Print

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

[sghayal]

I just got DNS-321 and found some issues with the speed.

What I am seeing is that transfer speeds are very very sluggish for Gigabit connection. What I am seeing is I get maximum FTP speeds of around 10 to 14 MBPS. (as reported during FTP) but actual speeds are around 450 to 500 KBPS.

This is my configuration.

1) Linux machine with 1 GBPS card
2) D-Link DGS 1008D Gigabit switch
3) DNS-321
4) Windows machine with 100 MBPS card

This are my parameters of comparasion
1) Sending file from windows to Linux (Fastest)
2) Sending file from Linux to DNS-321 (slow)
3) Sending file from Windows to DNS-321 (slow)

During my investigation I found that DNS-321 does not seem to support 1000Base-Tx standard.

If you look at standards supported in document below it does not have 1000Base-Tx

ftp://ftp10.dlink.com/pdfs/products/DNS-321/DNS-321_ds.pdf

This would mean that I have pipeline for 1GBPS but I don't have motor to throw in 1GBPS data.

Can someone clarify this and provide proper guidance.

Thanks,

Sandip Ghayal

[sghayal]

I do think the basic cause of getting equal speed at 100Base is because there is no support for 1000Base.

Thanks,

Sandip

[sghayal]

Ok I did proper test on this.

I created close to 7.9 GB file.

I transfered it from Linux machine to my windows machine and Linux machine to DNS-321.

I used Samba mount to mount shared drive from Linux on to windows and mount shared drive from DNS-321 onto Linux.

Both the file transfers took same time.

One thing to note here is when I was doing file transfers to Windows machine from Linux my Linux machine was also servering other network related things like some file transfers to my ATV box.

Thus it makes me conclude that my Linux machine is able to pump out more power then regular 100 MBPS link. Also during the copy to windows I was noticing that the n/w usage on my windows machine was around 85% (meaning entire pipe to window's machine was full).

When I did file transfer from Linux to DNS-321, I ensured that my linux machine was not doing anything apart from doing file transfer and still the rate of file transfer is same as my 100MBPS network.

This clearly proves to me that what I have got from you is 1 GBPS pipe but my pumping motor is 100 MBPS.

So The question is why do I spend $80 more to get this device when its performance essentially is going to be same as device supporting 100MBPS.

I am seriously thinking of returning this device back.

Thanks,

Sandip Ghayal

[Freeman]

It seems there could be a number of reasons why you're realizing 100Mbps ( lower case b for bits, upper case B for bytes ). Three questions... what kind of network card do you have in your linux box? And does this network card support jumbo frames? Are you using Cat 5e or Cat 6 cables between your linux box and your switch and between your switch and DNS 321?

I ask as all of these could affect your connection speed. I noticed that the D-Link switch you're using supports jumbo frames. I suggest if you have Cat 5e or 6 cables and all devices support jumbo frames you enable it on your Linux box and the DNS-321. Test your speed again and post your results assuming jumbo frames wasn't enabled when you first posted your results.

There's also a setting I've seen, something like "Run at wire speed". If your cables can't support gigabit there's the off chance that your network card or DNS 321, though I'm not sure if the DNS has this capability, is throttling down your connection to a speed the cable(s) can support.

Just a thought. Let us know how it turns out. I enabled jumbo frames on my network, I have an onboard Marvell NIC that supports 9k jumbo frames, a Netgear GS105 that supports 9K frames and the DNS 321 and  DNS 323 that also support 9k frames. I've enabled 9k frames on my PC and the DNS' and saw an increase of 3Mbps, from 15Mbps to 18Mbps ( according to a Vista file transfer dialogue window ). Doesn't seem like a huge increase but the time to transfer files dropped significantly.

[sghayal]

what kind of network card do you have in your linux box? And does this network card support jumbo frames?
Ans>> Yes it does support Jumbo Frames and is configured to use Jumbo frames. I don't have the name of the provider as this box came with the network card.

Are you using Cat 5e or Cat 6 cables between your linux box and your switch and between your switch and DNS 321?
ANS>> Yes

I ask as all of these could affect your connection speed. I noticed that the D-Link switch you're using supports jumbo frames. I suggest if you have Cat 5e or 6 cables and all devices support jumbo frames you enable it on your Linux box and the DNS-321.
ANS>> Results are with Jumbo frames enabled.

Test your speed again and post your results assuming jumbo frames wasn't enabled when you first posted your results.

There's also a setting I've seen, something like "Run at wire speed". If your cables can't support gigabit there's the off chance that your network card or DNS 321, though I'm not sure if the DNS has this capability, is throttling down your connection to a speed the cable(s) can support.
ANS>> This might be bit strange that my cables speed max out exactly at 100 MBPS. But I am using Cat5e/Cat6 standard cables (not crimped by me :-) )

Just a thought. Let us know how it turns out. I enabled jumbo frames on my network, I have an onboard Marvell NIC that supports 9k jumbo frames, a Netgear GS105 that supports 9K frames and the DNS 321 and  DNS 323 that also support 9k frames. I've enabled 9k frames on my PC and the DNS' and saw an increase of 3Mbps, from 15Mbps to 18Mbps ( according to a Vista file transfer dialogue window ). Doesn't seem like a huge increase but the time to transfer files dropped significantly
ANS>> And this is where my issue is. We are moving from 100 MPBS to 1000 MPBS signaling speed we should see significant in increase in network speeds almost 5-6 times when using a true Gigabit card.

ANS>> Now this is what I suspect the issue is. I looked at data sheet for DNS321 and DNS323 and I see one significant difference under Standards supported
DNS323 says IEEE 802.3ab 1000Base-T Gigabit where as DNS321 does not mention this standard. Which basically means we have 1GB pipe but have 100 MB pump to fill in. So anything you do you will get same speed as 100MBPS

[mig]

So The question is why do I spend $80 more to get this device when its performance essentially is going to be same as device supporting 100MBPS.

$80 more than what?
www.smallnetbuilder.com has a NAS chart that compares different products. http://www.smallnetbuilder.com/component/option,com_nas/Itemid,190/
If you select the "1000 Mbps 4K Jumbo Aveage Write Performance" benchmark
you will see the DNS-321 can achieve 16.1 MBytes/s which is above the 100Mbits/s (12.5MBytes/s ) theoretical limit of 100M Ethernet.

[Freeman]

Unfortunately, that's true. Real world gigabit speeds is somewhere above 100Mbps and below 1000Mbps. The rated speed of a network card's a theoretical maximum. For inexpensive consumer hardware I'm not surprised that I'm getting 18MBps, which is 144Mbps, while transferring files. With my 100Mbps network card I would be lucky if I could get 80Mbps. There could be a number of reasons for this, a number of system or network bottlenecks. I'll bet far better network speeds can be obtained if you were to a) transfer your files from a fast data source like a RAM drive b) the network card was connected to a hi speed data bus, PCI-X or PCIe c) the network card had a significant amount of dedicated high speed memory it could use as a buffer.

For testing purposes, one suggestion would be to attach your Linux box directly to your DNS. Setup static IPs and test out your speed once again. Who knows, maybe the switch is the bottlekneck ( sorry d-link ).

[sghayal]

Folks,

I think we all are missing a point here.

I have 100MBPS and 1000MBPS card and both card have smae thru puts when both of them are flushed with 1000MBPS line on other end, this is really unrealistic scenario if switch is also a Gigabit switch.

The real issue I feel is D-link for some reason beyond my imagination is not suporting 1000-BaseTX standard with DNS-321 though it provides 1000GBPS signaling speed. So that situtation is like D-link provides a pipe that will carry 1000 liters of water /second but the provided pump is only pumping at 100 liters of water / second. Is there a disconnect here?

I am going to try today evening to send file across gigabit network using my laptop which has gigabit card and my linux with gigabit card and see what kind of transfer speeds I get from that.

[nossy]

Folks,

I think we all are missing a point here.

I have 100MBPS and 1000MBPS card and both card have smae thru puts when both of them are flushed with 1000MBPS line on other end, this is really unrealistic scenario if switch is also a Gigabit switch.

The real issue I feel is D-link for some reason beyond my imagination is not suporting 1000-BaseTX standard with DNS-321 though it provides 1000GBPS signaling speed. So that situtation is like D-link provides a pipe that will carry 1000 liters of water /second but the provided pump is only pumping at 100 liters of water / second. Is there a disconnect here?

I am going to try today evening to send file across gigabit network using my laptop which has gigabit card and my linux with gigabit card and see what kind of transfer speeds I get from that.

I understand what you are saying exactly, but I doubt D-Link would admit to that fact if it is indeed how the NAS is setup.

[Freeman]

If you're going to try bypassing the switch definetly let us know how it goes. I was thinking about trying this myself just to see what speeds I could get directly connected to the DNS-321 or 323. Another idea came to mind that may be affecting your speeds, the PCI bus. Is this a PCI gigabit card or an onboard gigabit adapter attached to the PCI bus? The PCI bus could be a serious bottleneck for a gigabit adapter especially if there are a number of other devices in your system causing bus contention issues.

What we're trying to say here is there a number of factors that could affect your gigabit speed. It could be the DNS 321 but it could also be a number of other issues. I hope you figure it out, I'm starting to think my 18MBps isn't nearly enough.

[mig]

...Is there a disconnect here?

Yes, there are so many significant dissimilar characteristics between your two "test cases"
which makes your comparison practically inconclusive.

[sghayal]

Mig can you specify the reason for disconnect?

Thanks

[sghayal]

If you're going to try bypassing the switch definetly let us know how it goes. I was thinking about trying this myself just to see what speeds I could get directly connected to the DNS-321 or 323. Another idea came to mind that may be affecting your speeds, the PCI bus. Is this a PCI gigabit card or an onboard gigabit adapter attached to the PCI bus? The PCI bus could be a serious bottleneck for a gigabit adapter especially if there are a number of other devices in your system causing bus contention issues.

What we're trying to say here is there a number of factors that could affect your gigabit speed. It could be the DNS 321 but it could also be a number of other issues. I hope you figure it out, I'm starting to think my 18MBps isn't nearly enough.

Thats something I want to try but little bit scared of spoling my setup on Linux. I have found some issue on my Linux machine that if not connected to network properly causes my box to hang or reply really slow so don't want to touch that box much at this time as it is very critical component in my home network (running FTA TV :-) ).

I agree with yoru comments about PCI card and going to find it out but still I would hope slightly higher speed of transfer on 1GB line then 100MB line and strangely I am not seeing that.

[fordem]

If I could just chime in here ...

If you can transfer data at anything over 100 mbps, you're getting gigabit speeds - a lot of people do not seem to recognize that the transfer rate observed when copying files from one system to another is only as fast as the slowest link in the chain, which starts with a hard drive at one end and finishes with a hard drive at the other - the network may not be the bottleneck.

Back in the days of 10 mbps ethernet, 3Com's "parallel tasking" line of cards was the only thing that could approach wire speed, and to make that happen I had to load one card in a server with three data streams from client PCs using a memory-to-memory test procedure that 3Com outlined.

In those days the average throughput on a 10 mbps ethernet card was <3 mbps.

When 100 mps ethernet came along, I ran those same tests and got throughput in the vicinity of 25~35 mpbs and gigabit ethernet is no different - depending on the hardware - low end hardware ~170 mbps, high end hardware ~800 mbps.

I don't have a DNS-321 and so can not provide figures for it, but the older DNS-323 can deliver ~400 mbps - memory-to-memory, this does not include the transfer to/from the disks, with a disk-disk transfer I can hit 28MBPS on a read, or 224~280 mbps.

The 15~18 MB/s reported by the second poster is indicative of giagbit speeds.

[mig]

Mig can you specify the reason for disconnect?

You have preformed a completely uncontrolled test, therefore no reasonable conclusion can be reached.

You have chosen to test your DNS-321 with two VERY different computers:
different OS, different network cards, different motherboards, different filesystems.

And from that you conclude the DSN-321 does not support 1000Mbps network?!! 

What I think you should be trying to figure out is, why your linux box can't achieve the
transfer rate that smallnetbuilder.com (and others) are able to achieve, instead of making
claims that the DNS-321 is flawed.

As Freeman posted:

What we're trying to say here is there [are] a number of factors that could affect your gigabit speed. It could be the DNS 321 but it could also be a number of other issues. [...]

By the way, I'm not saying your tests are not valid. These are your "real world" operating
conditions, regardless of what transfer rates anyone else is able to achieve.  If you are not
able to achieve satisfactory transfer speeds in your environment, then maybe this is not the
right NAS for you.