2.10 The Zettabyte FilesystemThe Zettabyte filesystem (ZFS) is in a class of filesystems that never overwrite existing data. This type of filesystem design was pioneered at Berkeley and a production-capable implementation was released as the log-structured filesystem in 4.4BSD.The idea of a non-overwriting filesystem is sound and was picked up and greatly enhanced by Sun Microsystems, which rele..

2.9 The Fast FilesystemA regular file is a linear array of bytes and can be read and written starting at any byte in the file. The kernel distinguishes no record boundaries in regular files, although many programs recognize line-feed characters as distinguishing the ends of lines, and other programs may impose other structure. No system-related information about a file is kept in the file itself..

2.8 DevicesHistorically, the device interface was static and simple. Devices were discovered as the system was booted and did not change thereafter. A typical disk driver could be written in a few hundred lines of code. As the system has evolved, the complexity of the I/O system has increased, with the addition of new functionality. Devices may appear and later disappear while the system is runn..

2.7 I/O System OverviewThe basic model of the UNIX I/O system is a sequence of bytes that can be accessed either randomly or sequentially. There are no access methods and no control blocks in a typical UNIX user process. Different programs expect various levels of structure, but the kernel does not impose structure on I/O. For instance, the convention for text files is lines of ASCII characters ..

2.6 Memory ManagementEach process has its own private address space. The address space is initially divided into three logical segments: text, data, and stack. The text segment is read-only and contains the machine instructions of a program. The data and stack segments are both readable and writable. The data segment contains the initialized and uninitialized data portions of a program, whereas ..

2.5 Security The FreeBSD security model has been developed over 40 years of evolving application needs. The key insight is that security must be part of system design; it cannot be successfully added later. The model addresses many different goals:Support authenticated local and remote access by multiple users, as well as integration with distributed authentication and directory servicesAllow us..

Chap19. Controllers - 쿠버네티스는 여러 SW들의 집합체 * Controllers - take care of routine tasks to ensure the desired state (얌파일) of the cluster matches the observed state (현상태) - Each controller is responsible for a particular resource in the Kubernetes - 사람이 개입하는 일이 줄어듦 - 직접 손으로 입력하지 않아도, 수많은 쿠버네티스를 구성하는 SW들이 개발자가 요구하는 환경(desired state)을 observed state로 최대한 제공해야 함 / 개발자는 쿠버네티스에게 부탁함  * Label – key-value p..

Chap12. Private Multi-Node Docker / Docker in docker - Docker in docker – DinD - official but not recommended (권장 X) - 도커 안에서 다시 도커를 띄울 수 있도록 한다 + 경고가 정말 많다.     Chap13. Docker Swarm 1- 수천 수만대의 컴퓨터에서 SW 돌리기 위한 궁극적인 방법, 도커 스웜 (like 쿠버네티스) - SWARM – 떼, 구성 요소는 여러 개지만, 하나의 논리적인 군 (도커 스웜은 컨테이너들의 군) - 일일이 다 타이핑? 불가능 / 자동화된 도커 스웜 등장 -> 더 편하게 수많은 이미지와 컨테이너 컨트롤 가능- 얌파일을 커맨드라인을 통해 일꾼들에게 쫙 뿌림 – 개발자 관점 - 도커..

HEAM: Hashed Embedding Acceleration Using Processing-In-Memory https://arxiv.org/abs/2402.04032 HEAM : Hashed Embedding Acceleration using Processing-In-MemoryIn today's data centers, personalized recommendation systems face challenges such as the need for large memory capacity and high bandwidth, especially when performing embedding operations. Previous approaches have relied on DIMM-based near..

https://www.youtube.com/watch?v=PH-2FfFD2PU     # 강의 재생목록 https://youtube.com/playlist?list=PL7bmigfV0EqQw4WnD0wF-SRBYttCFeBbF&feature=shared Lightboards - Intro to Kubernetes www.youtube.comhttps://youtube.com/playlist?list=PL7bmigfV0EqQt5_pBPQ8tsZjI1w68-e0H&feature=shared Lightboards - Intro to Containers www.youtube.com     # 마이크로서비스 아키텍처https://learn.microsoft.com/ko-kr/azure/architecture/gu..