[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[netCDF #CFH-512758]: Rough Order of Mangitude Numbers
- Subject: [netCDF #CFH-512758]: Rough Order of Mangitude Numbers
- Date: Mon, 14 Feb 2011 11:25:24 -0700
Hi Barry,
> We plan to use NetCDF4 to package our satellite imagery to send to
> an end user. The plan is to describe our imagery as a two dimensional
> array of pixel values (each pixel value being a 16 bit Integer). Neither
> dimension is unlimited. We plan to use the Classic model. No compression
> or packing is planned for. Approximately 20 metadata attributes are
> planned for (each attribute being about 10 bytes long). No parallel
> processing planned for. The hardware platform is an Intel "XEONM388"
> processor with a clock spped of 2 Ghz. Memory = 8 GB. I need some rough
> order of magnitude numbers for how long it takes to write a 100 x 100
> array as described above. Also what percentage of the generated file size
> is overhead. If there are other factors that significantly affect the
> numbers feel free to include them as defaults in your estimates.
The write takes about 0.02 sec. Less than 2.6% of the file is
overhead.
--Russ
Russ Rew UCAR Unidata Program
address@hidden http://www.unidata.ucar.edu
Ticket Details
===================
Ticket ID: CFH-512758
Department: Support netCDF
Priority: Normal
Status: Closed