DCache Workshop

From Gridkaschool


Cesare delle Fratte, Luca Mazzaferro, Christoph Anton Mitterer, Oleg Tsigenov, Christian Bernardt


dCache is one of the most used storage solutions in the WLCG consisting of over 94 PB of storage distributed world wide on >77 sites. Depending on the Persistency Model, dCache provides methods for exchanging data with backend (tertiary) Storage Systems as well as space management, pool attraction, dataset replication, hot spot determination and recovery from disk or node failures. Beside HEP specific protocols, data in dCache can be accessed via NFSv4.1 (pNFS) as well as through WebDav. dCache has steadily improved its functionality up to the point that we are becoming the DESY storage cloud provider. This means that dCache users can now access data using the OwnCloud client software with its synchronisation functionality. In addition to that users can access their data by using the same user over NFSv41, WebDAV and gridFTP, which allows for a wide range of use cases from traditional HEP storage to even HPC application.

The workshop includes theoretical sessions and practical hands-on sessions such as installation, configuration of its components, simple usage and monitoring. The basic knowledge of Unix systems is required. Please familiarise yourself with a Linux terminal and the peculiarities of a linux text editor (vi, emacs etc.).


We would like to ask every participant to bring a notebook that has an ssh client installed. Please check on your machine.

Linux and MacOS machines most of the time have an ssh client installed. Please check. Windows machine users can install a putty client (​http://the.earth.li/~sgtatham/putty/latest/x86/putty.exe).


Thursday, September 4 2014, 10:50-18:30

Time Table

10:50 Overview, held by Christoph Mitterer

A welcome and overview to the course.

10:55 Introduction To dCache, held by Christoph Anton Mitterer

Gives an overview on dCache, its history, future and application areas, its basic functionality and special features, its structure, main components, databases, protocols and data access model as well as typical cluster setups.

11:35 Puppet and dCache, held by Luca Mazzaferro and Cesare delle Fratte

This talk describes how puppet is used together with the git repository within this hands-on and gives reasons why we use it this way. We also give you the outline of what we will do to install dCache with puppet and introduces you to the first hands-on part.

11:55 dCache Installation with Puppet, held by Cesare delle Fratte and Luca Mazzaferro

Last year we described the typical installation-procedure for a dCache cluster, including its external dependencies, the core-services and the file hierarchy provider, the creation of pools as well as the configuration system. This year this procedure will be done using puppet. Luca and Cesare will guide you through the process.

12:20 Lunch
13:30 [dCache Installation with Puppet (continued)], held by Cesare delle Fratte and Luca Mazzaferro
13:55 dCache Within Grids, held by Christoph Anton Mitterer

Gives some brief notes on grid-specific concepts, techniques, tools and clients that are important for using dCache within a grid (for example the LCG) and that will be referenced in later chapters.

14:05 Access Control, held by Christoph Anton Mitterer

Gives a basic overview on the main access control systems within dCache as well as their configuration.

14:25 Data Transfers To / From dCache, held by Oleg Tsigenov

Shows two typical access methods using WebDAV http and https access. It explains how to setup dCache to get unauthorised and authorised access to dCache. We will also use of x509 certificates

15:30 Coffee break
16:00 Pool Management And Pool Selection (with exercises) , held by Oleg Tsigenov

This part will first introduce you to the theory behind choosing pools for read and write access within dCache. In the hands-on part it covers some of the concepts and means of selecting pools for client read- and write-accesses as well as their configuration.

16:50 Typical Cluster Management Tasks , held by Oleg Tsigenov

This part will introduce you to a typical administrator task of adding pools to an existing dCache, balancing the files across pools in the pool group, migrating files and decommissioning a pool. Just a typical hardware lifecycle in dCache

17:10 Updating dCache using puppet , held by Cesare delle Fratte and Luca Mazzaferro

Having installed dCache using puppet one of course also wants to update dCache in the same way. Cesare and Luca will also provide you with a how-to.

18:20 [Bonus Material]

18:30 End of the workshop

Assigned excercise machines

Host name Type Name
gks-111 dCache Server Stephane
gks-112 dCache Client
gks-113 dCache Server Mirko
gks-114 dCache Client
gks-115 dCache Server Haykuhi
gks-116 dCache Client
gks-117 dCache Server Marco A.
gks-118 dCache Client
gks-119 dCache Server WooJin
gks-120 dCache Client
gks-123 dCache Server Sina
gks-124 dCache Client
gks-125 dCache Server Lorenz
gks-126 dCache Client
gks-127 dCache Server Jernej
gks-128 dCache Client


The dcache.org main page is the starting point for all interests about dCache. Either searching for documentation or support, news or source code, everything can be found there.


Thank you German Support Team. A special thanks to D-Grid and the HGF-Alliance Physics on the Terascale for funding.