[mapserver-users] MapServer webgis used too little capacity bandwidth

[Andy Colson]

Mr. Bic Phuong wrote:
> Dear MapServer Users and Developers,
> 
> I have 2 webgis servers:
> 
> - The first is MapServer webgis which using: - MapServer - OpenLayers - 
> ArcSDE for Oracle - Tilecache (RHEL 5.3 OS)
> - The second is a webgis developing with ASP.NET (Windows OS)
> 
> Using DU Meters, I have just tested the first webgis and found that this 
> using too little capacity of bandwidth, maximum is about 200Mbps. So 
> it's so long to complete the request.
> 
> While Google Map or the second webgis costs about 900Mbps or above of 
> bandwidth.
> 
> I also tested bandwidth of 2 servers above, they are equal.
> 
> I'm wondering why the first server used too little capacity of 
> bandwidth, can I make it using more capacity for fast complete client's 
> requests?
> 
> Thanks for your attention ! any help is appreciated
> 

First, I think we need to find the bottleneck.

a) If there is only one client, requesting one map, then you will not 
have enough data going over the line to use 200Mbps.

b) If you have lots of clients, all requesting lots of maps, then you'll 
have enough data going over the line to use 200Mbps.

Assuming b is true, then we need to see if you are cpu bound or io 
bound.  On you linux box watch "vmstat 5" for a while (you could even 
post the results if you want).

The last column "wa" is %cpu wait time for the hard drve.  If that's 
high then you're io bound.

Next column in is "id", or %cpu idle time.  If that's near zero then you 
are cpu bound.

-Andy