Personal computing discussed

Moderators: Flying Fox, morphine

 
Welch
Grand Gerbil Poohbah
Topic Author
Posts: 3254
Joined: Thu Nov 04, 2004 5:45 pm
Location: Alaska
Contact:

1700 Benchmark Requests Anyone?

Thu Apr 13, 2017 2:17 am

I'll have a limited amount of time in my office with a 1700, 16gb of 3200 GSkill Flare X and an Asus X370 Pro. I plan to take the opportunity to test a few things, perhaps power, that haven't been covered by TR or other sites yet, maybe because of the niche of their nature. Does anyone have a request for benching or testing that hasn't been covered yet that you are curious about?
"I think there is a world market for maybe five computers."
Thomas Watson, chairman of IBM, 1943

i5-2500K|Asus P67 Sabertooth|16GB Corsair 1600|MSI 7850 2GB|500gb 840 EVO|Corsair 400R|ET750w PSU|Corsair M95 / K90 / Vengeance 1300
 
Igor_Kavinski
Gerbil XP
Posts: 399
Joined: Fri Dec 22, 2006 2:34 am

Re: 1700 Benchmark Requests Anyone?

Thu Apr 13, 2017 2:43 am

Some database benchmarks would be great, especially comparing SQL SERVER and PostgreSQL on Ryzen.
 
Welch
Grand Gerbil Poohbah
Topic Author
Posts: 3254
Joined: Thu Nov 04, 2004 5:45 pm
Location: Alaska
Contact:

Re: 1700 Benchmark Requests Anyone?

Thu Apr 13, 2017 3:07 am

Igor_Kavinski wrote:
Some database benchmarks would be great, especially comparing SQL SERVER and PostgreSQL on Ryzen.


I may be able to oblige, I need to see about these being used for SMB servers anyhow, lots of SQL DB apps running across different client sites. Just a shame that no boards are really supporting ECC even though the chips do. You have any testing methods/programs or hardware comparisons you'd like to see it against? I've got varying Xeon based systems at my relative disposal to compare. I'll have to check which exact version but I believe I've got a 1230v3 and 1245v3 sitting in a few machines. Perhaps not 100% indentical matches but will provide some baseline for comparison.

Server or Consumer OS?
"I think there is a world market for maybe five computers."
Thomas Watson, chairman of IBM, 1943

i5-2500K|Asus P67 Sabertooth|16GB Corsair 1600|MSI 7850 2GB|500gb 840 EVO|Corsair 400R|ET750w PSU|Corsair M95 / K90 / Vengeance 1300
 
Igor_Kavinski
Gerbil XP
Posts: 399
Joined: Fri Dec 22, 2006 2:34 am

Re: 1700 Benchmark Requests Anyone?

Tue May 16, 2017 4:29 am

Welch wrote:
Server or Consumer OS?


Damn. So sorry, man. I just logged in today and saw this. It would be cool if you can test Ryzen 7, Ryzen 5 and the Xeons using the free tool available here:

http://www.toadworld.com/products/benchmark-factory

It will be fun to see these chips battle it out in MSSQL Server, PostGreSQL and MySQL.
 
Wirko
Gerbil First Class
Posts: 131
Joined: Fri Jun 15, 2007 4:38 am
Location: Central Europe

Re: 1700 Benchmark Requests Anyone?

Tue May 16, 2017 8:03 am

Some database vendors are not happy if you publish benchmark results.

http://sqlmag.com/database-performance-tuning/truth-about-tpc
 
chuckula
Gold subscriber
Graphmaster Gerbil
Posts: 1421
Joined: Wed Jan 23, 2008 9:18 pm
Location: Probably where I don't belong.

Re: 1700 Benchmark Requests Anyone?

Tue May 16, 2017 8:08 am

If you can put Linux on the system then I recommend the Phoronix Test Suite for automated benchmarking: https://www.phoronix-test-suite.com/

There are a whole bunch of benchmarks in the suite that you can run individually to test a wide range of applications.
4770K @ 4.7 GHz; 32GB DDR3-2133; GTX-1080; 512GB 840 Pro (2x); Fractal Define XL-R2; NZXT Kraken-X60
--Many thanks to the TR Forum for advice in getting it built.
 
southrncomfortjm
Silver subscriber
Gerbil Elite
Posts: 513
Joined: Mon Nov 12, 2012 7:57 pm

Re: 1700 Benchmark Requests Anyone?

Tue May 16, 2017 8:57 am

Crysis IMO.
Gaming: i5-3570k/Z77/212 Evo/Corsair 500R/16GB 1600 CL8/RX 480 8GB/840 250gb, EVO 500gb, SG 3tb/Tachyon 650w/Win10

HTPC: i3 3225/H77/8gb g.skill 1.25v/1+2TB HDD/Asus BR/Silverstone GD05B/Antec 380w/Win10
 
Kretschmer
Gerbil Team Leader
Posts: 294
Joined: Sun Oct 19, 2008 10:36 am

Re: 1700 Benchmark Requests Anyone?

Tue May 16, 2017 11:00 am

southrncomfortjm wrote:
Crysis IMO.

"Johnson! Are you playing video games in the office?"

"No sir, I'm benchmarking an older video game to fulfill a meme for a technology forum that I'm part of."
 
Takeshi7
Gerbil
Posts: 73
Joined: Tue Nov 21, 2006 12:50 am

Re: 1700 Benchmark Requests Anyone?

Tue May 16, 2017 11:13 am

Please run distributed.net OGR-28 on all threads and give me an estimation of how many nodes/s 16 threads can do.
 
southrncomfortjm
Silver subscriber
Gerbil Elite
Posts: 513
Joined: Mon Nov 12, 2012 7:57 pm

Re: 1700 Benchmark Requests Anyone?

Wed May 17, 2017 8:41 am

Kretschmer wrote:
southrncomfortjm wrote:
Crysis IMO.

"Johnson! Are you playing video games in the office?"

"No sir, I'm benchmarking an older video game to fulfill a meme for a technology forum that I'm part of."


+1
Gaming: i5-3570k/Z77/212 Evo/Corsair 500R/16GB 1600 CL8/RX 480 8GB/840 250gb, EVO 500gb, SG 3tb/Tachyon 650w/Win10

HTPC: i3 3225/H77/8gb g.skill 1.25v/1+2TB HDD/Asus BR/Silverstone GD05B/Antec 380w/Win10
 
Doctor Venture
Gerbil
Posts: 64
Joined: Thu Feb 19, 2015 2:23 am

Re: 1700 Benchmark Requests Anyone?

Thu May 18, 2017 3:47 pm

This is possibly too late, but I'd personally love to see how it would handle two concurrent Juniper vMX "instances" (or 4 vQFX-10K instances) either running in Linux using KVM, or in ESXi. I've got instances in quotes, since Juniper split both vMX and vQFX into two separate VMs that you need to interconnect. A routing engine VM, and a packet forwarding engine VM. I wish it could be three vMX instances, but the minimum requirements for the lab setup is 4 "vCPUs" (h/w threads) and 6GB RAM per-instance, so that 16GB RAM will prevent that (same with using Cisco XRv 9K image. that needs 16GB per-instance). vQFX is a little more forgiving, just needing 3 h/w threads and 3GB RAM per instance, but even when I've increased the resource allocations, it still takes about 20-30 minutes to fully load up.

I've got an old i7-2600K with 32GB RAM, but those 8 h/w threads are the limiting factor, when trying to test out some EVPN w/VXLAN setups I'm wanting to try. The old vMX engineering pre-releases were a single VM that could run with just 1GB RAM, and 1 h/w thread, but it's missing a lot of functionality. Works fine as purely L3 device, though.
 
whm1974
Maximum Gerbil
Posts: 4633
Joined: Fri Dec 05, 2014 5:29 am

Re: 1700 Benchmark Requests Anyone?

Thu May 18, 2017 5:17 pm

Doctor Venture wrote:
This is possibly too late, but I'd personally love to see how it would handle two concurrent Juniper vMX "instances" (or 4 vQFX-10K instances) either running in Linux using KVM, or in ESXi. I've got instances in quotes, since Juniper split both vMX and vQFX into two separate VMs that you need to interconnect. A routing engine VM, and a packet forwarding engine VM. I wish it could be three vMX instances, but the minimum requirements for the lab setup is 4 "vCPUs" (h/w threads) and 6GB RAM per-instance, so that 16GB RAM will prevent that (same with using Cisco XRv 9K image. that needs 16GB per-instance). vQFX is a little more forgiving, just needing 3 h/w threads and 3GB RAM per instance, but even when I've increased the resource allocations, it still takes about 20-30 minutes to fully load up.

I've got an old i7-2600K with 32GB RAM, but those 8 h/w threads are the limiting factor, when trying to test out some EVPN w/VXLAN setups I'm wanting to try. The old vMX engineering pre-releases were a single VM that could run with just 1GB RAM, and 1 h/w thread, but it's missing a lot of functionality. Works fine as purely L3 device, though.

That sounds like something that would greatly benefit from AMD's new 16c/32t "Threadripper" CPU with lots of memory.
 
Doctor Venture
Gerbil
Posts: 64
Joined: Thu Feb 19, 2015 2:23 am

Re: 1700 Benchmark Requests Anyone?

Thu May 18, 2017 5:31 pm

whm1974 wrote:
That sounds like something that would greatly benefit from AMD's new 16c/32t "Threadripper" CPU with lots of memory.


I've been thinking the same thing about Threadripper, and possibly a 2P Epyc setup. I'm just curious to see what kind of behavior happens with a stock Ryzen, before dropping the money on either setup. I fully expect Threadripper (gawd, I *hate* the name!) to cost a little bit less than the i7-6950X, and the Xeon's they were positioning Epyc against cost ~$4K each, so I don't expect AMD to undercut Intel too much. Either way, I'd have to earmark some money, to I could get the best bang for my buck, since I run a LOT of virtual machines like that, in different network simulations.

Once Epyc comes gets in the reviewers hands, and we start seeing some heavy workloads on it, is when I'll decide whether to drop a ton of money on a 2P Epyc server, a loaded out Threadripper workstation, or just go Intel on my workstation/gaming PC, and rent some server time somewhere (as long as they let me have bare-metal access).

Who is online

Users browsing this forum: Bing [Bot] and 1 guest