Per default dCache xrootd is restricted to read-only, because plain xrootd is completely unauthenticated. A typical error message on the clientside if the server is read-only looks like:

 [user] $ xrdcp -d 1 /bin/sh root://ford.desy.de//pnfs/desy.de/data/xrd_test2
Setting debug level 1
061024 18:43:05 001 Xrd: main: (C) 2004 SLAC INFN xrdcp 0.2 beta
061024 18:43:05 001 Xrd: Create: (C) 2004 SLAC INFN XrdClient kXR_ver002+kXR_asyncap
061024 18:43:05 001 Xrd: ShowUrls: The converted URLs count is 1
061024 18:43:05 001 Xrd: ShowUrls: URL n.1: root://ford.desy.de:1094//pnfs/desy.de/data/asdfas.
061024 18:43:05 001 Xrd: Open: Access to server granted.
061024 18:43:05 001 Xrd: Open: Opening the remote file /pnfs/desy.de/data/asdfas
061024 18:43:05 001 Xrd: XrdClient::TryOpen: doitparallel=1
061024 18:43:05 001 Xrd: Open: File open in progress.
061024 18:43:06 5819 Xrd: SendGenCommand: Server declared: Permission denied. Access is read only.(error code: 3003)
061024 18:43:06 001 Xrd: Close: File not opened.
Error accessing path/file for root://ford//pnfs/desy.de/data/asdfas

To enable read-write access, add the following line to ${dCacheHome}/etc/dcache.conf

..
xrootdIsReadOnly=false
..

and restart any domain(s) running a xrootd door.

Please note that due to the unauthenticated nature of this access mode, files can be written and read to/from any subdirectory in the pnfs namespace (including the automatic creation of parent directories). If there is no user information at the time of request, new files/subdirectories generated through xrootd will inherit UID/GID from its parent directory. The user used for this can be configured via the xrootd.authz.user property.

To overcome the security issue of uncontrolled xrootd read and write access mentioned in the previous section, it is possible to restrict read and write access on a per-directory basis (including subdirectories).

To activate this feature, a colon-seperated list containing the full paths of authorized directories must be added to /etc/dcache/dcache.conf. You will need to specify the read and write permissions separately.

..
xrootd.authz.read-paths=/pnfs/<example.org>/rpath1:/pnfs/<example.org>/rpath2
xrootd.authz.write-paths=/pnfs/<example.org>/wpath1:/pnfs/<example.org>/wpath2
..

A restart of the xrootd door is required to make the changes take effect. As soon as any of the above properties are set, all read or write requests to directories not matching the allowed path lists will be refused. Symlinks are however not restricted to these prefixes.

The xrootd dCache implementation includes a generic mechanism to plug in different authorization handlers. The only plugin available so far implements token-based authorization as suggested in http://people.web.psi.ch/feichtinger/doc/authz.pdf.

The first thing to do is to setup the keystore. The keystore file basically specifies all RSA-keypairs used within the authorization process and has exactly the same syntax as in the native xrootd tokenauthorization implementation. In this file, each line beginning with the keyword KEY corresponds to a certain Virtual Organisation (VO) and specifies the remote public (owned by the file catalogue) and the local private key belonging to that VO. A line containing the statement "KEY VO:*" defines a default keypair that is used as a fallback solution if no VO is specified in token-enhanced xrootd requests. Lines not starting with the KEY keyword are ignored. A template can be found in /usr/share/dcache/examples/xrootd/keystore.

The keys itself have to be converted into a certain format in order to be loaded into the authorization plugin. dCache expects both keys to be binary DER-encoded (Distinguished Encoding Rules for ASN.1). Furthermore the private key must be PKCS #8-compliant and the public key must follow the X.509-standard.

The following example demonstrates how to create and convert a keypair using OpenSSL:

Generate new RSA private key
[root] # openssl genrsa -rand 12938467 -out key.pem 1024

Create certificate request
[root] # openssl req -new -inform PEM -key key.pem -outform PEM -out certreq.pem

Create certificate by self-signing certificate request
[root] # openssl x509 -days 3650 -signkey key.pem -in certreq.pem -req -out cert.pem

Extract public key from certificate
[root] # openssl x509 -pubkey -in cert.pem -out pkey.pem
[root] # openssl pkcs8 -in key.pem -topk8 -nocrypt -outform DER -out <new_private_key>
[root] # openssl enc -base64 -d -in pkey.pem -out <new_public_key>

Only the last two lines are performing the actual conversion, therefore you can skip the previous lines in case you already have a keypair. Make sure that your keystore file correctly points to the converted keys.

To enable the plugin, it is necessary to add the following two lines to the file /etc/dcache/dcache.conf, so that it looks like

..
	xrootdAuthzPlugin=org.dcache.xrootd.security.plugins.tokenauthz.TokenAuthorizationFactory
	xrootdAuthzKeystore=<Path_to_your_Keystore>
	..

After doing a restart of dCache, any requests without an appropriate token should result in an error saying "authorization check failed: No authorization token found in open request, access denied.(error code: 3010)".

If both tokenbased authorization and read-only access are activated, the read-only restriction will dominate (local settings have precedence over remote file catalogue permissions).

The xrootd-implementation in dCache includes a pluggable authentication framework. To control which authentication mechanism is used by xrootd, add the xrootdAuthNPlugin option to your dCache configuration and set it to the desired value.

..
xrootdAuthNPlugin=gsi
..

..
dcache.authn.hostcert.verify=true
..

Authorization of the user information obtained by strong authentication is performed by contacting the gPlazma service. Please refer to Chapter 10, Authorization in dCache for instructions about how to configure gPlazma.

The previously explained methods to restrict access via xrootd can also be used together. The precedence applied in that case is as following:

The permission check executed by the authorization plugin (if one is installed) is given the lowest priority, because it can controlled by a remote party. E.g. in the case of token based authorization, access control is determined by the file catalogue (global namespace).

The same argument holds for many strong authentication mechanisms - for example, both the GSI protocol as well as the Kerberos protocols require trust in remote authorities. However, this only affects user authentication, while authorization decisions can be adjusted by local site administrators by adapting the gPlazma configuration.

To allow local site’s administrators to override remote security settings, write access can be further restricted to few directories (based on the local namespace, the pnfs). Setting xrootd access to read-only has the highest priority, overriding all other settings.

The xrootd-door has several other configuration properties. You can configure various timeout parameters, the thread pool sizes on pools, queue buffer sizes on pools, the xrootd root path, the xrootd user and the xrootd IO queue. Full descriptions on the effect of those can be found in /usr/share/dcache/defaults/xrootd.properties.