openstack/swift
Code Issues Proposed changes
60c127575b
swift/etc/object-server.conf-sample
Clay Gerrard 1d03803a85 Auditor will clean up stale rsync tempfiles 
DiskFile already fills in the _ondisk_info attribute when it tries to open
a diskfile - even if the DiskFile's fileset is not valid or deleted.
During this process the rsync tempfiles would be discovered and logged,
but no-one would attempt to clean them up - even if they were really old.

Instead of logging and ignoring unexpected files when validate a DiskFile
fileset we'll add unexpected files to the unexpected key in the
_ondisk_info attribute.

With a little bit of re-organization in the auditor's object_audit method
to get things into a single return path we can add an unconditional check
for unexpected files and remove those that are "old enough".

Since the replicator will kill any rsync processes that are running longer
than the configured rsync_timeout we know that any rsync tempfiles older
than this can be deleted.

Split unlink_older_than in common.utils into two functions to allow an
explicit list of previously discovered paths to be passed in to avoid an
extra listdir.  Since the getmtime handling already ignores OSError
there's less concern of race condition where a previous discovered
unexpected file is reaped by rsync while we're attempting to clean it up.

Update some doc on the new config option.

Closes-Bug: #1554005

Change-Id: Id67681cb77f605e3491b8afcb9c69d769e154283
2016-03-23 19:34:34 +00:00

348 lines
12 KiB
Plaintext
Raw Blame History

[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
# expiring_objects_account_name = expiring_objects
#
# Use an integer to override the number of pre-forked processes that will
# accept connections. NOTE: if servers_per_port is set, this setting is
# ignored.
# workers = auto
#
# Make object-server run this many worker processes per unique port of
# "local" ring devices across all storage policies. This can help provide
# the isolation of threads_per_disk without the severe overhead. The default
# value of 0 disables this feature.
# servers_per_port = 0
#
# 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
# The following caps the length of log lines to the value given; no limit if
# set to 0, the default.
# log_max_line_length = 0
#
# 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 =
# 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 sending a container update on object update.
# container_update_timeout = 1.0
# 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 is the total amount of seconds an object PUT/DELETE request takes at
# least. If it is faster, the object server will sleep this amount of time minus
# the already passed transaction time. This is only useful for simulating slow
# devices on storage nodes during testing and development.
# slow = 0
#
# Objects smaller than this are not evicted from the buffercache once read
# keep_cache_size = 5242880
#
# 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 SSYNC requests
# Set to 0 for unlimited
# Note that SSYNC requests are only used by the object reconstructor or the
# object replicator when configured to use ssync.
# replication_concurrency = 4
#
# Restricts incoming SSYNC requests to one per device,
# replication_currency above allowing. This can help control I/O to each
# device, but you may wish to set this to False to allow multiple SSYNC
# requests (up to the above replication_concurrency setting) per device.
# replication_one_per_device = True
#
# Number of seconds to wait for an existing replication device lock before
# giving up.
# replication_lock_timeout = 15
#
# These next two settings control when the SSYNC subrequest handler will
# abort an incoming SSYNC 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
#
# Use splice() for zero-copy object GETs. This requires Linux kernel
# version 3.0 or greater. If you set "splice = yes" but the kernel
# does not support it, error messages will appear in the object server
# logs at startup, but your object servers should continue to function.
#
# splice = no
[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
#
# daemonize = on
#
# Time in seconds to wait between replication passes
# interval = 30
# run_pause is deprecated, use interval instead
# run_pause = 30
#
# concurrency = 1
# stats_interval = 300
#
# default is rsync, alternative is ssync
# sync_method = rsync
#
# max duration of a partition rsync
# rsync_timeout = 900
#
# bandwidth limit for rsync in kB/s. 0 means unlimited
# rsync_bwlimit = 0
#
# passed to rsync for io op timeout
# rsync_io_timeout = 30
#
# Allow rsync to compress data which is transmitted to destination node
# during sync. However, this is applicable only when destination node is in
# a different region than the local one.
# NOTE: Objects that are already compressed (for example: .tar.gz, .mp3) might
# slow down the syncing process.
# rsync_compress = no
#
# Format of the rysnc module where the replicator will send data. See
# etc/rsyncd.conf-sample for some usage examples.
# rsync_module = {replication_ip}::object
#
# 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
#
# handoffs_first and handoff_delete are options for a special case
# such as disk full in the cluster. These two options SHOULD NOT BE
# CHANGED, except for such an extreme situations. (e.g. disks filled up
# or are about to fill up. Anyway, DO NOT let your drives fill up)
# handoffs_first is the flag to replicate handoffs prior to canonical
# partitions. It allows to force syncing and deleting handoffs quickly.
# If set to a True value(e.g. "True" or "1"), partitions
# that are not supposed to be on the node will be replicated first.
# handoffs_first = False
#
# handoff_delete is the number of replicas which are ensured in swift.
# If the number less than the number of replicas is set, object-replicator
# could delete local handoffs even if all replicas are not ensured in the
# cluster. Object-replicator would remove local handoff partition directories
# after syncing partition when the number of successful responses is greater
# than or equal to this number. By default(auto), handoff partitions will be
# removed when it has successfully replicated to all the canonical nodes.
# handoff_delete = auto
[object-reconstructor]
# You can override the default log routing for this app here (don't use set!):
# Unless otherwise noted, each setting below has the same meaning as described
# in the [object-replicator] section, however these settings apply to the EC
# reconstructor
#
# log_name = object-reconstructor
# log_facility = LOG_LOCAL0
# log_level = INFO
# log_address = /dev/log
#
# daemonize = on
#
# Time in seconds to wait between reconstruction passes
# interval = 30
# run_pause is deprecated, use interval instead
# run_pause = 30
#
# concurrency = 1
# stats_interval = 300
# node_timeout = 10
# http_timeout = 60
# lockup_timeout = 1800
# reclaim_age = 604800
# ring_check_interval = 15
# recon_cache_path = /var/cache/swift
# handoffs_first = False
[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
#
# Time in seconds to wait between auditor passes
# interval = 30
#
# You can set the disk chunk size that the auditor uses making it larger if
# you like for more efficient local auditing of larger objects
# disk_chunk_size = 65536
# files_per_second = 20
# concurrency = 1
# 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 =
# The auditor will cleanup old rsync tempfiles after they are "old
# enough" to delete. You can configure the time elapsed in seconds
# before rsync tempfiles will be unlinked, or the default value of
# "auto" try to use object-replicator's rsync_timeout + 900 and fallback
# to 86400 (1 day).
# rsync_tempfile_timeout = auto
# Note: Put it at the beginning of the pipleline to profile all middleware. But
# it is safer to put this after healthcheck.
[filter:xprofile]
use = egg:swift#xprofile
# This option enable you to switch profilers which should inherit from python
# standard profiler. Currently the supported value can be 'cProfile',
# 'eventlet.green.profile' etc.
# profile_module = eventlet.green.profile
#
# This prefix will be used to combine process ID and timestamp to name the
# profile data file. Make sure the executing user has permission to write
# into this path (missing path segments will be created, if necessary).
# If you enable profiling in more than one type of daemon, you must override
# it with an unique value like: /var/log/swift/profile/object.profile
# log_filename_prefix = /tmp/log/swift/profile/default.profile
#
# the profile data will be dumped to local disk based on above naming rule
# in this interval.
# dump_interval = 5.0
#
# Be careful, this option will enable profiler to dump data into the file with
# time stamp which means there will be lots of files piled up in the directory.
# dump_timestamp = false
#
# This is the path of the URL to access the mini web UI.
# path = /__profile__
#
# Clear the data when the wsgi server shutdown.
# flush_at_shutdown = false
#
# unwind the iterator of applications
# unwind = false
View Git Blame Copy Permalink