来自：机器之心
链接：https://ikarus.sg/how-i-built-kraken/
Coding, blogging, and building fun projects are common ways for developers to advance their skills. Many seasoned professionals have a habit of writing blogs, and their hands-on ability is beyond question.
Today, we introduce a machine learning enthusiast, WILL HO, who also enjoys blogging. He not only registered his own blog site but also built a 28-core Raspberry Pi cluster for self-hosting. During this process, he learned many skills, including Linux, Docker, Docker Swarm, Kubernetes, DNS, TLS, and network topology.
In his latest blog post, WILL HO introduces the 28-core Raspberry Pi cluster he built, named Kraken, which utilizes 7 Raspberry Pi 3B units.
As mentioned earlier, WILL HO built the Raspberry Pi cluster for self-hosting his blog site created with WordPress. WordPress is a blogging platform developed in PHP, allowing users to set up their own websites on servers that support PHP and MySQL databases, or use WordPress as a content management system.
Previously, he had also built a Raspberry Pi cluster named Octopi (one Raspberry Pi 1B+ and four Raspberry Pi 1B units), but he soon discovered significant performance bottlenecks when running WordPress on this cluster, with a new blog page taking about 10 seconds to load!
To solve this bottleneck, WILL HO decided to upgrade Octopi, leading to the star of our article today—Kraken. In the following sections, WILL HO describes the process of building Kraken. If you also have a need for building a Raspberry Pi cluster or want to learn tools like Docker, you can refer to the author’s method to set up your own cluster.
Kraken consists of 7 Raspberry Pi 3B units powered by a USB charger. WILL HO initially planned to build a cluster with 8 nodes, but the maximum number of ports on consumer-grade network switches is 8, accommodating 7 nodes and one cable to the router.
Another option was to use a commercial-grade network switch with 16 ports, but that was clearly not feasible due to the price.
The specifications of the Kraken cluster built with Raspberry Pi 3B are shown in the table below:
The required parts list is shown in the table below:
It is worth noting that the author chose a 32GB MicroSD card as the storage for the first node, hoping it would become the master node for the Docker Swarm setup. The author anticipates needing additional storage space to build and deploy Docker images.
Kraken (top) and Octopi (bottom)
Gigabit Upgrade for Kraken
The author found that he often reached the 100Mbps bandwidth limit on the built-in Ethernet port of the Raspberry Pi 3B. During the transfer of large files, the transfer speed even hovered at a frustrating 8MB/sec.
Inspired by Jeff Geerling’s blog, the author discovered that using a USB Gigabit Ethernet adapter could increase the bandwidth to over 200Mbps. Thus, he bought a bunch of cheap USB Gigabit Ethernet adapters and a Gigabit switch to start the upgrade.
Cheap USB Gigabit Ethernet adapters.
After the upgrade, Kraken looks like this:
Gigabit Kraken, Octopi and my cable management nightmare
When all costs are accounted for, building this Kraken cluster totaled $508.84.
Running iperf before the upgrade, the maximum bandwidth was 93.1 Mbps.
~ ❯ iperf -c 192.168.3.11------------------------------------------------------------Client connecting to 192.168.3.11, TCP port 5001TCP window size: 129 KByte (default)------------------------------------------------------------[ 4] local 192.168.3.71 port 57041 connected with 192.168.3.11 port 5001[ ID] Interval Transfer Bandwidth[ 4] 0.0-10.0 sec 111 MBytes 93.1 Mbits/sec
After installing the Gigabit adapter and running iperf, the maximum bandwidth was 224 Mbps!
~ ❯ iperf -c 192.168.3.11------------------------------------------------------------Client connecting to 192.168.3.11, TCP port 5001TCP window size: 145 KByte (default)------------------------------------------------------------[ 4] local 192.168.3.71 port 57298 connected with 192.168.3.11 port 5001[ ID] Interval Transfer Bandwidth[ 4] 0.0-10.0 sec 268 MBytes 224 Mbits/sec
With this simple module, each node achieved a bandwidth of 131Mbps. However, these speeds are still theoretical, as typical use cases involve writing data received from the network to disk, whereas iperf only receives data from the network without writing it to disk.
Even in web services, it is unlikely to fully utilize this new bandwidth continuously. It mainly helps to transfer large resources (such as image data) faster during the initial load, after which the user’s browser will cache the images.
Moreover, the infamous shared USB 2.0 bus among Raspberry Pi models 1 to 3 also limits actual bandwidth.
For uninitialized users, the theoretical unidirectional bandwidth of a single USB2.0 bus is 480Mbps, shared among the Ethernet port, SD card slot, and all USB ports.
The bandwidth distribution is as follows:
Although the numbers in the table may give the impression that this upgrade did not bring performance improvements, they represent the worst-case scenario. Typically, one expects to perform mostly read operations on a web server, with few write operations.
In the real world, bandwidth allocation is usually as follows:
The above is the author’s upgrade operation on the second Raspberry Pi cluster. However, if you are already familiar with the Docker system or are looking for a high-performance home setup, this tutorial is not recommended.
If you are interested in Docker and Kubernetes, the author strongly recommends setting up a cluster like this. He provides two reasons:
First, this cluster is compatible with the official supported latest version of Docker images. Additionally, the Raspberry Pi 3B runs on the armv7 CPU architecture. The latest Arm processors (arm64) are backward compatible with all code written and compiled on armv7. In contrast, arm64 processors are not backward compatible with armv6 processors (Raspberry Pi 1 and 2), which are being phased out by the community.
Second, this cluster is an ideal choice for most bandwidth-intensive applications, such as hosting your own blog, file synchronization services, media library management, note-taking applications, etc. Considering the USB 2.0 bus bottleneck in Raspberry Pi 3, if your application requires a lot of continuous writes (such as video encoding), the performance of this cluster may not meet the requirements.
In summary, building a Raspberry Pi 3 cluster is the most cost-effective way to learn Docker and clustering, and it will remain so for the foreseeable future. Therefore, if you just want to get familiar with Docker, it is highly recommended to give it a try.
Contact Liang Xu on WeChat
Add Liang Xu on WeChat to receive 3 sets of essential reading materials for programmers
→ Selected technical materials shared
→ High-level exchange community
All articles from this public account have been organized into a directory. Please reply with ‘m’ in the public account to get it!
Recommended Reading:
What are the differences between HarmonyOS and Android?
Hi: Please install this amazing plugin for both VSCode and IDEA
I ran the poetic code written by Lei Jun in 1994!
5T technology resources are being released! Including but not limited to: C/C++, Linux, Python, Java, PHP, Artificial Intelligence, Microcontrollers, Raspberry Pi, etc. Reply ‘1024’ in the public account to get it for free!
