
> -----------
> 100480507
> (1 row)
>
>
> real 2m6.270s
> user 0m0.004s
> sys 0m0.005s
I think you are getting about 40MB/s on your sequential scan of about 5GB of
heap data in this case. I calculate the size of the data as:
3 Integers (12 bytes), one text date field (10 bytes ?) and tuple overhead
(24 bytes) = 46 bytes per row
100 million rows x 46 bytes / row = 4.6 Gbytes
- Luke
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Tom Lane | 2006-10-04 21:00:52 | Re: Netflix Prize data |
| Previous Message | Mark Woodward | 2006-10-04 20:43:42 | Netflix Prize data |