WEBVTT 00:00:00.160 --> 00:00:06.040 computer problems are a fact of life and 00:00:03.719 --> 00:00:11.440 sometimes the fix is as simple as just turning it off and turning it back on 00:00:08.599 --> 00:00:15.360 again but other times it's not and when the system you're talking about is 00:00:13.040 --> 00:00:19.760 running an air traffic control system controlling a bunch of ATMs or say 00:00:17.400 --> 00:00:24.800 routing 911 calls keeping them up and running can be a matter of life and 00:00:21.480 --> 00:00:27.679 death now the stakes aren't nearly as 00:00:24.800 --> 00:00:31.960 high for us but this server here runs multiple apps that we rely on every day 00:00:30.320 --> 00:00:37.640 accelerates our game downloads with steam caching and it runs our DNS if 00:00:35.719 --> 00:00:41.920 that service goes down it breaks literally everyone in the company's 00:00:39.239 --> 00:00:47.760 internet which my boss informs me isn't great so how do we make it more reliable 00:00:44.280 --> 00:00:50.320 it's already a server we build more 00:00:47.760 --> 00:00:54.199 servers and what's really cool about this is everything we're about to show 00:00:52.039 --> 00:00:59.280 you courtesy of Intel who sponsored this video and sent over their new Emerald 00:00:56.320 --> 00:01:03.800 rapid Zeon CPUs can be done on nearly any computer 00:01:00.519 --> 00:01:05.360 even your dad's Old Dell that is as long 00:01:03.800 --> 00:01:11.640 as you have more than one so if one leaves for cigarettes we can still play 00:01:08.520 --> 00:01:15.439 catch more than one dell not more than 00:01:11.640 --> 00:01:17.200 one dad oh well anyways I'm done you 00:01:15.439 --> 00:01:21.720 want to check this out yeah let's have a look you got your lovely cat picture 00:01:18.960 --> 00:01:25.880 your crab rave on that computer M watch this like I can yeah I can interact with 00:01:23.840 --> 00:01:31.320 this just just give it a second okay it's it's going hey now it's on this 00:01:28.920 --> 00:01:37.520 computer and like no bamboozle here look watch whoa buddy watch watch watch boom 00:01:34.840 --> 00:01:42.439 unplugged I can just completely interact with this as I normally would so what's 00:01:39.840 --> 00:01:47.840 going on here what you guys just saw was the programs the lovely drawing the 00:01:45.159 --> 00:01:53.000 entire operating system just teleporting from the computer over here to the one 00:01:49.960 --> 00:01:55.600 over here no trickery this is possible 00:01:53.000 --> 00:01:58.560 thanks to the magic of virtualization we've talked about it before but if 00:01:56.880 --> 00:02:03.840 you're not familiar virtualization allows you to slice up a single machine 00:02:01.240 --> 00:02:09.160 into multiple less powerful virtual machines and this setup leverages that 00:02:06.759 --> 00:02:13.959 technology to allow us to move these virtual machines between multiple 00:02:11.720 --> 00:02:18.440 physical computers that way if one breaks another one can immediately take 00:02:16.599 --> 00:02:22.599 its place and the best part is that while this all sounds super fancy all 00:02:20.680 --> 00:02:26.200 the software we're using is both open- source and free and we're going to show 00:02:24.519 --> 00:02:29.400 you guys how the setup Works in a little bit first I want to take a look at the 00:02:27.800 --> 00:02:36.640 servers we're going to be using for our setup Gigabyte sent over four of their 00:02:32.000 --> 00:02:38.280 r163 sg2 aac1 servers these are Bare 00:02:36.640 --> 00:02:43.000 Bones so we're going to have to add a few of Our Own Parts but we should be 00:02:40.080 --> 00:02:47.040 able to build this in what like 5 minutes I'd like to see you try this guy 00:02:45.560 --> 00:02:51.519 we're going to add some of our own parts starting with a pair of patriot 480 gig 00:02:49.360 --> 00:02:56.480 SATA ssds that will function as a mirrored boot drive this kind of per 00:02:54.480 --> 00:03:00.879 machine redundancy isn't strictly speaking necessary because we could lose 00:02:59.319 --> 00:03:05.040 an entire ire machine in our configuration without having any issues 00:03:03.000 --> 00:03:09.599 but having them in pairs makes our lives easier in the future potentially since 00:03:07.519 --> 00:03:12.879 if one of them fails we can just replace it and then rebuild it from the other 00:03:11.480 --> 00:03:18.239 one then on the other side of the machine we're installing two of these 00:03:14.480 --> 00:03:21.000 kokia cd6 7 tbte drives for fast bulk 00:03:18.239 --> 00:03:26.000 storage that leaves us six more SATA Bays to do nothing with and two more 00:03:22.799 --> 00:03:28.480 NVMe Bays for potential future 00:03:26.000 --> 00:03:33.280 expansion moving back let's get our CPU installed we're using a Zeon Platinum 00:03:30.319 --> 00:03:39.000 8562 y+ in each node these were graciously provided by Intel and with 32 00:03:35.599 --> 00:03:40.519 cores 64 threads and 4.1 GHz max turbo 00:03:39.000 --> 00:03:45.159 clock speeds these are going to give us a ton of compute to share between our 00:03:42.280 --> 00:03:48.159 virtual machines all at a modest 300 wat TTP we're going to have it and the rest 00:03:47.040 --> 00:03:53.959 of the parts Linked In the video description now I've never installed in 00:03:50.480 --> 00:03:56.680 this socket before so good luck me step 00:03:53.959 --> 00:04:00.000 one is to install the carrier on the CPU and you can tell which one of the three 00:03:58.360 --> 00:04:03.920 you're supposed to use by the little marking right there on the CPU IHS line 00:04:02.319 --> 00:04:08.879 up our little Golden Triangle with our gigantic gargantuan hole in the whole 00:04:06.760 --> 00:04:12.159 thing triangle oh this is adorable it's got a cute little ARM so you can break 00:04:10.560 --> 00:04:16.959 the thermal pce seal with the cooler so you can get the cooler and the CPU separated more easily love to see it 00:04:15.560 --> 00:04:23.360 speaking of thermal paste we're going to be using a Honeywell PTM 7950 pad 00:04:20.600 --> 00:04:29.000 available at LTT Store.com this stuff is absolutely perfect for a server install 00:04:25.680 --> 00:04:30.600 because it lasts not forever but for a 00:04:29.000 --> 00:04:36.440 very very very long time without maintenance now you might think okay go 00:04:33.479 --> 00:04:41.800 ahead put it onto the CPU socket you'd be wrong instead I'm going to install it 00:04:39.120 --> 00:04:51.320 onto the cooler I'm going to know how to do that in a sec so arrow and arrow so 00:04:47.639 --> 00:04:54.880 maybe ah ah 00:04:51.320 --> 00:04:56.400 ah hey there we go damn look at that 00:04:54.880 --> 00:05:00.759 Vapor chamber love me a vapor chamber okay 00:04:59.840 --> 00:05:05.280 we're going to make sure all these are clicked into place look for our little 00:05:02.880 --> 00:05:10.039 arrow here line that up with the arrow on the 00:05:06.600 --> 00:05:12.080 socket and make sure that the locks are 00:05:10.039 --> 00:05:16.759 in their unlocked position then we should be able to just that's it's 00:05:14.600 --> 00:05:20.000 locked oh that's it okay next comes something you don't see me do very often 00:05:18.199 --> 00:05:24.120 and that is use a screwdriver other than the LTT screwdriver and that's because 00:05:22.280 --> 00:05:29.039 these need to be torqued to a specific value that is 6.9 inch PBS 00:05:29.759 --> 00:05:34.960 nice it's so cool to think that if I was doing this you know performing 00:05:32.919 --> 00:05:39.800 maintenance on the server or upgrading a bad RAM stick our entire operation could 00:05:37.400 --> 00:05:45.000 be chugging along as if nothing happened speaking of RAM we've gone with four 96 00:05:42.600 --> 00:05:49.840 gig Micron 5600 megat transfer per second registered ECC dims that's a 00:05:47.560 --> 00:05:53.520 somewhat unconventional choice because especially in a server giving up half of 00:05:51.800 --> 00:05:58.120 the memory channels means that we will be giving up some performance but we 00:05:56.319 --> 00:06:03.520 don't really need all of the performance for now and 3 84 gigs is a ton of 00:06:01.520 --> 00:06:08.560 capacity for our needs at the moment and of course if anything changes we can 00:06:05.759 --> 00:06:12.160 always add more without any downtime to our services the only thing that's 00:06:10.599 --> 00:06:15.919 really important here then is making sure that we install our sticks in the 00:06:13.919 --> 00:06:20.520 correct slots which is not always super intuitive so make sure to consult your 00:06:18.080 --> 00:06:23.880 manual we don't need a GPU for now though we could add one in the future so 00:06:22.360 --> 00:06:29.319 that means all that's really left is these NVIDIA connect X6 cards now 100 00:06:27.319 --> 00:06:34.680 Gig networking might seem a bit Overkill but because our setup uses high-speed 00:06:31.680 --> 00:06:37.840 drives in four servers and we want to be 00:06:34.680 --> 00:06:40.400 able to withstand two server failures 00:06:37.840 --> 00:06:45.919 anytime we're writing data it has to be simultaneously written to the drives on 00:06:42.680 --> 00:06:48.440 at least three machines that ensures we 00:06:45.919 --> 00:06:52.520 have three upto-date copies in the event of an unexpected failure now if you were 00:06:50.800 --> 00:06:55.919 doing this at home you obviously wouldn't want to spend this kind of 00:06:53.800 --> 00:07:01.160 money but the good news is that you can do this with as few as two machines and 00:06:58.840 --> 00:07:06.680 if you're not trying to run a highspeed caching server for a 100 people 10 or 25 00:07:04.680 --> 00:07:11.039 gig cards are available for a fraction of the price and you can connect them 00:07:09.000 --> 00:07:15.919 directly to each other without an expensive switch I mean even one gig 00:07:13.800 --> 00:07:20.000 could work for light applications like ensuring that your home automation 00:07:17.240 --> 00:07:24.479 system never goes down enough chitchat though let's get on with the demo and 00:07:22.080 --> 00:07:27.960 show you what happens if one of these things goes to heaven in a live 00:07:26.479 --> 00:07:31.360 environment but not before we get them in the rack and set up specific 00:07:29.520 --> 00:07:35.240 specifically here in the lab server room because if you didn't notice earlier the 00:07:33.000 --> 00:07:38.080 studio server room is kind of running out of space at least until these 00:07:36.599 --> 00:07:41.479 machines are up and running and we can take the machine they're replacing out 00:07:39.919 --> 00:07:47.199 let's go grab the service un fortunately the rest of the machines are now magically built off of camera and we can 00:07:44.919 --> 00:07:51.360 just slide them in what the hell is going on oh there we go beautiful these 00:07:49.680 --> 00:07:56.599 Gigabyte chassis come with nice toolless rails so installing these in our nice 00:07:54.440 --> 00:08:01.280 ginormous hammonded rack should be pretty easy yeah look at 00:07:58.440 --> 00:08:04.879 that it's getting close I can taste it we just need networking like we 00:08:03.000 --> 00:08:09.199 mentioned before 100 Gig but what we didn't mention before is that each is 00:08:06.440 --> 00:08:13.360 getting two of them specifically one to each of the network switches in the rack 00:08:11.599 --> 00:08:17.800 that way if one of those switches has a problem the servers will stay up and we 00:08:16.080 --> 00:08:22.800 even get an added bonus because some fancy Dell magic called VT we get the 00:08:20.879 --> 00:08:29.199 throughput of both of these cables so 200 gig to each surface pretty 00:08:26.720 --> 00:08:33.680 sick all that's left then is power and like any other good server ipmi which is 00:08:31.639 --> 00:08:37.039 a management interface and allows us to control the machines even if they're not 00:08:35.719 --> 00:08:41.279 working they have like a hardware problem we can still access them we can 00:08:39.039 --> 00:08:44.920 turn them on turn them off it's kind of magic if you have a server that doesn't 00:08:42.880 --> 00:08:49.399 have ipmi I don't know I don't even know if that's a server 00:08:47.040 --> 00:08:53.200 really there are two main elements to making this setup work clustering the 00:08:51.440 --> 00:08:57.000 hypervisor which controls our virtual machines and clustering the storage 00:08:55.360 --> 00:09:00.279 which you can skip if you have existing network storage you want to use instead 00:08:59.120 --> 00:09:03.839 if you're not not interested in how to set this up you can skip ahead to here 00:09:02.560 --> 00:09:08.560 to see what it's like when it's up and running this isn't going to be a perfect step-by-step guide but with the 00:09:07.000 --> 00:09:13.480 documentation you can find down in the description you should be able to replicate this setup pretty easily 00:09:11.880 --> 00:09:18.240 starting with networking we added both of our 100 Gig ports to a bond created a 00:09:15.920 --> 00:09:22.680 bridge and then added a VLAN for three different networks one for our VMS to 00:09:20.399 --> 00:09:27.519 use one for cluster communication and one for the storage they can all 00:09:25.120 --> 00:09:31.519 technically run on the same network but the cluster needs low latency and the 00:09:29.399 --> 00:09:35.040 storage ideally uses jumbo frames so splitting it up like this is best 00:09:33.160 --> 00:09:39.240 practice you'll also need to add each node's cluster Network IP address to the 00:09:37.120 --> 00:09:42.880 host file on each node with the networking up and running enable the no 00:09:40.920 --> 00:09:47.440 subscription repo and disable the Enterprise repo it's not recommended by 00:09:45.519 --> 00:09:50.880 the proxmox team for production they want you to pay for the Enterprise repo 00:09:49.120 --> 00:09:55.040 which is a bit more stable but the free one is totally fine for a home setup run 00:09:53.079 --> 00:09:59.399 any pending updates before proceeding then make sure you have a reliable and 00:09:57.079 --> 00:10:03.560 ideally local time server configured on on each of your individual servers as 00:10:01.600 --> 00:10:07.360 the clustering software wants the time very closely in sync to stay happy with 00:10:05.959 --> 00:10:12.760 that out of the way we can set up our cluster which handles syncing the configuration and management of any 00:10:10.680 --> 00:10:17.040 virtual machines between our physical machines and it also orchestrates 00:10:15.120 --> 00:10:21.800 migrating or restoring them when a machine goes down creating the cluster 00:10:19.440 --> 00:10:25.720 just takes actually a few clicks but you might want to consider the size of your 00:10:23.560 --> 00:10:28.720 setup before you continue that's because in order to make sure everything stays 00:10:27.120 --> 00:10:33.480 in sync in case of an issue with a machine you need the majority of servers 00:10:31.160 --> 00:10:37.480 online and available to be able to say hey I see that one's offline but you 00:10:35.480 --> 00:10:42.600 know we're we're still good they call this Quorum if you have an even number 00:10:40.040 --> 00:10:47.720 of machines let's say four like we do and each server gets the default single 00:10:45.399 --> 00:10:51.959 say or vote the minimum possible majority is then three servers so that 00:10:50.120 --> 00:10:55.360 means we can only withstand one going down which is the same amount of 00:10:53.839 --> 00:10:59.839 redundancy you'd get if you had three machines cuz you can only lose one to 00:10:57.760 --> 00:11:04.320 have two if you only have two computers then you only ever have a majority when 00:11:01.880 --> 00:11:09.040 both are online which obviously doesn't work that's not safe but you can screw 00:11:06.839 --> 00:11:13.160 it around this by adding a third machine like say a Raspberry Pi to be a 00:11:11.519 --> 00:11:16.320 tiebreaker but that's kind of beyond the scope of this video once you're ready 00:11:14.800 --> 00:11:20.120 select the cluster Network in the creation menu and then join the other 00:11:18.279 --> 00:11:23.600 machines to the cluster once they're in you should be able to see them in the 00:11:21.320 --> 00:11:28.200 web goey of any of the machines now on to clustering our storage by default 00:11:25.920 --> 00:11:32.040 proxmox is very heavily integrated with SEF and opens Source distributed storage 00:11:30.399 --> 00:11:35.839 system that's pretty easy to set up and maintain with that in mind newbie should 00:11:34.160 --> 00:11:39.560 start with Seth and you can follow the great tutorial on their Wiki but it 00:11:37.920 --> 00:11:43.440 isn't the most performant in a small cluster like this so we're going to be 00:11:41.000 --> 00:11:48.079 using something called linore with drbd or distributed replicated block devic 00:11:45.760 --> 00:11:51.480 another open source storage system it requires a bit more manual configuration 00:11:50.160 --> 00:11:55.519 but they do have a purpose-built tutorial for proxmox and host the files 00:11:53.959 --> 00:11:59.800 for free with an optional paid Enterprise version that operates on a 00:11:57.560 --> 00:12:03.720 similar model as proxmox itself unlike seph it doesn't handle its own storage 00:12:01.560 --> 00:12:08.040 devices so we mirrored our two kokia ssds with ZFS first and then pointed Lin 00:12:06.320 --> 00:12:11.480 store to that once it's installed and configured then you can add the 00:12:09.399 --> 00:12:14.760 clustered storage to proxmox create a virtual machine with that storage and 00:12:12.839 --> 00:12:18.360 it'll automatically be replicated in real time to the number of other nodes 00:12:16.519 --> 00:12:22.839 you specify and if you happen to migrate a VM to a server that doesn't have a 00:12:20.519 --> 00:12:26.839 copy on it it'll automatically stream the data over the network from one of 00:12:24.760 --> 00:12:33.760 those nodes in what they call dis list mode but let's just try it 00:12:30.480 --> 00:12:36.480 hey pretty nice right looking good it's 00:12:33.760 --> 00:12:39.720 like even cable managed I know right so 200 gig on each of them nice who are you 00:12:38.560 --> 00:12:44.040 people and what have you done with our infer team I made one small adjustment 00:12:42.320 --> 00:12:48.839 just for you look at the drives they're in the same spot no they're not the top 00:12:46.560 --> 00:12:53.399 one's different I hate you so much why would you do that but more importantly 00:12:50.839 --> 00:12:59.279 does it work uh yeah obviously okay well here's your Windows desktop obviously he 00:12:55.480 --> 00:13:01.160 says what editor a super cut of things 00:12:59.279 --> 00:13:06.839 not working here please Jake we have a leak oh God one failure you just 00:13:04.399 --> 00:13:11.680 downgraded my Wi-Fi four drives aren't working did you actually break it 00:13:09.079 --> 00:13:16.120 anyways you see our Windows right yeah our Windows is running right now on 00:13:13.680 --> 00:13:20.480 number four which is the bottom server yes now obviously remoting into the 00:13:18.360 --> 00:13:24.839 machine over Wi-Fi okay the video playbacks a little 00:13:23.000 --> 00:13:28.680 bit choppy that's not going to affect the type of workload we would normally 00:13:26.560 --> 00:13:34.720 be running on something like this like a DNS server or like are we finally doing 00:13:31.760 --> 00:13:39.160 active directory we will not not today not today but we can now but this is the 00:13:37.360 --> 00:13:42.839 kind of setup that you want for something like ad live playing the video 00:13:41.079 --> 00:13:48.800 Let's migrate to number one which is the top one the process will be a little bit 00:13:45.320 --> 00:13:51.639 faster but basically what it's doing is 00:13:48.800 --> 00:13:55.880 copying the memory like the RAM what's actually in memory and then once it's 00:13:53.639 --> 00:13:59.560 done most of it it pauses the operating system for a split second copies the 00:13:58.000 --> 00:14:04.199 last tiny little bit and boom that is so cool you're exactly 00:14:02.560 --> 00:14:08.839 where you were before because the storage is already there right so in 00:14:07.120 --> 00:14:13.839 terms of actual downtime like Interruption to that experience 17 00:14:11.120 --> 00:14:17.040 seconds no 270 milliseconds Oh I thought you were pointing the other no 17 00:14:15.079 --> 00:14:21.800 seconds is that whole process but oh yeah yeah well that's kind of downtime I 00:14:20.040 --> 00:14:26.160 guess no cuz that if there was somebody using this like as a virtual desktop for 00:14:23.759 --> 00:14:32.000 instance they would see like a quarter of a second blink and otherwise like 00:14:29.160 --> 00:14:37.360 nothing changed I wanted to show a more realistic to us demo sure come hither 00:14:35.560 --> 00:14:42.160 here's a Plex server we've got some videos on it and this is on server 00:14:39.480 --> 00:14:46.440 number one okay let's play a video now we go and move our Plex server to a 00:14:44.360 --> 00:14:51.600 different machine so it's copying the RAM at 2.5 gig gtes a second so it's 00:14:49.920 --> 00:14:56.480 like 2.8 gigabytes a second that's pretty good we haven't done any actual 00:14:53.399 --> 00:14:58.399 oh it's already done and No Interruption 00:14:56.480 --> 00:15:03.120 because video playback like many other applications uses buffers to hide small 00:15:01.279 --> 00:15:07.079 interruptions in the service in this case downloading the video in small 00:15:04.880 --> 00:15:12.560 chunks a little bit at a time yeah roughly 10c chunks it looks like here 00:15:09.320 --> 00:15:15.000 which is plenty to cover that 146 00:15:12.560 --> 00:15:19.240 milliseconds of downtime wow you want to try steam download with landan cach I 00:15:16.920 --> 00:15:25.440 mean we should yeah why not yep we're CPU bottleneck for sure using you know 00:15:22.279 --> 00:15:26.560 80 to 90% of a 24 core Threadripper but 00:15:25.440 --> 00:15:32.759 I realized I made a little bit of an oopsy here look you can see the CPU usage we're using % of our eight CPUs 00:15:30.720 --> 00:15:37.839 that I assigned to this steam cache we can see our Network traffic's going up 00:15:35.160 --> 00:15:41.480 sick except I made this as a container not a VM and the thing with containers 00:15:40.399 --> 00:15:48.079 they're great they're a little bit lighter weight better performance but they run within the kernel of the main 00:15:46.040 --> 00:15:52.000 system it'll shut down that container and then just reboot on the other 00:15:49.240 --> 00:15:57.600 machine right which means it's fine but there will be a longer downtime delay 00:15:54.560 --> 00:15:59.360 but way less than hey is that thing 00:15:57.600 --> 00:16:02.279 working oh I think the internet is not working somebody should go look at that 00:16:01.040 --> 00:16:06.480 yeah trying to figure out what's going on fixing the machine getting the machine back going so cool you're 00:16:05.199 --> 00:16:11.680 talking about the matter of a couple minutes maybe yeah now for the most 00:16:08.600 --> 00:16:14.360 impressive demo yet the unexpected 00:16:11.680 --> 00:16:18.360 migration which one am I yanking okay so number one has three VMS on it they're 00:16:16.319 --> 00:16:25.040 all in the high availability Jake's chain ah what means oh I get it okay 00:16:23.600 --> 00:16:30.839 sorry which one I wasn't even listening to number one number one and we'll see 00:16:28.600 --> 00:16:35.560 how how fast it does we're looking at server one from server two so go for 00:16:39.480 --> 00:16:46.839 it from my understanding this process 00:16:42.800 --> 00:16:49.000 takes a minute or two okay to go oh it's 00:16:46.839 --> 00:16:53.519 already detected the no is offline sure is if you're doing scheduled maintenance 00:16:51.440 --> 00:16:57.279 you can actually go and just shut off a machine and then it will just be like oh 00:16:56.079 --> 00:17:01.279 crap I need to move all those things before I shut off which is a little bit 00:16:59.079 --> 00:17:06.319 nicer in this case it has to be like sure that the server is down so all 00:17:03.800 --> 00:17:12.120 three of those are yelling at what was this say hello what happened are you 00:17:09.000 --> 00:17:14.640 alive what's going on I can hear them 00:17:12.120 --> 00:17:20.520 hello what happened are you alive what's going on oh hey hey oh it did something 00:17:17.520 --> 00:17:22.600 so in theory it should distribute them 00:17:20.520 --> 00:17:26.640 evenly because that's the option that's set right now right in terms of its 00:17:24.520 --> 00:17:30.880 workload you mean yeah there is also a mode that does like resour first 00:17:29.120 --> 00:17:34.480 checking sure but right now it's going how many VMS are in each one and just 00:17:32.640 --> 00:17:38.679 like filling that number so it's even that is so cool okay so what service was 00:17:37.280 --> 00:17:42.400 running on that one was that the steam cache so we should go download a game 00:17:40.679 --> 00:17:47.880 you could do go do Plex right now too let's go do it let's go do it come on let's go wait we can take this door and 00:17:46.640 --> 00:17:53.320 no movie Magic but but also magic virtualization 00:17:50.880 --> 00:17:56.159 magic this is flipping awesome and it's going to be an absolute game changer for 00:17:55.240 --> 00:18:01.799 the way that we manage our infrastructure and like I said at the beginning I think the the coolest thing 00:17:59.520 --> 00:18:07.679 about it is that this type of architecture doesn't even have to run on 00:18:04.400 --> 00:18:10.520 the kind of emerald Rapids latest server 00:18:07.679 --> 00:18:15.159 technology that Intel and Gigabyte and Micron and NVIDIA all sent over here so 00:18:13.400 --> 00:18:19.280 the takeaway for you guys is whether it's for work or whether it's just for 00:18:17.120 --> 00:18:23.280 your home automation or your Plex server at home something like this is 00:18:20.840 --> 00:18:27.799 absolutely attainable with potentially very little Financial outlay like go buy 00:18:25.520 --> 00:18:32.440 some used like eighth gen Intel core processors those are pretty cheap some 00:18:29.480 --> 00:18:35.159 cheap ddr4 and you're Off to the Races or if you're doing this more properly 00:18:33.679 --> 00:18:41.559 for your business check out Intel Emerald Rapids and their whole line of 00:18:36.880 --> 00:18:45.360 Zeon and GPU products down below where 00:18:41.559 --> 00:18:47.440 were you pointing down below that's the 00:18:45.360 --> 00:18:50.159 description get your mind out of the description