a80c720af5
For this commit, ssync is just a direct replacement for how
we use rsync. Assuming we switch over to ssync completely
someday and drop rsync, we will then be able to improve the
algorithms even further (removing local objects as we
successfully transfer each one rather than waiting for whole
partitions, using an index.db with hash-trees, etc., etc.)
For easier review, this commit can be thought of in distinct
parts:
1) New global_conf_callback functionality for allowing
services to perform setup code before workers, etc. are
launched. (This is then used by ssync in the object
server to create a cross-worker semaphore to restrict
concurrent incoming replication.)
2) A bit of shifting of items up from object server and
replicator to diskfile or DEFAULT conf sections for
better sharing of the same settings. conn_timeout,
node_timeout, client_timeout, network_chunk_size,
disk_chunk_size.
3) Modifications to the object server and replicator to
optionally use ssync in place of rsync. This is done in
a generic enough way that switching to FutureSync should
be easy someday.
4) The biggest part, and (at least for now) completely
optional part, are the new ssync_sender and
ssync_receiver files. Nice and isolated for easier
testing and visibility into test coverage, etc.
All the usual logging, statsd, recon, etc. instrumentation
is still there when using ssync, just as it is when using
rsync.
Beyond the essential error and exceptional condition
logging, I have not added any additional instrumentation at
this time. Unless there is something someone finds super
pressing to have added to the logging, I think such
additions would be better as separate change reviews.
FOR NOW, IT IS NOT RECOMMENDED TO USE SSYNC ON PRODUCTION
CLUSTERS. Some of us will be in a limited fashion to look
for any subtle issues, tuning, etc. but generally ssync is
an experimental feature. In its current implementation it is
probably going to be a bit slower than rsync, but if all
goes according to plan it will end up much faster.
There are no comparisions yet between ssync and rsync other
than some raw virtual machine testing I've done to show it
should compete well enough once we can put it in use in the
real world.
If you Tweet, Google+, or whatever, be sure to indicate it's
experimental. It'd be best to keep it out of deployment
guides, howtos, etc. until we all figure out if we like it,
find it to be stable, etc.
Change-Id: If003dcc6f4109e2d2a42f4873a0779110fff16d6
206 lines
6.3 KiB
Plaintext
206 lines
6.3 KiB
Plaintext
[DEFAULT]
|
|
# bind_ip = 0.0.0.0
|
|
# bind_port = 6000
|
|
# bind_timeout = 30
|
|
# backlog = 4096
|
|
# user = swift
|
|
# swift_dir = /etc/swift
|
|
# devices = /srv/node
|
|
# mount_check = true
|
|
# disable_fallocate = false
|
|
# expiring_objects_container_divisor = 86400
|
|
#
|
|
# Use an integer to override the number of pre-forked processes that will
|
|
# accept connections.
|
|
# workers = auto
|
|
#
|
|
# Maximum concurrent requests per worker
|
|
# max_clients = 1024
|
|
#
|
|
# You can specify default log routing here if you want:
|
|
# log_name = swift
|
|
# log_facility = LOG_LOCAL0
|
|
# log_level = INFO
|
|
# log_address = /dev/log
|
|
#
|
|
# comma separated list of functions to call to setup custom log handlers.
|
|
# functions get passed: conf, name, log_to_console, log_route, fmt, logger,
|
|
# adapted_logger
|
|
# log_custom_handlers =
|
|
#
|
|
# If set, log_udp_host will override log_address
|
|
# log_udp_host =
|
|
# log_udp_port = 514
|
|
#
|
|
# You can enable StatsD logging here:
|
|
# log_statsd_host = localhost
|
|
# log_statsd_port = 8125
|
|
# log_statsd_default_sample_rate = 1.0
|
|
# log_statsd_sample_rate_factor = 1.0
|
|
# log_statsd_metric_prefix =
|
|
#
|
|
# eventlet_debug = false
|
|
#
|
|
# You can set fallocate_reserve to the number of bytes you'd like fallocate to
|
|
# reserve, whether there is space for the given file size or not.
|
|
# fallocate_reserve = 0
|
|
#
|
|
# Time to wait while attempting to connect to another backend node.
|
|
# conn_timeout = 0.5
|
|
# Time to wait while sending each chunk of data to another backend node.
|
|
# node_timeout = 3
|
|
# Time to wait while receiving each chunk of data from a client or another
|
|
# backend node.
|
|
# client_timeout = 60
|
|
#
|
|
# network_chunk_size = 65536
|
|
# disk_chunk_size = 65536
|
|
|
|
[pipeline:main]
|
|
pipeline = healthcheck recon object-server
|
|
|
|
[app:object-server]
|
|
use = egg:swift#object
|
|
# You can override the default log routing for this app here:
|
|
# set log_name = object-server
|
|
# set log_facility = LOG_LOCAL0
|
|
# set log_level = INFO
|
|
# set log_requests = true
|
|
# set log_address = /dev/log
|
|
#
|
|
# max_upload_time = 86400
|
|
# slow = 0
|
|
#
|
|
# Objects smaller than this are not evicted from the buffercache once read
|
|
# keep_cache_size = 5424880
|
|
#
|
|
# If true, objects for authenticated GET requests may be kept in buffer cache
|
|
# if small enough
|
|
# keep_cache_private = false
|
|
#
|
|
# on PUTs, sync data every n MB
|
|
# mb_per_sync = 512
|
|
#
|
|
# Comma separated list of headers that can be set in metadata on an object.
|
|
# This list is in addition to X-Object-Meta-* headers and cannot include
|
|
# Content-Type, etag, Content-Length, or deleted
|
|
# allowed_headers = Content-Disposition, Content-Encoding, X-Delete-At, X-Object-Manifest, X-Static-Large-Object
|
|
#
|
|
# auto_create_account_prefix = .
|
|
#
|
|
# A value of 0 means "don't use thread pools". A reasonable starting point is
|
|
# 4.
|
|
# threads_per_disk = 0
|
|
#
|
|
# Configure parameter for creating specific server
|
|
# To handle all verbs, including replication verbs, do not specify
|
|
# "replication_server" (this is the default). To only handle replication,
|
|
# set to a True value (e.g. "True" or "1"). To handle only non-replication
|
|
# verbs, set to "False". Unless you have a separate replication network, you
|
|
# should not specify any value for "replication_server".
|
|
# replication_server = false
|
|
#
|
|
# Set to restrict the number of concurrent incoming REPLICATION requests
|
|
# Set to 0 for unlimited
|
|
# Note that REPLICATION is currently an ssync only item
|
|
# replication_concurrency = 4
|
|
#
|
|
# These next two settings control when the REPLICATION subrequest handler will
|
|
# abort an incoming REPLICATION attempt. An abort will occur if there are at
|
|
# least threshold number of failures and the value of failures / successes
|
|
# exceeds the ratio. The defaults of 100 and 1.0 means that at least 100
|
|
# failures have to occur and there have to be more failures than successes for
|
|
# an abort to occur.
|
|
# replication_failure_threshold = 100
|
|
# replication_failure_ratio = 1.0
|
|
|
|
[filter:healthcheck]
|
|
use = egg:swift#healthcheck
|
|
# An optional filesystem path, which if present, will cause the healthcheck
|
|
# URL to return "503 Service Unavailable" with a body of "DISABLED BY FILE"
|
|
# disable_path =
|
|
|
|
[filter:recon]
|
|
use = egg:swift#recon
|
|
#recon_cache_path = /var/cache/swift
|
|
#recon_lock_path = /var/lock
|
|
|
|
[object-replicator]
|
|
# You can override the default log routing for this app here (don't use set!):
|
|
# log_name = object-replicator
|
|
# log_facility = LOG_LOCAL0
|
|
# log_level = INFO
|
|
# log_address = /dev/log
|
|
#
|
|
# vm_test_mode = no
|
|
# daemonize = on
|
|
# run_pause = 30
|
|
# concurrency = 1
|
|
# stats_interval = 300
|
|
#
|
|
# The sync method to use; default is rsync but you can use ssync to try the
|
|
# EXPERIMENTAL all-swift-code-no-rsync-callouts method. Once verified as stable
|
|
# and nearly as efficient (or moreso) than rsync, we plan to deprecate rsync so
|
|
# we can move on with more features for replication.
|
|
# sync_method = rsync
|
|
#
|
|
# max duration of a partition rsync
|
|
# rsync_timeout = 900
|
|
#
|
|
# bandwith limit for rsync in kB/s. 0 means unlimited
|
|
# rsync_bwlimit = 0
|
|
#
|
|
# passed to rsync for io op timeout
|
|
# rsync_io_timeout = 30
|
|
#
|
|
# node_timeout = <whatever's in the DEFAULT section or 10>
|
|
# max duration of an http request; this is for REPLICATE finalization calls and
|
|
# so should be longer than node_timeout
|
|
# http_timeout = 60
|
|
#
|
|
# attempts to kill all workers if nothing replicates for lockup_timeout seconds
|
|
# lockup_timeout = 1800
|
|
#
|
|
# The replicator also performs reclamation
|
|
# reclaim_age = 604800
|
|
#
|
|
# ring_check_interval = 15
|
|
# recon_cache_path = /var/cache/swift
|
|
#
|
|
# limits how long rsync error log lines are
|
|
# 0 means to log the entire line
|
|
# rsync_error_log_line_length = 0
|
|
|
|
[object-updater]
|
|
# You can override the default log routing for this app here (don't use set!):
|
|
# log_name = object-updater
|
|
# log_facility = LOG_LOCAL0
|
|
# log_level = INFO
|
|
# log_address = /dev/log
|
|
#
|
|
# interval = 300
|
|
# concurrency = 1
|
|
# node_timeout = <whatever's in the DEFAULT section or 10>
|
|
# slowdown will sleep that amount between objects
|
|
# slowdown = 0.01
|
|
#
|
|
# recon_cache_path = /var/cache/swift
|
|
|
|
[object-auditor]
|
|
# You can override the default log routing for this app here (don't use set!):
|
|
# log_name = object-auditor
|
|
# log_facility = LOG_LOCAL0
|
|
# log_level = INFO
|
|
# log_address = /dev/log
|
|
#
|
|
# files_per_second = 20
|
|
# bytes_per_second = 10000000
|
|
# log_time = 3600
|
|
# zero_byte_files_per_second = 50
|
|
# recon_cache_path = /var/cache/swift
|
|
|
|
# Takes a comma separated list of ints. If set, the object auditor will
|
|
# increment a counter for every object whose size is <= to the given break
|
|
# points and report the result after a full scan.
|
|
# object_size_stats =
|