WEBVTT 00:00:01.000 --> 00:00:07.520 okay so we built seven Gamers one CPU a 00:00:04.720 --> 00:00:11.799 $30,000 computer running unraid as an operating system and using it and some 00:00:09.840 --> 00:00:18.880 really cool open- Source virtualization technology to run seven discret gaming 00:00:16.000 --> 00:00:23.800 virtual machines at once all fully capable of like high performance gaming 00:00:21.519 --> 00:00:28.480 so that was cool $30,000 computer two thumbs up very awesome 10 out of 10 IGN 00:00:26.080 --> 00:00:32.719 Etc then what we did was we showed it off at CES okay so we got that out of 00:00:31.199 --> 00:00:37.000 the way the world was able to see it in person then after that we brought it 00:00:34.680 --> 00:00:41.520 back to the office converted our entire conference room here into a land Center 00:00:39.520 --> 00:00:46.000 and had an inter office gaming competition complete with tan being 00:00:44.160 --> 00:00:49.079 terrible at video games yes the very worst one here except he did kill me 00:00:47.440 --> 00:00:55.000 once and you can check that video out here so you might be asking yourself why 00:00:52.199 --> 00:01:00.280 is lion is still milking this damn thing what could possibly be left to do and 00:00:57.600 --> 00:01:05.500 the answer is of course we're going to overclock 00:01:09.799 --> 00:01:16.200 it Intel brings ddr4 to the mainstream 00:01:13.040 --> 00:01:18.880 with their core i7 6700 K and core i5 00:01:16.200 --> 00:01:22.600 6600k processors check out the link in the video description to learn more so 00:01:21.119 --> 00:01:27.400 the first step anytime you do any Performance Tuning is to get a baseline 00:01:25.799 --> 00:01:32.399 measurement because if you don't then you have no idea if the dials you're 00:01:29.200 --> 00:01:33.680 turning are doing anything at all so I'm 00:01:32.399 --> 00:01:38.799 going to introduce you guys to the benchmarks that we're going to be running cinebench R15 is going to tell 00:01:37.079 --> 00:01:42.119 us what we need to know about CPU performance we are going to be using 00:01:40.600 --> 00:01:47.520 Crystal dis Mark to tell us what we need to know about our SSD array performance 00:01:45.240 --> 00:01:51.960 IID to 64 cash and memory Benchmark is going to be interesting especially once 00:01:50.280 --> 00:01:56.320 we run it on all machines at once more on that later and we're going to be 00:01:53.320 --> 00:01:58.799 using fire strike extreme to see how our 00:01:56.320 --> 00:02:02.880 gpus are doing some of the stuff that's open is just tempor monitoring and stuff 00:02:01.000 --> 00:02:07.600 like that and finally we're going to be having a look using our handy dandy wall 00:02:05.479 --> 00:02:12.160 power meter dudad here at what kind of power consumption we see when we're 00:02:09.599 --> 00:02:17.760 hitting the whole system at once but let's start with a single VM Baseline 00:02:15.560 --> 00:02:22.560 with all the other ones sitting idle and I'll show you guys on screen hopefully 00:02:19.959 --> 00:02:28.000 right now how I plan to go through this entire test suite and show you guys the 00:02:25.720 --> 00:02:33.000 scores so here we go we're getting a cin bench score of around 600 we're getting 00:02:30.319 --> 00:02:38.879 Crystal dis Mark scores in the uh area of sort of you know two uh gigabytes per 00:02:36.280 --> 00:02:44.640 second reads and around 400 megabytes per second rights to our array our 00:02:41.640 --> 00:02:47.280 memory scores we're seeing about 5 GB 00:02:44.640 --> 00:02:53.560 per second so on average reads and wrs to our quad Channel ddr4 memory and our 00:02:50.280 --> 00:02:56.640 3D Mark fir strike extreme score is 6148 00:02:53.560 --> 00:02:58.640 so the next test and this one I will 00:02:56.640 --> 00:03:04.959 need some helping hands for is going to be to hit all 7 VMS at once for our 00:03:02.879 --> 00:03:09.680 Baseline score to see what happens when they have to actually share resources 00:03:07.080 --> 00:03:14.760 which especially for things like memory it's not very pleasant sometimes okay so 00:03:12.760 --> 00:03:19.319 I've assembled a crack Squad of helpers whose intelligence and physical 00:03:17.239 --> 00:03:25.120 coordination uh lead me to believe that it is probable nay likely are both kind 00:03:23.959 --> 00:03:29.080 of the same thing that they will be able to perform the skills that I set out for 00:03:27.319 --> 00:03:34.640 them today task actually not skills don't worry too much about that basically what you guys have to do is 00:03:32.159 --> 00:03:40.120 all press a button at the same time oh that's that's not not going to work okay 00:03:36.879 --> 00:03:43.200 Colton you're fired again thank you okay 00:03:40.120 --> 00:03:46.319 so two of you will have to press two 00:03:43.200 --> 00:03:48.319 buttons at once at the same time Johnny 00:03:46.319 --> 00:03:52.200 you got this okay Johnny you're on machines one and two yvon you're on 00:03:50.280 --> 00:03:55.280 machine three Colton you're here Nick you're here and I'll go over there and I 00:03:53.879 --> 00:03:59.079 will tell you which button to press and you will all press it at the same time 00:03:57.720 --> 00:04:05.120 you're going to click the button that says Run next to CPU in the cinebench 00:04:03.079 --> 00:04:10.040 R15 program has everyone got your cursor positioned yes okay so I'm going to say 00:04:08.079 --> 00:04:15.400 don't do it yet I guess teran's not here I don't have to give instructions like 00:04:11.280 --> 00:04:17.799 that okay it 3 2 1 00:04:15.400 --> 00:04:23.440 go okay so you can see here with our seven instances of cinebench running we 00:04:20.400 --> 00:04:26.199 are actually pinning the entire CPU here 00:04:23.440 --> 00:04:31.639 at 100% usage that was exactly our intent and will tell us without any 00:04:29.320 --> 00:04:36.479 extra a turbo boost for only activating a couple of cores at a time how all of 00:04:33.960 --> 00:04:41.320 our VMS can run in a worst case scenario where they are sharing as much resources 00:04:38.360 --> 00:04:45.919 as possible okay so we're scoring around 500 points which is about 100 lower than 00:04:43.840 --> 00:04:55.560 we did when we were just running it on a single VM fascinating okay everyone 00:04:50.840 --> 00:04:58.280 ready 3 2 1 go okay so this is 00:04:55.560 --> 00:05:02.639 interesting on the read side of things really there wasn't much an effect from 00:05:00.400 --> 00:05:07.960 the numbers I've looked at so far but on the right side of things some of our VMS 00:05:04.720 --> 00:05:09.800 were so starved for disc time that they 00:05:07.960 --> 00:05:13.759 actually timed out on their sequential right Benchmark very very interesting 00:05:12.800 --> 00:05:20.039 this isn't something we're going to retest after we overclock because we can't overclock storage but uh I just 00:05:17.759 --> 00:05:24.840 wanted to have this as just a for my information sort of number Ida 64 cash 00:05:22.720 --> 00:05:31.400 and memory Benchmark it's a gray window this one I'm really interested in 00:05:27.160 --> 00:05:33.639 because desktops really don't care much 00:05:31.400 --> 00:05:38.400 about their memory bandwidth these days I mean dual Channel quad Channel DDR3 00:05:36.600 --> 00:05:43.840 ddr4 it's all fast enough but if you're trying to hit 00:05:40.639 --> 00:05:45.680 something with s VMS at once I'm 00:05:43.840 --> 00:05:49.759 expecting the performance to be affected somewhat it's this is really interesting 00:05:48.080 --> 00:05:54.880 so you can actually see the systems are running the benchmarks at different 00:05:51.639 --> 00:05:58.120 speeds NX VM over here so this is player 00:05:54.880 --> 00:05:59.680 number five is actually still running 00:05:58.120 --> 00:06:04.639 the memory benchmarks or at least at least it was before I uh and mine is 00:06:02.639 --> 00:06:09.039 almost done running all of the level one and level two cash benchmarks so it does 00:06:06.680 --> 00:06:13.000 seem like their ability to even run these tests is affected by the fact that 00:06:10.919 --> 00:06:19.400 we're hitting them all at once here we go last one position your cursor over 00:06:15.599 --> 00:06:22.120 Run 3 2 1 fire strike 00:06:19.400 --> 00:06:26.720 extreme thank you for that clicking like random times like okay I guess that's it 00:06:24.919 --> 00:06:30.720 3 two one f with extreme okay you guys are dismissed for 00:06:28.800 --> 00:06:35.800 now thank you I'll call you back once I overclock the system so check this out 00:06:32.720 --> 00:06:38.199 this is what our uh memory and cach 00:06:35.800 --> 00:06:45.639 benchmarking looked like this is what our benchmarking looks 00:06:41.639 --> 00:06:47.319 like in fir strike extreme so with seven 00:06:45.639 --> 00:06:55.000 instances of it running we're actually getting up near 100% utilization closer 00:06:50.759 --> 00:06:55.000 to like 90 here 00:07:00.080 --> 00:07:08.599 okay very interesting so 3D Mark scores not affected much by our CPU and RAM 00:07:06.000 --> 00:07:13.680 sharing because 3D Mark is mostly dependent on the graphics card and each 00:07:10.319 --> 00:07:16.120 VM has its own R9 Nano so all that's 00:07:13.680 --> 00:07:21.000 left now to do is to record our score so we can create some average score graphs 00:07:18.400 --> 00:07:24.319 for you guys and establish our Baseline so that we can find out if our 00:07:22.759 --> 00:07:29.919 overclocking helps now most Server Motherboard makers 00:07:27.000 --> 00:07:36.120 do not have any overclocking features but this is a Seuss and this is 00:07:32.440 --> 00:07:39.319 technically a WS or workstation board so 00:07:36.120 --> 00:07:41.400 in the AI tweaker menu we've got their 00:07:39.319 --> 00:07:47.720 AI overclock tuner which has two settings neither of which I have played 00:07:43.160 --> 00:07:52.199 with at all manual and OC 00:07:47.720 --> 00:07:54.479 tune so I'm just going to go let's OC 00:07:52.199 --> 00:07:58.520 tune it level three and find out if the system works 00:07:57.280 --> 00:08:02.130 there's a very good chance this not going to work I have not tested did 00:08:00.360 --> 00:08:04.440 this at 00:08:04.440 --> 00:08:13.960 all so this is actually a really bizarre Quirk of this system it starts up 00:08:13.960 --> 00:08:20.440 here oh oh if it turns on at all it 00:08:18.000 --> 00:08:28.080 starts up here oh wow yeah that's not 00:08:24.159 --> 00:08:30.759 posting let's clear simos and then 00:08:28.080 --> 00:08:34.560 uh we will go from there 00:08:32.519 --> 00:08:40.919 okay something to see if that does 00:08:37.000 --> 00:08:44.240 anything oh that was it I need this bar 00:08:40.919 --> 00:08:44.240 to get past like 00:08:44.920 --> 00:08:51.240 here oh that wasn't it like I I 00:08:52.600 --> 00:08:59.760 oh I know what it is because we did a 00:08:57.160 --> 00:09:07.440 seimos clear that bio setting that I need the 4G 00:09:03.399 --> 00:09:09.320 decoding setting is not enabled so we 00:09:07.440 --> 00:09:13.160 are not able to boot with all of these PCI 00:09:10.959 --> 00:09:19.200 devices so maybe by 00:09:16.240 --> 00:09:24.880 unplugging all the video cards I will be able to have them not 00:09:22.240 --> 00:09:30.279 get picked up and I will be able to get into the 00:09:26.279 --> 00:09:34.000 BIOS this is how you remove the graphics 00:09:30.279 --> 00:09:34.000 cards from Seven Gamers one 00:09:36.800 --> 00:09:44.680 CPU there we go okay they're out so 00:09:42.560 --> 00:09:50.760 now can try again okay so that was 00:09:48.040 --> 00:09:56.959 it the problem with having a system that doesn't Post in its default 00:09:54.079 --> 00:10:02.720 configuration okay so let's try manual this time um 00:09:59.560 --> 00:10:05.720 my understanding is that on these types 00:10:02.720 --> 00:10:09.560 of boards you can expect somewhere in 00:10:05.720 --> 00:10:13.959 the neighborhood of like5 MHz so just 00:10:09.560 --> 00:10:17.959 for LS let's try 105 and see what 00:10:13.959 --> 00:10:20.480 happens I'm guessing not a whole lot and 00:10:17.959 --> 00:10:20.480 that's what I 00:10:21.399 --> 00:10:26.480 got okay then okay so after four 00:10:24.959 --> 00:10:30.680 attempts we're back in the BIOS our setting did stick but obviously didn't 00:10:29.000 --> 00:10:36.519 work so let's try a more conservative 103 which would be a 3% overclock okay 00:10:34.880 --> 00:10:43.040 so because we have no video card we have to use VNC to get into our VM and find 00:10:40.000 --> 00:10:48.240 out if everything is working as intended 00:10:43.040 --> 00:10:49.800 well that is not reporting correctly at 00:10:48.240 --> 00:10:56.200 all so that's a thing so we're going to have 00:10:53.040 --> 00:10:59.279 to run a benchmark and find out okay I 00:10:56.200 --> 00:11:03.079 tell you VMS really screw up hard 00:10:59.279 --> 00:11:07.680 Hardware reporting both CPU 00:11:03.079 --> 00:11:09.639 Z and Ida 64 are reporting numbers that 00:11:07.680 --> 00:11:14.279 would indicate that our CPU is not overclocked but cinebench is reporting 00:11:12.240 --> 00:11:17.360 that it is overclocked and even though these scores are not directly comparable 00:11:16.160 --> 00:11:23.279 because we don't even have any of the other VMS booted we're getting 900 in 00:11:20.560 --> 00:11:27.040 cinebench which would indicate that everything's working properly at the 00:11:25.399 --> 00:11:31.440 very least so now we can proceed to the next step and put our graphics cards 00:11:29.040 --> 00:11:38.680 back back in okay all our video cards are showing up which basically means we 00:11:33.600 --> 00:11:41.000 can start the array and fire up our 00:11:38.680 --> 00:11:47.240 VMS did it just do that or did you do that hey all 00:11:44.279 --> 00:11:52.959 right say that again so now it is time to overclock our video cards now the R9 00:11:49.720 --> 00:11:53.839 Nano isn't uh really known to be much of 00:11:52.959 --> 00:11:59.040 an overclocker uh but we're going to go 00:11:56.480 --> 00:12:02.440 ahead and increase the power limit as high as it goes and we're going to 00:12:00.480 --> 00:12:11.760 increase our core clock to like I don't know 1050 and see what happens hey 00:12:06.839 --> 00:12:13.360 Graphics 1050 MHz just like that I guess 00:12:11.760 --> 00:12:20.279 water cooling helps a little bit with the whole overclocking the R9 Nano 00:12:16.160 --> 00:12:24.440 situation very nice what the hell 00:12:20.279 --> 00:12:26.360 afterburner is detecting all seven gpus 00:12:24.440 --> 00:12:32.040 that shouldn't be possible cuz we've passed them through 00:12:28.760 --> 00:12:34.720 to separate VMS it's also detecting wow 00:12:32.040 --> 00:12:38.519 afterburner doesn't know what's going on so it's got them all being used while 00:12:36.839 --> 00:12:43.880 we're running The Benchmark so it knows there's seven but it doesn't know that 00:12:41.040 --> 00:12:51.199 it's only using one of them and it's just cloning this core clock graph which 00:12:47.279 --> 00:12:54.199 actually has the card not reaching uh 00:12:51.199 --> 00:12:57.160 not reaching 1,000 mahz anyway 00:12:54.199 --> 00:13:01.959 so I guess all that's left now then is to run some benchmarks and find out if 00:12:59.720 --> 00:13:08.920 we got any benefit for our trouble everyone ready overclocked cin bench 00:13:06.279 --> 00:13:12.120 Benchmark what damn it Nick if ID wanted someone to just start The Benchmark 00:13:10.199 --> 00:13:17.920 early I'd have asked Taran to help please work please 00:13:15.160 --> 00:13:27.240 work please work no no what no just kidding player 00:13:22.560 --> 00:13:30.440 whatever it is so it's 1 2 3 4 5 6 7 and 00:13:27.240 --> 00:13:34.040 then you put OC score in a bench but my 00:13:30.440 --> 00:13:37.720 keyboard says six don't worry about that 00:13:34.040 --> 00:13:41.160 okay actually that does seem to be 00:13:37.720 --> 00:13:42.920 faster good yeah 40 points better on 00:13:41.160 --> 00:13:52.759 mine 30 points everyone ready ready 3 two 1 run 00:13:49.160 --> 00:13:52.759 it please don't 00:13:55.600 --> 00:14:00.399 crash oh M oh 00:14:03.000 --> 00:14:06.720 why it's okay give it 00:14:07.720 --> 00:14:15.959 time power draw 1,600 Watts so did 00:14:12.360 --> 00:14:18.199 everything but Nicks launch yeah okay so 00:14:15.959 --> 00:14:23.320 after much struggling we managed to achieve whopping overclocks of anywhere 00:14:21.680 --> 00:14:30.320 from zero to 70 00:14:26.560 --> 00:14:34.240 mahz on our graphics cards you building 00:14:30.320 --> 00:14:35.759 fire strike extreme scores in the very 00:14:34.240 --> 00:14:42.680 very close to what we were already getting range leading us to believe that this 00:14:39.720 --> 00:14:47.160 whole thing was a terrible idea but I'm really glad that you guys got to come 00:14:44.519 --> 00:14:54.519 along for the adventure with us because um that is what we do on this 00:14:51.160 --> 00:14:56.519 channel that is what we do this is a 00:14:54.519 --> 00:15:04.240 sponsor spot I have been looking forward to for quite some time we recoverd 00:15:00.600 --> 00:15:06.880 dat.com what they do is pretty obvious 00:15:04.240 --> 00:15:11.519 they recover data and why we're affiliated with them will be pretty 00:15:08.759 --> 00:15:17.440 obvious if you checked out the data recovery Vlog which if you haven't 00:15:13.560 --> 00:15:20.000 already is a pretty uh pretty exciting 00:15:17.440 --> 00:15:24.360 piece of content as far as they go on this channel anyway they gave me some 00:15:22.560 --> 00:15:27.959 bullet points to talk about and I will do that but then I'll get into why 00:15:26.160 --> 00:15:32.360 they're so special to me so first of all they're one of the only dat recovery 00:15:29.480 --> 00:15:36.600 companies to invest in R&D so if the technology to recover your data doesn't 00:15:34.120 --> 00:15:40.880 exist they create it they're fast they're techsavvy they have friendly 00:15:38.199 --> 00:15:45.519 customer service available 247 and that was indeed my experience their data 00:15:43.360 --> 00:15:50.519 recovery guarantee policy means that if they don't recover any data there is no 00:15:48.040 --> 00:15:55.000 recovery fee they have worldwide emergency data response options 00:15:52.440 --> 00:15:58.639 including onsite remote and in lab that's 247 365 they've got 00:15:57.399 --> 00:16:02.399 state-of-the-art equipment utilizing today's most advanced technology with 00:16:00.639 --> 00:16:07.720 proprietary in-house developed tools they've got iso4 class 10 and iso5 class 00:16:05.639 --> 00:16:12.800 100 clean rooms to enable them to provide a Optimum solution for a 00:16:10.360 --> 00:16:19.480 recovery environment and basically what it boils down to for me is they got my 00:16:16.319 --> 00:16:22.160 data back it was an extremely 00:16:19.480 --> 00:16:27.480 complicated raid array not a recommended raid array so I had three raid fives 00:16:25.319 --> 00:16:32.279 that were Hardware raid fives on separate LSI controllers and then I had 00:16:29.720 --> 00:16:37.920 those striped together in raid zero for an effective raid 50 so three raid five 00:16:34.959 --> 00:16:43.639 stripes in Windows I thought it should be pretty safe because I can lose up to 00:16:40.759 --> 00:16:48.680 one SSD per controller before I should run into any issues but what I didn't 00:16:45.399 --> 00:16:50.759 account for is losing a controller 00:16:48.680 --> 00:16:55.880 outright so one of the controllers failed causing the array to go into an 00:16:53.319 --> 00:17:01.560 unrecoverable State and we recoverd dat.com had me plug in all those 24 00:16:58.480 --> 00:17:03.880 drives to a host bus adapter and they 00:17:01.560 --> 00:17:09.319 were able to remotely using their own Linux tool reconstruct the whole thing 00:17:06.319 --> 00:17:13.240 allow me to copy it off and basically 00:17:09.319 --> 00:17:14.959 save my turkey which uh thanks to those 00:17:13.240 --> 00:17:19.600 guys and if you guys have a data recovery emergency then check them out 00:17:17.360 --> 00:17:24.959 the link is at the video description I heartily endorse we recoverd dat.com so 00:17:23.439 --> 00:17:28.120 thanks for watching guys if you disliked this video hit the dislike button but if 00:17:26.600 --> 00:17:32.000 you liked it and you thought it was crazy and a an extreme hit the like 00:17:30.080 --> 00:17:35.240 button get subscribed and maybe even consider supporting us by buying a cool 00:17:33.559 --> 00:17:39.880 shirt like this one changing your Amazon bookmark one with our affiliate code instructions for up there or just 00:17:38.200 --> 00:17:45.120 contributing directly through our all new Linus Tech tips Forum freshly 00:17:42.039 --> 00:17:47.320 updated for 2016 which you can check out 00:17:45.120 --> 00:17:49.960 at the link in the video description and now that you're done watching this and 00:17:48.480 --> 00:17:53.240 you're wondering hey what should I watch next maybe check out the video where I 00:17:51.799 --> 00:17:56.520 show you how to quadruple your network speed for 100 bucks that is assuming 00:17:55.240 --> 00:18:02.000 that you have a couple of really good computers already and you have like networking equipment in you have eBay 00:17:59.320 --> 00:18:06.590 and etc etc etc terms and conditions they 00:18:03.919 --> 00:18:09.510 apply links up there