Print

Please login or register.
1 Hour 1 Day 1 Week 1 Month Forever
Login with username, password and session length

[marekwk]

trying to replace my Linksys WRT54G.  bought one of their "N" products, and was getting ~4.5 MB/sec as opposed to ~2.5 MB/sec on the "G" product.  However, the router kept dropping connectivity and needed resettting few times a day.  Since I was eyeing this D-link unit for awhile, Liksys went back as an RMA.

And today I picked up D-655.  Set up was a breeze for the most part (although still need to spend some time on QoS).  No dropped connections is a good thing.  However, I am only getting ~2.8-3.5 MB/sec when transferring files to "N" laptop.  Hardly an improvement

Any ideas?  Anything I missed in the setup?

802.1 mode = mixed
transmission rate = auto
channel width = auto (20/40)
security =WPA

there are 4 wired connections (gotta love 1MB) and 2 laptops, one "G" adapter and one "N".  Before I bought this unit I asked whether intrduducing the "G" client would throttle down my "N" connection.  Was told that's not the case.

[mig]

I have a similar situation, previous wireless router/gateway was Linksys WRT45G,
then I purchased the DIR-655 and some DWA-552 PCI adapters to increase the
connection for a couple computers in the house.

I setup the DIR-655 as N only, and kept the WRT45G on the network for 'G' clients.
You need to make sure you disable all the 'gateway' features on the router that is
not handling your ISP connection.

I get 270 @ 100% signal on the DIR-655 (no drop-offs).  The WRT54G operates at 54 (as always)

[marekwk]

well, I would like to remove the WRT54G entirely.  And the connections speeds are not really that relevant to me.  I am more interested in "real life" improvement in transfer speed of files between clients.  Guess I could get an D-link "N" adapter for the laptop that's currently using "G" and see what happens when I am using only "N" mode on the router.

cheers!

[Lycan]

I've been seeing this. Look at the CPU usage. It may be spiking causing the LAN to LAN performance to degrade.

[mig]

... And the connections speeds are not really that relevant to me.  I am more interested in "real life" improvement in transfer speed of files between clients.

What method or program do you use to benchmark improvements on your "real life" transfer speeds?

[marekwk]

transferring the same folder (different types of files) between the laptop and desktop using different routers.  Consistent results w/ specific routers.  Same PC / laptop hardware.  No apps running... only variable are the routers.

[mig]

transferring the same folder (different types of files) between the laptop and desktop using different routers...

What is the technique you use to make the transfer?

[marekwk]

I suspect that my technique will be called unreliable.  however, this is what I use in real life, hence this test - I open network neighborhood, locate the folder (always the same, on the same box), and then drag & drop to the same destination on the same target laptop.  the "real" life scenario.

[jebling]

And today I picked up D-655.  Set up was a breeze for the most part (although still need to spend some time on QoS).  No dropped connections is a good thing.  However, I am only getting ~2.8-3.5 MB/sec when transferring files to "N" laptop.  Hardly an improvement
 

i also just bought a d-655 router... have 2 wireless n setups (connected speed 270Mbps) and 1 hard wired (connected at 1 Gbps).   when transferring from the wired computer to either wireless i see same as you around 3.5 MB/sec however when transferring from wireless to hardwired computer i get nearly double the speed at 6.5 MB/sec... am curious why the difference... ideally if it can be achieved in one direction it should be achievable in the other.

[marekwk]

what wireless adapters do you have on your notebooks?

[jebling]

what wireless adapters do you have on your notebooks?

not running notebooks both are desktops located in other rooms... i am using draft 2.0 compliant adapters as follows:

AWLH6080 300N Wireless PCI Adapter

one wireless connects at 270 and the other at 300 both are running xp pro sp2

[marekwk]

different results here... and not as good as yours.  tried it in both direction:

1) from wired desktop (XP Pro SP2) to a laptop (Dell 1505 a/b/g/n adapter... still digging to find out who really makes it) running Vista Ultimate SP1 = ~3MB / sec. 

2) From laptop back to the desktop (same folder) only getting ~2.5 MB / sec.

and yes, I am only connecting at 117 on "N" laptop and 54 on "G" laptop.

[jebling]

different results here... and not as good as yours.  tried it in both direction:

1) from wired desktop (XP Pro SP2) to a laptop (Dell 1505 a/b/g/n adapter... still digging to find out who really makes it) running Vista Ultimate SP1 = ~3MB / sec. 

2) From laptop back to the desktop (same folder) only getting ~2.5 MB / sec.

and yes, I am only connecting at 117 on "N" laptop and 54 on "G" laptop.

i see you're connecting at 117 and noticed from your 1st post you are running wpa not sure what cipher... however from a sticky post from lycan you need to be running the following encryption settings to obtain connection of 300:

"If you are using encryption the router must be configured to use AES cipher. In some firmware versions/models, the only way to get the AES cipher is to run WPA2. If you can not select the Cipher, selecting WPA2 only will force this cipher type."

confirming his position if you log into your router and go into manual wireless setup you will notice near the bottom of the page a discussion pertaining to wpa or wpa2 ending with the following recommendation:

"To achieve better wireless performance use WPA2 Only security mode (or in other words AES cipher)."

[mig]

I used IOmeter http://sourceforge.net/projects/iometer to test my DIR-655 in N only mode
with a connection at 300, and I see ~4.5 MBytes/sec

[EricP]

Copying from a wired desktop to my laptop with an Encore wireless N adapter, 270mbps link speed... I see about 5-6MB/sec. Going from the wireless to the desktop, I see 6.5 and almost 7MB/sec. That's a bit strange, eh?