[pgpool-general: 1092] PGPool hangs on pcp_attach/detach
Oleg Mürk
oleg.myrk at gmail.com
Wed Oct 17 19:47:30 JST 2012
Hello,
I am observing a situation when pgpool hangs in master/slave mode with
postgresql streaming replication:
* Start pgpool:
sudo pgpool -f /etc/pgpool2/mx_large-pgpool.conf -F
/etc/pgpool2/pcp.conf -a /etc/pgpool2/pool_hba.conf -n -d
* To reproduce:
$ sudo pcp_attach_node 100 localhost 9899 mx mx 1
$ sudo pcp_node_info 100 localhost 9899 mx mx 1
mx-db2 5434 1 0.600000
$ sudo pcp_detach_node 100 localhost 9899 mx mx 1
$ sudo pcp_node_info 100 localhost 9899 mx mx 1
*** hangs here ***
* Also connecting to the port hangs:
psql -p 6434 -U mx_large mx_large
* This freeze is not deterministic, but attaching/detaching standby
node and asking info for a few times will eventually freeze pgpool
* Pgpool version is: pgpool-II version 3.2.1, running on Debian
Wheezy, Postgresql 9.1
* Pgpool's debug output is attached (pgpool.out)
* Pgpool's conf is in the end of this email, changes are marked by #XXX:OM
On a related note which parts of pgpool.conf are reloaded by "pgpool reload".
Is it possible to add/remove standby nodes to pgpool using "pgpool
reload" or other means without losing existing connections to pgpool?
Thank You,
Oleg Mürk
$ sudo cat /etc/pgpool2/mx_large-pgpool.conf
# ----------------------------
# pgPool-II configuration file
# ----------------------------
#
# This file consists of lines of the form:
#
# name = value
#
# 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
# pgPool-II documentation.
#
# 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, or use "pgpool reload". Some
# parameters, which are marked below, require a server shutdown and restart to
# take effect.
#
#------------------------------------------------------------------------------
# CONNECTIONS
#------------------------------------------------------------------------------
# - pgpool Connection Settings -
listen_addresses = '*'
# Host name or IP address to listen on:
# '*' for all, '' for no TCP/IP connections
# (change requires restart)
port = 6434
# Port number
# (change requires restart)
socket_dir = '/var/run/postgresql'
# Unix domain socket path
# The Debian package defaults to
# /var/run/postgresql
# (change requires restart)
# - pgpool Communication Manager Connection Settings -
pcp_port = 9899
# Port number for pcp
# (change requires restart)
#XXX:OM
pcp_socket_dir = '/var/run/pgpool-mx_large'
# Unix domain socket path for pcp
# The Debian package defaults to
# /var/run/postgresql
# (change requires restart)
# - Backend Connection Settings -
backend_hostname0 = 'mx-db1'
# Host name or IP address to
connect to for backend 0
backend_port0 = 5434
# Port number for backend 0
backend_weight0 = 2
# Weight for backend 0 (only in
load balancing mode)
#backend_data_directory0 = '/data'
# Data directory for backend 0
backend_flag0 = 'DISALLOW_TO_FAILOVER'
# Controls various backend behavior
# ALLOW_TO_FAILOVER or DISALLOW_TO_FAILOVER
backend_hostname1 = 'mx-db2'
backend_port1 = 5434
backend_weight1 = 3
#backend_data_directory1 = '/data1'
#backend_flag1 = 'DISALLOW_TO_FAILOVER'
# - Authentication -
#XXX:OM
enable_pool_hba = on
# Use pool_hba.conf for client authentication
authentication_timeout = 60
# Delay in seconds to complete
client authentication
# 0 means no timeout.
#XXX:OM
pool_passwd = 'mx_large-pool_passwd'
# - SSL Connections -
ssl = off
# Enable SSL support
# (change requires restart)
#ssl_key = './server.key'
# Path to the SSL private key file
# (change requires restart)
#ssl_cert = './server.cert'
# Path to the SSL public certificate file
# (change requires restart)
#ssl_ca_cert = ''
# Path to a single PEM format file
# containing CA root certificate(s)
# (change requires restart)
#ssl_ca_cert_dir = ''
# Directory containing CA root certificate(s)
# (change requires restart)
#------------------------------------------------------------------------------
# POOLS
#------------------------------------------------------------------------------
# - Pool size -
#XXX:OM
num_init_children = 32
# Number of pools
# (change requires restart)
max_pool = 4
# Number of connections per pool
# (change requires restart)
# - Life time -
child_life_time = 300
# Pool exits after being idle for
this many seconds
child_max_connections = 0
# Pool exits after receiving that
many connections
# 0 means no exit
connection_life_time = 0
# Connection to backend closes
after being idle for this many seconds
# 0 means no close
client_idle_limit = 0
# Client is disconnected after
being idle for that many seconds
# (even inside an explicit transactions!)
# 0 means no disconnection
#------------------------------------------------------------------------------
# LOGS
#------------------------------------------------------------------------------
# - Where to log -
log_destination = 'stderr'
# Where to log
# Valid values are combinations of stderr,
# and syslog. Default to stderr.
# - What to log -
print_timestamp = on
# Print timestamp on each line
# (change requires restart)
#XXX:OM
log_connections = on
# Log connections
#XXX:OM
log_hostname = on
# Hostname will be shown in ps status
# and in logs if connections are logged
log_statement = off
# Log all statements
log_per_node_statement = off
# Log all statements
# with node and backend informations
log_standby_delay = 'none'
# Log standby delay
# Valid values are combinations of always,
# if_over_threshold, none
# - Syslog specific -
syslog_facility = 'LOCAL0'
# Syslog local facility. Default to LOCAL0
syslog_ident = 'pgpool'
# Syslog program identification string
# Default to 'pgpool'
# - Debug -
debug_level = 0
# Debug message verbosity level
# 0 means no message, 1 or more mean verbose
#------------------------------------------------------------------------------
# FILE LOCATIONS
#------------------------------------------------------------------------------
#XXX:OM
pid_file_name = '/var/run/pgpool-mx_large/pgpool.pid'
# PID file name
# (change requires restart)
#XXX:OM
logdir = '/var/run/pgpool-mx_large/'
# Directory of pgPool status file
# (change requires restart)
#------------------------------------------------------------------------------
# CONNECTION POOLING
#------------------------------------------------------------------------------
connection_cache = on
# Activate connection pools
# (change requires restart)
# Semicolon separated list of queries
# to be issued at the end of a session
# The default is for 8.3 and later
reset_query_list = 'ABORT; DISCARD ALL'
# The following one is for 8.2 and before
#reset_query_list = 'ABORT; RESET ALL; SET SESSION AUTHORIZATION DEFAULT'
#------------------------------------------------------------------------------
# REPLICATION MODE
#------------------------------------------------------------------------------
replication_mode = off
# Activate replication mode
# (change requires restart)
replicate_select = off
# Replicate SELECT statements
# when in replication or parallel mode
# replicate_select is higher priority than
# load_balance_mode.
insert_lock = on
# Automatically locks a dummy row or a table
# with INSERT statements to keep SERIAL data
# consistency
# Without SERIAL, no lock will be issued
lobj_lock_table = ''
# When rewriting lo_creat command in
# replication mode, specify table name to
# lock
# - Degenerate handling -
replication_stop_on_mismatch = off
# On disagreement with the packet kind
# sent from backend, degenerate the node
# which is most likely "minority"
# If off, just force to exit this session
failover_if_affected_tuples_mismatch = off
# On disagreement with the number of affected
# tuples in UPDATE/DELETE queries, then
# degenerate the node which is most likely
# "minority".
# If off, just abort the transaction to
# keep the consistency
#------------------------------------------------------------------------------
# LOAD BALANCING MODE
#------------------------------------------------------------------------------
#XXX:OM
load_balance_mode = on
# Activate load balancing mode
# (change requires restart)
ignore_leading_white_space = on
# Ignore leading white spaces of each query
white_function_list = ''
# Comma separated list of function names
# that don't write to database
# Regexp are accepted
black_function_list = 'nextval,setval'
# Comma separated list of function names
# that write to database
# Regexp are accepted
#------------------------------------------------------------------------------
# MASTER/SLAVE MODE
#------------------------------------------------------------------------------
#XXX:OM
master_slave_mode = on
# Activate master/slave mode
# (change requires restart)
#XXX:OM
master_slave_sub_mode = 'stream'
# Master/slave sub mode
# Valid values are combinations slony or
# stream. Default is slony.
# (change requires restart)
# - Streaming -
#XXX:OM
sr_check_period = 60
# Streaming replication check period
# Disabled (0) by default
#XXX:OM
sr_check_user = 'mx_large'
# Streaming replication check user
# This is necessary even if you disable
# streaming replication delay check with
# sr_check_period = 0
#XXX:OM
sr_check_password = 'mx_large'
# Password for streaming
replication check user
delay_threshold = 0
# Threshold before not dispatching
query to standby node
# Unit is in bytes
# Disabled (0) by default
# - Special commands -
follow_master_command = ''
# Executes this command after master failover
# Special values:
# %d = node id
# %h = host name
# %p = port number
# %D = database cluster path
# %m = new master node id
# %H = hostname of the new master node
# %M = old master node id
# %P = old primary node id
# %% = '%' character
#------------------------------------------------------------------------------
# PARALLEL MODE AND QUERY CACHE
#------------------------------------------------------------------------------
parallel_mode = off
# Activates parallel query mode
# (change requires restart)
enable_query_cache = off
# Activates query cache
# (change requires restart)
pgpool2_hostname = ''
# Set pgpool2 hostname
# (change requires restart)
# - System DB info -
system_db_hostname = 'localhost'
# (change requires restart)
system_db_port = 5432
# (change requires restart)
system_db_dbname = 'pgpool'
# (change requires restart)
system_db_schema = 'pgpool_catalog'
# (change requires restart)
system_db_user = 'pgpool'
# (change requires restart)
system_db_password = ''
# (change requires restart)
#------------------------------------------------------------------------------
# HEALTH CHECK
#------------------------------------------------------------------------------
health_check_period = 0
# Health check period
# Disabled (0) by default
health_check_timeout = 20
# Health check timeout
# 0 means no timeout
health_check_user = 'nobody'
# Health check user
health_check_password = ''
# This parameter is not yet implemented.
# Password for health check user
#------------------------------------------------------------------------------
# FAILOVER AND FAILBACK
#------------------------------------------------------------------------------
failover_command = ''
# Executes this command at failover
# Special values:
# %d = node id
# %h = host name
# %p = port number
# %D = database cluster path
# %m = new master node id
# %H = hostname of the new master node
# %M = old master node id
# %P = old primary node id
# %% = '%' character
failback_command = ''
# Executes this command at failback.
# Special values:
# %d = node id
# %h = host name
# %p = port number
# %D = database cluster path
# %m = new master node id
# %H = hostname of the new master node
# %M = old master node id
# %P = old primary node id
# %% = '%' character
fail_over_on_backend_error = on
# Initiates failover when writing to the
# backend communication socket fails
# This is the same behaviour of pgpool-II
# 2.2.x and previous releases
# If set to off, pgpool will report an
# error and disconnect the session.
#------------------------------------------------------------------------------
# ONLINE RECOVERY
#------------------------------------------------------------------------------
recovery_user = 'nobody'
# Online recovery user
recovery_password = ''
# Online recovery password
recovery_1st_stage_command = ''
# Executes a command in first stage
recovery_2nd_stage_command = ''
# Executes a command in second stage
recovery_timeout = 90
# Timeout in seconds to wait for the
# recovering node's postmaster to start up
# 0 means no wait
client_idle_limit_in_recovery = 0
# Client is disconnected after being idle
# for that many seconds in the second stage
# of online recovery
# 0 means no disconnection
# -1 means immediate disconnection
#------------------------------------------------------------------------------
# OTHERS
#------------------------------------------------------------------------------
relcache_expire = 0
# Life time of relation cache in seconds.
# 0 means no cache expiration(the default).
# The relation cache is used for cache the
# query result against PostgreSQL system
# catalog to obtain various information
# including table structures or if it's a
# temporary table or not. The cache is
# maintained in a pgpool child local memory
# and being kept as long as it survives.
# If someone modify the table by using
# ALTER TABLE or some such, the relcache is
# not consistent anymore.
# For this purpose, cache_expiration
# controls the life time of the cache.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: pgpool.out
Type: application/octet-stream
Size: 33582 bytes
Desc: not available
URL: <http://www.pgpool.net/pipermail/pgpool-general/attachments/20121017/f9bac377/attachment.obj>
More information about the pgpool-general
mailing list