SpaceManager
is making reservations against free space
available in link
groups. The total free space in the given link
group is the sum of available spaces in all links. The
available space in each link is the sum of all sizes of
available space in all pools assinged to a given
link. Therefore for the space reservation to work correctly it
is essential that each pool belongs to one and only one link,
and each link belongs to only one link group. Link groups are
assigned several parameters that determine what kind of space
the link group corresponds to and who can make reservations
against this space.
Now that the SRM
SpaceManager
is activated you can make
a space reservation. As mentioned above you need link groups to
make a space reservation.
Login to the admin
interface and cd to the cell
SrmSpaceManager
.
[user] $
ssh -p 22224 -l admin admin.example.org
(local) admin >
cd SrmSpaceManager
Type ls link groups to get information about link groups.
(SrmSpaceManager) admin >
ls link groups
The lack of output tells you that there are no link groups. As there are no link groups, no space can be reserved.
For a general introduction about link groups see the section called “Link Groups”.
Example:
In this example we will create a link group for the VO
desy
. In order to do so we need to
have a pool, a pool group and a link. Moreover, we define
unit groups named any-store
,
world-net
and
any-protocol
. (See the section called “Types of Units”.)
Define a pool in your layout file, add it to your pool
directory and restart the poolDomain
.
[poolDomain] [poolDomain/pool] path=/srv/dcache/spacemanager-pool name=spacemanager-pool
[root] #
mkdir -p /srv/dcache/spacemanager-pool
[root] #
/usr/bin/dcache restart
In the admin interface, cd to the
PoolManager
and create a pool group, a link and a link
group.
(SrmSpaceManager) admin >
..
(local) admin >
cd PoolManager
(PoolManager) admin >
psu create pgroup spacemanager_poolGroup
(PoolManager) admin >
psu addto pgroup spacemanager_poolGroup spacemanager-pool
(PoolManager) admin >
psu removefrom pgroup default spacemanager-pool
(PoolManager) admin >
psu create link spacemanager_WriteLink any-store world-net any-protocol
(PoolManager) admin >
psu set link spacemanager_WriteLink -readpref=10 -writepref=10 -cachepref=0 -p2ppref=-1
(PoolManager) admin >
psu add link spacemanager_WriteLink spacemanager_poolGroup
(PoolManager) admin >
psu create linkGroup spacemanager_WriteLinkGroup
(PoolManager) admin >
psu set linkGroup custodialAllowed spacemanager_WriteLinkGroup true
(PoolManager) admin >
psu set linkGroup replicaAllowed spacemanager_WriteLinkGroup true
(PoolManager) admin >
psu set linkGroup nearlineAllowed spacemanager_WriteLinkGroup true
(PoolManager) admin >
psu set linkGroup onlineAllowed spacemanager_WriteLinkGroup true
(PoolManager) admin >
psu addto linkGroup spacemanager_WriteLinkGroup spacemanager_WriteLink
(PoolManager) admin >
save
(PoolManager) admin >
..
Check whether the link group is available. Note that this can take several minutes to propagate
to spacemanager
.
(local) admin >
cd SrmSpaceManager
(SrmSpaceManager) admin >
ls link groups
FLAGS CNT RESVD AVAIL FREE UPDATED NAME --rc:no 0 0 + 7278624768 = 7278624768 2011-11-28 12:12:51 spacemanager_WriteLinkGroup
The link group
spacemanager_WriteLinkGroup
was created. Here the flags indicate first
the status (- indicates that neither the expired [e] nor the released flags [r] are set),
followed by the type of reservations allowed in the link group (here replica [r], custodial [c],
nearline [n] and online [o] files; output [o] files are not allowed - see help ls
link groups for details on the format). No space reservations have been created, as
indicated by the count field. Since no space reservation has been created, no space in the
link group is reserved.
Now you need to edit the
LinkGroupAuthorization.conf
file. This
file contains a list of the link groups and all the VOs and
the VO Roles that are permitted to make reservations in a
given link group.
Specify the location of the
LinkGroupAuthorization.conf
file in the
/etc/dcache/dcache.conf
file.
spacemanager.authz.link-group-file-name=/path/to/LinkGroupAuthorization.conf
The file LinkGroupAuthorization.conf
has following syntax:
LinkGroup <NameOfLinkGroup> followed by the list of the Fully Qualified Attribute Names (FQANs). Each FQAN is on a separate line, followed by an empty line, which is used as a record separator, or by the end of the file.
FQAN is usually a string of the form
<VO>/Role=<VORole>. Both
<VO> and
<VORole> can be set to
*
, in this case all VOs or VO Roles will
be allowed to make reservations in this link group. Any line
that starts with # is a comment and may appear anywhere.
Rather than an FQAN, a mapped user name can be used. This allows clients or protocols that do not provide VOMS attributes to make use of space reservations.
#SpaceManagerLinkGroupAuthorizationFile LinkGroup <NameOfLinkGroup> /<VO>/Role=<VORole>
Note
You do not need to restart the srm
or dCache
after changing the
LinkGroupAuthorization.conf
file. The
changes will be applied automatically after a few minutes.
Use update link groups to be sure that
the LinkGroupAuthorization.conf
file
and the link groups have been updated.
(SrmSpaceManager) admin >
update link groups
Update started.
Example:
In the example above you created the link group
spacemanager_WriteLinkGroup
. Now you
want to allow members of the VO desy
with the role production
to make a
space reservation in this link group.
#SpaceManagerLinkGroupAuthorizationFile # this is comment and is ignored LinkGroup spacemanager_WriteLinkGroup # /desy/Role=production
Example:
In this more general example for a
SpaceManagerLinkGroupAuthorizationFile
members of the VO desy
with role
test
are authorized to make a space
reservation in a link group called
desy-test-LinkGroup
. Moreover, all
members of the VO desy
are authorized to
make a reservation in the link group called
desy-anyone-LinkGroup
and anyone
is authorized to make a space reservation in the link
group called default-LinkGroup
.
#SpaceManagerLinkGroupAuthorizationFile # this is a comment and is ignored LinkGroup desy-test-LinkGroup /desy/Role=test LinkGroup desy-anyone-LinkGroup /desy/Role=* LinkGroup default-LinkGroup # allow anyone :-) */Role=*
Example:
Now you can make a space reservation for the VO desy
.
(SrmSpaceManager) admin >
reserve space -owner=/desy/Role=production -desc=DESY_TEST -lifetime=10000 -lg=spacemanager_WriteLinkGroup 5MB
110000 voGroup:/desy voRole:production retentionPolicy:CUSTODIAL accessLatency:NEARLINE linkGroupId:0 size:5000000 created:Fri Dec 09 12:43:48 CET 2011 lifetime:10000000ms expiration:Fri Dec 09 15:30:28 CET 2011 description:DESY_TEST state:RESERVED used:0 allocated:0
The space token of the reservation is 110000
.
Check the status of the reservation by
(SrmSpaceManager) admin >
ls spaces -e -h
TOKEN RETENTION LATENCY FILES ALLO USED FREE SIZE EXPIRES DESCRIPTION 110000 CUSTODIAL NEARLINE 0 0B + 0B + 5.0M = 5.0M 2011-12-09 12:43:48 DESY_TEST(SrmSpaceManager) admin >
ls link groups -h
FLAGS CNT RESVD AVAIL FREE UPDATED NAME --rc:no 1 5.0M + 7.3G = 7.3G 2011-11-28 12:12:51 spacemanager_WriteLinkGroup
Here the -h
option indicates that approximate, but human readable,
byte sizes are to be used, and -e
indicates that ephemeral (time
limited) reservations should be displayed too (by default time limited reservations are
not displayed as they are often implicit reservations). As can be seen, 5 MB are now reserved in
the link group, although with approximate byte sizes, 5 MB do not make a visible difference
in the 7.3 GB total size.
You can now copy a file into that space token.
[user] $
srmcp file:////bin/sh srm://<dcache.example.org>:8443/data/world-writable/space-token-test-file -space_token=110000
Now you can check via the Webadmin Interface or the Web Interface that the
file has been copied to the pool
spacemanager-pool
.
There are several parameters to be specified for a space reservation.
(SrmSpaceManager) admin >
reserve space [-al=online|nearline] [-desc=<string>] -lg=<name> [-lifetime=<seconds>] [-owner=<user>|<fqan>] [-rp=output|replica|custodial] <size>
- [-owner=<user>|<fqan>]
The owner of the space is identified by either mapped user name or FQAN. The owner must be authorized to reserve space in the link group in which the space is to be created. Besides the dCache admin, only the owner can release the space. Anybody can however write into the space (although the link group may only allow certain storage groups and thus restrict which file system paths can be written to space reservation, which in turn limits who can upload files to it).
- [-al=<AccessLatency>]
AccessLatency
needs to match one of the access latencies allowed for the link group.- [-rp=<RetentionPolicy>]
RetentionPolicy
needs to match one of the retention policies allowed for the link group.- [-desc=<Description>]
You can chose a value to describe your space reservation.
- -lg=<LinkGroupName>
Which link group to create the reservation in.
- <size>
The size of the space reservation should be specified in bytes, optionally using a byte unit suffix using either SI or IEEE prefixes.
- [-lifetime=<lifetime]>
The life time of the space reservation should be specified in seconds. If no life time is specified, the space reservation will not expire automatically.
If a space reservation is not needed anymore it can be released with
(SrmSpaceManager) admin >
release space <spaceTokenId>
Example:
(SrmSpaceManager) admin >
reserve space -owner=/desy -desc=DESY_TEST -lifetime=600 5000000
110042 voGroup:/desy voRole:production retentionPolicy:CUSTODIAL accessLatency:NEARLINE linkGroupId:0 size:5000000 created:Thu Dec 15 12:00:35 CET 2011 lifetime:600000ms expiration:Thu Dec 15 12:10:35 CET 2011 description:DESY_TEST state:RESERVED used:0 allocated:0(SrmSpaceManager) admin >
release space 110042
110042 voGroup:/desy voRole:production retentionPolicy:CUSTODIAL accessLatency:NEARLINE linkGroupId:0 size:5000000 created:Thu Dec 15 12:00:35 CET 2011 lifetime:600000ms expiration:Thu Dec 15 12:10:35 CET 2011 description:DESY_TEST state:RELEASED used:0 allocated:0
You can see that the value for state
has
changed from RESERVED
to
RELEASED
.
If so authorized, a user can make a space reservation through
the SRM
protocol. A user is authorized to do so using the
LinkGroupAuthorization.conf
file.
In order to be able to take advantage of the virtual organization (VO) infrastructure and VO based authorization and VO based access control to the space in dCache, certain things need to be in place:
User needs to be registered with the VO.
User needs to use voms-proxy-init to create a VO proxy.
dCache needs to use
gPlazma
with modules that extract VO attributes from the user’s proxy. (See Chapter 10, Authorization in dCache, have a look atvoms
plugin and see the section called “Authentication and Authorization in dCache” for an example withvoms
.
Only if these 3 conditions are satisfied the VO based
authorization of the SpaceManager
will work.
As mentioned above dCache space
reservation functionality access control is currently
performed at the level of the link groups. Access to making
reservations in each link group is controlled by the
SpaceManagerLinkGroupAuthorizationFile
.
This file contains a list of the link groups and all the VOs and the VO Roles that are permitted to make reservations in a given link group.
When a SRM
Space Reservation request is executed, its
parameters, such as reservation size, lifetime,
access latency and retention policy as well as user’s VO
membership information is forwarded to the SRM
SpaceManager
.
Once a space reservation is created, no access control is performed, any user can store the files in this space reservation, provided he or she knows the exact space token.
A user who is given the rights in the
SpaceManagerLinkGroupAuthorizationFile
can
make a space reservation by
[user] $
srm-reserve-space -retention_policy=<RetentionPolicy> -lifetime=<lifetimeInSecs> -desired_size=<sizeInBytes> -guaranteed_size=<sizeInBytes> srm://<example.org>:8443
Space token =SpaceTokenId
and release it by
[user] $
srm-release-space srm://<example.org>:8443 -space_token=SpaceTokenId
Note
Please note that it is obligatory to specify the retention policy while it is optional to specify the access latency.
Example:
[user] $
srm-reserve-space -retention_policy=REPLICA -lifetime=300 -desired_size=5500000 -guaranteed_size=5500000 srm://srm.example.org:8443
Space token =110044
The space reservation can be released by:
[user] $
srm-release-space srm://srm.example.org:8443 -space_token=110044
If a client uses a regular grid proxy, created with
grid-proxy-init, and not a VO proxy, which
is created with the voms-proxy-init, when
it is communicating with SRM
server in dCache, then the VO
attributes can not be extracted from its credential. In this
case the name of the user is extracted from the Distinguished
Name (DN) to use name mapping. For the purposes of the space
reservation the name of the user as mapped by gplazma
is used as its VO Group name, and the VO Role is left
empty. The entry in the
SpaceManagerLinkGroupAuthorizationFile
should be:
#LinkGroupAuthorizationFile # <userName>
Edit the file /etc/dcache/dcache.conf
to enable space
reservation for non SRM
transfers.
spacemanager.enable.reserve-space-for-non-srm-transfers=true
If the spacemanager
is enabled,
spacemanager.enable.reserve-space-for-non-srm-transfers
is set to true
, and if the transfer
request comes from a door, and there was no prior space
reservation made for this file, the SpaceManager
will
try to reserve space before satisfying the request.
Possible values are true
or
false
and the default value is
false
.
This is analogous to implicit space reservations performed by the
srm
, except that these reservations are created by the
spacemanager
itself. Since an SRM
client uses a non-SRM
protocol
for the actual upload, setting the above option to true while disabling
implicit space reservations in the srm
, will still allow files
to be uploaded to a link group even when no space token is provided. Such
a configuration should however be avoided: If the srm
does not
create the reservation itself, it has no way of communicating access
latency, retention policy, file size, nor lifetime to spacemanager
.
There are a few parameters in
/usr/share/dcache/defaults/*.properties
that you might find useful for nontrivial SRM
deployment.
dcache.enable.space-reservation
tells if the space
management is activated in SRM
.
Possible values are true
and
false
. Default is true
.
Usage example:
dcache.enable.space-reservation=true
srm.enable.space-reservation.implicit
tells if
the space should be reserved for SRM
Version 1 transfers and
for SRM
Version 2 transfers that have no space token
specified.
Possible values are true
and
false
. This is enabled by default. It has no
effect if dcache.enable.space-reservation
is set to
true
.
Usage example:
srm.enable.space-reservation.implicit=true
dcache.enable.overwrite
tells SRM
and
GridFTP
servers if the overwrite is allowed. If enabled on
the SRM
node, should be enabled on all GridFTP
nodes.
Possible values are true
and
false
. Default is false
.
Usage example:
dcache.enable.overwrite=true
srm.enable.overwrite-by-default
Set this to
true
if you want overwrite to be enabled
for SRM
v1.1 interface as well as for SRM
v2.2 interface
when client does not specify desired overwrite mode. This
option will be considered only if
dcache.enable.overwrite
is set to
true
.
Possible values are true
and
false
. Default is false
.
Usage example:
srm.enable.overwrite-by-default=false
srm.db.host
tells SRM
which
database host to connect to.
Default value is localhost
.
Usage example:
srm.db.host=database-host.example.org
spaceManagerDatabaseHost
tells SpaceManager
which database host to connect to.
Default value is localhost
.
Usage example:
spaceManagerDatabaseHost=database-host.example.org
pinmanager.db.host
tells PinManager
which database host to connect to.
Default value is localhost
.
Usage example:
pinmanager.db.host=database-host.example.org
srm.db.name
tells SRM
which database
to connect to.
Default value is srm
.
Usage example:
srm.db.name=srm
srm.db.user
tells SRM
which database
user name to use when connecting to database. Do not change
unless you know what you are doing.
Default value is dcache
.
Usage example:
srm.db.user=dcache
srm.db.password
tells SRM
which
database password to use when connecting to database. The
default value is an empty
value (no password).
Usage example:
srm.db.password=NotVerySecret
srm.db.password.file
tells SRM
which
database password file to use when connecting to database. Do
not change unless you know what you are doing. It is
recommended that MD5 authentication method is used. To learn
about file format please see http://www.postgresql.org/docs/8.1/static/libpq-pgpass.html. To
learn more about authentication methods please visit http://www.postgresql.org/docs/8.1/static/encryption-options.html,
Please read "Encrypting Passwords Across A Network" section.
This option is not set by default.
Usage example:
srm.db.password.file=/root/.pgpass
srm.request.enable.history-database
enables
logging of the transition history of the SRM
request in the
database. The request transitions can be examined through the
command line interface. Activation of this option might lead
to the increase of the database activity, so if the PostgreSQL
load generated by SRM
is excessive, disable it.
Possible values are true
and
false
. Default is false
.
Usage example:
srm.request.enable.history-database=true
transfermanagers.enable.log-to-database
tells SRM
to store
the information about the remote (copy, srmCopy) transfer
details in the database. Activation of this option might lead to
the increase of the database activity, so if the PostgreSQL load
generated by SRM
is excessive, disable it.
Possible values are true
and
false
. Default is false
.
Usage example:
transfermanagers.enable.log-to-database=false
srmVersion
is not used by SRM
; it was
mentioned that this value is used by some publishing scripts.
Default is version1
.
srm.root
tells SRM
what the root
of all SRM
paths is in pnfs. SRM
will prepend path to all
the local SURL paths passed to it by SRM
client. So if the
srm.root
is set to
/pnfs/fnal.gov/THISISTHEPNFSSRMPATH
and
someone requests the read of
srm://srm.example.org:8443/file1
, SRM
will
translate the SURL path /file1
into
/pnfs/fnal.gov/THISISTHEPNFSSRMPATH/file1
. Setting
this variable to something different from /
is equivalent of performing Unix chroot for
all SRM
operations.
Default value is /
.
Usage example:
srm.root="/pnfs/fnal.gov/data/experiment"
srm.limits.parallel-streams
specifies the number of the
parallel streams that SRM
will use when performing third
party transfers between this system and remote GSI-FTP
servers, in response to SRM
v1.1 copy or SRM
V2.2 srmCopy
function. This will have no effect on srmPrepareToPut and
srmPrepareToGet command results and parameters of GridFTP
transfers driven by the SRM
clients.
Default value is 10
.
Usage example:
srm.limits.parallel-streams=20
srm.limits.transfer-buffer.size
specifies the number of bytes
to use for the in memory buffers for performing third party
transfers between this system and remote GSI-FTP
servers, in
response to SRM
v1.1 copy or SRM
V2.2 srmCopy
function. This will have no effect on srmPrepareToPut and
srmPrepareToGet command results and parameters of GridFTP
transfers driven by the SRM
clients.
Default value is 1048576
.
Usage example:
srm.limits.transfer-buffer.size=1048576
srm.limits.transfer-tcp-buffer.size
specifies the number of
bytes to use for the tcp buffers for performing third party
transfers between this system and remote GSI-FTP
servers, in
response to SRM
v1.1 copy or SRM
V2.2 srmCopy
function. This will have no effect on srmPrepareToPut and
srmPrepareToGet command results and parameters of GridFTP
transfers driven by the SRM
clients.
Default value is 1048576
.
Usage example:
srm.limits.transfer-tcp-buffer.size=1048576
srm.service.gplazma.cache.timeout
specifies the
duration that authorizations will be cached. Caching decreases
the volume of messages to the gPlazma
cell or other
authorization mechanism. To turn off caching, set the value
to 0
.
Default value is 120
.
Usage example:
srm.service.gplazma.cache.timeout=60
srm.limits.request.bring-online.lifetime
,
srm.limits.request.put.lifetime
and
srm.limits.request.copy.lifetime
specify the lifetimes of
the srmPrepareToGet (srmBringOnline) srmPrepareToPut and
srmCopy requests lifetimes in millisecond. If the system is
unable to fulfill the requests before the request lifetimes
expire, the requests are automatically garbage collected.
Default value is 14400000
(4 hours)
Usage example:
srm.limits.request.bring-online.lifetime=14400000 srm.limits.request.put.lifetime=14400000 srm.limits.request.copy.lifetime=14400000
srm.limits.request.scheduler.ready.max
and
srm.limits.request.put.scheduler.ready.max
specify the
maximum number of the files for which the transfer URLs will
be computed and given to the users in response to SRM
get
(srmPrepareToGet) and put (srmPrepareToPut) requests. The rest
of the files that are ready to be transfered are put on the
Ready
queues, the maximum length of these
queues are controlled by
srm.limits.request.scheduler.ready-queue.size
and
srm.limits.request.put.scheduler.ready-queue.size
parameters. These
parameters should be set according to the capacity of the
system, and are usually greater than the maximum number of the
GridFTP
transfers that this dCache instance GridFTP
doors can sustain.
Usage example:
srm.limits.request.scheduler.ready-queue.size=10000 srm.limits.request.scheduler.ready.max=2000 srm.limits.request.put.scheduler.ready-queue.size=10000 srm.limits.request.put.scheduler.ready.max=1000
srm.limits.request.copy.scheduler.thread.pool.size
and
transfermanagers.limits.external-transfers
.
srm.limits.request.copy.scheduler.thread.pool.size
is used to specify how many parallel
srmCopy file copies to execute simultaneously. Once the
SRM
contacted the remote SRM
system, and obtained a Transfer
URL (usually GSI-FTP
URL), it contacts a Copy Manager
module (usually RemoteGSIFTPTransferManager
), and asks it to
perform a GridFTP
transfer between the remote GridFTP
server
and a dCache pool. The maximum number of simultaneous
transfers that RemoteGSIFTPTransferManager
will support is
transfermanagers.limits.external-transfers
, therefore it is important that
transfermanagers.limits.external-transfers
is greater than or equal to
srm.limits.request.copy.scheduler.thread.pool.size
.
Usage example:
srm.limits.request.copy.scheduler.thread.pool.size=250 transfermanagers.limits.external-transfers=260
srm.enable.custom-get-host-by-address
srm.enable.custom-get-host-by-address
enables using the BNL developed
procedure for host by IP resolution if standard InetAddress
method failed.
Usage example:
srm.enable.custom-get-host-by-address=true
srm.enable.recursive-directory-creation
allows or
disallows automatic creation of directories via SRM
. Set this to true
or false
.
Automatic directory creation is allowed by default.
Usage example:
srm.enable.recursive-directory-creation=true
This option allows you to control how often the SRM
door will reload the
server’s host certificate from the filesystem. For the specified period,
the host certificate will be kept in memory. This speeds up the rate at
which the door can handle requests, but also causes it to be unaware of
changes to the host certificate (for instance in the case of renewal).
By changing this parameter you can control how long the host certificate is cached by the door and consequently how fast the door will be able to detect and reload a renewed host certificate.
Please note that the value of this parameter has to be specified in seconds.
Usage example:
hostCertificateRefreshPeriod=86400
The trustAnchorRefreshPeriod
option is similar to
hostCertificateRefreshPeriod
. It applies to the set
of CA certificates trusted by the SRM
door for signing end-entity
certificates (along with some metadata, these form so called
trust anchors).
The trust anchors are needed to make a decision about
the trustworthiness of a certificate in X.509 client
authentication. The GSI
security protocol used by SRM
builds upon
X.509 client authentication.
By changing this parameter you can control how long the set of trust anchors remains cached by the door. Conversely, it also influences how often the door reloads the set of trusted certificates.
Please note that the value of this parameter has to be specified in seconds.
Tip
Trust-anchors usually change more often than the host certificate. Thus, it might be sensible to set the refresh period of the trust anchors lower than the refresh period of the host certificate.
Usage example:
trustAnchorRefreshPeriod=3600