I’ve dug and dug and can’t seem to find something specific.
I’ve got a dell R720xd that i just “upgraded” to from (2) different older pc systems I was using with true nas.
When transfering files to the old machines and using them for backup from my windows machine things went resonably fast, I would see over 100meg, often asmuch as 500meg transfer speeds.
Now I’m not getting even 100meg, in fact 10meg is pretty much the peak.
I have put the 710perc in IT mode. I did do this myself, but it seemed to work. This where I’m most suspicious. Not sure how to troubleshoot further.
On boot it shows the LSI firmware as expected.
I put in all enterprise hard drives
Here are the specs on the new machine:
TrueNAS-13.0-U6.3
(2)Intel(R) Xeon(R) CPU E5-2640 v2 @ 2.00GHz
64Gig DDR 3 ECC Memory
(12) SEAGATE ST4000NM0023 drives
Set up (2) storage pools with 6 drives each.
(2) 2.5 in Boot drives in mirror
(1) ATA TOSHIBA MK5055GS
(1) ATA M4-CT512M4SSD2 (Crucial)
I set this up pretty much the same way as both of my other machines and transferred the files one machine at a time, it took forever.
I’ve probably missed something stupid, I’m some what new, but I’ve been running the other 2 machines for at least 2 years, seems like longer.
I am weak on Unix, have used it on and off for a long time, but not in depth enough to say I know it.
Any thoughts would be appreciated it.
Thanks
You should add the HBA / PERC card to your hardware listing.
I guess we can check the 710’s PERC status first. Run the commands in the Shell window and paste the results back using Preformatted text (Ctrl+e), looks like </> on toolbar where you type comments.
sas2flash -list && sas3flash - list
Testing Network. We will use that to test network speed and network hardware. You can get it for your Windows machine https://iperf.fr/
It gets used in a Client and Server mode. On one machine you set it up as the server, waiting for the Client to begin the test.
Makes a TrueNAS a server for test, second puts one in Client mode, run on Widows machine in a command window. You will have to change to the directory where you unzipped iperf3 and change the IP address to your servers. Copy and paste the results from TrueNAS using Preformatted text, again.
iperf -s
iperf3.exe -c 192.168.1.100
Here is the output of the sas commands
RESULT IN SYSTEM FAILURE.
root@truenas-720[~]# sas2flash -list && sas3flash - list
LSI Corporation SAS2 Flash Utility
Version 16.00.00.00 (2013.03.01)
Copyright (c) 2008-2013 LSI Corporation. All rights reserved
Adapter Selected is a LSI SAS: SAS2308_2(D1)
Controller Number : 0
Controller : SAS2308_2(D1)
PCI Address : 00:03:00:00
SAS Address : 0000000-0-0000-0000
NVDATA Version (Default) : 14.01.00.06
NVDATA Version (Persistent) : 14.01.00.06
Firmware Product ID : 0x2214 (IT)
Firmware Version : 20.00.07.00
NVDATA Vendor : LSI
NVDATA Product ID : SAS9207-8i
BIOS Version : 07.39.02.00
UEFI BSD Version : N/A
FCODE Version : N/A
Board Name : SAS9207-8i
Board Assembly : N/A
Board Tracer Number : N/A
Finished Processing Commands Successfully.
Exiting SAS2Flash.
Avago Technologies SAS3 Flash Utility
Version 16.00.00.00 (2017.05.02)
Copyright 2008-2017 Avago Technologies. All rights res
Thanks, that helps confirm you have IT mode and lets others make comments if you need to update anything.
Iperf is giving me fits, I’ll mess with it some more later. I don’t really think it is a network issue, my old machines worked just fine and I have the new server in the same location and plugged into the same ports, literally in the case of one as I plugged it’s ethernet cable into the 720
Have you checked your drives? You should be scheduling regular SMART tests. How do you have your VDEV and pool set up? Raid-Z2? Both pools have this issue?
I have ran smart tests and I have raid-z2. I didn’t try the other pool, that is a good idea. I will try that first
With the below I’m going to look at the cable and another nic card just to be sure it isn’t something like that.
I perf was not looking good.
[ ID] Interval Transfer Bandwidth
[ 1] 0.00-3.08 sec 32.1 MBytes 87.5 Mbits/sec
root@truenas-720[~]# iperf -c 192.168.10.4 -p 5201 -t 120
Client connecting to 192.168.10.4, TCP port 5201
TCP window size: 32.8 KByte (default)
[ 1] local 192.168.10.5 port 43021 connected with 192.168.10.4 port 5201
tcp write failed: Broken pipe
shutdown failed: Socket is not connected
[ ID] Interval Transfer Bandwidth
[ 1] 0.00-3.07 sec 32.1 MBytes 87.7 Mbits/sec
root@truenas-720[~]# iperf -c 192.168.10.4 -p 5201 -t 120 -C
Client connecting to 1
@Dwdmdave couple quick questions, aside from iperf
looking to be giving you grief.
- Any
dedup
being used?
- Paste results of
for disk in /dev/sd?; do; hdparm -W $disk; done
inside of a code block (the </>
button in the reply window) please.
I will have to fire the guy who cabled this and pay the next one better.
It looks like the wall jack has gone bad or I bumped something moving the servers around. I can get Gig speeds (914 M) with a direct cable from the server to my main switch but when I use the wall jack I only get the 100meg or sometimes less. Even though it connects at a GigE.
I’ll try some transfers next and see.
Thanks for the quick responses and pointing me in the right direction.
1 Like
Just an update, after troubleshooting the cabling I found I bad port, well slow port on my cisco 3560G. Not sure why/when but I have tested it now.
Thanks for the help again.