# This is the configuration file for StorageManager (SM)

[ObjectStorage]
# 'service' is the module that SM will use for cloud IO.
# Current options are "LocalStorage" and "S3".
# "LocalStorage" will use a directory on the local filesystem as if it
# were cloud storage.  "S3" is the module that uses real cloud storage.
# Both modules have their own sections below.
#
# Note, changing this after running postConfigure will leave you with an
# an inconsistent view of the data.
service = LocalStorage

# object_size is a tuneable value, but also implies a maximum capacity.
# Each file managed by StorageManager is broken into chunks of
# object_size bytes.  Each chunk is stored in the cache as a file,
# so the filesystem the cache is put on needs to have enough inodes to
# support at least cache_size/object_size files.
#
# Regarding tuning, object stores do not support modifying stored data;
# entire objects must be replaced on modification, and entire
# objects are fetched on read.  This results in read and write amplification.
#
# Network characteristics are important to consider.  If the machine is
# in the cloud and has low-latency and high-bandwidth access to the object
# store, then the limiting factor may be the get/put rate imposed by your
# cloud provider.  In that case, using a larger object size will reduce
# the number of get/put ops required to perform a task.  If the machine has
# low-bandwidth access to the object store, a lower value will reduce
# the degree of read/write amplification, reducing the total amount of data
# to transfer.
#
# Of course, you will only really know how a complex system works by
# experimentation.  If you experience poor performance using the default,
# our suggestion is to reduce it to 2M and try again, then increase it to
# 10M and try again.
#
# object_size should not be changed after you have run postConfigure.
# Things may fail that normally wouldn't.  This is a temporary limitation which
# will be addressed in later versions.
object_size = 5M

# metadata_path is where SM will put its metadata.  From the caller's
# perspective, each file will be represented by a metadata file in this
# path.  A metadata file is a small json document enumerating the objects
# that compose the file.
metadata_path = @ENGINE_DATADIR@/storagemanager/metadata

# journal_path is where SM will store deltas to apply to objects.
# If an existing object is modified, that modification (aka delta) will
# be written to a journal file corresponding to that object.  Periodically,
# those deltas will be merged with the object they apply to, resulting
# in a new object.
journal_path = @ENGINE_DATADIR@/storagemanager/journal

# max_concurrent_downloads is what is sounds like, per node.
# This is not a global setting.
max_concurrent_downloads = 21

# max_concurrent_uploads is what is sounds like, per node.
# This is not a global setting.  Currently, a file is locked while
# modifications to it are synchronized with cloud storage.  If your network
# has low upstream bandwidth, consider lowering this value to the minimum
# necessary to saturate your network.  This will reduce the latency of certain
# operations and improve your experience.
max_concurrent_uploads = 21

# common_prefix_depth is the depth of the common prefix that all files
# managed by SM have.  Ex: /var/lib/columnstore/data1, and
# /var/lib/columnstore/data2 differ at the 4th directory element,
# so they have a common prefix depth of 3.  For Columnstore, it should
# be set to the number of directories that precede the data* directories.
# The default value of 3 works with package installations, where data* would be in
# /var/lib/columnstore
#
# This value is used to manage the ownership of prefixes between
# StorageManager instances that share a filesystem.  For example,
# if you have SM data stored on a distributed filesystem for fault-tolerance
# reasons, and all nodes have it mounted, SM instances will be able to
# negotiate ownership of data from a failed instance.
common_prefix_depth = 3

[S3]
# These should be self-explanatory.  Region can be blank or commented
# if using a private cloud storage system.  Bucket has to be set to
# something though.  Obviously, do not change these after running
# postConfigure, or SM will not be able to find your data.
region = some_region
bucket = some_bucket

# Specify the endpoint to connect to if using an S3 compatible object
# store like Google Cloud Storage or IBM's Cleversafe.
# The default endpoint if left unchanged is "s3.amazonaws.com"
# The default endpoint is only valid for amazon buckets located in
# region us-east-1. All other regions require setting this to region
# specific endpoints. Format for this is usually s3.[region].amazonaws.com
# endpoint = storage.googleapis.com

# For the best performance do not specify a prefix.  It may be useful,
# however, if you must use a bucket with other data in it.  Because
# of the way object stores route data and requests, keep the
# prefix as short as possible for performance reasons.
# prefix = cs/

# Put your HMAC access keys here.  Keys can also be set through the
# environment vars AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY.
# If set, SM will use these values and ignore the envvars.
# aws_access_key_id =
# aws_secret_access_key =

# If you want StorageManager to assume an IAM role to use for its S3
# accesses, specify the name of the role in iam_role_name.  The name
# should be only the name, rather than the full path.
#
# The specified role must already exist and have permission to get, put,
# delete, and 'head' on the specified S3 bucket.
# iam_role_name =

# If an IAM role is specified, sts_endpoint and sts_region are used to specify
# which STS server & region to use to assume the role.  The default for
# sts_endpoint is 'sts.amazonaws.com', and the default for sts_region is
# 'us-east-1'.
# sts_region =
# sts_endpoint =

# If running on AWS EC2 instance the value ec2_iam_mode can be set
# 'enabled' and allow StorageManager to detect IAM role assigned
# to EC2 instances. This will then use the the temporary credentials
# provided by EC2 metadata for S3 authentication access/secret keys.
# ec2_iam_mode=enabled

# Setting use_http to 'enabled' for host to use http instead of https
# The default is use_http = disabled (https)
# use_http = enabled

# Setting ssl_verify to 'disabled' for how to not use SSL verification
# Default is ssl_verify = enabled
# ssl_verify = disabled

# libs3_debug setting controls S3 library debugging printouts
# Default is libs3_debug = disabled
# libs3_debug = disabled

# Sets the maximum time in seconds for the connection phase to take. This
# timeout only limits the connection phase, it has no impact once the connection
# is established. The default value indicating that the default libcurl
# timeout (300 seconds?) will be used.
# connect_timeout = 5.5

# Sets the maximum time in seconds for the entire transfer operation to take.
# Default (no value) - no timeout at all.
# timeout = 7.5

# The LocalStorage section configures the 'local storage' module
# if specified by ObjectStorage/service.
[LocalStorage]

# path specifies where the module should store object data.
path = @ENGINE_DATADIR@/storagemanager/fake-cloud

# introduce latency to fake-cloud operations.  Useful for debugging.
fake_latency = n

# max_latency specifies how much latency should be added to fake-cloud
# ops.  Values are randomized between 1 and max_latency in microseconds.
max_latency = 50000

[Cache]

# cache_size can be specified in terms of tera-, giga-, mega-, kilo-
# bytes using T/t G/g M/m K/k.  Drive manufacturers use a power-of-10
# notion of what that means, which means 1m = 1,000,000 bytes.  These
# settings use the programmer's power-of-2 notion, which means
# 1m = 1,048,576 bytes.
#
# This number will include space used by journal files, but does not
# include space used by metadata files.  In this version, journal data
# currently being written and downloads in progress are also not accounted
# for, so disk usage can temporarily go above this number.  You will want to
# leave a little space available on the mount for those operations.
cache_size = 2g

# Cache/path is where cached objects get stored.
path = @ENGINE_DATADIR@/storagemanager/cache