# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User Nate Coraor <nate@bx.psu.edu> # Date 1277996648 14400 # Node ID e7678fd94340e969552c8cea825bc2a2cbace68e # Parent 9dc53a421c64732b11637f6e5698f82b0196f772 Restructure and document the sample config file. --- a/lib/galaxy/web/buildapp.py +++ b/lib/galaxy/web/buildapp.py @@ -154,13 +154,13 @@ def wrap_in_middleware( app, global_conf # performance if debug: # Middleware to check for WSGI compliance - if asbool( conf.get( 'use_lint', True ) ): + if asbool( conf.get( 'use_lint', False ) ): from paste import lint app = lint.make_middleware( app, conf ) log.debug( "Enabling 'lint' middleware" ) # Middleware to run the python profiler on each request if asbool( conf.get( 'use_profile', False ) ): - import profile + from paste.debug import profile app = profile.ProfileMiddleware( app, conf ) log.debug( "Enabling 'profile' middleware" ) # Middleware that intercepts print statements and shows them on the --- a/universe_wsgi.ini.sample +++ b/universe_wsgi.ini.sample @@ -1,120 +1,173 @@ +# +# Galaxy is configured by default to be useable in a single-user development +# environment. To tune the application for a multi-user production +# environment, see the documentation at: +# +# http://bitbucket.org/galaxy/galaxy-central/wiki/Config/ProductionServer +# + +# Throughout this sample configuration file, except where stated otherwise, +# uncommented values override the default if left unset, whereas commented +# values are set to the default value. +# examples of many of these options are explained in more detail in the wiki: +# +# Config hackers are encouraged to check there before asking for help. + # ---- HTTP Server ---------------------------------------------------------- +# Configuration of the internal HTTP server. + [server:main] +# The internal HTTP server to use. Currently only Paste is provided. This +# option is required. use = egg:Paste#http -port = 8080 -host = 127.0.0.1 -use_threadpool = true -threadpool_workers = 10 -# ---- HTTP gzip compression ---- -# If planning to run Galaxy as a production service, we recommend running Galaxy -# through a proxy and enabling gzip compression there (instructions at -# http://bitbucket.org/galaxy/galaxy-central/wiki/Config/ProductionServer ) -# but you may also turn on Paste's built-in gzip compressor by uncommenting the following lines -# and also the 'filter-with = gzip' line under [app:main]. This will reduce network traffic -# and should speed up the interface, especially the visualization module. -# [filter:gzip] -# use = egg:Paste#gzip +# The port on which to listen. +#port = 8080 -# ---- Galaxy Web Interface ------------------------------------------------- +# The address on which to listen. By default, only listen to localhost (Galaxy +# will not be accessible over the network). Use '0.0.0.0' to listen on all +# available network interfaces. +#host = 127.0.0.1 + +# Use a threadpool for the web server instead of creating a thread for each +# request. +use_threadpool = True + +# Number of threads in the web server thread pool. +#threadpool_workers = 10 + +# ---- Filters -------------------------------------------------------------- + +# Filters sit between Galaxy and the HTTP server. + +# These filters are disabled by default. They can be enabled with +# 'filter-with' in the [app:main] section below. + +# Define the gzip filter. +[filter:gzip] +use = egg:Paste#gzip + +# Define the proxy-prefix filter. +[filter:proxy-prefix] +use = egg:PasteDeploy#prefix +prefix = /galaxy + +# ---- Galaxy --------------------------------------------------------------- + +# Configuration of the Galaxy application. + [app:main] -# Uncomment following line to enable Paste gzip compression -# filter-with = gzip +# -- Application and filtering -# Uncomment following line below to enable visualization module -# enable_tracks = True - -# Specifies the factory for the universe WSGI application +# The factory for the WSGI application. This should not be changed. paste.app_factory = galaxy.web.buildapp:app_factory -# By default, Galaxy uses a SQLite database found here -database_file = database/universe.sqlite +# If not running behind a proxy server, you may want to enable gzip compression +# to decrease the size of data transferred over the network. If using a proxy +# server, please enable gzip compression there instead. +#filter-with = gzip -# You may use a SQLAlchemy connection string to specify an external database -# instead. PostgreSQL and MySQL are supported. -#database_connection = postgres:///galaxy -#database_engine_option_echo = true -#database_engine_option_echo_pool = true -#database_engine_option_pool_size = 10 -#database_engine_option_max_overflow = 20 +# If running behind a proxy server and Galaxy is served from a subdirectory, +# enable the proxy-prefix filter and set the prefix in the +# [filter:proxy-prefix] section above. +#filter-with = proxy-prefix -# If using MySQL, see: -# http://rapd.wordpress.com/2008/03/02/sqlalchemy-sqlerror-operationalerror-20... -# To handle this issue, try the following setting: -#database_engine_option_pool_recycle = 7200 +# -- Database -# Where dataset files are saved -file_path = database/files -# Temporary storage for additional datasets, this should be shared through the cluster -new_file_path = database/tmp +# By default, Galaxy uses a SQLite database at 'database/universe.sqlite'. You +# may use a SQLAlchemy connection string to specify an external database +# instead. This string takes many options which are explained in detail in the +# config file documentation. +#database_connection = sqlite:///./database/universe.sqlite?isolation_level=IMMEDIATE -# Tools -tool_config_file = tool_conf.xml -tool_path = tools -tool_data_path = tool-data +# If the server logs errors about not having enough database pool connections, +# you will want to increase these values, or consider running more Galaxy +# processes. +#database_engine_option_pool_size = 5 +#database_engine_option_max_overflow = 10 -# Datatype converters -datatype_converters_config_file = datatype_converters_conf.xml -datatype_converters_path = %(here)s/lib/galaxy/datatypes/converters +# If using MySQL and the server logs the error "MySQL server has gone away", +# you will want to set this to some positive value (7200 should work). +#database_engine_option_pool_recycle = -1 -# Datatype indexers -datatype_indexers_path = %(here)s/lib/galaxy/datatypes/indexers -# Metadata -set_metadata_externally = False +# -- Files and directories -# Session support (beaker) -use_beaker_session = True -session_type = file -session_data_dir = %(here)s/database/beaker_sessions -session_key = galaxysessions -session_secret = changethisinproduction +# Dataset files are stored in this directory. +#file_path = database/files -# Galaxy session security -id_secret = changethisinproductiontoo +# Temporary files are stored in this directory. +#new_file_path = database/tmp -# Directories of files contained in the following directory can be uploaded to -# a library from the Admin view -#library_import_dir = /var/opt/galaxy/import +# Tool config file, defines what tools are available in Galaxy. +#tool_config_file = tool_conf.xml -# The following can be configured to allow non-admin users to upload a -# directory of files. The configured directory must contain sub-directories -# named the same as the non-admin user's Galaxy login ( email ). The non-admin -# user is restricted to uploading files or sub-directories of files contained -# in their directory. -#user_library_import_dir = /var/opt/galaxy/import/users +# Path to the directory containing the tools defined in the config. +#tool_path = tools -# The admin library upload tool may contain a box allowing admins to paste -# filesystem paths to files and directories to add to a library. Set to True -# to enable. Please note the security implication that this will give Galaxy -# Admins access to anything your Galaxy user has access to. -#allow_library_path_paste = False +# Directory where data used by tools is located, see the samples in that +# directory and the wiki for help: +# http://bitbucket.org/galaxy/galaxy-central/wiki/DataIntegration +#tool_data_path = tool-data -# path to sendmail -sendmail_path = /usr/sbin/sendmail +# Datatypes config file, defines what data (file) types are available in +# Galaxy. +#datatypes_config_file = datatypes_conf.xml -# Address to join mailing list -mailing_join_addr = galaxy-user-join@bx.psu.edu +# -- Mail and notification -# For use by 'report this error' link on error-state datasets -#smtp_server = smtp.example.org -#error_email_to = galaxy-bugs@example.org +# Galaxy sends mail for various things: Subscribing users to the mailing list +# if they request it, emailing password resets, notification from the Galaxy +# Sample Tracking system, and reporting dataset errors. To do this, it needs +# to send mail through an SMTP server, which you may define here. +#smtp_server = None -# Use the new iframe / javascript based layout -use_new_layout = true +# On the user registration form, users may choose to join the mailing list. +# This is the address of the list they'll be subscribed to. +#mailing_join_addr = galaxy-user-join@bx.psu.edu -# Comma separated list of UCSC / gbrowse / GeneTrack browsers to use for viewing -ucsc_display_sites = main,test,archaea,ucla -gbrowse_display_sites = wormbase,tair,modencode_worm,modencode_fly -# Define your GeneTrack servers in tool-data/shared/genetrack/genetrack_sites.txt -#genetrack_display_sites = +# Datasets in an error state include a link to report the error. Those reports +# will be sent to this address. Error reports are disabled if no address is set. +#error_email_to = None -# Enable the (experimental! beta!) Web API. Documentation forthcoming. -#enable_api = False +# -- Display sites -# Serving static files (needed if running standalone) +# Galaxy can display data at various external browsers. These options specify +# which browsers should be available. URLs and builds available at these +# browsers are defined in the specifield files. + +# UCSC browsers: tool-data/shared/ucsc/ucsc_build_sites.txt +#ucsc_display_sites = main,test,archaea,ucla + +# GBrowse servers: tool-data/shared/gbrowse/gbrowse_build_sites.txt +#gbrowse_display_sites = wormbase,tair,modencode_worm,modencode_fly + +# GeneTrack servers: tool-data/shared/genetrack/genetrack_sites.txt +#genetrack_display_sites = main,test + +# -- UI Localization + +# Append "/{brand}" to the "Galaxy" text in the masthead. +#brand = None + +# The URL linked by the "Galaxy/brand" text. +#logo_url = / + +# The URL linked by the "Galaxy Wiki" link in the "Help" menu. +#wiki_url = http://bitbucket.org/galaxy/galaxy-central/wiki + +# The URL linked by the "Email comments..." link in the "Help" menu. +#bugs_email = None + +# The URL linked by the "How to Cite..." link in the "Help" menu. +#citation_url = http://bitbucket.org/galaxy/galaxy-central/wiki/Citations + +# Serve static content, which must be enabled if you're not serving it via a +# proxy server. These options should be self explanatory and so are not +# documented individually. You can use these paths (or ones in the proxy +# server) to point to your own styles. static_enabled = True static_cache_time = 360 static_dir = %(here)s/static/ @@ -123,94 +176,142 @@ static_favicon_dir = %(here)s/static/fav static_scripts_dir = %(here)s/static/scripts/ static_style_dir = %(here)s/static/june_2007_style/blue -## Leave these commented out for the defaults at the main galaxy site -## Uncomment and adjust these to change locally configurable items in the masthead -## for a local mirror where you are doing private software development -## -## Brand: appends "/[brand]" to the "Galaxy" text in the masthead -## logo_url: replaces the default "Galaxy + brand" link url -## wiki_url: replaces the default galaxy main wiki -## bugs_email: replaces the default galaxy bugs email list -##citation_url: point to a URL listing citations -#brand = Private local mirror -#logo_url = / -#wiki_url = /path/to/my/local/wiki -#bugs_email = mailto:galaxy-bugs@example.org -#citation_url = /path/to/my/citations +# -- Logging and Debugging -# ---- Logging and Debugging ------------------------------------------------ +# Verbosity of console log messages. Acceptable values can be found here: +# http://docs.python.org/library/logging.html#logging-levels +#log_level = DEBUG -# Verbosity of log messages -log_level = DEBUG +# Print database operations to the server log (warning, quite verbose!). +#database_engine_option_echo = False -# Log memory usage -log_memory_usage = False +# Print database pool operations to the server log (warning, quite verbose!). +#database_engine_option_echo_pool = False -# Log events -log_events = True +# Turn on logging of application events and some user events to the database. +#log_events = True -# Log user actions -log_actions = True +# Turn on logging of user actions to the database. Actions currently logged are +# grid views, tool searches, and use of "recently" used tools menu. The +# log_events and log_actions functionality will eventually be merged. +#log_actions = True -# Configuration for debugging middleware +# Debug enables access to various config options useful for development and +# debugging: use_lint, use_profile, use_printdebug and use_interactive. It +# also causes the files used by PBS/SGE (submission script, output, and error) +# to remain on disk after the job is complete. Debug mode is disabled if +# commented, but is uncommented by default in the sample config. debug = True -use_lint = False -# Interactive debugging - NEVER enable this on a public site +# Check for WSGI compliance. +#use_lint = False + +# Run the Python profiler on each request. +#use_profile = False + +# Intercept print statements and show them on the returned page. +#use_printdebug = True + +# Enable live debugging in your browser. This should NEVER be enabled on a +# public site. Enabled in the sample config for development. use_interactive = True -# Write thread status periodically to 'heartbeat.log' (careful, uses disk space rapidly!) +# Write thread status periodically to 'heartbeat.log', (careful, uses disk +# space rapidly!). Useful to determine why your processes may be consuming a +# lot of CPU. #use_heartbeat = False -# Enable the memory debugging interface (careful, negatively impacts server performance) +# Enable the memory debugging interface (careful, negatively impacts server +# performance). #use_memdump = False -# Profiling middleware (cProfile based) -#use_profile = False +# -- Data Libraries -# ---- Users and Security --------------------------------------------------- +# These library upload options are described in much more detail in the wiki: +# http://bitbucket.org/galaxy/galaxy-central/wiki/DataLibraries/UploadingFiles + +# Add an option to the library upload form which allows administrators to +# upload a directory of files. +#library_import_dir = None + +# Add an option to the library upload form which allows authorized +# non-administrators to upload a directory of files. The configured directory +# must contain sub-directories named the same as the non-admin user's Galaxy +# login ( email ). The non-admin user is restricted to uploading files or +# sub-directories of files contained in their directory. +#user_library_import_dir = None + +# Add an option to the admin library upload tool allowing admins to paste +# filesystem paths to files and directories in a box, and these paths will be +# added to a library. Set to True to enable. Please note the security +# implication that this will give Galaxy Admins access to anything your Galaxy +# user has access to. +#allow_library_path_paste = False + +# -- Users and Security + +# Galaxy encodes various internal values when these values will be output in +# some format (for example, in a URL or cookie). You should set a key to be +# used by the algorithm that encodes and decodes these values. It can be any +# string. If left unchanged, anyone could construct a cookie that would grant +# them access to others' sessions. +#id_secret = USING THE DEFAULT IS NOT SECURE! # User authentication can be delegated to an upstream proxy server (usually -# Apache). This is explained on the Galaxy wiki: -# -# http://g2.trac.bx.psu.edu/wiki/HowToInstall/ApacheProxy - -# Use user provided in an upstream server's $REMOTE_USER variable +# Apache). The upstream proxy should set a REMOTE_USER header in the request. +# Enabling remote user disables regular logins. For more information, see: +# http://bitbucket.org/galaxy/galaxy-central/wiki/Config/ApacheProxy #use_remote_user = False # If use_remote_user is enabled and your external authentication -# method just returns bare usernames, set a default mail domain -#remote_user_maildomain = example.org +# method just returns bare usernames, set a default mail domain to be appended +# to usernames, to become your Galaxy usernames (email addresses). +#remote_user_maildomain = None -# If use_remote_user is enabled, set a logout anchor href option -#remote_user_logout_href = /logout +# If use_remote_user is enabled, you can set this to a URL that will log your +# users out. +#remote_user_logout_href = None -# this should be a comma-separated list of valid Galaxy users -#admin_users = user1@example.org,user2@example.org +# Administrative users - set this to a comma-separated list of valid Galaxy +# users (email addresses). These users will have access to the Admin section +# of the server, and will have access to create users, groups, roles, +# libraries, and more. For more information, see: +# http://bitbucket.org/galaxy/galaxy-central/wiki/Admin/AdminInterface +#admin_users = None -# Force everyone to log in (disable anonymous access) +# Force everyone to log in (disable anonymous access). #require_login = False -# Can users register new accounts? +# Allow unregistered users to create new accounts (otherwise, they will have to +# be created by an admin). #allow_user_creation = True -# Can an admin user delete user accounts? +# Allow administrators to delete accounts. #allow_user_deletion = False -# Should default dataset access permissions be private for new users; default is False (datasets are public) -new_user_dataset_access_role_default_private = False +# By default, users' data will be public, but setting this to True will cause +# it to be private. Does not affect existing users and data, only ones created +# after this option is set. Users may still change their default back to +# public. +#new_user_dataset_access_role_default_private = False -# ---- Job Execution -------------------------------------------------------- +# -- Beta features + +# Enable Galaxy's built-in visualization module, Trackster. +#enable_tracks = False + +# Enable the (experimental! beta!) Web API. Documentation forthcoming. +#enable_api = False + +# -- Job Execution # If running multiple Galaxy processes, one can be designated as the job # runner. For more information, see: # http://bitbucket.org/galaxy/galaxy-central/wiki/Config/LoadBalancing #enable_job_running = True -# Number of concurrent jobs to run (local job runner) -#local_job_queue_workers = 5 - -# Should jobs be tracked through the database, rather than in memory +# Should jobs be tracked through the database, rather than in memory. +# Necessary if you're running the load balanced setup. #track_jobs_in_database = False # Enable job recovery (if Galaxy is restarted while cluster jobs are running, @@ -218,47 +319,50 @@ new_user_dataset_access_role_default_pri # running more than one Galaxy server using the same database. #enable_job_recovery = True -# Job queue cleanup interval in minutes. Currently only used by RoundRobin -job_queue_cleanup_interval = 30 +# Setting metadata on job outputs to in a separate process (or if using a +# cluster, on the cluster). Thanks to Python's Global Interpreter Lock and the +# hefty expense that setting metadata incurs, your Galaxy process may become +# unresponsive when this operation occurs internally. +#set_metadata_externally = False + +# Number of concurrent jobs to run (local job runner) +#local_job_queue_workers = 5 # Jobs can be killed after a certain amount of execution time. Format is in -# hh:mm:ss. Currently only implemented for PBS. Leave commented for -# unlimited. -#job_walltime = 10:00:00 +# hh:mm:ss. Currently only implemented for PBS. +#job_walltime = None -# Clustering Galaxy is not a straightforward process and requires a lot of -# pre-configuration. See the ClusteringGalaxy Wiki before attempting to set -# any of these options: -# -# http://g2.trac.bx.psu.edu/wiki/ClusteringGalaxy -# -# If running normally (without a cluster), do not change anything in this -# section. +# Clustering Galaxy is not a straightforward process and requires some +# pre-configuration. See the the wiki before attempting to set any of these +# options: +# http://bitbucket.org/galaxy/galaxy-central/wiki/Config/Cluster # Comma-separated list of job runners to start. local is always started. If # left commented, no jobs will be run on the cluster, even if a cluster URL is # explicitly defined in the [galaxy:tool_runners] section below. The runners # currently available are 'pbs' and 'sge'. -#start_job_runners = pbs +#start_job_runners = None # The URL for the default runner to use when a tool doesn't explicity define a -# runner below. For help on the cluster URL format, see the ClusteringGalaxy -# Wiki. Leave commented if not using a cluster job runner. -#default_cluster_job_runner = pbs:/// +# runner below. +#default_cluster_job_runner = local:/// # The cluster runners have their own thread pools used to prepare and finish -# jobs (so that these operations do not block normal queue operation). The -# value here is the number of worker threads available to each runner. +# jobs (so that these sometimes lengthy operations do not block normal queue +# operation). The value here is the number of worker threads available to each +# started runner. #cluster_job_queue_workers = 3 -# The PBS options are described in detail in the Galaxy Configuration section of -# the ClusteringGalaxy Wiki, and are only necessary when using file staging. +# These options are only used when using file staging with PBS. #pbs_application_server = #pbs_stage_path = #pbs_dataset_server = +# ---- Tool Job Runners ----------------------------------------------------- + # Individual per-tool job runner overrides. If not listed here, a tool will # run with the runner defined with default_cluster_job_runner. + [galaxy:tool_runners] biomart = local:/// @@ -270,8 +374,8 @@ ucsc_table_direct_archaea1 = local:/// ucsc_table_direct_test1 = local:/// upload1 = local:/// +# ---- Galaxy Message Queue ------------------------------------------------- -# Galaxy Message Queue # Galaxy uses AMQ protocol to receive messages from external sources like # bar code scanners. Galaxy has been tested against RabbitMQ AMQP implementation. # For Galaxy to receive messages from a message queue the RabbitMQ server has @@ -279,6 +383,7 @@ upload1 = local:/// # and 'port' fields should point to where the RabbitMQ server is running. [galaxy_amqp] + #host = 127.0.0.1 #port = 5672 #userid = galaxy --- a/lib/galaxy/config.py +++ b/lib/galaxy/config.py @@ -23,6 +23,7 @@ class ConfigurationError( Exception ): pass class Configuration( object ): + deprecated_options = ( 'database_file', ) def __init__( self, **kwargs ): self.config_dict = kwargs self.root = kwargs.get( 'root_dir', '.' ) @@ -31,7 +32,7 @@ class Configuration( object ): os.umask( self.umask ) # can't get w/o set, so set it back self.gid = os.getgid() # if running under newgrp(1) we'll need to fix the group of data created on the cluster # Database related configuration - self.database = resolve_path( kwargs.get( "database_file", "database/universe.d" ), self.root ) + self.database = resolve_path( kwargs.get( "database_file", "database/universe.sqlite" ), self.root ) self.database_connection = kwargs.get( "database_connection", False ) self.database_engine_options = get_database_engine_options( kwargs ) self.database_create_tables = string_as_bool( kwargs.get( "database_create_tables", "True" ) ) @@ -68,7 +69,6 @@ class Configuration( object ): self.output_size_limit = int( kwargs.get( 'output_size_limit', 0 ) ) self.job_walltime = kwargs.get( 'job_walltime', None ) self.admin_users = kwargs.get( "admin_users", "" ) - self.sendmail_path = kwargs.get('sendmail_path',"/usr/sbin/sendmail") self.mailing_join_addr = kwargs.get('mailing_join_addr',"galaxy-user-join@bx.psu.edu") self.error_email_to = kwargs.get( 'error_email_to', None ) self.smtp_server = kwargs.get( 'smtp_server', None ) @@ -80,8 +80,8 @@ class Configuration( object ): self.pbs_stage_path = kwargs.get('pbs_stage_path', "" ) self.use_heartbeat = string_as_bool( kwargs.get( 'use_heartbeat', 'False' ) ) self.use_memdump = string_as_bool( kwargs.get( 'use_memdump', 'False' ) ) - self.log_actions = string_as_bool( kwargs.get( 'log_actions', 'False' ) ) - self.log_events = string_as_bool( kwargs.get( 'log_events', 'False' ) ) + self.log_actions = string_as_bool( kwargs.get( 'log_actions', 'True' ) ) + self.log_events = string_as_bool( kwargs.get( 'log_events', 'True' ) ) self.ucsc_display_sites = kwargs.get( 'ucsc_display_sites', "main,test,archaea,ucla" ).lower().split(",") self.gbrowse_display_sites = kwargs.get( 'gbrowse_display_sites', "wormbase,tair,modencode_worm,modencode_fly" ).lower().split(",") self.genetrack_display_sites = kwargs.get( 'genetrack_display_sites', "main,test" ).lower().split(",") @@ -159,7 +159,11 @@ class Configuration( object ): raise eggs.EggNotFetchable( 'You must scramble the %s egg to use the %s job runner. Instructions are available at:\n http://bitbucket.org/galaxy/galaxy-central/wiki/Config/Cluster' % ( runner_to_egg[runner], runner ) ) except KeyError: raise Exception( 'No such job runner: %s. Please double-check the value of start_job_runners in universe_wsgi.ini' % runner ) - + # Check for deprecated options. + for key in self.config_dict.keys(): + if key in self.deprecated_options: + log.warning( "Config option '%s' is deprecated and will be removed in a future release. Please consult the latest version of the sample configuration file." % key ) + def is_admin_user( self,user ): """ Determine if the provided user is listed in `admin_users`.