Re: netcdf question

• To: Quinn Sloan <sloan@xxxxxxxxxxxxxxxxxxx>
• Subject: Re: netcdf question
• From: Mike Hamilton <hamilton@xxxxxxxxxxxxxx>
• Date: Tue, 28 Feb 1995 10:37:13 -0800 (PST)

On Mon, 27 Feb 1995, Quinn Sloan wrote:
<some stuff deleted>
> then it takes over 30 minutes to perform the same writing.
> I am using two sparc 10's in this case running SunOS
> release 4.1.3 and NFS and f77.  The times that I've
> given are really approximate, but from my experience,
> the ratio of (time using one machine) / (time using 2 machines)
> is significantly greater than the ratio
> (disk write) / (ethernet + disk write)
> at least for the type of simple I/O operations that I'm 
> used to.
> 
> Can you tell me if its normal for netcdf to take a long
> time to write across the ethernet, and if there are any
> common pitfalls that people run into when trying to 
> do so?  I realize that this might be dependent on 
> my code, so if it would help you to see some of the 
> netcdf call's that I'm using, please let me know.

Hmm.  I guess it could depend on how busy your network was...

It's an interesting question.  I don't have the answer, but
I'd be interested to hear what kind of responses you get.

Mike

+-----------------------------------+-----------------------------------+
| Michael Hamilton                  | Internet: hamilton@xxxxxxxxxxxxxx |
| Climate Research Division         | voice:    (619) 534-0855          |
| Scripps Institute of Oceanography | fax:      (619) 534-8561          |
+-----------------------------------+-----------------------------------+

• References:
  • netcdf question
    • From: Quinn Sloan