Realtek RTL8125B 2.5Gbe NIC Slow Throughput

[shauno100]

So a couple of things here...

From an IOPS perspective, you have a fairly high delta between the min/max, and generally low performance. While your avg is fine, it does appear that the backing system or zpool (layout) is not quite able to keep up with the speeds posted as average. You can see that in a relatively large standard deviation in IOPS.

I ran the same test on my, admittedly high end system, with 8-way mirror of 10TB HDDs.



While my standard deviation in both bw and iops is higher than yours, the performance is far greater.
For fun, here's what 2 mirrors of 960GB Optane looks like:

Which, funnily enough looks slower than my HDDs above, but in reality outside of this specific benchmark, they aren't! which kinda proves my point here- does any of this really matter?

I provide this comparison as I'm trying to give you a benchmark to compare against. I have no idea what your workload is nor what you are trying to do. What metric matters to you, IOPS or bandwidth?

From a disk performance perspective, super back of the napkin math, you are getting about 1/4 of the maximum performance of your pools worth of maximum network bandwidth. That ratio is fine, especially if IOPs don't really matter. Considering you have a cheap Realtek NIC and a relatively slow back-end pool, the system seems to be pretty much in homeostasis.

Thanks for the info, in all honesty getting more bandwidth on the network is my main priority. I mainly store movies and video files on the NAS and stream to my devices at home, so no real high IOPS situations.

So to confirm, would installing a well supported (driver wise) NIC likely give me better performance, or would a complete hardware upgrade including a better NIC be required due to my average fio results?

From the replies here it would seem that my Realtek 2.5Gbe USB adaptor and/or the RTL8125B NIC in my TrueNAS Scale machine are at fault (poor drivers) and my cheapest option for potentially better 2.5Gbe speeds is to buy a new NIC for the TRUENAS Scale box.

 

[NickF]

So to confirm, would installing a well supported (driver wise) NIC likely give me better performance, or would a complete hardware upgrade including a better NIC be required due to my average fio results?

I don't think so, no.

From the replies here it would seem that my Realtek 2.5Gbe USB adaptor and/or the RTL8125B NIC in my TrueNAS Scale machine are at fault (poor drivers) and my cheapest option for potentially better 2.5Gbe speeds is to buy a new NIC for the TRUENAS Scale box.

Its fine for what you are doing with the system that you have from a performance standpoint. It is, however, a bottleneck to systems larger than yours. It is also potentially unreliable and unstable. But for your workload it's probably fine, worst case scenario Plex stops serving media and you move the ethernet cord back your gigabit realtek port...or buy an Intel one.

 

[Davvo]

Your NIC is performing outstandingly well for a Realtek NIC, which are known for being a big no for TN.
Your pool performance doesn't justify an upgrade of your NIC if we look at the performances alone (and leave aside it being Realtek) since it won't cap your 2.5Gbps bandwith.

 

[shauno100]

Thanks for the replies all, i will stick with my current setup, when i mentioned streaming i do not use Plex i mainly just stream over Samba shares to my 4K TV over WiFi using Kodi. I do have personal data in separate shares backed up to BackBlaze B2 also. The original question was just more related to the performance between my TrueNAS SCALE system and my desktop PC with the new 2.5Gbe USB NIC on desktop and 2.5Gbe NIC installed in TrueNAS SCALE system.

In conclusion when compared to my original 1Gbe NIC in the TrueNAS SCALE system i am at least now seeing an approx. 40% increase in data transfer rates to my PC so i'm happy with that (For the time being ).

 

[shauno100]

Just providing an update. I ended upgrading my hardware to an Intel 12th gen platform, as mentioned i was due for an upgrade and was planning to anyway. I am now getting the full 2.5Gbe bandwidth according to iperf with the builtin 2.5Gbe Realtek RTL8125BG chip using the manually installed R8125 driver from Realtek.

Code:

iperf3 -c 192.168.225.250
Connecting to host 192.168.225.250, port 5201
[  4] local 192.168.225.55 port 60609 connected to 192.168.225.250 port 5201
[ ID] Interval           Transfer     Bandwidth
[  4]   0.00-1.00   sec   282 MBytes  2.36 Gbits/sec
[  4]   1.00-2.00   sec   280 MBytes  2.35 Gbits/sec
[  4]   2.00-3.00   sec   282 MBytes  2.37 Gbits/sec
[  4]   3.00-4.00   sec   278 MBytes  2.33 Gbits/sec
[  4]   4.00-5.00   sec   280 MBytes  2.35 Gbits/sec
[  4]   5.00-6.00   sec   283 MBytes  2.37 Gbits/sec
[  4]   6.00-7.00   sec   283 MBytes  2.37 Gbits/sec
[  4]   7.00-8.00   sec   283 MBytes  2.37 Gbits/sec
[  4]   8.00-9.00   sec   283 MBytes  2.37 Gbits/sec
[  4]   9.00-10.00  sec   283 MBytes  2.37 Gbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bandwidth
[  4]   0.00-10.00  sec  2.75 GBytes  2.36 Gbits/sec                  sender
[  4]   0.00-10.00  sec  2.75 GBytes  2.36 Gbits/sec                  receiver


iperf Done.

 

[NickF]

Neat. Good job.

 

[das1996]

Just providing an update. I ended upgrading my hardware to an Intel 12th gen platform, as mentioned i was due for an upgrade and was planning to anyway. I am now getting the full 2.5Gbe bandwidth according to iperf with the builtin 2.5Gbe Realtek RTL8125BG chip using the manually installed R8125 driver from Realtek.

Are the above results from scale or core?

I'm seeing great speeds (2.37gbps in either direction) with scale, but slower (~2 gbps) with core in iperf3 testing between a windows box and the nas (both using rtl8125).