Like every other website on the planet, SmallNetBuilder uses cookies. Our cookies track login status, but we only allow admins to log in anyway, so those don't apply to you. Any other cookies you pick up during your visit come from advertisers, which we don't control.
If you continue to use the site, you agree to tolerate our use of cookies. Thank you!

Wi-Fi Router Charts

Click for Wi-Fi Router Charts

Mesh System Charts

Click for Wi-Fi Mesh System Charts

Mode Comparison

To get a better feel for the non-cached performance of the NV in its different modes, it's more helpful to compare test data taken with a larger file size (I use 128 MBytes), which is relatively free of caching effects. Figures 13 and 14 show write performance for the NV with 100 Mbps and 1Gbps network connections respectively.

Be sure to note the approximately 2 to 1 scale change between 100Mbps and 1Gbps graphs. I've also included results from the TeraStation review since it is also a TeraByte RAID NAS, and threw in results from the ReadyNAS 600/X6 review to test Infrant's assertion of NV's improved performance.


Figure 13: 128M file Write performance comparison - 100Mbps LAN

Figure 13: 128M file Write performance comparison - 100Mbps LAN
(click image to enlarge)

Figure 13 shows both Infrant products handily beating the Terastation, but the NV's read speed with a 100 Mbps Ethernet connection falling below that of the ReadyNAS 600 previously tested. When I shared these results with Infrant, they suggested that the journaling settings could be the cause of the NV's lower write speed. But my test notes from the ReadyNAS 600 show that I used the same settings that I described earlier, for the NV test runs.

Since I couldn't put the drives back into the 600 chassis because I had upgraded the NV to new firmware, I reran the NV with a 1 Gbps Ethernet connection, no jumbo frames and journaling completely turned off (all other runs had journaling enabled, but full journaling disabled). Figure 14 has all the data, including, once again, data from the Buffalo Terastation review.

Update 13 March 2006: Further testing revealed that I had recorded the settings incorrectly for the ReadyNAS 600. So all 600 results shown were taken with all journaling features disabled. When I ran the ReadyNAS 600 and NV with the same journaling settings, the NV turned in higher performance in all cases.


Figure 14: 128M file Write performance comparison - 1 Gbps LAN

Figure 14: 128M file Write performance comparison - 1 Gbps LAN
(click image to enlarge)

The plot is a mite busy, but the two lines of interest for this experiment are the "Infrant NV RAID 5 1G" and "Infrant NV RAID 5 1G No Journaling". The results show that turning journaling completely off boosts non-cached write performance by about 50%, propelling the NV past the ReadyNAS 600 and the various jumbo frame modes. But given that most writes will see some benefit from caching, it's questionable whether you would ever see this effect for writes.


Figure 15: 128M file Write performance comparison - 100Mbps LAN

Figure 15: 128M file Read performance comparison - 100Mbps LAN
(click image to enlarge)

Moving on to the 100 Mbps Read plot in Figure 15, you can see that the Terastation, ReadyNAS 600 and NV are more closely matched, although the 600 once again comes out on top for most of the record sizes tested. The read results in Figure 16 taken with a 1 Gbps LAN connection, show both the 600 and NV leave the Terastation in the dust and a similar ~50% boost in read speed from fully disabling journaling.


Figure 16: 128M file Read performance comparison - 1 Gbps LAN

Figure 16: 128M file Read performance comparison - 1 Gbps LAN
(click image to enlarge)

The other interesting thing shown by Figure 16 is the cluster of 1G, 1G 4k Jumbo, and 1G 9k Jumbo lines in the center of the chart. Since jumbo frames have no effect on read performance, what is shown amounts to run-to-run variation - a good thing to keep in mind when trying to infer too much from closely-spaced plot lines!

Support Us!

If you like what we do and want to thank us, just buy something on Amazon. We'll get a small commission on anything you buy. Thanks!

Don't Miss These

  • 1
  • 2