openstack/swift
Code Issues Proposed changes
swift/etc/account-server.conf-sample
Tim Burke ae6300af86 wsgi: Reap stale workers (after a timeout) following a reload 
Add a new tunable, `stale_worker_timeout`, defaulting to 86400 (i.e. 24
hours). Once this time elapses following a reload, the manager process
will issue SIGKILLs to any remaining stale workers.

This gives operators a way to configure a limit for how long old code
and configs may still be running in their cluster.

To enable this, the temporary reload child (which waits for the reload
to complete then closes the accept socket on all the old workers) has
grown the ability to send state to the re-exec'ed manager. Currently,
this is limited to just the set of pre-re-exec child PIDs and their
reload times, though it was designed to be reasonably extensible.

This allows the new manager to recognize stale workers as they exit
instead of logging

   Ignoring wait() result from unknown PID ...

With the improved knowledge of subprocesses, we can kick the log level
for the above message up from info to warning; we no longer expect it
to trigger in practice.

Drive-by: Add logging to ServersPerPortStrategy.register_worker_exit
that's comparable to what WorkersStrategy does.

Change-Id: I8227939d04fda8db66fb2f131f2c71ce8741c7d9
2025-01-16 13:44:21 +11:00

338 lines
13 KiB
Plaintext
Raw Permalink Blame History

[DEFAULT]
# bind_ip = 0.0.0.0
bind_port = 6202
# keep_idle = 600
# bind_timeout = 30
# backlog = 4096
# user = swift
# swift_dir = /etc/swift
# devices = /srv/node
# mount_check = true
# disable_fallocate = false
#
# 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
# 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
#
# Hashing algorithm for log anonymization. Must be one of algorithms supported
# by Python's hashlib.
# log_anonymization_method = MD5
#
# Salt added during log anonymization
# log_anonymization_salt =
#
# Template used to format logs. All words surrounded by curly brackets
# will be substituted with the appropriate values
# log_format = {remote_addr} - - [{time.d}/{time.b}/{time.Y}:{time.H}:{time.M}:{time.S} +0000] "{method} {path}" {status} {content_length} "{referer}" "{txn_id}" "{user_agent}" {trans_time:.4f} "{additional_info}" {pid} {policy_index}
#
# 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 =
#
# If you don't mind the extra disk space usage in overhead, you can turn this
# on to preallocate disk space with SQLite databases to decrease fragmentation.
# db_preallocation = off
#
# Enable this option to log all sqlite3 queries (requires python >=3.3)
# db_query_logging = off
#
# eventlet_debug = false
#
# You can set fallocate_reserve to the number of bytes or percentage of disk
# space you'd like fallocate to reserve, whether there is space for the given
# file size or not. Percentage will be used if the value ends with a '%'.
# fallocate_reserve = 1%
#
# You can set scheduling priority of processes. Niceness values range from -20
# (most favorable to the process) to 19 (least favorable to the process).
# nice_priority =
#
# You can set I/O scheduling class and priority of processes. I/O niceness
# class values are IOPRIO_CLASS_RT (realtime), IOPRIO_CLASS_BE (best-effort) and
# IOPRIO_CLASS_IDLE (idle). I/O niceness priority is a number which goes from
# 0 to 7. The higher the value, the lower the I/O priority of the process.
# Work only with ionice_class.
# ionice_class =
# ionice_priority =
[pipeline:main]
pipeline = healthcheck recon backend_ratelimit account-server
[app:account-server]
use = egg:swift#account
# You can override the default log routing for this app here:
# set log_name = account-server
# set log_facility = LOG_LOCAL0
# set log_level = INFO
# set log_requests = true
# set log_address = /dev/log
#
# You can disable REPLICATE handling (default is to allow it). When deploying
# a cluster with a separate replication network, you'll want multiple
# account-server processes running: one for client-driven traffic and another
# for replication traffic. The server handling client-driven traffic may set
# this to false. If there is only one account-server process, leave this as
# true.
# replication_server = true
#
# You can set scheduling priority of processes. Niceness values range from -20
# (most favorable to the process) to 19 (least favorable to the process).
# nice_priority =
#
# You can set I/O scheduling class and priority of processes. I/O niceness
# class values are IOPRIO_CLASS_RT (realtime), IOPRIO_CLASS_BE (best-effort) and
# IOPRIO_CLASS_IDLE (idle). I/O niceness priority is a number which goes from
# 0 to 7. The higher the value, the lower the I/O priority of the process.
# Work only with ionice_class.
# ionice_class =
# ionice_priority =
#
# You can set fallocate_reserve to the number of bytes or percentage
# of disk space you'd like kept free at all times. If the disk's free
# space falls below this value, then PUT, POST, and REPLICATE requests
# will be denied until the disk ha s more space available. Percentage
# will be used if the value ends with a '%'.
# fallocate_reserve = 1%
#
# When reloading servers with SIGUSR1, workers running with old config/code
# are allowed some time to finish serving in-flight requests. Use this to
# configure the grace period (in seconds), after which the reloaded server
# will issue SIGKILLs to remaining stale workers.
# stale_worker_timeout = 86400
[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
[filter:backend_ratelimit]
use = egg:swift#backend_ratelimit
# Config options can optionally be loaded from a separate config file. Config
# options in this section will be used unless the same option is found in the
# config file, in which case the config file option will be used. See the
# backend-ratelimit.conf-sample file for details of available config options.
# backend_ratelimit_conf_path = /etc/swift/backend-ratelimit.conf
# The minimum interval between attempts to reload any config file at
# backend_ratelimit_conf_path while the server is running. A value of 0 means
# that the file is loaded at start-up but not subsequently reloaded. Note that
# config options in this section are never reloaded after start-up.
# config_reload_interval = 60
[account-replicator]
# You can override the default log routing for this app here (don't use set!):
# log_name = account-replicator
# log_facility = LOG_LOCAL0
# log_level = INFO
# log_address = /dev/log
#
# Maximum number of database rows that will be sync'd in a single HTTP
# replication request. Databases with less than or equal to this number of
# differing rows will always be sync'd using an HTTP replication request rather
# than using rsync.
# per_diff = 1000
#
# Maximum number of HTTP replication requests attempted on each replication
# pass for any one container. This caps how long the replicator will spend
# trying to sync a given database per pass so the other databases don't get
# starved.
# max_diffs = 100
#
# Number of replication workers to spawn.
# concurrency = 8
#
# Time in seconds to wait between replication passes
# interval = 30.0
# run_pause is deprecated, use interval instead
# run_pause = 30.0
#
# Process at most this many databases per second
# databases_per_second = 50
#
# node_timeout = 10
# conn_timeout = 0.5
#
# The replicator also performs reclamation
# reclaim_age = 604800
#
# 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.
# rsync_compress = no
#
# Format of the rsync module where the replicator will send data. See
# etc/rsyncd.conf-sample for some usage examples.
# rsync_module = {replication_ip}::account
#
# recon_cache_path = /var/cache/swift
#
# You can set scheduling priority of processes. Niceness values range from -20
# (most favorable to the process) to 19 (least favorable to the process).
# nice_priority =
#
# You can set I/O scheduling class and priority of processes. I/O niceness
# class values are IOPRIO_CLASS_RT (realtime), IOPRIO_CLASS_BE (best-effort) and
# IOPRIO_CLASS_IDLE (idle). I/O niceness priority is a number which goes from
# 0 to 7. The higher the value, the lower the I/O priority of the process.
# Work only with ionice_class.
# ionice_class =
# ionice_priority =
#
# The handoffs_only and handoff_delete options are for special-case emergency
# situations such as full disks in the cluster. These options SHOULD NOT
# BE ENABLED except in emergencies. When handoffs_only mode is enabled
# the replicator will *only* replicate from handoff nodes to primary
# nodes and will not sync primary nodes with other primary nodes.
#
# This has two main effects: first, the replicator becomes much more
# effective at removing misplaced databases, thereby freeing up disk
# space at a much faster pace than normal. Second, the replicator does
# not sync data between primary nodes, so out-of-sync account and
# container listings will not resolve while handoffs_only is enabled.
#
# This mode is intended to allow operators to temporarily sacrifice
# consistency in order to gain faster rebalancing, such as during a
# capacity addition with nearly-full disks. It is not intended for
# long-term use.
#
# handoffs_only = no
#
# handoff_delete is the number of replicas which are ensured in swift.
# If the number less than the number of replicas is set, account-replicator
# could delete local handoffs even if all replicas are not ensured in the
# cluster. The replicator would remove local handoff account database after
# syncing 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
[account-auditor]
# You can override the default log routing for this app here (don't use set!):
# log_name = account-auditor
# log_facility = LOG_LOCAL0
# log_level = INFO
# log_address = /dev/log
#
# Will audit each account at most once per interval
# interval = 1800.0
#
# accounts_per_second = 200
# recon_cache_path = /var/cache/swift
#
# You can set scheduling priority of processes. Niceness values range from -20
# (most favorable to the process) to 19 (least favorable to the process).
# nice_priority =
#
# You can set I/O scheduling class and priority of processes. I/O niceness
# class values are IOPRIO_CLASS_RT (realtime), IOPRIO_CLASS_BE (best-effort) and
# IOPRIO_CLASS_IDLE (idle). I/O niceness priority is a number which goes from
# 0 to 7. The higher the value, the lower the I/O priority of the process.
# Work only with ionice_class.
# ionice_class =
# ionice_priority =
[account-reaper]
# You can override the default log routing for this app here (don't use set!):
# log_name = account-reaper
# log_facility = LOG_LOCAL0
# log_level = INFO
# log_address = /dev/log
#
# concurrency = 25
# interval = 3600.0
# node_timeout = 10
# conn_timeout = 0.5
#
# Normally, the reaper begins deleting account information for deleted accounts
# immediately; you can set this to delay its work however. The value is in
# seconds; 2592000 = 30 days for example. The sum of this value and the
# container-updater interval should be less than the account-replicator
# reclaim_age. This ensures that once the account-reaper has deleted a
# container there is sufficient time for the container-updater to report to the
# account before the account DB is removed.
# delay_reaping = 0
#
# If the account fails to be reaped due to a persistent error, the
# account reaper will log a message such as:
# Account <name> has not been reaped since <date>
# You can search logs for this message if space is not being reclaimed
# after you delete account(s).
# Default is 2592000 seconds (30 days). This is in addition to any time
# requested by delay_reaping.
# reap_warn_after = 2592000
#
# You can set scheduling priority of processes. Niceness values range from -20
# (most favorable to the process) to 19 (least favorable to the process).
# nice_priority =
#
# You can set I/O scheduling class and priority of processes. I/O niceness
# class values are IOPRIO_CLASS_RT (realtime), IOPRIO_CLASS_BE (best-effort) and
# IOPRIO_CLASS_IDLE (idle). I/O niceness priority is a number which goes from
# 0 to 7. The higher the value, the lower the I/O priority of the process.
# Work only with ionice_class.
# ionice_class =
# ionice_priority =
# Note: Put it at the beginning of the pipeline to profile all middleware. But
# it is safer to put this after healthcheck. Not intended for production
# environments!
[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/account.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