Accountsdb plugin postgres improvement (#21034)

Summary of Changes

Added the reference postgresql.conf
Prepare slot update statement to reduce overhead in updating slot
Support custom connection string
Allow the plugin to panic on replication issues to ensure consistency
This commit is contained in:
Lijun Wang 2021-10-30 20:18:11 -07:00 committed by GitHub
parent 7409d9d268
commit 696501500f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 968 additions and 50 deletions

View File

@ -2,7 +2,7 @@
* Script for cleaning up the schema for PostgreSQL used for the AccountsDb plugin.
*/
DROP TRIGGER account_update_trigger;
DROP TRIGGER account_update_trigger ON account;
DROP FUNCTION audit_account_update;
DROP TABLE account_audit;
DROP TABLE account;

View File

@ -0,0 +1,802 @@
# This a reference configuration file for the PostgreSQL database version 14.
# -----------------------------
# PostgreSQL configuration file
# -----------------------------
#
# This file consists of lines of the form:
#
# name = value
#
# (The "=" is optional.) Whitespace may be used. Comments are introduced with
# "#" anywhere on a line. The complete list of parameter names and allowed
# values can be found in the PostgreSQL documentation.
#
# The commented-out settings shown in this file represent the default values.
# Re-commenting a setting is NOT sufficient to revert it to the default value;
# you need to reload the server.
#
# This file is read on server startup and when the server receives a SIGHUP
# signal. If you edit the file on a running system, you have to SIGHUP the
# server for the changes to take effect, run "pg_ctl reload", or execute
# "SELECT pg_reload_conf()". Some parameters, which are marked below,
# require a server shutdown and restart to take effect.
#
# Any parameter can also be given as a command-line option to the server, e.g.,
# "postgres -c log_connections=on". Some parameters can be changed at run time
# with the "SET" SQL command.
#
# Memory units: B = bytes Time units: us = microseconds
# kB = kilobytes ms = milliseconds
# MB = megabytes s = seconds
# GB = gigabytes min = minutes
# TB = terabytes h = hours
# d = days
#------------------------------------------------------------------------------
# FILE LOCATIONS
#------------------------------------------------------------------------------
# The default values of these variables are driven from the -D command-line
# option or PGDATA environment variable, represented here as ConfigDir.
data_directory = '/var/lib/postgresql/14/main' # use data in another directory
# (change requires restart)
hba_file = '/etc/postgresql/14/main/pg_hba.conf' # host-based authentication file
# (change requires restart)
ident_file = '/etc/postgresql/14/main/pg_ident.conf' # ident configuration file
# (change requires restart)
# If external_pid_file is not explicitly set, no extra PID file is written.
external_pid_file = '/var/run/postgresql/14-main.pid' # write an extra PID file
# (change requires restart)
#------------------------------------------------------------------------------
# CONNECTIONS AND AUTHENTICATION
#------------------------------------------------------------------------------
# - Connection Settings -
#listen_addresses = 'localhost' # what IP address(es) to listen on;
# comma-separated list of addresses;
# defaults to 'localhost'; use '*' for all
# (change requires restart)
listen_addresses = '*'
port = 5433 # (change requires restart)
max_connections = 200 # (change requires restart)
#superuser_reserved_connections = 3 # (change requires restart)
unix_socket_directories = '/var/run/postgresql' # comma-separated list of directories
# (change requires restart)
#unix_socket_group = '' # (change requires restart)
#unix_socket_permissions = 0777 # begin with 0 to use octal notation
# (change requires restart)
#bonjour = off # advertise server via Bonjour
# (change requires restart)
#bonjour_name = '' # defaults to the computer name
# (change requires restart)
# - TCP settings -
# see "man tcp" for details
#tcp_keepalives_idle = 0 # TCP_KEEPIDLE, in seconds;
# 0 selects the system default
#tcp_keepalives_interval = 0 # TCP_KEEPINTVL, in seconds;
# 0 selects the system default
#tcp_keepalives_count = 0 # TCP_KEEPCNT;
# 0 selects the system default
#tcp_user_timeout = 0 # TCP_USER_TIMEOUT, in milliseconds;
# 0 selects the system default
#client_connection_check_interval = 0 # time between checks for client
# disconnection while running queries;
# 0 for never
# - Authentication -
#authentication_timeout = 1min # 1s-600s
#password_encryption = scram-sha-256 # scram-sha-256 or md5
#db_user_namespace = off
# GSSAPI using Kerberos
#krb_server_keyfile = 'FILE:${sysconfdir}/krb5.keytab'
#krb_caseins_users = off
# - SSL -
ssl = on
#ssl_ca_file = ''
ssl_cert_file = '/etc/ssl/certs/ssl-cert-snakeoil.pem'
#ssl_crl_file = ''
#ssl_crl_dir = ''
ssl_key_file = '/etc/ssl/private/ssl-cert-snakeoil.key'
#ssl_ciphers = 'HIGH:MEDIUM:+3DES:!aNULL' # allowed SSL ciphers
#ssl_prefer_server_ciphers = on
#ssl_ecdh_curve = 'prime256v1'
#ssl_min_protocol_version = 'TLSv1.2'
#ssl_max_protocol_version = ''
#ssl_dh_params_file = ''
#ssl_passphrase_command = ''
#ssl_passphrase_command_supports_reload = off
#------------------------------------------------------------------------------
# RESOURCE USAGE (except WAL)
#------------------------------------------------------------------------------
# - Memory -
shared_buffers = 1GB # min 128kB
# (change requires restart)
#huge_pages = try # on, off, or try
# (change requires restart)
#huge_page_size = 0 # zero for system default
# (change requires restart)
#temp_buffers = 8MB # min 800kB
#max_prepared_transactions = 0 # zero disables the feature
# (change requires restart)
# Caution: it is not advisable to set max_prepared_transactions nonzero unless
# you actively intend to use prepared transactions.
#work_mem = 4MB # min 64kB
#hash_mem_multiplier = 1.0 # 1-1000.0 multiplier on hash table work_mem
#maintenance_work_mem = 64MB # min 1MB
#autovacuum_work_mem = -1 # min 1MB, or -1 to use maintenance_work_mem
#logical_decoding_work_mem = 64MB # min 64kB
#max_stack_depth = 2MB # min 100kB
#shared_memory_type = mmap # the default is the first option
# supported by the operating system:
# mmap
# sysv
# windows
# (change requires restart)
dynamic_shared_memory_type = posix # the default is the first option
# supported by the operating system:
# posix
# sysv
# windows
# mmap
# (change requires restart)
#min_dynamic_shared_memory = 0MB # (change requires restart)
# - Disk -
#temp_file_limit = -1 # limits per-process temp file space
# in kilobytes, or -1 for no limit
# - Kernel Resources -
#max_files_per_process = 1000 # min 64
# (change requires restart)
# - Cost-Based Vacuum Delay -
#vacuum_cost_delay = 0 # 0-100 milliseconds (0 disables)
#vacuum_cost_page_hit = 1 # 0-10000 credits
#vacuum_cost_page_miss = 2 # 0-10000 credits
#vacuum_cost_page_dirty = 20 # 0-10000 credits
#vacuum_cost_limit = 200 # 1-10000 credits
# - Background Writer -
#bgwriter_delay = 200ms # 10-10000ms between rounds
#bgwriter_lru_maxpages = 100 # max buffers written/round, 0 disables
#bgwriter_lru_multiplier = 2.0 # 0-10.0 multiplier on buffers scanned/round
#bgwriter_flush_after = 512kB # measured in pages, 0 disables
# - Asynchronous Behavior -
#backend_flush_after = 0 # measured in pages, 0 disables
effective_io_concurrency = 1000 # 1-1000; 0 disables prefetching
#maintenance_io_concurrency = 10 # 1-1000; 0 disables prefetching
#max_worker_processes = 8 # (change requires restart)
#max_parallel_workers_per_gather = 2 # taken from max_parallel_workers
#max_parallel_maintenance_workers = 2 # taken from max_parallel_workers
#max_parallel_workers = 8 # maximum number of max_worker_processes that
# can be used in parallel operations
#parallel_leader_participation = on
#old_snapshot_threshold = -1 # 1min-60d; -1 disables; 0 is immediate
# (change requires restart)
#------------------------------------------------------------------------------
# WRITE-AHEAD LOG
#------------------------------------------------------------------------------
# - Settings -
wal_level = minimal # minimal, replica, or logical
# (change requires restart)
fsync = off # flush data to disk for crash safety
# (turning this off can cause
# unrecoverable data corruption)
synchronous_commit = off # synchronization level;
# off, local, remote_write, remote_apply, or on
#wal_sync_method = fsync # the default is the first option
# supported by the operating system:
# open_datasync
# fdatasync (default on Linux and FreeBSD)
# fsync
# fsync_writethrough
# open_sync
full_page_writes = off # recover from partial page writes
#wal_log_hints = off # also do full page writes of non-critical updates
# (change requires restart)
#wal_compression = off # enable compression of full-page writes
#wal_init_zero = on # zero-fill new WAL files
#wal_recycle = on # recycle WAL files
#wal_buffers = -1 # min 32kB, -1 sets based on shared_buffers
# (change requires restart)
#wal_writer_delay = 200ms # 1-10000 milliseconds
#wal_writer_flush_after = 1MB # measured in pages, 0 disables
#wal_skip_threshold = 2MB
#commit_delay = 0 # range 0-100000, in microseconds
#commit_siblings = 5 # range 1-1000
# - Checkpoints -
#checkpoint_timeout = 5min # range 30s-1d
#checkpoint_completion_target = 0.9 # checkpoint target duration, 0.0 - 1.0
#checkpoint_flush_after = 256kB # measured in pages, 0 disables
#checkpoint_warning = 30s # 0 disables
max_wal_size = 1GB
min_wal_size = 80MB
# - Archiving -
#archive_mode = off # enables archiving; off, on, or always
# (change requires restart)
#archive_command = '' # command to use to archive a logfile segment
# placeholders: %p = path of file to archive
# %f = file name only
# e.g. 'test ! -f /mnt/server/archivedir/%f && cp %p /mnt/server/archivedir/%f'
#archive_timeout = 0 # force a logfile segment switch after this
# number of seconds; 0 disables
# - Archive Recovery -
# These are only used in recovery mode.
#restore_command = '' # command to use to restore an archived logfile segment
# placeholders: %p = path of file to restore
# %f = file name only
# e.g. 'cp /mnt/server/archivedir/%f %p'
#archive_cleanup_command = '' # command to execute at every restartpoint
#recovery_end_command = '' # command to execute at completion of recovery
# - Recovery Target -
# Set these only when performing a targeted recovery.
#recovery_target = '' # 'immediate' to end recovery as soon as a
# consistent state is reached
# (change requires restart)
#recovery_target_name = '' # the named restore point to which recovery will proceed
# (change requires restart)
#recovery_target_time = '' # the time stamp up to which recovery will proceed
# (change requires restart)
#recovery_target_xid = '' # the transaction ID up to which recovery will proceed
# (change requires restart)
#recovery_target_lsn = '' # the WAL LSN up to which recovery will proceed
# (change requires restart)
#recovery_target_inclusive = on # Specifies whether to stop:
# just after the specified recovery target (on)
# just before the recovery target (off)
# (change requires restart)
#recovery_target_timeline = 'latest' # 'current', 'latest', or timeline ID
# (change requires restart)
#recovery_target_action = 'pause' # 'pause', 'promote', 'shutdown'
# (change requires restart)
#------------------------------------------------------------------------------
# REPLICATION
#------------------------------------------------------------------------------
# - Sending Servers -
# Set these on the primary and on any standby that will send replication data.
max_wal_senders = 0 # max number of walsender processes
# (change requires restart)
#max_replication_slots = 10 # max number of replication slots
# (change requires restart)
#wal_keep_size = 0 # in megabytes; 0 disables
#max_slot_wal_keep_size = -1 # in megabytes; -1 disables
#wal_sender_timeout = 60s # in milliseconds; 0 disables
#track_commit_timestamp = off # collect timestamp of transaction commit
# (change requires restart)
# - Primary Server -
# These settings are ignored on a standby server.
#synchronous_standby_names = '' # standby servers that provide sync rep
# method to choose sync standbys, number of sync standbys,
# and comma-separated list of application_name
# from standby(s); '*' = all
#vacuum_defer_cleanup_age = 0 # number of xacts by which cleanup is delayed
# - Standby Servers -
# These settings are ignored on a primary server.
#primary_conninfo = '' # connection string to sending server
#primary_slot_name = '' # replication slot on sending server
#promote_trigger_file = '' # file name whose presence ends recovery
#hot_standby = on # "off" disallows queries during recovery
# (change requires restart)
#max_standby_archive_delay = 30s # max delay before canceling queries
# when reading WAL from archive;
# -1 allows indefinite delay
#max_standby_streaming_delay = 30s # max delay before canceling queries
# when reading streaming WAL;
# -1 allows indefinite delay
#wal_receiver_create_temp_slot = off # create temp slot if primary_slot_name
# is not set
#wal_receiver_status_interval = 10s # send replies at least this often
# 0 disables
#hot_standby_feedback = off # send info from standby to prevent
# query conflicts
#wal_receiver_timeout = 60s # time that receiver waits for
# communication from primary
# in milliseconds; 0 disables
#wal_retrieve_retry_interval = 5s # time to wait before retrying to
# retrieve WAL after a failed attempt
#recovery_min_apply_delay = 0 # minimum delay for applying changes during recovery
# - Subscribers -
# These settings are ignored on a publisher.
#max_logical_replication_workers = 4 # taken from max_worker_processes
# (change requires restart)
#max_sync_workers_per_subscription = 2 # taken from max_logical_replication_workers
#------------------------------------------------------------------------------
# QUERY TUNING
#------------------------------------------------------------------------------
# - Planner Method Configuration -
#enable_async_append = on
#enable_bitmapscan = on
#enable_gathermerge = on
#enable_hashagg = on
#enable_hashjoin = on
#enable_incremental_sort = on
#enable_indexscan = on
#enable_indexonlyscan = on
#enable_material = on
#enable_memoize = on
#enable_mergejoin = on
#enable_nestloop = on
#enable_parallel_append = on
#enable_parallel_hash = on
#enable_partition_pruning = on
#enable_partitionwise_join = off
#enable_partitionwise_aggregate = off
#enable_seqscan = on
#enable_sort = on
#enable_tidscan = on
# - Planner Cost Constants -
#seq_page_cost = 1.0 # measured on an arbitrary scale
#random_page_cost = 4.0 # same scale as above
#cpu_tuple_cost = 0.01 # same scale as above
#cpu_index_tuple_cost = 0.005 # same scale as above
#cpu_operator_cost = 0.0025 # same scale as above
#parallel_setup_cost = 1000.0 # same scale as above
#parallel_tuple_cost = 0.1 # same scale as above
#min_parallel_table_scan_size = 8MB
#min_parallel_index_scan_size = 512kB
#effective_cache_size = 4GB
#jit_above_cost = 100000 # perform JIT compilation if available
# and query more expensive than this;
# -1 disables
#jit_inline_above_cost = 500000 # inline small functions if query is
# more expensive than this; -1 disables
#jit_optimize_above_cost = 500000 # use expensive JIT optimizations if
# query is more expensive than this;
# -1 disables
# - Genetic Query Optimizer -
#geqo = on
#geqo_threshold = 12
#geqo_effort = 5 # range 1-10
#geqo_pool_size = 0 # selects default based on effort
#geqo_generations = 0 # selects default based on effort
#geqo_selection_bias = 2.0 # range 1.5-2.0
#geqo_seed = 0.0 # range 0.0-1.0
# - Other Planner Options -
#default_statistics_target = 100 # range 1-10000
#constraint_exclusion = partition # on, off, or partition
#cursor_tuple_fraction = 0.1 # range 0.0-1.0
#from_collapse_limit = 8
#jit = on # allow JIT compilation
#join_collapse_limit = 8 # 1 disables collapsing of explicit
# JOIN clauses
#plan_cache_mode = auto # auto, force_generic_plan or
# force_custom_plan
#------------------------------------------------------------------------------
# REPORTING AND LOGGING
#------------------------------------------------------------------------------
# - Where to Log -
#log_destination = 'stderr' # Valid values are combinations of
# stderr, csvlog, syslog, and eventlog,
# depending on platform. csvlog
# requires logging_collector to be on.
# This is used when logging to stderr:
#logging_collector = off # Enable capturing of stderr and csvlog
# into log files. Required to be on for
# csvlogs.
# (change requires restart)
# These are only used if logging_collector is on:
#log_directory = 'log' # directory where log files are written,
# can be absolute or relative to PGDATA
#log_filename = 'postgresql-%Y-%m-%d_%H%M%S.log' # log file name pattern,
# can include strftime() escapes
#log_file_mode = 0600 # creation mode for log files,
# begin with 0 to use octal notation
#log_rotation_age = 1d # Automatic rotation of logfiles will
# happen after that time. 0 disables.
#log_rotation_size = 10MB # Automatic rotation of logfiles will
# happen after that much log output.
# 0 disables.
#log_truncate_on_rotation = off # If on, an existing log file with the
# same name as the new log file will be
# truncated rather than appended to.
# But such truncation only occurs on
# time-driven rotation, not on restarts
# or size-driven rotation. Default is
# off, meaning append to existing files
# in all cases.
# These are relevant when logging to syslog:
#syslog_facility = 'LOCAL0'
#syslog_ident = 'postgres'
#syslog_sequence_numbers = on
#syslog_split_messages = on
# This is only relevant when logging to eventlog (Windows):
# (change requires restart)
#event_source = 'PostgreSQL'
# - When to Log -
#log_min_messages = warning # values in order of decreasing detail:
# debug5
# debug4
# debug3
# debug2
# debug1
# info
# notice
# warning
# error
# log
# fatal
# panic
#log_min_error_statement = error # values in order of decreasing detail:
# debug5
# debug4
# debug3
# debug2
# debug1
# info
# notice
# warning
# error
# log
# fatal
# panic (effectively off)
#log_min_duration_statement = -1 # -1 is disabled, 0 logs all statements
# and their durations, > 0 logs only
# statements running at least this number
# of milliseconds
#log_min_duration_sample = -1 # -1 is disabled, 0 logs a sample of statements
# and their durations, > 0 logs only a sample of
# statements running at least this number
# of milliseconds;
# sample fraction is determined by log_statement_sample_rate
#log_statement_sample_rate = 1.0 # fraction of logged statements exceeding
# log_min_duration_sample to be logged;
# 1.0 logs all such statements, 0.0 never logs
#log_transaction_sample_rate = 0.0 # fraction of transactions whose statements
# are logged regardless of their duration; 1.0 logs all
# statements from all transactions, 0.0 never logs
# - What to Log -
#debug_print_parse = off
#debug_print_rewritten = off
#debug_print_plan = off
#debug_pretty_print = on
#log_autovacuum_min_duration = -1 # log autovacuum activity;
# -1 disables, 0 logs all actions and
# their durations, > 0 logs only
# actions running at least this number
# of milliseconds.
#log_checkpoints = off
#log_connections = off
#log_disconnections = off
#log_duration = off
#log_error_verbosity = default # terse, default, or verbose messages
#log_hostname = off
log_line_prefix = '%m [%p] %q%u@%d ' # special values:
# %a = application name
# %u = user name
# %d = database name
# %r = remote host and port
# %h = remote host
# %b = backend type
# %p = process ID
# %P = process ID of parallel group leader
# %t = timestamp without milliseconds
# %m = timestamp with milliseconds
# %n = timestamp with milliseconds (as a Unix epoch)
# %Q = query ID (0 if none or not computed)
# %i = command tag
# %e = SQL state
# %c = session ID
# %l = session line number
# %s = session start timestamp
# %v = virtual transaction ID
# %x = transaction ID (0 if none)
# %q = stop here in non-session
# processes
# %% = '%'
# e.g. '<%u%%%d> '
#log_lock_waits = off # log lock waits >= deadlock_timeout
#log_recovery_conflict_waits = off # log standby recovery conflict waits
# >= deadlock_timeout
#log_parameter_max_length = -1 # when logging statements, limit logged
# bind-parameter values to N bytes;
# -1 means print in full, 0 disables
#log_parameter_max_length_on_error = 0 # when logging an error, limit logged
# bind-parameter values to N bytes;
# -1 means print in full, 0 disables
#log_statement = 'none' # none, ddl, mod, all
#log_replication_commands = off
#log_temp_files = -1 # log temporary files equal or larger
# than the specified size in kilobytes;
# -1 disables, 0 logs all temp files
log_timezone = 'Etc/UTC'
#------------------------------------------------------------------------------
# PROCESS TITLE
#------------------------------------------------------------------------------
cluster_name = '14/main' # added to process titles if nonempty
# (change requires restart)
#update_process_title = on
#------------------------------------------------------------------------------
# STATISTICS
#------------------------------------------------------------------------------
# - Query and Index Statistics Collector -
#track_activities = on
#track_activity_query_size = 1024 # (change requires restart)
#track_counts = on
#track_io_timing = off
#track_wal_io_timing = off
#track_functions = none # none, pl, all
stats_temp_directory = '/var/run/postgresql/14-main.pg_stat_tmp'
# - Monitoring -
#compute_query_id = auto
#log_statement_stats = off
#log_parser_stats = off
#log_planner_stats = off
#log_executor_stats = off
#------------------------------------------------------------------------------
# AUTOVACUUM
#------------------------------------------------------------------------------
#autovacuum = on # Enable autovacuum subprocess? 'on'
# requires track_counts to also be on.
#autovacuum_max_workers = 3 # max number of autovacuum subprocesses
# (change requires restart)
#autovacuum_naptime = 1min # time between autovacuum runs
#autovacuum_vacuum_threshold = 50 # min number of row updates before
# vacuum
#autovacuum_vacuum_insert_threshold = 1000 # min number of row inserts
# before vacuum; -1 disables insert
# vacuums
#autovacuum_analyze_threshold = 50 # min number of row updates before
# analyze
#autovacuum_vacuum_scale_factor = 0.2 # fraction of table size before vacuum
#autovacuum_vacuum_insert_scale_factor = 0.2 # fraction of inserts over table
# size before insert vacuum
#autovacuum_analyze_scale_factor = 0.1 # fraction of table size before analyze
#autovacuum_freeze_max_age = 200000000 # maximum XID age before forced vacuum
# (change requires restart)
#autovacuum_multixact_freeze_max_age = 400000000 # maximum multixact age
# before forced vacuum
# (change requires restart)
#autovacuum_vacuum_cost_delay = 2ms # default vacuum cost delay for
# autovacuum, in milliseconds;
# -1 means use vacuum_cost_delay
#autovacuum_vacuum_cost_limit = -1 # default vacuum cost limit for
# autovacuum, -1 means use
# vacuum_cost_limit
#------------------------------------------------------------------------------
# CLIENT CONNECTION DEFAULTS
#------------------------------------------------------------------------------
# - Statement Behavior -
#client_min_messages = notice # values in order of decreasing detail:
# debug5
# debug4
# debug3
# debug2
# debug1
# log
# notice
# warning
# error
#search_path = '"$user", public' # schema names
#row_security = on
#default_table_access_method = 'heap'
#default_tablespace = '' # a tablespace name, '' uses the default
#default_toast_compression = 'pglz' # 'pglz' or 'lz4'
#temp_tablespaces = '' # a list of tablespace names, '' uses
# only default tablespace
#check_function_bodies = on
#default_transaction_isolation = 'read committed'
#default_transaction_read_only = off
#default_transaction_deferrable = off
#session_replication_role = 'origin'
#statement_timeout = 0 # in milliseconds, 0 is disabled
#lock_timeout = 0 # in milliseconds, 0 is disabled
#idle_in_transaction_session_timeout = 0 # in milliseconds, 0 is disabled
#idle_session_timeout = 0 # in milliseconds, 0 is disabled
#vacuum_freeze_table_age = 150000000
#vacuum_freeze_min_age = 50000000
#vacuum_failsafe_age = 1600000000
#vacuum_multixact_freeze_table_age = 150000000
#vacuum_multixact_freeze_min_age = 5000000
#vacuum_multixact_failsafe_age = 1600000000
#bytea_output = 'hex' # hex, escape
#xmlbinary = 'base64'
#xmloption = 'content'
#gin_pending_list_limit = 4MB
# - Locale and Formatting -
datestyle = 'iso, mdy'
#intervalstyle = 'postgres'
timezone = 'Etc/UTC'
#timezone_abbreviations = 'Default' # Select the set of available time zone
# abbreviations. Currently, there are
# Default
# Australia (historical usage)
# India
# You can create your own file in
# share/timezonesets/.
#extra_float_digits = 1 # min -15, max 3; any value >0 actually
# selects precise output mode
#client_encoding = sql_ascii # actually, defaults to database
# encoding
# These settings are initialized by initdb, but they can be changed.
lc_messages = 'C.UTF-8' # locale for system error message
# strings
lc_monetary = 'C.UTF-8' # locale for monetary formatting
lc_numeric = 'C.UTF-8' # locale for number formatting
lc_time = 'C.UTF-8' # locale for time formatting
# default configuration for text search
default_text_search_config = 'pg_catalog.english'
# - Shared Library Preloading -
#local_preload_libraries = ''
#session_preload_libraries = ''
#shared_preload_libraries = '' # (change requires restart)
#jit_provider = 'llvmjit' # JIT library to use
# - Other Defaults -
#dynamic_library_path = '$libdir'
#extension_destdir = '' # prepend path when loading extensions
# and shared objects (added by Debian)
#gin_fuzzy_search_limit = 0
#------------------------------------------------------------------------------
# LOCK MANAGEMENT
#------------------------------------------------------------------------------
#deadlock_timeout = 1s
#max_locks_per_transaction = 64 # min 10
# (change requires restart)
#max_pred_locks_per_transaction = 64 # min 10
# (change requires restart)
#max_pred_locks_per_relation = -2 # negative values mean
# (max_pred_locks_per_transaction
# / -max_pred_locks_per_relation) - 1
#max_pred_locks_per_page = 2 # min 0
#------------------------------------------------------------------------------
# VERSION AND PLATFORM COMPATIBILITY
#------------------------------------------------------------------------------
# - Previous PostgreSQL Versions -
#array_nulls = on
#backslash_quote = safe_encoding # on, off, or safe_encoding
#escape_string_warning = on
#lo_compat_privileges = off
#quote_all_identifiers = off
#standard_conforming_strings = on
#synchronize_seqscans = on
# - Other Platforms and Clients -
#transform_null_equals = off
#------------------------------------------------------------------------------
# ERROR HANDLING
#------------------------------------------------------------------------------
#exit_on_error = off # terminate session on any error?
#restart_after_crash = on # reinitialize after backend crash?
#data_sync_retry = off # retry or panic on failure to fsync
# data?
# (change requires restart)
#recovery_init_sync_method = fsync # fsync, syncfs (Linux 5.8+)
#------------------------------------------------------------------------------
# CONFIG FILE INCLUDES
#------------------------------------------------------------------------------
# These options allow settings to be loaded from files other than the
# default postgresql.conf. Note that these are directives, not variable
# assignments, so they can usefully be given more than once.
include_dir = 'conf.d' # include files ending in '.conf' from
# a directory, e.g., 'conf.d'
#include_if_exists = '...' # include file only if it exists
#include = '...' # include file
#------------------------------------------------------------------------------
# CUSTOMIZED OPTIONS
#------------------------------------------------------------------------------
# Add settings for extensions here

View File

@ -32,11 +32,13 @@ impl std::fmt::Debug for AccountsDbPluginPostgres {
#[derive(Clone, Debug, PartialEq, Serialize, Deserialize)]
pub struct AccountsDbPluginPostgresConfig {
pub host: String,
pub user: String,
pub threads: Option<usize>,
pub host: Option<String>,
pub user: Option<String>,
pub port: Option<u16>,
pub connection_str: Option<String>,
pub threads: Option<usize>,
pub batch_size: Option<usize>,
pub panic_on_db_errors: Option<bool>,
}
#[derive(Error, Debug)]
@ -46,6 +48,9 @@ pub enum AccountsDbPluginPostgresError {
#[error("Error preparing data store schema. Error message: ({msg})")]
DataSchemaError { msg: String },
#[error("Error preparing data store schema. Error message: ({msg})")]
ConfigurationError { msg: String },
}
impl AccountsDbPlugin for AccountsDbPluginPostgres {
@ -54,10 +59,9 @@ impl AccountsDbPlugin for AccountsDbPluginPostgres {
}
/// Do initialization for the PostgreSQL plugin.
/// # Arguments
///
/// Format of the config file:
/// The `accounts_selector` section allows the user to controls accounts selections.
/// # Format of the config file:
/// * The `accounts_selector` section allows the user to controls accounts selections.
/// "accounts_selector" : {
/// "accounts" : \["pubkey-1", "pubkey-2", ..., "pubkey-n"\],
/// }
@ -72,13 +76,21 @@ impl AccountsDbPlugin for AccountsDbPluginPostgres {
/// "accounts_selector" : {
/// "accounts" : \["*"\],
/// }
/// "host" specifies the PostgreSQL server.
/// "user" specifies the PostgreSQL user.
/// "threads" optional, specifies the number of worker threads for the plugin. A thread
/// maintains a PostgreSQL connection to the server. The default is 10.
/// "batch_size" optional, specifies the batch size of bulk insert when the AccountsDb is created
/// from restoring a snapshot. The default is "10".
/// * "host", optional, specifies the PostgreSQL server.
/// * "user", optional, specifies the PostgreSQL user.
/// * "port", optional, specifies the PostgreSQL server's port.
/// * "connection_str", optional, the custom PostgreSQL connection string.
/// Please refer to https://docs.rs/postgres/0.19.2/postgres/config/struct.Config.html for the connection configuration.
/// When `connection_str` is set, the values in "host", "user" and "port" are ignored. If `connection_str` is not given,
/// `host` and `user` must be given.
/// * "threads" optional, specifies the number of worker threads for the plugin. A thread
/// maintains a PostgreSQL connection to the server. The default is '10'.
/// * "batch_size" optional, specifies the batch size of bulk insert when the AccountsDb is created
/// from restoring a snapshot. The default is '10'.
/// * "panic_on_db_errors", optional, contols if to panic when there are errors replicating data to the
/// PostgreSQL database. The default is 'false'.
/// # Examples
///
/// {
/// "libpath": "/home/solana/target/release/libsolana_accountsdb_plugin_postgres.so",
/// "host": "host_foo",
@ -86,6 +98,7 @@ impl AccountsDbPlugin for AccountsDbPluginPostgres {
/// "threads": 10,
/// "accounts_selector" : {
/// "owners" : ["9oT9R5ZyRovSVnt37QvVoBttGpNqR3J7unkb567NP8k3"]
/// }
/// }
fn on_load(&mut self, config_file: &str) -> Result<()> {

View File

@ -33,11 +33,14 @@ const DEFAULT_POSTGRES_PORT: u16 = 5432;
const DEFAULT_THREADS_COUNT: usize = 100;
const DEFAULT_ACCOUNTS_INSERT_BATCH_SIZE: usize = 10;
const ACCOUNT_COLUMN_COUNT: usize = 9;
const DEFAULT_PANIC_ON_DB_ERROR: bool = false;
struct PostgresSqlClientWrapper {
client: Client,
update_account_stmt: Statement,
bulk_account_insert_stmt: Statement,
update_slot_with_parent_stmt: Statement,
update_slot_without_parent_stmt: Statement,
}
pub struct SimplePostgresClient {
@ -66,6 +69,19 @@ pub struct DbAccountInfo {
pub write_version: i64,
}
pub(crate) fn abort() -> ! {
#[cfg(not(test))]
{
// standard error is usually redirected to a log file, cry for help on standard output as
// well
eprintln!("Validator process aborted. The validator log may contain further details");
std::process::exit(1);
}
#[cfg(test)]
panic!("process::exit(1) is intercepted for friendly test failure...");
}
impl DbAccountInfo {
fn new<T: ReadableAccountInfo>(account: &T, slot: u64) -> DbAccountInfo {
let data = account.data().to_vec();
@ -179,13 +195,32 @@ impl SimplePostgresClient {
) -> Result<Client, AccountsDbPluginError> {
let port = config.port.unwrap_or(DEFAULT_POSTGRES_PORT);
let connection_str = format!("host={} user={} port={}", config.host, config.user, port);
let connection_str = if let Some(connection_str) = &config.connection_str {
connection_str.clone()
} else {
if config.host.is_none() || config.user.is_none() {
let msg = format!(
"\"connection_str\": {:?}, or \"host\": {:?} \"user\": {:?} must be specified",
config.connection_str, config.host, config.user
);
return Err(AccountsDbPluginError::Custom(Box::new(
AccountsDbPluginPostgresError::ConfigurationError { msg },
)));
}
format!(
"host={} user={} port={}",
config.host.as_ref().unwrap(),
config.user.as_ref().unwrap(),
port
)
};
match Client::connect(&connection_str, NoTls) {
Err(err) => {
let msg = format!(
"Error in connecting to the PostgreSQL database: {:?} host: {:?} user: {:?} config: {:?}",
err, config.host, config.user, connection_str);
"Error in connecting to the PostgreSQL database: {:?} connection_str: {:?}",
err, connection_str
);
error!("{}", msg);
Err(AccountsDbPluginError::Custom(Box::new(
AccountsDbPluginPostgresError::DataStoreConnectionError { msg },
@ -238,7 +273,7 @@ impl SimplePostgresClient {
Err(err) => {
return Err(AccountsDbPluginError::Custom(Box::new(AccountsDbPluginPostgresError::DataSchemaError {
msg: format!(
"Error in preparing for the accounts update PostgreSQL database: {} host: {} user: {} config: {:?}",
"Error in preparing for the accounts update PostgreSQL database: {} host: {:?} user: {:?} config: {:?}",
err, config.host, config.user, config
),
})));
@ -263,7 +298,7 @@ impl SimplePostgresClient {
Err(err) => {
return Err(AccountsDbPluginError::Custom(Box::new(AccountsDbPluginPostgresError::DataSchemaError {
msg: format!(
"Error in preparing for the accounts update PostgreSQL database: {} host: {} user: {} config: {:?}",
"Error in preparing for the accounts update PostgreSQL database: {} host: {:?} user: {:?} config: {:?}",
err, config.host, config.user, config
),
})));
@ -272,6 +307,52 @@ impl SimplePostgresClient {
}
}
fn build_slot_upsert_statement_with_parent(
client: &mut Client,
config: &AccountsDbPluginPostgresConfig,
) -> Result<Statement, AccountsDbPluginError> {
let stmt = "INSERT INTO slot (slot, parent, status, updated_on) \
VALUES ($1, $2, $3, $4) \
ON CONFLICT (slot) DO UPDATE SET parent=excluded.parent, status=excluded.status, updated_on=excluded.updated_on";
let stmt = client.prepare(stmt);
match stmt {
Err(err) => {
return Err(AccountsDbPluginError::Custom(Box::new(AccountsDbPluginPostgresError::DataSchemaError {
msg: format!(
"Error in preparing for the slot update PostgreSQL database: {} host: {:?} user: {:?} config: {:?}",
err, config.host, config.user, config
),
})));
}
Ok(stmt) => Ok(stmt),
}
}
fn build_slot_upsert_statement_without_parent(
client: &mut Client,
config: &AccountsDbPluginPostgresConfig,
) -> Result<Statement, AccountsDbPluginError> {
let stmt = "INSERT INTO slot (slot, status, updated_on) \
VALUES ($1, $2, $3) \
ON CONFLICT (slot) DO UPDATE SET status=excluded.status, updated_on=excluded.updated_on";
let stmt = client.prepare(stmt);
match stmt {
Err(err) => {
return Err(AccountsDbPluginError::Custom(Box::new(AccountsDbPluginPostgresError::DataSchemaError {
msg: format!(
"Error in preparing for the slot update PostgreSQL database: {} host: {:?} user: {:?} config: {:?}",
err, config.host, config.user, config
),
})));
}
Ok(stmt) => Ok(stmt),
}
}
/// Internal function for updating or inserting a single account
fn upsert_account_internal(
account: &DbAccountInfo,
@ -406,6 +487,11 @@ impl SimplePostgresClient {
Self::build_bulk_account_insert_statement(&mut client, config)?;
let update_account_stmt = Self::build_single_account_upsert_statement(&mut client, config)?;
let update_slot_with_parent_stmt =
Self::build_slot_upsert_statement_with_parent(&mut client, config)?;
let update_slot_without_parent_stmt =
Self::build_slot_upsert_statement_without_parent(&mut client, config)?;
let batch_size = config
.batch_size
.unwrap_or(DEFAULT_ACCOUNTS_INSERT_BATCH_SIZE);
@ -417,6 +503,8 @@ impl SimplePostgresClient {
client,
update_account_stmt,
bulk_account_insert_stmt,
update_slot_with_parent_stmt,
update_slot_without_parent_stmt,
}),
})
}
@ -455,32 +543,15 @@ impl PostgresClient for SimplePostgresClient {
let client = self.client.get_mut().unwrap();
let result = match parent {
Some(parent) => {
client.client.execute(
"INSERT INTO slot (slot, parent, status, updated_on) \
VALUES ($1, $2, $3, $4) \
ON CONFLICT (slot) DO UPDATE SET parent=$2, status=$3, updated_on=$4",
&[
&slot,
&parent,
&status_str,
&updated_on,
],
)
}
None => {
client.client.execute(
"INSERT INTO slot (slot, status, updated_on) \
VALUES ($1, $2, $3) \
ON CONFLICT (slot) DO UPDATE SET status=$2, updated_on=$3",
&[
&slot,
&status_str,
&updated_on,
],
)
}
};
Some(parent) => client.client.execute(
&client.update_slot_with_parent_stmt,
&[&slot, &parent, &status_str, &updated_on],
),
None => client.client.execute(
&client.update_slot_without_parent_stmt,
&[&slot, &status_str, &updated_on],
),
};
match result {
Err(err) => {
@ -541,6 +612,7 @@ impl PostgresClientWorker {
exit_worker: Arc<AtomicBool>,
is_startup_done: Arc<AtomicBool>,
startup_done_count: Arc<AtomicUsize>,
panic_on_db_errors: bool,
) -> Result<(), AccountsDbPluginError> {
while !exit_worker.load(Ordering::Relaxed) {
let mut measure = Measure::start("accountsdb-plugin-postgres-worker-recv");
@ -555,21 +627,38 @@ impl PostgresClientWorker {
match work {
Ok(work) => match work {
DbWorkItem::UpdateAccount(request) => {
self.client
.update_account(request.account, request.is_startup)?;
if let Err(err) = self
.client
.update_account(request.account, request.is_startup)
{
error!("Failed to update account: ({})", err);
if panic_on_db_errors {
abort();
}
}
}
DbWorkItem::UpdateSlot(request) => {
self.client.update_slot_status(
if let Err(err) = self.client.update_slot_status(
request.slot,
request.parent,
request.slot_status,
)?;
) {
error!("Failed to update slot: ({})", err);
if panic_on_db_errors {
abort();
}
}
}
},
Err(err) => match err {
RecvTimeoutError::Timeout => {
if !self.is_startup_done && is_startup_done.load(Ordering::Relaxed) {
self.client.notify_end_of_startup()?;
if let Err(err) = self.client.notify_end_of_startup() {
error!("Error in notifying end of startup: ({})", err);
if panic_on_db_errors {
abort();
}
}
self.is_startup_done = true;
startup_done_count.fetch_add(1, Ordering::Relaxed);
}
@ -578,6 +667,9 @@ impl PostgresClientWorker {
}
_ => {
error!("Error in receiving the item {:?}", err);
if panic_on_db_errors {
abort();
}
break;
}
},
@ -616,6 +708,10 @@ impl ParallelPostgresClient {
let worker = Builder::new()
.name(format!("worker-{}", i))
.spawn(move || -> Result<(), AccountsDbPluginError> {
let panic_on_db_errors = *config
.panic_on_db_errors
.as_ref()
.unwrap_or(&DEFAULT_PANIC_ON_DB_ERROR);
let result = PostgresClientWorker::new(config);
match result {
@ -626,10 +722,17 @@ impl ParallelPostgresClient {
exit_clone,
is_startup_done_clone,
startup_done_count_clone,
panic_on_db_errors,
)?;
Ok(())
}
Err(err) => Err(err),
Err(err) => {
error!("Error when making connection to database: ({})", err);
if panic_on_db_errors {
abort();
}
Err(err)
}
}
})
.unwrap();