ceph cluster

First, the environment Node Overview mon:ceph-node01 ceph-node02 ceph-node03osd:ceph-node01 ceph-node02 ceph-node03mds:ceph-node01 CEPH-NODE02 operating system: Ubuntu 14.10 Each OSD host has an OSD with a usable capacity of 15GB per OSD. Second, the test process 1.

Because the kubelet itself does not support RBD commands, a kube system plugin is required:Download Plugin Quay.io/external_storage/rbd-provisioner：Https://quay.io/repository/external_storage/rbd-provisioner?tag=latesttab=tagsDownload Docker pull quay.io/external_storage/rbd-provisioner:latest on node of k8s clusterInstall only the plugin itself will error: need to install kube roles and permissions The following are:Https://github.com/kubernetes-incubator/external-storageHttps://github.com/kube

Ceph Object Gateway CRLF Vulnerability (CVE-2015-5245)Ceph Object Gateway CRLF Vulnerability (CVE-2015-5245) Release date:Updated on:Affected Systems: Ceph Ceph Description: CVE (CAN) ID: CVE-2015-5245Ceph Object Gateway is an Object Storage interface built on librados. It allows applications to access the distribute

[TOC]k8s Mount Ceph RBDk8s Mount Ceph RBD There are two ways, one is the traditional way of PVPVC, which means that the administrator needs to pre-create the relevant PV and PVC, and then the corresponding deployment or replication to mount the PVC use. After k8s 1.4, Kubernetes provides a more convenient way to dynamically create PV, that is, Storageclass. Using Storageclass, you do not have to create a fi

Thomas is my pseudonym used by the Ceph China Community Translation team, which was first published in the Ceph China community. Now reproduced to my blog, for everyone to circulateCEPH ObjectStore API IntroductionThis article was translated by the Ceph China Community-thomas, Chen School Draft.English Source: The CEPH

Summary of common Hadoop and Ceph commandsIt is very practical to summarize the commonly used Hadoop and Ceph commands.HadoopCheck whether the nm is alive. bin/yarn node list deletes the directory and hadoop dfs-rm-r/directory.Hadoop classpath allows you to view the paths of all classes.Hadoop leave safe mode method: hadoop dfsadmin-safemode leave wordcount program: generate random text bin/hadoop jar hadoo

Ceph source code analysis: Network Module Because Ceph has a long history, the network does not use the epoll model that is currently commonly used, but uses a multi-threaded model similar to MySQL. Each connection (socket) has a read thread, read data from the socket continuously. A write thread writes data to the socket. Multi-threaded implementation is simple, but the concurrency performance is not flatt

Ceph's data management begins with the Ceph client's write operation, and since Ceph uses multiple replicas and strong consistency policies to ensure data security and integrity, a write request data is written to the primary OSD first and then primary The OSD further copies the data to the secondary and other tertiary OSD and waits for their completion notification before sending the final completion confi

In the case of a network, Ubuntu installation software is very convenient, to install Ceph, also on a command to fix, want to install ceph0.72 on ubuntu14.04, because the official source of Ceph Ceph-extra does not contain ubuntu14.04 trusty package, Ceph, which uses 163 of its source, is an unwanted version, so it com

Ceph Cluster Problem Grooming Created: Linhaifeng, last modified: Yesterday 5:35 afternoon 1: Will the data be sent to the log disk and deleted immediately or delayed?Validation: Tuning Parameters#从日志到数据盘最大同步间隔间隔秒数, Default: 5Filestore Max sync interval = 15Process Analysis: A client object sent to Ceph's PG, note that the log is written to return the results, and then within 15 seconds of the

Calculation formula for PG: Calculation formula for the entire cluster PG The calculation formula for PG in each pool: Total PGs = (TOTAL_NUMBER_OF_OSD *)/Max_replication_count/pool_count The result of the settlement is taken up to the value of the n-th square of the 2. For example, the total number of OSD is 160, the number of copies of the number of 3,pool is also 3, then the result is calculated according to the above formula is 1777.7.

According to http://ovirt-china.org/mediawiki/index.php/%E5% AE %89%E8%A3%85%E9%83%A8%E7%BD%B2Ceph_Calamari The original article is as follows: Calamari is a tool for managing and monitoring CEpH clusters and provides rest APIs. The recommended deployment platform is ubuntu. This article uses centos 6.5.Installation and deployment Obtain calamari code# git clone https://github.com/ceph/calamari.git# g

0. IntroductionThis article describes how to configure the cache pool tiering. The role of the cache pool is to provide a scalable cache for caching Ceph hotspot data or for direct use as a high-speed pool. How to create a cache pool: First make a virtual bucket tree from an SSD disk,Then create a cache pool, set its crush mapping rule and related configuration, and finally associate the pool to the cache pool that you need to use.1. Build SSD bucket

Tag: Ceph Storage Umount ErrorPhenomenon: [Email protected]:~# Umount/mnt/ceph-zhangboUmount:/mnt/ceph-zhangbo: The device is busy.(In some cases lsof (8) or fuser (1)) can be foundUseful information about processes that use the deviceWorkaround:1, according to the above tips, we use Fuser to check the use of the situation[Email protected]:~# fuser-m/mnt/

As Ceph is increasingly used in various storage business processes, its performance and tuning strategy has become a topic for users to pay close attention to, one of the key factors affecting performance is the OSD storage engine implementation; The Ceph base component Rados is a strong consistent, object storage System, The storage engines supported by its OSD are as follows:The ObjectStore layer encapsul

Ceph1:VI/etc/hosts (on all nodes)127.0.0.1 localhost192.168.1.15 ceph1192.168.1.16 ceph2192.168.1.17 ceph3Ssh-keygen-Q-t rsa-f ~ /. Ssh/id_rsa-C ''-N''VI ~ /. Ssh/configHost ceph2Hostname ceph2User RootStricthostkeychecking NoHost ceph3Hostname ceph3User RootStricthostkeychecking NoSsh-copy-ID ceph2Ssh-copy-ID ceph3 To get latest CEpH-deploy: Wget-Q-o-'https: // ceph.com/git /? P = CEpH. Git; A = blob_plai

Crush Algorithm1, the purpose of crushOptimize allocation data, efficiently reorganize data, flexibly constrain object copy placement, maximize data security when hardware fails2. ProcessIn the Ceph architecture, the Ceph client is directly read and written to the Rados Object stored on the OSD, so ceph needs to go through (pool, Object) → (pool, PG) →osd set→osd

Ceph-dokan compiled using the following is compiled on the Win7 64-bit machine, running 1. Download the source code, compile can refer to the inside of the readme.md Https://github.com/ketor/ceph-dokan 2. Download TDM-GCC and install, select 32 bit (default) when installing Https://sourceforge.net/projects/tdm-gcc/files/TDM-GCC%20Installer/tdm-gcc-5.1.0-3.exe/download 3. Download and install Dokan, select v

1. Environmental descriptionWith Kolla deployed Ceph, since the OSD 0 occupies the SATA 0 channel, the system disk needs to be swapped with the OSD 0 jumper, after the jumper switch, the OSD 0 does not start properly.2, Reason analysis:Before switching jumpers, the device file of the OSD 0 is/dev/sda2, the switch jumper becomes/dev/sdc2,osd at startup,--osd-journal/dev/sda2, specifies the log device, because the log partition device name becomes/DEV/S

If you need to add a host name: OSD4 ip:192.168.0.110 OSD1. Create a directory for Mount directories and placement profiles in OSD4SSH 192.168.0.110 (this is from Mon host ssh to OSD4 host)Mkdir/ceph/osd.4Mkdir/etc/ceph2. On OSD4, format the EXT4 Sda3 partition, mount the partition.Mkfs.ext4/dev/sda3Mount-o User_xattr/dev/sda3/ceph/osd.43. The id_dsa.pub of the Mon host is copied to the OSD4 host for passwo