Need? No. Want? Probably.
You can run Plex on a regular hard drive but an SSD is faster and much better. An NVMe SSD is even faster, this machine has an NVMe m.2 slot, and there’s good sales going on right now, so might as well use it.
The Plex media itself (movies etc) can live on an HDD. But Plex itself should preferably be running on an SSD.
Awesome! Thank you for your feedback!
Can you point to any deal going on now? Is that the one from ebay?
This should do the trick:
Hey everyone, I have a Samsung 970 Evo+ in the built-in M.2 slot of the HP 290-p0043w and have a gigabit network cable connection directly between it and an gigabit port on an Asus X99 Deluxe motherboard. Both systems are running Windows 10.
I noticed that when I copy a large file from the Asus to the HP, I get consistent 113 MBps (904 Mbps) transfer speeds, as I would expect from a gigabit connection. However, when I copy a large file from the HP to the Asus, I only get 69-73 MBps (552-584 Mbps) on average. This is not what I would expect, this is significantly slower than gigabit.
The Asus machine has a Samsung 860 Pro SATA SSD as its target drive, while the HP has the Samsung 970 Evo+ its target drive. I have tried multiple Cat 6 Ethernet cables to connect the two machines and get the same results with both, so it’s not the cable. I also tried copying from the boot HDD that came with the HP in place of the 970 Evo+ and get very similar results (113 MBps when writing to the HP’s HDD from the Asus, and 73 MBps when writing from the HP’s HDD to the Asus SSD). So clearly it is network limited somehow. It’s not the drives, it’s not the cable, and it’s not the M2 interface the 970 Evo+ is hooked into since I get the same results with the HDD. Same results after restarting both computers.
For all of these tests, the copy is initiated through Windows File Explorer from the Asus machine. The folders are shared using Windows’ default drive sharing feature (right click a drive → sharing → advanced sharing → network).
My guess is it has something to do with the network adapter. In device manager, if I go to Realtek PCIe GBE Family Controller, I see “Transmit Buffers” having a value of 128 (I can’t make it higher) and receive buffers of 512 (also can’t make it higher). I have Speed and Duplex set to “1.0 Gbps Full Duplex.” I’m not sure what these values mean and if they are responsible for the slower speeds when transferring from the HP to the Asus.
Considering all of this, does anybody know what is wrong here or what I can do to fix it? Why is the transfer speed from the HP to the Asus so much slower than the other way around?
Are you running any security software on one vs the other? Are you able to try using iperf to see if you get the same results?
I ran iperf as you suggested. Please see the result below:
PS C:\Users\USERNAME\Downloads\iperf-3.1.3-win64> .\iperf3.exe -c HP-HOSTNAME -p 577
Connecting to host HP-HOSTNAME, port 577
[ 4] local fe80::.........:4609 port 58675 connected to fe80::.......:f560 port 577
[ ID] Interval Transfer Bandwidth
[ 4] 0.00-1.00 sec 112 MBytes 936 Mbits/sec
[ 4] 1.00-2.00 sec 112 MBytes 936 Mbits/sec
[ 4] 2.00-3.00 sec 112 MBytes 936 Mbits/sec
[ 4] 3.00-4.00 sec 112 MBytes 936 Mbits/sec
[ 4] 4.00-5.00 sec 112 MBytes 936 Mbits/sec
[ 4] 5.00-6.00 sec 112 MBytes 935 Mbits/sec
[ 4] 6.00-7.00 sec 112 MBytes 936 Mbits/sec
[ 4] 7.00-8.00 sec 111 MBytes 935 Mbits/sec
[ 4] 8.00-9.00 sec 112 MBytes 936 Mbits/sec
[ 4] 9.00-10.00 sec 112 MBytes 935 Mbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bandwidth
[ 4] 0.00-10.00 sec 1.09 GBytes 936 Mbits/sec sender
[ 4] 0.00-10.00 sec 1.09 GBytes 936 Mbits/sec receiver
iperf Done.
PS C:\Users\USERNAME\Downloads\iperf-3.1.3-win64> .\iperf3.exe -s -p 577
-----------------------------------------------------------
Server listening on 577
-----------------------------------------------------------
Accepted connection from fe80::.......:f560, port 49676
[ 5] local fe80::.........:4609 port 577 connected to fe80::1d0:6eda:a58:f560 port 49677
[ ID] Interval Transfer Bandwidth
[ 5] 0.00-1.00 sec 71.3 MBytes 598 Mbits/sec
[ 5] 1.00-2.00 sec 71.3 MBytes 598 Mbits/sec
[ 5] 2.00-3.00 sec 72.1 MBytes 605 Mbits/sec
[ 5] 3.00-4.00 sec 72.0 MBytes 604 Mbits/sec
[ 5] 4.00-5.00 sec 72.2 MBytes 606 Mbits/sec
[ 5] 5.00-6.00 sec 72.1 MBytes 605 Mbits/sec
[ 5] 6.00-7.00 sec 72.2 MBytes 605 Mbits/sec
[ 5] 7.00-8.00 sec 72.1 MBytes 605 Mbits/sec
[ 5] 8.00-9.00 sec 71.6 MBytes 600 Mbits/sec
[ 5] 9.00-10.00 sec 71.4 MBytes 599 Mbits/sec
[ 5] 10.00-10.01 sec 1023 KBytes 591 Mbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bandwidth
[ 5] 0.00-10.01 sec 0.00 Bytes 0.00 bits/sec sender
[ 5] 0.00-10.01 sec 719 MBytes 602 Mbits/sec receiver
It seems to be the exact same. So it is some kind of network limitation. What can I do about this?
Also, no, I am not running any security software on either machines.
Can you run this command on both PCs?
netsh interface tcp show global
On the HP:
TCP Global Parameters
----------------------------------------------
Receive-Side Scaling State : enabled
Receive Window Auto-Tuning Level : normal
Add-On Congestion Control Provider : default
ECN Capability : enabled
RFC 1323 Timestamps : disabled
Initial RTO : 3000
Receive Segment Coalescing State : enabled
Non Sack Rtt Resiliency : disabled
Max SYN Retransmissions : 2
Fast Open : disabled
Fast Open Fallback : enabled
HyStart : enabled
Pacing Profile : off
On the Asus:
TCP Global Parameters
----------------------------------------------
Receive-Side Scaling State : enabled
Chimney Offload State : disabled
NetDMA State : disabled
Direct Cache Access (DCA) : disabled
Receive Window Auto-Tuning Level : normal
Add-On Congestion Control Provider : default
ECN Capability : disabled
RFC 1323 Timestamps : disabled
Initial RTO : 3000
Receive Segment Coalescing State : disabled
Non Sack Rtt Resiliency : disabled
Max SYN Retransmissions : 2
TCP Fast Open : enabled
Can you try running this command and do some testing. If you don’t see any improvement run the 2nd command to restore the current config.
netsh int tcp set global autotuninglevel=disabled
netsh int tcp set global autotuninglevel=normal
Unfortunately I did not see an improvement after disabling the autotuning and re-running iperf (results were exactly the same), although I did not restart either machine after running (but I did restart the shell).
My assumption is that this is a hardware limitation. Can’t other people here with HP 290-p0043w machines verify that they have the exact same issue?
Unfortunately I don’t run windows and I’m assuming most the the users in this forum don’t as well. The NIC performs at full capacity in Linux. You may want to see if there are some new drivers available.
Thanks, I installed the latest drivers from HPs website (Realtek NIC Driver (Windows 10 v1709)) but they didn’t improve anything. I tried iperf3 again with multiple target machines (other laptops hooked up with the ethernet cable) and was still consistently getting 607 Mbps. I will try running Linux next and see if that improves it. If so, I’m wondering what feature in Windows is limiting it.
This is iperf between my 290 and my NAS
[ ID] Interval Transfer Bitrate Retr Cwnd
[ 5] 0.00-1.00 sec 112 MBytes 939 Mbits/sec 0 274 KBytes
[ 5] 1.00-2.00 sec 112 MBytes 936 Mbits/sec 0 274 KBytes
[ 5] 2.00-3.00 sec 110 MBytes 926 Mbits/sec 0 287 KBytes
[ 5] 3.00-4.00 sec 111 MBytes 932 Mbits/sec 0 287 KBytes
[ 5] 4.00-5.00 sec 111 MBytes 929 Mbits/sec 0 301 KBytes
[ 5] 5.00-6.00 sec 111 MBytes 933 Mbits/sec 0 301 KBytes
[ 5] 6.00-7.00 sec 110 MBytes 922 Mbits/sec 0 301 KBytes
[ 5] 7.00-8.00 sec 112 MBytes 940 Mbits/sec 0 301 KBytes
[ 5] 8.00-9.00 sec 110 MBytes 920 Mbits/sec 0 301 KBytes
[ 5] 9.00-10.00 sec 110 MBytes 926 Mbits/sec 0 301 KBytes
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.00 sec 1.08 GBytes 931 Mbits/sec 0 sender
[ 5] 0.00-10.00 sec 1.08 GBytes 929 Mbits/sec receiver
[ ID] Interval Transfer Bitrate Retr Cwnd
[ 5] 0.00-1.00 sec 85.3 MBytes 715 Mbits/sec 25 249 KBytes
[ 5] 1.00-2.00 sec 110 MBytes 920 Mbits/sec 28 319 KBytes
[ 5] 2.00-3.00 sec 110 MBytes 924 Mbits/sec 13 423 KBytes
[ 5] 3.00-4.00 sec 112 MBytes 938 Mbits/sec 27 248 KBytes
[ 5] 4.00-5.00 sec 111 MBytes 931 Mbits/sec 0 586 KBytes
[ 5] 5.00-6.00 sec 111 MBytes 928 Mbits/sec 27 366 KBytes
[ 5] 6.00-7.00 sec 110 MBytes 924 Mbits/sec 13 418 KBytes
[ 5] 7.00-8.00 sec 112 MBytes 937 Mbits/sec 14 448 KBytes
[ 5] 8.00-9.00 sec 110 MBytes 926 Mbits/sec 36 351 KBytes
[ 5] 9.00-10.00 sec 111 MBytes 928 Mbits/sec 0 637 KBytes
I’ve installed Ubuntu 20.04, and latest Plex, and I have Plex pass, but HW transcoding is not working. Have narrowed it down to this issue - PlexMediaServer install: Intel i915 Hardware: Not found ; any idea why it wouldn’t be finding my processor gpu?
What’s your specific hardware?
HP 290-p0043w, with an nvme SSD.
What processor specifically? I am aware of the thread we are in.
Intel Celeron G4900 3.10GHz
Have you run lscpu? to see what it is reading as?