Link Aggregation in Action

In order to get an idea of how link aggregation really helps, we first set up the NAS with just a single active network link. The first set of tests downloads the Blu-ray folder from the NAS starting with the PC connected to port 3, followed by simultaneous download of two different copies of the content from the NAS to the PCs connected to ports 3 and 4. The same concept is extended to three simultaneous downloads via ports 3, 4 and 5. A similar set of tests is run to evaluate the uplink part (i.e, data moves from the PCs to the NAS). The final set of tests involve simultaneous upload and download activities from the different PCs in the setup.

The upload and download speeds of the wired NICs on the PCs were monitored and graphed. This gives an idea of the maximum possible throughput from the NAS's viewpoint and also enables us to check if link aggregation works as intended.

The above graph shows that the download and upload links are limited to under 1 Gbps (taking into account the transfer inefficiencies introduced by various small files in the folder). However, the full duplex 1 Gbps nature of the NAS network link enables greater than 1 Gbps throughput when handling simultaneous uploads and downloads.

In our second wired experiment, we teamed the ports on the NAS with the default options (other than explicitly changing the teaming type to 802.3ad LACP). This left the hash type at Layer 2. Running our transfer experiments showed that there was no improvement over the single link results from the previous test.

In our test setup / configuration, Layer 2 as the transmit hash policy turned out to be ineffective. Readers interested in understanding more about the transmit hash policies which determine the distribution of traffic across the different physical ports in a team should peruse the Linux kernel documentation here (search for the description of the parameter 'xmit_hash_policy').

After altering the hash policy to Layer 2 + 3 in the ReadyNAS UI, the effectiveness of link aggregation became evident.

In the pure download case with two PCs, we can see each of the PCs getting around 800 Mbps (implying that the NAS was sending out data on both the physical NICs in the team). An interesting aspect to note in the pure download case with three PCs is that Machine 1 (connected to port 3) manages the same 800 Mbps as in the previous case, but the download rates on Machines 2 and 3 (connected to ports 4 and 5) add up to a similar amount. This shows that the the network ports 4 and 5 are bottlenecked by a 1 Gbps connection to the switch chip handling the link aggregation ports. This is also the reason why Netgear suggests using port 3 as one of the ports for handling the data transfer to/from the link aggregated ports. Simultaneous uploads and downloads also show some improvement, but the pure upload case is not any different from the single link case. These could be attributed to the limitations of the NAS itself. Note that we are using real-world data streams transferred using the OS file copy tools (and not artificial benchmarking programs) in these experiments.

Introduction and Benchmarking Setup The Promise of Gigabit Wi-Fi and Concluding Remarks
POST A COMMENT

67 Comments

View All Comments

  • MrX8503 - Saturday, January 2, 2016 - link

    The iPad Pro's lighting connector is USB3 and the storage is PCIe and NVMe. Reply
  • dsumanik - Sunday, January 3, 2016 - link

    Whoop de doo...go onto your ipad pro, right now. USB3 and pcie storage dont do anything to solve the fundamental problem: IOS is content consumption and delivery platform, end of story.

    Pic your favorite photo editing app, id recommend Pixelmator, enlight, vsco, or snapseed. Great apps... all of em. Now export those files to ready to print 300DPI 4x6, 5x7, 10x8 jpegs.

    See you in an hour.

    OK done?

    Now send them to the printer (easy, just email etc). Now Go pick em up

    ...hey wait....

    why dont these pictures look like they do on my ipad Pro.

    Cuz you didn't use the correct color space, and didnt retouch the photos using your local printers profile, so the colors just dont match bruh.

    Apple forgot the pros, when they made the ipad pro.

    Right now all the apple lovers are saying:

    "god that dsumanik is so dumb my ipad pro is the best tablet ever its amazing....oh damn new update on angry bird lets check it out...OMG its so amazing on this big screen"

    ...2 hrs later posts on anandtech:

    "dsumanik you are just dumb, dont you have a life, you just are an apple hater and a stupid ninny boo boo head and the apple pencil is amazing and beats the surface pro any day"

    Actually let's be honest:

    you're all still exporting!

    BAHAHAHAH
    Reply
  • sor - Thursday, December 31, 2015 - link

    To be fair, most of his rant is true, but degrades into an Apple hate diatribe at the end. The "OMG QUAD SLI!" Motherboard review, with no trace of SLI test was roundly criticized. The excuse was "well, we don't have four video cards", fair enough I guess, but something you'd expect from an amateur blogger. Why even bother reviewing a $500 motherboard that only justifies its existence by having quad SLI if you can't test it? If the manufacturer wants you to review it, demand the necessary equipment to make it worth doing. Reply
  • melgross - Thursday, December 31, 2015 - link

    No, that's not the review. Maybe you should have read what it said before jumping to conclusions so that you could try to refute me. Reply
  • Makaveli - Thursday, December 31, 2015 - link

    Here's an idea keep your off topic apple crap out of a netgear router review please and thank you! Reply
  • VictorBd - Friday, January 1, 2016 - link

    Rude. Reply
  • dave_the_nerd - Thursday, December 31, 2015 - link

    The guy who does the NAS and Networking reviews isn't the same guy(s) who do the mobile device reviews. Or the GPU reviews, for that matter.

    Anandtech reviews are usually worth waiting for, regardless.
    Reply
  • BurntMyBacon - Monday, January 11, 2016 - link

    @dave_the_nerd: "The guy who does the NAS and Networking reviews isn't the same guy(s) who do the mobile device reviews. Or the GPU reviews, for that matter."

    Nor would you want them to be. Now what you should be asking is what legitimate reason could exist that would delay the review. Could be the author was sick. Perhaps there were issues with the test selection. Also, it could very well be that their initial results didn't match up the larger tech community and rather than just post as is, they set out to find out why.

    @dave_the_nerd: "Anandtech reviews are usually worth waiting for, regardless."
    Only the ones that you actually wait for. ;')
    Reply
  • Ryan Smith - Thursday, December 31, 2015 - link

    "I've been seeing, and reading, a lot of reviews here during December, and I'm still waiting for the review of the ipad Pro, which came out some time ago now, and was promised for December. Well, here we are, and it's the last day in December, and where is it?"

    And that is a perfectly reasonable critique to make; we haven't been able to get it out nearly as quickly as we had hoped. Suffice it to say, we had planned to have the iPad Pro review out this week. However things didn't work out like Josh and I wanted, and as a result it wasn't possible to complete it in time.

    At this point it's a matter of days. If we can't get it out the Monday before CES then you'll see it the week afterwards. But either way you'll see it. We've put a lot of work into this one, and I want to give you guys a review worth waiting for.
    Reply
  • c0y0te - Thursday, December 31, 2015 - link

    Thanks Ryan. I have been waiting for the iPad Pro review as well. Reply

Log in

Don't have an account? Sign up now