from the Data Deluge? A case for file filtering in eBPF Giulia Frascaria October 28, 2020 1 The data deluge on modern storage 2 Compute node CPU Network Storage node Flash The data deluge on CPU Network Storage node Flash Data DoS in reverse! 11 Compute node CPU Network Storage node Flash Data So similar yet so different ● DoS is malicious ● Data transfer is business-critical ● We 12 So similar yet so different ● DoS is malicious ● Data transfer is business-critical ● We can blindly drop DoS 13 But could we reduce data transfer size? eBPF filter-reduce 14 Filter Reduce input

closed loop, realizing a complete, transparent software supply chain management. Intel Linaro Red Hat AMD Google Huawei Contribution to Linux Kernel Patches 2500 2000 1500 1000 500 0 5.1 5.2 5 evaluation, and various development tools such as secPaver, to simplify security configuration. Data center Cloud native Edge HPC Embedded/Industrial … CPU: x86, ARM, RISC-V DPU NPU Media Bus Server codes (PACs): The register value is authenticated before being used as a pointer to access the data or code, so as to defend against return-oriented programming (ROP) and jump-oriented programming

Cilium Hubble Important common packages Debugging toFQDNs and DNS Debugging Mutexes / Locks and Data Races Hubble Bumping the vendored Cilium dependency Release Management Organization Release tracking Cilium’s eBPF implementation is optimized for maximum performance, can be attached to XDP (eXpress Data Path), and supports direct server return (DSR) as well as Maglev consistent hashing if the load balancing issues you can delete aws-node DaemonSet prior to installing Cilium. OpenShift To install Cilium on OpenShift [https://www.openshift.com/], perform the following steps: Default Configuration: Datapath

Cilium Hubble Important common packages Debugging toFQDNs and DNS Debugging Mutexes / Locks and Data Races Release Management Organization Release tracking Release Cadence Backporting process Backport run in standalone mode or as a cluster making it a great choice for local testing with multi-node data paths. Agent nodes are joined to the master node using a node-token which can be found on the master etcd Installation with external etcd Installation on Microsoft Azure Cloud (beta) Installation on OpenShift OKD Quick Installation This guides takes you through the quick installation procedure. The default

Cilium Hubble Important common packages Debugging toFQDNs and DNS Debugging Mutexes / Locks and Data Races Hubble Bumping the vendored Cilium dependency Documentation Style Header Titles Body Code Cilium’s eBPF implementation is optimized for maximum performance, can be attached to XDP (eXpress Data Path), and supports direct server return (DSR) as well as Maglev consistent hashing if the load balancing issues you can delete aws-node DaemonSet prior to installing Cilium. OpenShift To install Cilium on OpenShift [https://www.openshift.com/], perform the following steps: Default Configuration: Datapath

Cilium Hubble Important common packages Debugging toFQDNs and DNS Debugging Mutexes / Locks and Data Races Hubble Bumping the vendored Cilium dependency Release Management Organization Release tracking Cilium’s eBPF implementation is optimized for maximum performance, can be attached to XDP (eXpress Data Path), and supports direct server return (DSR) as well as Maglev consistent hashing if the load balancing open http://localhost:12000/ to access the UI. Hubble UI is not the only way to get access to Hubble data. A command line tool, the Hubble CLI, is also available. It can be installed by following the instructions

Photos ...................... 238 7.2.3. Organising Photos .................. 239 7.2.4. Removing Red Eye ................. 240 7.3. The GIMP ........................................ 242 7.4. Drawing architecture. In August 1991, Linus Benedict Torvalds, a Finnish second-year student of computer science at the University of Helsinki, started working on Minix. 4 Chapter 1. Introducing Ubuntu Ubuntu applications Data Storage • Easy to upgrade and downgrade • User data stored in home directory • Easy to migrate and replicate user data and configuration to another computer • User data saved in multiple

2015/06/26 7.1 认识 Linux 文件系统 7.1.1 磁盘组成与分区的复习 7.1.2 文件系统特性： 索引式文件系统 7.1.3 Linux 的 EXT2 文件系统（inode）: data block, superblock,dumpe2fs 7.1.4 与目录树的关系 7.1.5 EXT2/EXT3 文件的存取与日志式文件系统的功能 7.1.6 Linux 文件系统的运行 DRAM根据技术的更新又分好几代，而使用上较广泛的有所谓的SDRAM与DDR SDRAM两 种。 这两种内存的差别除了在于脚位与工作电压上的不同之外，DDR是所谓的双倍数据传送 速度（Double Data Rate）， 他可以在一次工作周期中进行两次数据的传送，感觉上就好像 鸟哥的 Linux 私房菜：基础学习篇 第四版 46 0.2 个人电脑架构与相关设备元件 是CPU的倍频啦！ 所以传输 wikipedia.org/wiki/中央处 理器）。 [4]图片参考： Wiki book: http://en.wikibooks.org/wiki/IB/Group_4/Computer_Science/Computer_Organisation 作 者：陈锦辉，“计算机概论-探索未来2008”，金禾信息，2007出版 [5]更详细的RISC架构可以参考维基百科： http://zh.wikipedia

DRAM根据技术的更新又分好几代，而使用上较广泛的有所谓的SDRAM与DDR SDRAM两种。 这两种内存的差别除了在 于脚位与工作电压上的不同之外，DDR是所谓的双倍数据传送速度（Double Data Rate）， 他可以在一次工作周 期中进行两次数据的传送，感觉上就好像是CPU的倍频啦！ 所以传输频率方面比SDRAM还要好。新一代的PC大多使用 DDR内存了。 下表列出SDRAM与DDR wikipedia.org/wiki/中央处 理器）。 [4]图片参考：Wiki book: http://en.wikibooks.org/wiki/IB/Group_4/Computer_Science/Computer_Organisation作 者：陈锦辉，“计算机概论-探索未来2008”，金禾信息，2007出版 [5]更详细的RISC架构可以参考维基百科：http://zh.wikipedia 装，也是一个很不错的方式的！ 各大Linux Distributions的主要异同：支持标准！ 不过，由于发展Linux distributions的社群与公司实在太多了，例如在台湾有名的Red Hat, SuSE, Ubuntu, Fedora, Debian等等，所以很多人都很担心，如此一来每个distribution是否都不相同呢？ 这 就不需要担心了，因为每个Linux distr

woody). We show that Debian 3.0 includes more than 105,000,000 physical SLOC (almost twice than Red Hat 9, released about 8 months later), showing that the Debian development model (based on the work of other development methods (like the more centralized one, based on the work of employees, used by Red Hat or Microsoft) to manage distributions of this size. It is also shown that if Debian had been developed fine paper [Wheeler2001]. We encourage the reader to at least browse it, and compare the data it offers for Red Hat Linux with those found here. The structure of this paper is as follows. Next section provides