galaxy job runner config

# 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:runner0]

# The internal HTTP server to use.  Currently only Paste is provided.  This
# option is required.
use = egg:Paste#http

# The port on which to listen.
port = 8080

# 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 = 7

# ---- 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]

# -- Application and filtering
# The factory for the WSGI application.  This should not be changed.
paste.app_factory = galaxy.web.buildapp:app_factory

# 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

# 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 proxy-prefix is enabled and you're running more than one Galaxy instance
# behind one hostname, you will want to set this to the same path as the prefix
# in the filter above.  This value becomes the "path" attribute set in the
# cookie so the cookies from each instance will not clobber each other.
cookie_path = /galaxyp

# -- Database
# 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
database_connection = postgres://xxxxxxx:xxxxxx@localhost:5432/galaxy

# 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
database_engine_option_pool_size = 10
database_engine_option_max_overflow = 20

# 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

# If large database query results are causing memory or response time issues in
# the Galaxy process, leave the result on the server instead.  This option is
# only available for PostgreSQL and is highly recommended.
#database_engine_option_server_side_cursors = False
database_engine_option_server_side_cursors = True

# Create only one connection to the database per thread, to reduce the
# connection overhead.  Recommended when not using SQLite:
#database_engine_option_strategy = threadlocal
database_engine_option_strategy = threadlocal

# Log all database transactions, can be useful for debugging and performance
# profiling.  Logging is done via Python's 'logging' module under the qualname
# 'galaxy.model.orm.logging_connection_proxy'
#database_query_profiling_proxy = False

# -- Files and directories

# Dataset files are stored in this directory.
file_path = database/files

# Temporary files are stored in this directory.
new_file_path = database/tmp

# Tool config file, defines what tools are available in Galaxy.
tool_config_file = tool_conf.xml

# Path to the directory containing the tools defined in the config.
tool_path = tools

# 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

# Directory where chrom len files are kept, currently mainly used by trackster
len_file_path = tool-data/shared/ucsc/chrom


# Datatypes config file, defines what data (file) types are available in
# Galaxy.
datatypes_config_file = datatypes_conf.xml

# Each job is given a unique empty directory as its current working directory.
# This option defines in what parent directory those directories will be
# created.
job_working_directory = database/job_working_directory

# If using a cluster, Galaxy will write job scripts and stdout/stderr to this
# directory.
cluster_files_directory = database/pbs

# External service types config file, defines what types of external_services configurations
# are available in Galaxy.
#external_service_type_config_file = external_service_types_conf.xml

# Path to the directory containing the external_service_types defined in the config.
#external_service_type_path = external_service_types

# -- Mail and notification

# 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 (host:port).
# Galaxy will automatically try STARTTLS but will continue upon failure.
smtp_server = localhost

# If your SMTP server requires a username and password, you can provide them
# here (password in cleartext here, but if your server supports STARTTLS it
# will be sent over the network encrypted).
#smtp_username = None
#smtp_password = None

# 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

# 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 = xxxxxxxxxxxxxx

# -- Display sites

# 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
ucsc_display_sites = main

# GBrowse servers: tool-data/shared/gbrowse/gbrowse_build_sites.txt
#gbrowse_display_sites = wormbase,tair,modencode_worm,modencode_fly,yeast_sgd
gbrowse_display_sites = wormbase,tair,modencode_worm,modencode_fly,yeast_sgd

# GeneTrack servers: tool-data/shared/genetrack/genetrack_sites.txt
#genetrack_display_sites = main,test
genetrack_display_sites = main

# -- Next gen LIMS interface on top of existing Galaxy Sample/Request management code.

use_nglims = False
nglims_config_file = tool-data/nglims.yaml

# -- UI Localization

# Append "/{brand}" to the "Galaxy" text in the masthead.
brand = UF HPC

# 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
wiki_url = http://wiki.g2.bx.psu.edu/

# The URL linked by the "Email comments..." link in the "Help" menu.
bugs_email = mailto:xxxxxxxxxxxxxx

# The URL linked by the "How to Cite..." link in the "Help" menu.
#citation_url = http://bitbucket.org/galaxy/galaxy-central/wiki/Citations
citation_url = http://wiki.g2.bx.psu.edu/Citing%20Galaxy

# 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/
static_images_dir = %(here)s/static/images
static_favicon_dir = %(here)s/static/favicon.ico
static_scripts_dir = %(here)s/static/scripts/
static_style_dir = %(here)s/static/june_2007_style/blue

# -- Advanced proxy features

# For help on configuring the Advanced proxy features, see:
# http://usegalaxy.org/production

# Apache can handle file downloads (Galaxy-to-user) via mod_xsendfile.  Set
# this to True to inform Galaxy that mod_xsendfile is enabled upstream.
apache_xsendfile = True

# If using compression in the upstream proxy server, use this option to disable
# gzipping of library .tar.gz and .zip archives, since the proxy server will do
# it faster on the fly.
upstream_gzip = True

# -- 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 = INFO
log_level = DEBUG
#log_level = ERROR

# Print database operations to the server log (warning, quite verbose!).
#database_engine_option_echo = False

# Print database pool operations to the server log (warning, quite verbose!).
#database_engine_option_echo_pool = False

# Turn on logging of application events and some user events to the database.
#log_events = 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

# 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 = False
#debug = True

# Check for WSGI compliance.
#use_lint = True

# Run the Python profiler on each request.
#use_profile = True

# 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
use_interactive = False

# 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).
#use_memdump = False

# -- Data Libraries

# 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 = /galaxy/data/admin_upload

# 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 = /galaxy/incoming

# 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 may choose to download multiple files from a library in an archive.  By
# default, Galaxy allows users to select from a few different archive formats
# if testing shows that Galaxy is able to create files using these formats.
# Specific formats can be disabled with this option, separate more than one
# format with commas.  Available formats are currently 'zip', 'gz', and 'bz2'.
#disable_library_comptypes =

# Some sequencer integration features in beta allow you to automatically
# transfer datasets.  This is done using a lightweight transfer manager which
# runs outside of Galaxy (but is spawned by it automatically).  Galaxy will
# communicate with this manager over the port specified here.
#transfer_manager_port = 8163

# Search data libraries with whoosh
#enable_whoosh_library_search = True
# Whoosh indexes are stored in this directory.
#whoosh_index_dir = database/whoosh_indexes

# Search data libraries with lucene
#enable_lucene_library_search = False
# maxiumum file size to index for searching, in MB
#fulltext_max_size = 500
#fulltext_noindex_filetypes=bam,sam,wig,bigwig,fasta,fastq,fastqsolexa,fastqillumina,fastqsanger
# base URL of server providing search functionality using lucene
#fulltext_url = http://localhost:8081

# -- 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!
id_secret = xxxxxxxxxxxxxxxxxxxxxxxxxx

# User authentication can be delegated to an upstream proxy server (usually
# 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 = True
#use_remote_user = False

# If use_remote_user is enabled and your external authentication
# 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 =

# If use_remote_user is enabled, you can set this to a URL that will log your
# users out.
remote_user_logout_href = xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

# 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 = xxxxxxxxxxxxxx,xxxxxxxxxxxxxx

# Force everyone to log in (disable anonymous access).
require_login = True

# Allow unregistered users to create new accounts (otherwise, they will have to
# be created by an admin).
allow_user_creation = True

# Allow administrators to delete accounts.
#allow_user_deletion = False
allow_user_deletion = True

# Allow users to remove their datasets from disk immediately (otherwise,
# datasets will be removed after a time period specified by an administrator in
# the cleanup scripts run via cron)
allow_user_dataset_purge = True

# 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 = True

# -- Beta features

# Enable Galaxy to communicate directly with a sequencer
#enable_sequencer_communication = False

# Enable Galaxy's built-in visualization module, Trackster.
enable_tracks = True

# Enable Galaxy Pages. Pages are custom webpages that include embedded Galaxy items,
# such as datasets, histories, workflows, and visualizations; pages are useful for
# documenting and sharing multiple analyses or workflows. Pages are created using a
# WYSIWYG editor that is very similar to a word processor.
enable_pages = True

# Enable authentication via OpenID.  Allows users to log in to their Galaxy
# account by authenticating with an OpenID provider.
enable_openid = False

# Enable the (experimental! beta!) Web API.  Documentation forthcoming.
#enable_api = False

# Enable tool tags (associating tools with tags).  This has its own option
# since its implementation has a few performance implications on startup for
# large servers.
#enable_tool_tags = False

# Enable Galaxy's "Upload via FTP" interface.  You'll need to install and
# configure an FTP server (we've used ProFTPd since it can use Galaxy's
# database for authentication) and set the following two options.

# This should point to a directory containing subdirectories matching users'
# email addresses, where Galaxy will look for files.
#ftp_upload_dir = None

# This should be the hostname of your FTP server, which will be provided to
# users in the help text.
#ftp_upload_site = None

# -- 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/WebApplicationScaling
enable_job_running = True

# Should jobs be tracked through the database, rather than in memory.
# Necessary if you're running the load balanced setup.
track_jobs_in_database = True

# This enables splitting of jobs into tasks, if specified by the particular tool config.
# This is a new feature and not recommended for production servers yet.
#use_tasked_jobs = False
#local_task_queue_workers = 2

# Enable job recovery (if Galaxy is restarted while cluster jobs are running,
# it can "recover" them when it starts).  This is not safe to use if you are
# running more than one Galaxy server using the same database.
enable_job_recovery = True

# 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 = True

# Although it is fairly reliable, setting metadata can occasionally fail.  In
# these instances, you can choose to retry setting it internally or leave it in
# a failed state (since retrying internally may cause the Galaxy process to be
# unresponsive).  If this option is set to False, the user will be given the
# option to retry externally, or set metadata manually (when possible).
#retry_metadata_internally = True
retry_metadata_internally = False

# If (for example) you run on a cluster and your datasets (by default,
# database/files/) are mounted read-only, this option will override tool output
# paths to write outputs to the working directory instead, and the job manager
# will move the outputs to their proper place in the dataset directory on the
# Galaxy server after the job completes.
#outputs_to_working_directory = False

# Number of concurrent jobs to run (local job runner)
local_job_queue_workers = 10

# Jobs can be killed after a certain amount of execution time.  Format is in
# hh:mm:ss.  Currently only implemented for PBS.
#job_walltime = None

# Jobs can be killed if any of their outputs grow over a certain size (in
# bytes).  0 for no limit.
output_size_limit = 0

# 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 'drmaa'.
#start_job_runners = None
start_job_runners = pbs

# The URL for the default runner to use when a tool doesn't explicitly define a
# runner below.
#default_cluster_job_runner = local:///
default_cluster_job_runner = pbs:///galaxy/-l nodes=1:ppn=1,pmem=1gb,walltime=200:00:00

# The cluster runners have their own thread pools used to prepare and finish
# 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 = 10

# ---- 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]

upload1 = pbs:///galaxy/-l nodes=1:ppn=1,pmem=1gb,walltime=120:00:00
fastq_groomer = pbs:///galaxy/-l nodes=1:ppn=1,pmem=1gb,walltime=240:00:00
bowtie = pbs:///galaxy/-l nodes=1:ppn=5,pmem=2gb,walltime=336:00:00

#biomart = local:///
#encode_db1 = local:///
#hbvar = local:///
#microbial_import1 = local:///
#ucsc_table_direct1 = local:///
#ucsc_table_direct_archaea1 = local:///
#ucsc_table_direct_test1 = local:///
#upload1 = local:///
#biomart = pbs:///galaxy
#encode_db1 = pbs:///galaxy
#hbvar = pbs:///galaxy
#microbial_import1 = pbs:///galaxy
#ucsc_table_direct1 = pbs:///galaxy
#ucsc_table_direct_archaea1 = pbs:///galaxy
#ucsc_table_direct_test1 = pbs:///galaxy
#upload1 = pbs:///galaxy