Gbps of GBps? There is a substantial difference.From my 10GB Qnap(Raid 5) to my PC with an Intel 10GB card(Normal ssd).
I've never hit the 1GB transfer speed.
Got any tips?
Gbps of GBps? There is a substantial difference.From my 10GB Qnap(Raid 5) to my PC with an Intel 10GB card(Normal ssd).
I've never hit the 1GB transfer speed.
Got any tips?
Exactly this - even if your 1150Mb? connection is being "limited" by a gig port, are you really missing out on that ~150Mbps? Surely it's better to have some bandwidth "spare" for other devices (e.g. those on wifi or other cabled devices), rather than saturating the whole of your connection with a single download
From my 10GB Qnap(Raid 5) to my PC with an Intel 10GB card(Normal ssd).
I've never hit the 1GB transfer speed.
Got any tips?
Gbps of GBps? There is a substantial difference.
With 80-100GB game downloads common place and even patches hitting silly levels some times, good old Steam will happily saturate your bandwidth, other users be damned .
I think like me he might have read your original post as you wouldn't get 1 gigabit when you meant gigabyte, you might be limited by the low end CPUs in the NAS devices or your transfer has blown out of the cache of your SSD, I see a bursty near 2 Gigabyte on transfers but it drops to about 1.4Gigabyte quite quickly.
If you use Crystal disk mark on y
our NAS share you can see what its burst rate is, you will probably see ~1000 Megabyte unless your SSDs are particularly slow.
Of course Raid 5 doesn't offer the performance benefits of say raid 0 or 10 so might just be that.
Example of 10Gb Crystal diskmark on my NAS share, this is two slow 4TB Samsung QVO drives in raid 0 Normal SATA SSDs like this top out at 550MB.
If you wanted to confirm your network has the performance or if it is the drives you can do some iperf tests between NAS and a client to see what your network performance is without drives.
If I use crystelmark I only get (usingSEQ1M 5X 8Gib) 627 MB read and 922 MB write.
My QNAP TS-932 only has a Alpine AL324 ARM® Cortex-A57 quad-core 1.7GHz processor.
So it could be that?
I use it only for steam games.
Would it be faster going to Rain 0
Strange I would have expected reverse for write to be slower with Raid5, Raid 0 offers zero protection, so not ideal for NAS usage case, I only did that as its a spare scratch area, you still have decent performance if it is just steam games you won't really get much performance uplift in use anyway, games are lots of little files generally so would be reliant on random performance a lot more.
This is my iperf3
0.00-1.00 sec 432 MBytes 3.62 Gbits/sec
[ 4] 1.00-2.00 sec 397 MBytes 3.33 Gbits/sec
[ 4] 2.00-3.00 sec 398 MBytes 3.34 Gbits/sec
[ 4] 3.00-4.00 sec 382 MBytes 3.21 Gbits/sec
[ 4] 4.00-5.00 sec 403 MBytes 3.38 Gbits/sec
[ 4] 5.00-6.00 sec 431 MBytes 3.62 Gbits/sec
[ 4] 6.00-7.00 sec 465 MBytes 3.90 Gbits/sec
[ 4] 7.00-8.00 sec 450 MBytes 3.78 Gbits/sec
[ 4] 8.00-9.00 sec 444 MBytes 3.73 Gbits/sec
[ 4] 9.00-10.00 sec 436 MBytes 3.66 Gbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bandwidth
[ 4] 0.00-10.00 sec 4.14 GBytes 3.56 Gbits/sec sender
[ 4] 0.00-10.00 sec 4.14 GBytes 3.56 Gbits/sec receiver
I have no idea what it means
Update in reverse
Reverse mode, remote host 169.254.5.245 is sending
[ 4] local 169.254.11.122 port 51929 connected to 169.254.5.245 port 5201
[ ID] Interval Transfer Bandwidth
[ 4] 0.00-1.00 sec 699 MBytes 5.86 Gbits/sec
[ 4] 1.00-2.00 sec 700 MBytes 5.87 Gbits/sec
[ 4] 2.00-3.00 sec 704 MBytes 5.90 Gbits/sec
[ 4] 3.00-4.00 sec 702 MBytes 5.89 Gbits/sec
[ 4] 4.00-5.00 sec 701 MBytes 5.88 Gbits/sec
[ 4] 5.00-6.00 sec 703 MBytes 5.90 Gbits/sec
[ 4] 6.00-7.00 sec 704 MBytes 5.91 Gbits/sec
[ 4] 7.00-8.00 sec 703 MBytes 5.90 Gbits/sec
[ 4] 8.00-9.00 sec 703 MBytes 5.90 Gbits/sec
[ 4] 9.00-10.00 sec 711 MBytes 5.96 Gbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bandwidth Retr
[ 4] 0.00-10.00 sec 6.87 GBytes 5.90 Gbits/sec 0 sender
[ 4] 0.00-10.00 sec 6.86 GBytes 5.90 Gbits/sec receiver
Connecting to host 172.16.72.11, port 5201
[ 5] local 172.16.72.5 port 38764 connected to 172.16.72.11 port 5201
[ ID] Interval Transfer Bitrate Retr Cwnd
[ 5] 0.00-1.00 sec 1.12 GBytes 9.58 Gbits/sec 0 778 KBytes
[ 5] 1.00-2.00 sec 1.15 GBytes 9.89 Gbits/sec 0 778 KBytes
[ 5] 2.00-3.00 sec 1.15 GBytes 9.87 Gbits/sec 0 865 KBytes
[ 5] 3.00-4.00 sec 1.15 GBytes 9.90 Gbits/sec 0 909 KBytes
[ 5] 4.00-5.00 sec 1.15 GBytes 9.88 Gbits/sec 0 961 KBytes
[ 5] 5.00-6.00 sec 1.15 GBytes 9.85 Gbits/sec 0 961 KBytes
[ 5] 6.00-7.00 sec 1.15 GBytes 9.89 Gbits/sec 0 961 KBytes
[ 5] 7.00-8.00 sec 1.15 GBytes 9.88 Gbits/sec 0 961 KBytes
[ 5] 8.00-9.00 sec 1.15 GBytes 9.90 Gbits/sec 0 961 KBytes
[ 5] 9.00-10.00 sec 1.15 GBytes 9.89 Gbits/sec 0 961 KBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.00 sec 11.5 GBytes 9.85 Gbits/sec 0 sender
[ 5] 0.00-10.00 sec 11.5 GBytes 9.84 Gbits/sec receiver
It means your network isn't running at 10 Gbps for whatever reason. Check your cables etc. This is my NAS to one of my ESXi hosts going over a couple of switches (Mikrotik and UniFi)
Code:Connecting to host 172.16.72.11, port 5201 [ 5] local 172.16.72.5 port 38764 connected to 172.16.72.11 port 5201 [ ID] Interval Transfer Bitrate Retr Cwnd [ 5] 0.00-1.00 sec 1.12 GBytes 9.58 Gbits/sec 0 778 KBytes [ 5] 1.00-2.00 sec 1.15 GBytes 9.89 Gbits/sec 0 778 KBytes [ 5] 2.00-3.00 sec 1.15 GBytes 9.87 Gbits/sec 0 865 KBytes [ 5] 3.00-4.00 sec 1.15 GBytes 9.90 Gbits/sec 0 909 KBytes [ 5] 4.00-5.00 sec 1.15 GBytes 9.88 Gbits/sec 0 961 KBytes [ 5] 5.00-6.00 sec 1.15 GBytes 9.85 Gbits/sec 0 961 KBytes [ 5] 6.00-7.00 sec 1.15 GBytes 9.89 Gbits/sec 0 961 KBytes [ 5] 7.00-8.00 sec 1.15 GBytes 9.88 Gbits/sec 0 961 KBytes [ 5] 8.00-9.00 sec 1.15 GBytes 9.90 Gbits/sec 0 961 KBytes [ 5] 9.00-10.00 sec 1.15 GBytes 9.89 Gbits/sec 0 961 KBytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate Retr [ 5] 0.00-10.00 sec 11.5 GBytes 9.85 Gbits/sec 0 sender [ 5] 0.00-10.00 sec 11.5 GBytes 9.84 Gbits/sec receiver
I'd be checking your cables. But something isn't right if it's meant to be 10 Gbps.God knows what I have to check.
169.254.11.122 port 51929 connected to 169.254.5.245
This is on my intel 10GB nic
I'd be checking your cables. But something isn't right if it's meant to be 10 Gbps.
How exactly is your IP addressing set up? These are APIPA ranges.
@Avalon Aren't SolarFlare and Mellanox the go-to 10Gb NIC for 'our sort' of hobbyist these days? Decent driver support and cheap 2nd hand, certainly for SolarFlares. The HotLava cards look phenomenal as well, but definitely on the pricier side with no eBay bargains to be had.
This is my iperf3
[...snip]
I think it could be my PIC-E slot on my motherboard being slow.
First of I would set them both up on a /30 network if it's just point to point. So 172.16.0.1 and 172.16.0.2 with a 255.255.255.252 netmask so rule out any APIPA weirdness.
PC:
172.16.0.1/30
NAS:
172.16.0.2/30
No gateway. Then try it. What actual NICs are you using in both the PC and NAS? Are they both showing 10000 Mbps full duplex?
What OS is it on the PC and are the drivers up to date?
This is my QNAP:
What's the CPU on the NAS doing when you're testing? If you're pegging something at 100% then start looking there.
Do you get a graph of all 4 CPU cores? 21% is close to 25% and I'm wondering if whatever you're doing is single threaded and taking a single core up to 100%. The speeds posted on the QNAP page for the NAS are a bit weird in that they are quoted as being achieved by two 10Gb connections.
I agree, however i'm only providing my router with 95% of total speed that can be dispersed and then saturated amongst devices, so i'm losing 5% of bandwith on nothing other than the limitation of a port which seems absurd to meExactly this - even if your 1150Mb? connection is being "limited" by a gig port, are you really missing out on that ~150Mbps? Surely it's better to have some bandwidth "spare" for other devices (e.g. those on wifi or other cabled devices), rather than saturating the whole of your connection with a single download
I agree, however i'm only providing my router with 95% of total speed that can be dispersed and then saturated amongst devices, so i'm losing 5% of bandwith on nothing other than the limitation of a port which seems absurd to me
So the supplied router doesn't have a port fast enough for the incoming service? Surely that's an issue for the ISP to deal with?