Poor performance

[ssevenup]

Is anyone else noticing that the Linux client performance is Slooow? My MacOSX boxes will commonly run at 500+ MB/min. The best my Linux box can do is 250. The Macs are 100base-T connected. The Linux cluster and file server are gigabit connected and on the same gigabit switch as my Win2k Retrospect server. Is this a "nice" priority situation?

 

--MM

 

[natew]

Hi

 

Do you notice the speed problem when you backup a smaller subvolume on the linux client? Are you backing up a large number of smaller files? That will take much longer than larger files.

 

You could try renicing the client process but I'm not convinced the speed problem is on the client side.

 

Nate

[ssevenup]

This is a basic system load with not much user data yet. As such, it's a mixture of file types and sizes. The backup fluctuates around the 250MB/min number, where the OSX backup fluctuates around the 500-600MB/min number. I have no reason to suspect it's a file size or file type issue. I could try re-nicing, but I was more interested in what others are seeing without doing so.

 

Then again I have a trouble ticket with our network operations because of a massive glaring performance discrepency among our buildings. The network hardware is all similar and the routes in question are also, yet I get 2 to 5 times the performance if I relocate my server from it's normal location to another building. I can push packets at wire speed using a tool like iperf, but Retrospect server crawls in one subnet and flys in the other. The location of the client seems to have nothing to do with it. It has everyone totally baffled.

 

--MM

 

[natew]

Hi

 

I responded to your other post about the speed thing between buildings

 

Nate