7d0e5ebe69
This commit lets the object server use splice() and tee() to move data
from disk to the network without ever copying it into user space.
Requires Linux. Sorry, FreeBSD folks. You still have the old
mechanism, as does anyone who doesn't want to use splice. This
requires a relatively recent kernel (2.6.38+) to work, which includes
the two most recent Ubuntu LTS releases (Precise and Trusty) as well
as RHEL 7. However, it excludes Lucid and RHEL 6. On those systems,
setting "splice = on" will result in warnings in the logs but no
actual use of splice.
Note that this only applies to GET responses without Range headers. It
can easily be extended to single-range GET requests, but this commit
leaves that for future work. Same goes for PUT requests, or at least
non-chunked ones.
On some real hardware I had laying around (not a VM), this produced a
37% reduction in CPU usage for GETs made directly to the object
server. Measurements were done by looking at /proc/<pid>/stat,
specifically the utime and stime fields (user and kernel CPU jiffies,
respectively).
Note: There is a Python module called "splicetee" available on PyPi,
but it's licensed under the GPL, so it cannot easily be added to
OpenStack's requirements. That's why this patch uses ctypes instead.
Also fixed a long-standing annoyance in FakeLogger:
>>> fake_logger.warn('stuff')
>>> fake_logger.get_lines_for_level('warn')
[]
>>>
This, of course, is because the correct log level is 'warning'. Now
you get a KeyError if you call get_lines_for_level with a bogus log
level.
Change-Id: Ic6d6b833a5b04ca2019be94b1b90d941929d21c8
283 lines
9.8 KiB
Plaintext
283 lines
9.8 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
|
|
# expiring_objects_account_name = expiring_objects
|
|
#
|
|
# 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
|
|
#
|
|
# 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
|
|
#
|
|
# Restricts incoming REPLICATION 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 REPLICATION
|
|
# 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 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
|
|
#
|
|
# 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
|
|
#
|
|
# 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 ssync is verified
|
|
# as having performance comparable to, or better 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
|
|
#
|
|
# bandwidth 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
|
|
#
|
|
# 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-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
|
|
#
|
|
# 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 =
|
|
|
|
# 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
|