Planet Ceph

Aggregated news from external sources

  • June 11, 2018
    ceph erasure默认的min_size分析

    引言 最近接触了两个集群都使用到了erasure code,一个集群是hammer版本的,一个环境是luminous版本的,两个环境都出现了incomplete,触发的原因有类似的地方,都是有osd的离线的问题 准备在本地环境进行复验的时候,发现了一个跟之前接触的erasure不同的地方,这里做个记录,以防后面出现同样的问题 分析过程 准备了一个luminous的集群,使用默认的erasure的profile进行了创建存储池的相关工作 [root@lab102 ~]# ceph osd erasure-code-profile get defaultk=2m=1plugin=jerasuretechnique=reed_sol_van 默认的是2+1的纠删码的配置,创建完了以后存储池的配置是这样的 [root@lab102 ~]# ceph osd dump|grep poolpool 1 ‘rbd’ erasure size 3 min_size 3 crush_rule 2 object_hash rjenkins pg_num 256 pgp_num 256 last_change 41 flags hashpspool stripe_width 8192 application rbdrc 然后停止了一个osd以后,状态变成了这样的 [root@lab102 ~]# ceph -s cluster: id: 9ec7768a-5e7c-4f8e-8a85-89895e338cca health: HEALTH_WARN 1 osds …Read more

  • May 30, 2018
    Storage for Data Platforms in 10 minutes

    Kyle Bader and I teamed up to deliver a quick (and hopefully painless) review of what types of storage your Big Data strategy needs to succeed alongside the better-understood (and more traditional) existing approaches to structured data. Data platform engineers need to receive support from both the Compute and the Storage infrastructure teams to deliver. …Read more

  • May 29, 2018
    cephfs元数据池故障的恢复

    前言 cephfs 在L版本已经比较稳定了,这个稳定的意义个人觉得是在其故障恢复方面的成熟,一个文件系统可恢复是其稳定必须具备的属性,本篇就是根据官网的文档来实践下这个恢复的过程 实践过程 部署一个ceph Luminous集群 [root@lab102 ~]# ceph -vceph version 12.2.5 (cad919881333ac92274171586c827e01f554a70a) luminous (stable) 创建filestore ceph-deploy osd create lab102 –filestore –data /dev/sdb1 –journal /dev/sdb2 这里想用filestore进行测试就按上面的方法去创建osd即可 传入测试数据 doc pic vidio这里提供下载链接 链接:https://pan.baidu.com/s/19tlFi4butA2WjnPAdNEMwg 密码:ugjo 这个是网上下载的模板的数据,方便进行真实的文件的模拟,dd产生的是空文件,有的时候会影响到测试 需要更多的测试文档推荐可以从下面网站下载 视频下载: https://videos.pexels.com/popular-videos 图片下载: https://www.pexels.com/ 文档下载: http://office.mmais.com.cn/Template/Home.shtml 元数据模拟故障 跟元数据相关的故障无非就是mds无法启动,或者元数据pg损坏了,这里我们模拟的比较极端的情况,把metadata的元数据对象全部清空掉,这个基本能覆盖到最严重的故障了,数据的损坏不在元数据损坏的范畴 清空元数据存储池 for object in `rados -p metadata ls`;do rados -p metadata rm $object;done …Read more

  • May 28, 2018
    Ceph and Ceph Manager Dashboard presentations at openSUSE Conference 2018

    Last weekend, the openSUSE Conference 2018 took place in Prague (Czech Republic). Our team was present to talk about Ceph and our involvement in developing the Ceph manager dashboard, which will be available as part of the upcoming Ceph “Mimic” release. The presentations were held by Laura Paduano and Kai Wagner from our team – …Read more

  • May 24, 2018
    How to Survive an OpenStack Cloud Meltdown with Ceph

    Los Tres Caballeros —sans sombreros— descended on Vancouver this week to participate in the “Rocky” OpenStack Summit. For the assembled crowd of clouderati, Sébastien Han, Sean Cohen and yours truly had one simple question: what if your datacenter was wiped out in its entirety, but your users hardly even noticed? We have touched on the …Read more

  • May 22, 2018
    OpenStack Summit Vancouver: How to Survive an OpenStack Cloud Meltdown with Ceph

    Date: 22/05/18 Video: Source: Sebastian Han (OpenStack Summit Vancouver: How to Survive an OpenStack Cloud Meltdown with Ceph)

  • May 17, 2018
    See you at the OpenStack Summit

    Next week is the OpenStack Summit conference. I will attend and will be giving a talk How to Survive an OpenStack Cloud Meltdown with Ceph. See you there! Source: Sebastian Han (See you at the OpenStack Summit)

  • May 7, 2018
    Crypto Unleashed

    Cryptography made easy…er Cryptography does not have to be mysterious — as author of Serious Cryptography Jean-Philippe Aumasson points out. It is meant to be fiendishly complex to break, and it remains very challenging to implement (see jokes on rolling your own crypto found all over the Net), but it is well within the grasp …Read more

  • May 6, 2018
    See you at the Red Hat summit

    I will be attending the Red Hat summit as I’m co-presenting a lab. This goal of the lab is to deploy an OpenStack Hyperconverged environment (HCI) with Ceph. See you in San Francisco! Source: Sebastian Han (See you at the Red Hat summit)

  • April 30, 2018
    Ceph Nano big updates

    With its two latest versions (v1.3.0 and v1.4.0) Ceph Nano brought some nifty new functionalities that I’d like to highlight in the article. Multi cluster support This is feature is available since v1.3.0. You can now run more than a single instance of cn, you can run as many as your system allows it (CPU …Read more

  • April 11, 2018
    cosbench使用方法

    前言 cosbench的功能很强大,但是配置起来可能就有点不是太清楚怎么配置了,本篇将梳理一下这个测试的配置过程,以及一些测试注意项目,以免无法完成自己配置模型的情况 安装 cosbench模式是一个控制端控制几个driver向后端rgw发起请求 下载最新版本 https://github.com/intel-cloud/cosbench/releases/download/v0.4.2.c4/0.4.2.c4.zip [root@lab102 cosbench]# unzip 0.4.2.zip[root@lab102 cosbench]# yum install java-1.7.0-openjdk nmap-ncat 同时可以执行的workloads的个数通过下面的control参数控制 concurrency=1 默认是一个,这个为了保证单机的硬件资源足够,保持单机启用一个workload 创建一个s3用户 [root@lab101 ~]# radosgw-admin user create –uid=test1 –display-name=”test1″ –access-key=test1 –secret-key=test1{ “user_id”: “test1”, “display_name”: “test1”, “email”: “”, “suspended”: 0, “max_buckets”: 1000, “auid”: 0, “subusers”: [], “keys”: [ { “user”: “test1”, “access_key”: “test1”, “secret_key”: “test1” } ], “swift_keys”: [], …Read more

  • April 11, 2018
    ceph的ISCSI GATEWAY

    前言 最开始接触这个是在L版本的监控平台里面看到的,有个iscsi网关,但是没看到有类似的介绍,然后通过接口查询到了一些资料,当时由于有比较多的东西需要新内核,新版本的支持,所以并没有配置出来,由于内核已经更新迭代了几个小版本了,经过测试验证可以跑起来了,这里只是把东西跑起来,性能相关的对比需要根据去做 实践过程 架构图 这个图是引用的红帽的架构图,可以理解为一个多路径的实现方式,那么这个跟之前的有什么不同 主要是有个新的tcmu-runner来处理LIO TCM后端存储的用户空间端的守护进程,这个是在内核之上多了一个用户态的驱动层,这样只需要根据tcmu的标准来对接接口就可以了,而不用去直接跟内核进行交互 需要的软件 Ceph Luminous 版本的集群或者更新的版本RHEL/CentOS 7.5或者Linux kernel v4.16或者更新版本的内核其他控制软件 targetcli-2.1.fb47 or newer package ython-rtslib-2.1.fb64 or newer package cmu-runner-1.3.0 or newer package eph-iscsi-config-2.4 or newer package eph-iscsi-cli-2.5 or newer package 以上为配置这个环境需要的软件,下面为我使用的版本的软件,统一打包放在一个下载路径我安装的版本如下: kernel-4.16.0-0.rc5.git0.1targetcli-fb-2.1.fb48python-rtslib-2.1.67tcmu-runner-1.3.0-rc4ceph-iscsi-config-2.5ceph-iscsi-cli-2.6 下载链接: 链接:https://pan.baidu.com/s/12OwR5ZNtWFW13feLXy3Ezg 密码:m09k 如果环境之前有安装过其他版本,需要先卸载掉,并且需要提前部署好一个Luminous 最新版本的集群官方建议调整的参数 # ceph tell osd.* injectargs ‘–osd_client_watch_timeout 15’# ceph tell osd.* injectargs ‘–osd_heartbeat_grace 20’# ceph …Read more

Careers