This article will give a brief introduction to the basic situation of Ceph, so that readers can establish a preliminary impression of Ceph without involving technical details.
2.1 What is Ceph?
Ceph's official website, Ceph.com , defines Ceph simply and concisely with the following sentence:
“Ceph is a unified, distributed storage system designed for excellent performance, reliability and scalability.”
That is, Ceph is a unified, distributed storage system designed for excellent performance, reliability, and scalability. It should be said that this sentence really points out the essence of Ceph, and can be used as a basic starting point for understanding the design ideas and implementation mechanisms of the Ceph system. In this definition, special attention should be paid to the two modifiers of the concept of "storage system", namely "uniform" and "distributed".
Specifically, "unified" means that Ceph can provide three functions of object storage, block storage, and file system storage at the same time to simplify deployment and operation and maintenance under the premise of meeting different application needs. "Distributed" in Ceph systems means true decentralized structure and system scalability without theoretical upper limit. In practice, Ceph can be deployed on thousands of servers. As of early March 2013, the largest system deployed by Ceph in a production environment was Dreamhost's object storage business cluster, and its managed physical storage capacity was 3PB [ 1 ].
2.2 Why pay attention to Ceph?
In fact, Ceph is not a new open source project. On the contrary, from the initial release to the popularity, Ceph has gone a long way over seven years. The author believes that there are two main reasons why Ceph should be understood:
First of all, Ceph itself does have more prominent advantages.
Ceph has many advantages worth mentioning, including unified storage capacity, scalability, reliability, performance, automated maintenance, and so on. In essence, these advantages of Ceph are derived from its advanced core design ideas. The author summarizes it into eight words-"No need to look up the table, it is good." Based on this design idea, Ceph gives full play to the computing power of the storage device itself, and at the same time eliminates the dependence on a single central node of the system, thereby realizing a truly decentralized structure. Based on this design idea and structure, Ceph achieves a high degree of reliability and scalability on the one hand, and on the other hand guarantees a relatively low latency and high aggregate bandwidth for client access. Through the introduction of the follow-up content, the reader can see that almost all the excellent features of Ceph are related to this core design idea.
Second, Ceph is currently highly valued in the OpenStack community.
OpenStack is currently the most popular open source cloud operating system. According to the author's observation, the most powerful driving factor for Ceph's popularity in the past year or two is the actual needs of the OpenStack community. At present, Ceph has become one of the most popular open source storage solutions in the OpenStack community. Its actual application mainly involves block storage and object storage, and it has begun to expand into the field of file systems. The relevant situation in this part will also be introduced in subsequent articles.
2.3 The emergence and development of Ceph
Generally speaking, there are three sources of open source projects: one is the topic of Daniel ’s work in the school, the paper is published and then open source; the second is the product of Daniel in the enterprise, and the chance is that it is open source; the third is that some Daniel suddenly Appearance, and then a voter followed the open source. There are many examples of each category, and open source projects of different origins also have their own different characteristics. Specifically, the principle and technology of the first type of projects are likely to be quite unique, and Ceph is in this list. In contrast, the design and implementation of the second type of project is likely to be quite mature, and the actual deployment application opportunities in the production environment are obtained before or at the early stage of open source. This background factor is likely to have an impact on the subsequent development of an open source project.
Closer to home. The Ceph project originated from the research project of its founder Sage Weil while studying for a PhD at the University of California, Santa Cruz. The starting time of the project is 2004 [ 2 ]. At the 2006 OSDI academic conference, Sage published a paper introducing Ceph [ 3 ], and provided a download link for the Ceph project at the end of the paper. As a result, Ceph began to become widely known.
Ceph is developed using C ++ language. For a typical system project that emphasizes performance, this choice is understandable.
As an open source project, Ceph follows the LGPL agreement.
According to the information on the official website of Inktank [ 4 ], Cpeh's ecosystem participates in the following figure:
It is not difficult to see that the vendors or organizations listed in the picture have a clear cloud computing flavor.
With the increasing popularity of Ceph, Sage Weil founded Inktank in 2011 to lead Ceph development and community maintenance. Currently, the release cycle of Ceph is three months.
2.4 Sage Weil and his affairs
Before starting the follow-up technical discussions, a moderate gossip Sage Weil's life experience is really necessary, because this Xiongtai is really a young man among the young men of IT. He is involved in engineering, research, and entrepreneurship, and they are quite God-building man.
Sage's engineering capabilities naturally need not be talked about, and the OSDI in which he published the Ceph paper is also the highest-level academic conference in the field of computer operating systems. As for entrepreneurship, Sage is the co-founder of DreamHost, which was in 1997, when he had just been to college. . . Interested students can go to LinkedIn to study Sage's resume , basically want to work and work, want to go to school to go to school, want to start a business to start a business, want to read a blog to study a blog, do whatever you want, do everything you want, it is a kind of expression The urge to admire. . .
The basic situation of Ceph is introduced here. The next article will open more technical content, and first discuss the design ideas of Ceph.
