Search results

I finally tackled the side panel having actually bought the 4.5" hole saw required to create the cut outs for the fans. Not the easiest job but they seem to have come out ok. There are a couple of marks to the black finish, but nothing too obvious. Fans fitted with silverstone filters New...

Very useful info there, thank you. I actually managed to source the second solid side panel direct from corsair this week. I will be modifying it to fit a pair of 120mm fans to provide the airflow across the expansion cards. Good as that bracket would be, it would still benefit from some...

I bought some Arctic P14's to replace the old scythe kama flow 120mms as the case has provision for the same number of 140mm fans as 120mm so it makes sense to use the larger diameter. I swapped the front intakes out as well as the top exhaust. They seem to shift a hefty quantity of air at...

I originally wanted a server case like a Norco but backplane failures are what put me off more than cost. The drive cages for the 750D seem to mount in quite well on the right side as they anchor both at the top and bottom. The ones on the left don't have any anchor at the top so there is some...

The Corsair Obsidian 750D can fit 18x 3.5 drives with the additional cages leaving 4x 2.5" sleds and 3x 5.25" bays available. Fitting the additional drive bays beyond 12 drives does depend on your motherboard and expansion card configuration. I went this route to avoid using backplanes after...

On to the case swap. The 750D is quite a bit bigger than the CM690. I put a new 8TB drive in already as that is going to be used as an rsync disk for certain files from the main array. Deconstructing the 690 was simple enough but the last 6 years in the loft haven't been kind. That green cloth...

Raid controller alarm went off last month. Looking at it, a disk had possibly died as it had simply disappeared. I ordered two 2TB ultrastars to replace the dead drive and provide a hot spare. Can't moan too much as it's been running pretty much 24/7 for nearly 6 years I discovered when...

Bought some new fans for the juniper switch to try and quieten it down a bit without triggering a fan failure warning. 2x 40x40x28mm 12,500rpm San Ace 109P0412J3013 fans instead of 18,000rpm. Idle fan voltage is 4.5V so something like a noctua that maxes out at 5000rpm would run too slow at...

Have you tried covering the smbus pins on the pcie connector with tape? (Like this) May or may not work, but certainly worth trying.

That would be a dell OEM version of a SFN-8522. Precisely which version is very hard to determine.

I bought some OM3 fibres from FS along with some LC-LC links for the wall boxes I got from RS a few months back. Wall boxes should be pretty resilient as the fibres will enter at the base of the boxes keeping the connection virtually flush with the wall to avoid breaking them. Since I now have...

Just pushed the 1903 update on my threadripper machine and iperf performance is now fixed on this machine. Across 5 instances I saw just shy of 40Gbit/s and a single instance gave just over 16Gbit/s. I'll look into doing the X79 system tomorrow and see if it also sees the same improvement.

In respect of the pcie link width issue I spotted, I've now fixed it by swapping the NIC and audio interface around as both were in 8x slots. GetNetAdapterHardwareInfo reports the correct link width and speed now but it didn't make 1 iota of difference to the throughput though. Something I've...

What baffles me is that windows itself isn't necessarily the issue as I've seen plenty of other people have no issues achieving near 10 gigabits/s transfers using windows 10 with similar or even older hardware. The performance I'm seeing on my threadripper system isn't actually too bad but it's...

Run the same test on a live boot of fedora 30 and all is well. Definitely seems to be a windows issue.

Doing a quick iperf test on the local machine itself to the loopback address sees an average of 4.5Gbits/s. Setting the TCP window size to 2048000 results some heavy variability but the best I've seen is 8.9GBits/s and the average is around 6.5. This suggests to me that it's a windows issue...

1.9.230.0 downloaded from the intel site about a month or so ago. (driver date suggests 27/11/2018) There was also a firmware update which I did on both cards, but I can't remember the version on that one. NTttcp performance: PS I:\Downloads\NTtcp> ./ntttcp.exe -s -m 8,*,192.168.0.160 -l 128k...

Just ran some basic testing on the 3 machines that are going to be linked together via 10Gbe and found some slightly strange performance issues. This is the kit that is linked together: Switch - Juniper EX3300 with juniper SR transceivers no vlans or L3 features enabled 1500 MTU PC1 - Windows...

Finally picked up a second OM3 fibre so I can do a test run at 10Gb. Performance in one direction looks pretty good, but not so good in the other direction. Running my threadripper workstation with the intel x710 as the iperf server net 7Gbps with the 9600k/solarflare NAS as the client. The...

For anyone else who isn't sure on solarflare cards and finds this thread, they seem to be a good choice. Works out of the box on linux, windows drivers and mac drivers available too. It's been happy with intel, avago, cisco and juniper SFP's too. I'm kicking myself for missing out on 3x SFN8522...