How To: Building Your Own Render Farm
Hardware Component Selection For Each Node
Processor selection is dependent on two things: how much you're able to spend and resulting value. Even more so than normal desktop systems, render nodes are sensitive to these factors. There is a certain point on the processor performance curve where the next increment in compute speed results in a pricing jump that is out of order with the increase in performance. However, with today's higher bus speeds, too little cache on a processor can leave it starved for data. So, for discussion's sake, we'll shy away from Celerons as the bottom-end processor and instead use low-end dual-core Pentiums.
Using a lower-cost dual-core Pentium can give you a very inexpensive render node with a minimum sacrifice of performance. The Cinema 4D Release 10 chart shows the performance curve. While dual-core Pentiums and Celerons are not in these charts, you can see that there are spots in the Intel processor lineup where there is a significant jump in price for very little increase in performance. Find the price that you are willing to pay and then look at the best performance for your price range.
A dual-core Pentium, a slightly faster Core 2 Duo, or even a low-end Core 2 Quad are all good choices for building a node. It's really all about how much you want to spend here, because this is the single most expensive component required for each node. At the other end of the spectrum, building a Core i7-based system is going to increase the price of the entire node out of proportion to its increased performance. However, if you want to moderately future-proof your nodes and increase the likelihood of being able to get a processor upgrade for it later, you may want to consider that route.
A low-profile 1U heat sink is required for a corresponding case, most of which are made to specifically draw air from the front to the back of the machine. The limits in choices in processor cooling also limit (or even restrict) the possibility of overclocking the nodes. The Dynatron P199 pictured above is fairly typical and can handle quad-core processors.
Storage
Because the local drive will just be used for your operating system and applications, pick a small drive. An 80 GB drive is the smallest SATA drive commonly available, so that's what we recommend. However, if you use a drive with a digital audio workstation (that setup is discussed below) then a 320 GB, or maybe even a 500 GB drive, is a better choice.
Assuming you are building multiple nodes, you are only going to buy a single DVD drive (even if you are building 10 systems). You'll build your first machine, install the operating system plus software with updates, and then use Sysprep to blank the registration number. Next, use Norton Ghost 14 or similar drive-imaging software to clone the disk for subsequent machines. Each new system will require a fresh network name, and you will have to enter the Windows license key for each of the cloned machines. This keeps you from having to install the operating system, the applications, and the updates on each of the machines separately. If you build additional nodes using the same hardware in the future, it's also a good idea to clone one extra drive and keep the original as a master drive.
The operating system for your nodes should be similar (but not necessarily identical) to your operating system. Since 64-bit Windows XP is still available through OEM channels, there is no need for you to even consider putting Vista on your nodes, wasting memory and processing power. If your 3D application's network renderer (and all of the plugins that your network renderer needs, including third-party plugins) are supported under Linux, you may want to consider running Linux on the nodes instead, which makes the nodes even cheaper. A total of 10 copies of XP (for 10 nodes) may sound like a big expense, but it actually adds $140 per unit, pushing the cost of these machines to about $485 per unit for a dual-core node or $610 per unit for a quad-core configuration.
| Component | Dual-Core | Price | Quad-Core | Price |
|---|---|---|---|---|
| Casing | Supermicro CSE-512L-260 | $94.99 | Supermicro CSE-512L-260 | $94.99 |
| Motherboard | Asus P5B-VM SE | $59.99 | Asus P5B-VM SE | $59.99 |
| Processor | Intel Core 2 Duo E7200 | $91.99 | Intel Core 2 Quad Q8200 | $164.99 |
| Heat Sink | Dynatron P199 | $30.99 | Dynatron P199 | $30.99 |
| Memory | Patriot Viper PVS24G6400LLK – (2 GB x 2) | $51.99 | Two Patriot Viper PVS24G6400LLK – (2 GB x 4) | $103.98 |
| Hard Drive | Seagate Barracuda 7200.10 ST380215A 80 GB | $36.99 | Seagate Barracuda 7200.10 ST380215A 80 GB | $36.99 |
| Operating System | Windows XP Pro 64-bit | $139.99 | Windows XP Pro 64-bit | $139.99 |
| Total (With Shipping) | $485.11 | $610.10 |
So here’s what we’re looking at for a per-node price, with both dual- and quad-core processors. Remember, these are prices we found when this article was written, and they should change in the near future.
I got to say: building a cheapo C2D might be OK, but still it is better nowadays to buy cheap C2Q instead, because the price/performance ratio of the machine is considerably better.
However, please DO NOT spend more than 30% of you money on useless M$ products.
Be serious, and keep cheap things cheap, and spend your hard earned money on a better machine or on your wife/kids/bear instead.
Use linux, solaris, whatsoever ...
Better performance, better memory management, higher stability.
IN FACT, most real design/3D applications run under unixoid operating systems.
I got to say: building a cheapo C2D might be OK, but still it is better nowadays to buy cheap C2Q instead, because the price/performance ratio of the machine is considerably better.
However, please DO NOT spend more than 30% of you money on useless M$ products.
Be serious, and keep cheap things cheap, and spend your hard earned money on a better machine or on your wife/kids/bear instead.
Use linux, solaris, whatsoever ...
Better performance, better memory management, higher stability.
IN FACT, most real design/3D applications run under unixoid operating systems.
I'm not to the point yet where I really need a render farm, but this information might come in handy in a year or two. (and I severely doubt GPU rendering will make CPU rendering a thing of the past in 2 years)
I look forward to future articles on workstations
-Is there any chance of a comparison between workstation graphics cards and gaming graphics cards?
Please someone clarify this. How could they render a movie for 3,000 years? Did they have this render farms hidden in Egypt??
1) Cases cablable of taking a 2 slot grpahics card woudl future proff setting up anode at this time in case GPU rendering does become applciable over the lifetiem of the node. So (m)ATX cases not rack mounts
2) Resale of a (m)ATX "reglaur" looking desktop a few years down he road to "home users" is easier than a rack mount server. So should factor that into the value.
3) With 500-1TB being the sweet spot for Gb/$ I would go with those drives and use the render node also as a distributed (redundant) back up solution , this address where are you going to store all your work over the years.
What do you think the meaning of parallel processing is? Doing a lot of that work at once, right? If we have a huge render farm of 5000+ processors, we cut down that time to less than a year, wouldn't we?
Of course, a lot of that depends how fast each processor in the render farm is, but the general public won't care about that; just give 'em the huge numbers and don't tell them you were using 1.6ghz celery's in your render farms.
As MonsterCookie pointed already out, use some good scaling multi-processor/-node OS for good distributed performance (m$ doesn't apply).
Finally a decent article on TH... almost without the usual vi$hta or $even (aka vi$hta sp2+) m$ pu$hers behind.
What? xpire x64 is working for TH? almost unbelievable...
Also, none of the usual m$ fankiddie and gamer comments, (at least) till now...
If a task took 100 man hours, that means it took 2 guys 50 hours each to do something. If you did that with 10 guys, it would take each man 10 hours of work. There is a point of diminishing efficiency, which is mentioned in the article. The extreme to this is, it would take 100 men, 1 hour of work to complete the same task. The efficiency has been drasticly reduced.
This is whats being done in these rendering farms. A bunch of processors are put together, tasked with a job, and they belt out the results. If you did that with just one processor, it would take the 3k years in egypt to come up with a result.
I do agree with graphics card rendering,but don't think this article is worthless!
When I read about xeons, I also read about AMD making similar, low power processors like that (45nm or lower?,and a TDP of around 65W, which is 30W lower than their previous processor line).
It might not be beneficial to buy xeons, but perhaps it might when going with AMD.
Like buy a few XO netbooks for the developing countries, and sponsor lots of children.
Another idea we have been playing with is using cheap USB keyfobs either as system drives or to persist config data etc. - much faster boot times, very low power consumption and great MTTF.