mirror of https://github.com/schoebel/mars
Merge branch 'mars0.1.y' into mars0.1a.y
This commit is contained in:
Thomas Schoebel-Theuer
commit
71720650c3
11
ChangeLog
11
ChangeLog
|
|
@ -285,6 +285,17 @@ Hint: branch 0.1a will get a merge from here, and then get the
|
|||
(except Football related ones) will then go to 0.1b.
|
||||
Finally, when 0.1a is stable, I will close this branch.
|
||||
|
||||
mars0.1stable60
|
||||
* Major improvement: new option --ignore-sync allows primary
|
||||
Handover without --force even when some sync is running
|
||||
somewhere. Any running syncs will restart from scratch
|
||||
(which might take some time, depending on LV size and
|
||||
many more factors like the network).
|
||||
* Minor fix: split-cluster did not work correctly when no
|
||||
resources were existing anymore, at all.
|
||||
* Doc: major update. More explanation on CAP theorem, and
|
||||
on differences / commonalities with DRBD.
|
||||
|
||||
mars0.1stable59
|
||||
* Major fix: "marsadm up" did not work when sync could not
|
||||
be started. Now does "best effort".
|
||||
|
|
|
|||
|
|
@ -44,7 +44,9 @@ Actions for inplace FS shrinking:
|
|||
|
||||
Actions for inplace FS extension:
|
||||
|
||||
./football.sh expand <resource> <percent>
|
||||
./football.sh extend <resource> <percent>
|
||||
Increase mounted filesystem size during operations.
|
||||
|
||||
Combined actions:
|
||||
|
||||
|
|
@ -168,6 +170,11 @@ General features:
|
|||
# Set this to your convenience.
|
||||
football_logdir="${football_logdir:-${logdir:-$HOME/football-logs}}"
|
||||
|
||||
## football_backup_dir
|
||||
# In this directory, various backups are created.
|
||||
# Intended for manual repair.
|
||||
football_backup_dir="${football_backup_dir:-$football_logdir/backups}"
|
||||
|
||||
## screener
|
||||
# When enabled, handover execution to the screener.
|
||||
# Very useful for running Football in masses.
|
||||
|
|
@ -201,6 +208,11 @@ General features:
|
|||
# of the temporary shrink mirror filesystem.
|
||||
rsync_opt_prepare="${rsync_opt_prepare:---exclude='.filemon2' --delete}"
|
||||
|
||||
## rsync_opt_hot
|
||||
# This is only used at the final rsync, immediately before going
|
||||
# online again.
|
||||
rsync_opt_hot="${rsync_opt_hot:---delete}"
|
||||
|
||||
## rsync_nice
|
||||
# Typically, the preparation steps are run with background priority.
|
||||
rsync_nice="${rsync_nice:-nice -19}"
|
||||
|
|
@ -215,6 +227,42 @@ General features:
|
|||
# Number of rsync lines to skip in output (avoid overflow of logfiles).
|
||||
rsync_skip_lines="${rsync_skip_lines:-1000}"
|
||||
|
||||
## use_tar
|
||||
# Use incremental Gnu tar in place of rsync:
|
||||
# 0 = don't use tar
|
||||
# 1 = only use for the first (full) data transfer, then use rsync
|
||||
# 2 = always use tar
|
||||
# Experience: tar has better performance on local data than rsync, but
|
||||
# it tends to produce false-positive failure return codes on online
|
||||
# filesystems which are altered during tar.
|
||||
# The combined mode 1 tries to find a good compromise between both
|
||||
# alternatives.
|
||||
use_tar="${use_tar:-1}"
|
||||
|
||||
## tar_exe
|
||||
# Use this for activation of patched tar versions, such as the
|
||||
# 1&1-internal patched spacetools-tar.
|
||||
tar_exe="${tar_exe:-/bin/tar}"
|
||||
|
||||
## tar_options_src and tar_options_dst
|
||||
# Here you may give different options for both sides of tar invocations
|
||||
# (source and destination), such as verbosity options etc.
|
||||
tar_options_src="${tar_options_src:-}"
|
||||
tar_options_dst="${tar_options_dst:-}"
|
||||
|
||||
## tar_is_fixed
|
||||
# Tell whether your tar version reports false-positive transfer errors,
|
||||
# or not.
|
||||
tar_is_fixed="${tar_is_fixed:-0}"
|
||||
|
||||
## tar_state_dir
|
||||
# This directory is used for keeping incremental tar state information.
|
||||
tar_state_dir="${tar_state_dir:-/var/tmp}"
|
||||
|
||||
## buffer_cmd
|
||||
# Speed up tar by intermediate buffering.
|
||||
buffer_cmd="${buffer_cmd:-buffer -m 16m -S 1024m || cat}"
|
||||
|
||||
## wait_timeout
|
||||
# Avoid infinite loops upon waiting.
|
||||
wait_timeout="${wait_timeout:-$(( 24 * 60 ))}" # Minutes
|
||||
|
|
@ -223,6 +271,11 @@ General features:
|
|||
# Some LVM versions are requiring this for unattended batch operations.
|
||||
lvremove_opt="${lvremove_opt:--f}"
|
||||
|
||||
## automatic recovery options: enable_failure_*
|
||||
enable_failure_restart_vm="${enable_failure_restart_vm:-1}"
|
||||
enable_failure_recreate_cluster="${enable_failure_recreate_cluster:-0}"
|
||||
enable_failure_rebuild_mars="${enable_failure_rebuild_mars:-1}"
|
||||
|
||||
## critical_status
|
||||
# This is the "magic" exit code indicating _criticality_
|
||||
# of a failed command.
|
||||
|
|
@ -281,5 +334,394 @@ General features:
|
|||
PLUGIN football-1and1config
|
||||
|
||||
1&1 specfic plugin for dealing with the cm3 clusters
|
||||
and its concrete configuration .
|
||||
and its concrete configuration.
|
||||
|
||||
## enable_1and1config
|
||||
# ShaHoLin-specifc plugin for working with the infong platform
|
||||
# (istore, icpu, infong) via 1&1-specific clustermanager cm3
|
||||
# and related toolsets. Much of it is bound to a singleton database
|
||||
# instance (clustermw & siblings).
|
||||
enable_1and1config="${enable_1and1config:-$(if [[ "$0" =~ tetris ]]; then echo 1; else echo 0; fi)}"
|
||||
|
||||
|
||||
PLUGIN football-cm3
|
||||
|
||||
1&1 specfic plugin for dealing with the cm3 cluster manager
|
||||
and its concrete operating enviroment (singleton instance).
|
||||
|
||||
Current maximum cluster size limit:
|
||||
|
||||
Maximum #syncs running before migration can start:
|
||||
|
||||
Following marsadm --version must be installed:
|
||||
|
||||
Following mars kernel modules must be loaded:
|
||||
|
||||
Specific actions for plugin football-cm3:
|
||||
|
||||
./football.sh clustertool {GET|PUT} <url>
|
||||
Call through to the clustertool via REST.
|
||||
Useful for manual inspection and repair.
|
||||
|
||||
## enable_cm3
|
||||
# ShaHoLin-specifc plugin for working with the infong platform
|
||||
# (istore, icpu, infong) via 1&1-specific clustermanager cm3
|
||||
# and related toolsets. Much of it is bound to a singleton database
|
||||
# instance (clustermw & siblings).
|
||||
enable_cm3="${enable_cm3:-$(if [[ "$0" =~ tetris ]]; then echo 1; else echo 0; fi)}"
|
||||
|
||||
## skip_resource_ping
|
||||
# Enable this only for testing. Normally, a resource name denotes a
|
||||
# container name == machine name which must be runnuing as a precondition,
|
||||
# und thus must be pingable over network.
|
||||
skip_resource_ping="${skip_resource_ping:-0}"
|
||||
|
||||
## date_lock
|
||||
# Don't enter critical sections at certain days of the week,
|
||||
# and/or during certain hours.
|
||||
# This is a regex matching against "date +%u_%H"
|
||||
date_lock="${date_lock:-}"
|
||||
|
||||
## check_ping_rounds
|
||||
# Number of pings to try before a container is assumed to
|
||||
# not respond.
|
||||
check_ping_rounds="${check_ping_rounds:-5}"
|
||||
|
||||
## workaround_firewall
|
||||
# Documentation of technical debt for later generations:
|
||||
# This is needed since July 2017. In the many years before, no firewalling
|
||||
# was effective at the replication network, because it is a physically
|
||||
# separate network from the rest of the networking infrastructure.
|
||||
# An attacker would first need to gain root access to the _hypervisor_
|
||||
# (not only to the LXC container and/or to KVM) before gaining access to
|
||||
# those physical replication network interfaces.
|
||||
# Since about that time, which is about the same time when the requirements
|
||||
# for Container Football had been communicated, somebody introduced some
|
||||
# unnecessary firewall rules, based on "security arguments".
|
||||
# These arguments were however explicitly _not_ required by the _real_
|
||||
# security responsible person, and explicitly _not_ recommended by him.
|
||||
# Now the problem is that it is almost politically impossible to get
|
||||
# rid of suchalike "security feature".
|
||||
# Until the problem is resolved, Container Football requires
|
||||
# the _entire_ local firewall to be _temporarily_ shut down in order to
|
||||
# allow marsadm commands over ssh to work.
|
||||
# Notice: this is _not_ increasing the general security in any way.
|
||||
# LONGTERM solution / TODO: future versions of mars should no longer
|
||||
# depend on ssh.
|
||||
# Then this "feature" can be turned off.
|
||||
workaround_firewall="${workaround_firewall:-1}"
|
||||
|
||||
## ip_magic
|
||||
# Similarly to workaround_firewall, this is needed since somebody
|
||||
# introduced additional firewall rules also disabling sysadmin ssh
|
||||
# connections at the _ordinary_ sysadmin network.
|
||||
ip_magic="${ip_magic:-1}"
|
||||
|
||||
## do_split_cluster
|
||||
# The current MARS branch 0.1a.y is not yet constructed for forming
|
||||
# a BigCluster constisting of several thousands of machines.
|
||||
# When a future version of mars0.1b.y (or 0.2.y) will allow this,
|
||||
# this can be disabled.
|
||||
do_split_cluster="${do_split_cluster:-1}"
|
||||
|
||||
## forbidden_hosts
|
||||
# Regex for excluding hostnames from any Football actions.
|
||||
# The script will fail when some of these is encountered.
|
||||
forbidden_hosts="${forbidden_hosts:-}"
|
||||
|
||||
## forbidden_flavours
|
||||
# Regex for excluding flavours from any Football actions.
|
||||
# The script will fail when some of these is encountered.
|
||||
forbidden_flavours="${forbidden_flavours:-}"
|
||||
|
||||
## forbidden_bz_ids
|
||||
# PROVISIONARY regex for excluding certain bz_ids from any Football actions.
|
||||
# NOTICE: bz_ids are deprecated and should not be used in future
|
||||
# (technical debts).
|
||||
# The script will fail when some of these is encountered.
|
||||
forbidden_bz_ids="${forbidden_bz_ids:-}"
|
||||
|
||||
## clustertool_host
|
||||
# URL prefix of the internal configuation database REST interface.
|
||||
clustertool_host="${clustertool_host:-http://clustermw:3042}"
|
||||
|
||||
## clustertool_user
|
||||
# Username for clustertool access.
|
||||
# By default, scans for a *.password file (see next option).
|
||||
clustertool_user="${clustertool_user:-$(get_cred_file "*.password" | head -1 | sed 's:.*/::g' | cut -d. -f1)}"
|
||||
|
||||
## clustertool_passwd_file
|
||||
# Here you can supply the encrpted password.
|
||||
# By default, a file $clustertool_user.password is used
|
||||
# containing the encrypted password.
|
||||
clustertool_passwd_file="${clustertool_passwd_file:-$(get_cred_file "$clustertool_user.password")}"
|
||||
|
||||
## clustertool_passwd
|
||||
# Here you may override the password via config file.
|
||||
# For security reasons, dont provide this at the command line.
|
||||
clustertool_passwd="${clustertool_passwd:-$(< $clustertool_passwd_file)}" || echo "cannot read a password file *.password for clustermw: you MUST supply the credentials via default curl config files (see man page)"
|
||||
|
||||
## do_migrate
|
||||
# Keep this enabled. Only disable for testing.
|
||||
do_migrate="${do_migrate:-1}" # must be enabled; disable for dry-run testing
|
||||
|
||||
## always_migrate
|
||||
# Only use for testing, or for special situation.
|
||||
# This skip the test whether the resource has already migration.
|
||||
always_migrate="${always_migrate:-0}" # only enable for testing
|
||||
|
||||
## check_segments
|
||||
# 0 = disabled
|
||||
# 1 = only display the segment names
|
||||
# 2 = check for equality
|
||||
# WORKAROUND, potentially harmful when used inadequately.
|
||||
# The historical physical segment borders need to be removed for
|
||||
# Container Football.
|
||||
# Unfortunately, the subproject aiming to accomplish this did not
|
||||
# proceed for one year now. In the meantime, Container Football can
|
||||
# be only played within the ancient segment borders.
|
||||
# After this big impediment is eventually resolved, this option
|
||||
# should be switched off.
|
||||
check_segments="${check_segments:-1}"
|
||||
|
||||
## enable_mod_deflate
|
||||
# Internal, for support.
|
||||
enable_mod_deflate="${enable_mod_deflate:-1}"
|
||||
|
||||
## enable_segment_move
|
||||
# Seems to be needed by some other tooling.
|
||||
enable_segment_move="${enable_segment_move:-1}"
|
||||
|
||||
## override_hwclass_id
|
||||
# When necessary, override this from $include_dir/plugins/*.conf
|
||||
override_hwclass_id="${override_hwclass_id:-}" # typically 25007
|
||||
|
||||
## override_hvt_id
|
||||
# When necessary, override this from $include_dir/plugins/*.conf
|
||||
override_hvt_id="${override_hvt_id:-}" # typically 8057 or 8059
|
||||
|
||||
## override_overrides
|
||||
# When this is set and other override_* variables are not set,
|
||||
# then try to _guess_ some values.
|
||||
# No guarantees for correctness either.
|
||||
override_overrides=${override_overrides:-1}
|
||||
|
||||
## iqn_base and iet_type and iscsi_eth and iscsi_tid
|
||||
# Workaround: this is needed for _dynamic_ generation of iSCSI sessions
|
||||
# bypassing the ordinary ones as automatically generated by the
|
||||
# cm3 cluster manager (only at the old istore architecture).
|
||||
# Notice: not needed for regular operations, only for testing.
|
||||
# Normally, you dont want to shrink over a _shared_ 1MBit iSCSI line.
|
||||
iqn_base="${iqn_base:-iqn.2000-01.info.test:test}"
|
||||
iet_type="${iet_type:-blockio}"
|
||||
iscsi_eth="${iscsi_eth:-eth1}"
|
||||
iscsi_tid="${iscsi_tid:-4711}"
|
||||
|
||||
## monitis_downtime_script
|
||||
# ShaHoLin-internal
|
||||
monitis_downtime_script="${monitis_downtime_script:-}"
|
||||
|
||||
## monitis_downtime_duration
|
||||
# ShaHoLin-internal
|
||||
monitis_downtime_duration="${monitis_downtime_duration:-20}" # Minutes
|
||||
|
||||
## shaholin_finished_log
|
||||
# ShaHoLin-specific logfile, reporting _only_ successful completion
|
||||
# of an action.
|
||||
shaholin_finished_log="${shaholin_finished_log:-$football_logdir/shaholin-finished.log}"
|
||||
|
||||
## ticket
|
||||
# OPTIONAL: the meaning is ShaHoLin specific.
|
||||
# This can be used for updating JIRA tickets.
|
||||
# Can be set on the command line like "./tetris.sh $args --ticket=TECCM-4711
|
||||
ticket="${ticket:-}"
|
||||
|
||||
## ticket_get_cmd
|
||||
# Optional: when set, this script can be used for retrieving ticket IDs
|
||||
# in place of commandline option --ticket=
|
||||
ticket_get_cmd="${ticket_get_cmd:-}"
|
||||
|
||||
## ticket_update_cmd
|
||||
# This can be used for calling an external command which updates
|
||||
# the ticket(s) given by the $ticket parameter.
|
||||
ticket_update_cmd="${ticket_update_cmd:-}"
|
||||
|
||||
## shaholin_action
|
||||
# OPTIONAL: specific action script with parameters.
|
||||
shaholin_action="${shaholin_action:-}"
|
||||
|
||||
|
||||
PLUGIN football-basic
|
||||
|
||||
Generic driver for systemd-controlled MARS pools.
|
||||
The current version supports only a flat model:
|
||||
(1) There is a single "big cluster" at metadata level.
|
||||
All cluster members are joined via merge-cluster.
|
||||
All occurring names need to be globally unique.
|
||||
(2) The network uses BGP or other means, thus any hypervisor
|
||||
can (potentially) start any VM at any time.
|
||||
(3) iSCSI or remote devices are not supported for now
|
||||
(LocalSharding model). This may be extended in a future
|
||||
release.
|
||||
This plugin is exclusive-or with cm3.
|
||||
|
||||
Plugin specific actions:
|
||||
|
||||
./football.sh basic_add_host <hostname>
|
||||
Manually add another host to the hostname cache.
|
||||
|
||||
## pool_cache_dir
|
||||
# Directory for caching the pool status.
|
||||
pool_cache_dir="${pool_cache_dir:-$script_dir/pool-cache}"
|
||||
|
||||
## initial_hostname_file
|
||||
# This file must contain a list of storage and/or hypervisor hostnames
|
||||
# where a /mars directory must exist.
|
||||
# These hosts are then scanned for further cluster members,
|
||||
# and the transitive closure of all host names is computed.
|
||||
initial_hostname_file="${initial_hostname_file:-./hostnames.input}"
|
||||
|
||||
## hostname_cache
|
||||
# This file contains the transitive closure of all host names.
|
||||
hostname_cache="${hostname_cache:-$pool_cache_dir/hostnames.cache}"
|
||||
|
||||
## resources_cache
|
||||
# This file contains the transitive closure of all resource names.
|
||||
resources_cache="${resources_cache:-$pool_cache_dir/resources.cache}"
|
||||
|
||||
## res2hyper_cache
|
||||
# This file contains the association between resources and hypervisors.
|
||||
res2hyper_cache="${res2hyper_cache:-$pool_cache_dir/res2hyper.assoc}"
|
||||
|
||||
## enable_basic
|
||||
# This plugin is exclusive-or with cm3.
|
||||
enable_basic="${enable_basic:-$(if [[ "$0" =~ football ]]; then echo 1; else echo 0; fi)}"
|
||||
|
||||
## ssh_port
|
||||
# Set this for separating sysadmin access from customer access
|
||||
ssh_port="${ssh_port:-}"
|
||||
|
||||
## basic_mnt_dir
|
||||
# Names the mountpoint directory at hypervisors.
|
||||
# This must co-incide with the systemd mountpoints.
|
||||
basic_mnt_dir="${basic_mnt_dir:-/mnt}"
|
||||
|
||||
|
||||
PLUGIN football-downtime
|
||||
|
||||
Generic plugin for communication of customer downtime.
|
||||
|
||||
## downtime_cmd_{set,unset}
|
||||
# External command for setting / unsetting (or communicating) a downtime
|
||||
# Empty = don't do anything
|
||||
downtime_cmd_set="${downtime_cmd_set:-}"
|
||||
downtime_cmd_unset="${downtime_cmd_unset:-}"
|
||||
|
||||
|
||||
PLUGIN football-motd
|
||||
|
||||
Generic plugin for motd. Communicate that Football is running
|
||||
at login via motd.
|
||||
|
||||
## enable_motd
|
||||
# whether to use the motd plugin.
|
||||
enable_motd="${enable_motd:-0}"
|
||||
|
||||
## update_motd_cmd
|
||||
# Distro-specific command for generating motd from several sources.
|
||||
# Only tested for Debian Jessie at the moment.
|
||||
update_motd_cmd="${update_motd_cmd:-update-motd}"
|
||||
|
||||
## download_motd_script and motd_script_dir
|
||||
# When no script has been installed into /etc/update-motd.d/
|
||||
# you can do it dynamically here, bypassing any "official" deployment
|
||||
# methods. Use this only for testing!
|
||||
# An example script (which should be deployed via your ordinary methods)
|
||||
# can be found under $script_dir/update-motd.d/67-football-running
|
||||
download_motd_script="${download_motd_script:-}"
|
||||
motd_script_dir="${motd_script_dir:-/etc/update-motd.d}"
|
||||
|
||||
## motd_file
|
||||
# This will contain the reported motd message.
|
||||
# It is created by this plugin.
|
||||
motd_file="${motd_file:-/var/motd/football.txt}"
|
||||
|
||||
## motd_color_on and motd_color_off
|
||||
# ANSI escape sequences for coloring the generated motd message.
|
||||
motd_color_on="${motd_color_on:-\\033[31m}"
|
||||
motd_color_off="${motd_color_off:-\\033[0m}"
|
||||
|
||||
|
||||
PLUGIN football-report
|
||||
|
||||
Generic plugin for communication of reports.
|
||||
|
||||
## report_cmd_{start,warning,failed,finished}
|
||||
# External command which is called at start / failure / finish
|
||||
# of Football.
|
||||
# The following variables can be used (e.g. as parameters) when
|
||||
# escaped with a backslash:
|
||||
# $res = name of the resource (LV, container, etc)
|
||||
# $primary = the current (old)
|
||||
# $secondary_list = list of current (old) secondaries
|
||||
# $target_primary = the target primary name
|
||||
# $target_secondary = list of target secondaries
|
||||
# $operation = the operation name
|
||||
# $target_percent = the value used for shrinking
|
||||
# $txt = some informative text from Football
|
||||
# Further variables are possible by looking at the sourcecode, or by
|
||||
# defining your own variables or functions externally or via plugins.
|
||||
# Empty = don't do anything
|
||||
report_cmd_start="${report_cmd_start:-}"
|
||||
report_cmd_warning="${report_cmd_warning:-$script_dir/screener.sh notify "$res" warning "$txt"}"
|
||||
report_cmd_failed="${report_cmd_failed:-}"
|
||||
report_cmd_finished="${report_cmd_finished:-}"
|
||||
|
||||
|
||||
PLUGIN football-waiting
|
||||
|
||||
Generic plugig, interfacing with screener: when this is used
|
||||
by your script and enabled, then you will be able to wait for
|
||||
"screener.sh continue" operations at certain points in your
|
||||
script.
|
||||
|
||||
## enable_*_waiting
|
||||
#
|
||||
# When this is enabled, and when Football had been started by screener,
|
||||
# then football will delay the start of several operations until a sysadmin
|
||||
# does one of the following manually:
|
||||
#
|
||||
# a) ./screener.sh continue $session
|
||||
# b) ./screener.sh resume $session
|
||||
# c) ./screener.sh attach $session and press the RETURN key
|
||||
# d) doing nothing, and $wait_timeout has exceeded
|
||||
#
|
||||
# CONVENTION: football resource names are used as screener session ids.
|
||||
# This ensures that only 1 operation can be started for the same resource,
|
||||
# and it simplifies the handling for junior sysadmins.
|
||||
#
|
||||
enable_startup_waiting="${enable_startup_waiting:-0}"
|
||||
enable_handover_waiting="${enable_handover_waiting:-0}"
|
||||
enable_migrate_waiting="${enable_migrate_waiting:-0}"
|
||||
enable_shrink_waiting="${enable_shrink_waiting:-0}"
|
||||
|
||||
## enable_cleanup_delayed and wait_before_cleanup
|
||||
# By setting this, you can delay the cleanup operations for some time.
|
||||
# This way, you are keeping the old LV contents as a kind of "backup"
|
||||
# for some limited time.
|
||||
# HINT: dont set to wait_before_cleanuplarge values, because it can
|
||||
# seriously slow down Football.
|
||||
enable_cleanup_delayed="${enable_cleanup_delayed:-0}"
|
||||
wait_before_cleanup="${wait_before_cleanup:-180}" # Minutes
|
||||
|
||||
## reduce_wait_msg
|
||||
# Instead of reporting the waiting status once per minute,
|
||||
# decrease the frequency of resporting.
|
||||
# Warning: dont increase this too much. Do not exceed
|
||||
# session_timeout/2 from screener. Because of the Nyquist criterion,
|
||||
# stay on the safe side by setting session_timeout at least to _twice_
|
||||
# the time than here.
|
||||
reduce_wait_msg="${reduce_wait_msg:-60}" # Minutes
|
||||
|
||||
|
||||
\end{verbatim}
|
||||
|
|
|
|||
|
|
@ -43,7 +43,9 @@ Actions for inplace FS shrinking:
|
|||
|
||||
Actions for inplace FS extension:
|
||||
|
||||
./football.sh expand <resource> <percent>
|
||||
./football.sh extend <resource> <percent>
|
||||
Increase mounted filesystem size during operations.
|
||||
|
||||
Combined actions:
|
||||
|
||||
|
|
@ -126,7 +128,8 @@ General features:
|
|||
PLUGIN football-1and1config
|
||||
|
||||
1&1 specfic plugin for dealing with the cm3 clusters
|
||||
and its concrete configuration .
|
||||
and its concrete configuration.
|
||||
|
||||
|
||||
PLUGIN football-cm3
|
||||
|
||||
|
|
@ -141,6 +144,12 @@ PLUGIN football-cm3
|
|||
|
||||
Following mars kernel modules must be loaded:
|
||||
|
||||
Specific actions for plugin football-cm3:
|
||||
|
||||
./football.sh clustertool {GET|PUT} <url>
|
||||
Call through to the clustertool via REST.
|
||||
Useful for manual inspection and repair.
|
||||
|
||||
|
||||
PLUGIN football-basic
|
||||
|
||||
|
|
@ -162,6 +171,11 @@ Plugin specific actions:
|
|||
Manually add another host to the hostname cache.
|
||||
|
||||
|
||||
PLUGIN football-downtime
|
||||
|
||||
Generic plugin for communication of customer downtime.
|
||||
|
||||
|
||||
PLUGIN football-motd
|
||||
|
||||
Generic plugin for motd. Communicate that Football is running
|
||||
|
|
@ -180,4 +194,5 @@ PLUGIN football-waiting
|
|||
"screener.sh continue" operations at certain points in your
|
||||
script.
|
||||
|
||||
|
||||
\end{verbatim}
|
||||
|
|
|
|||
|
|
@ -0,0 +1,17 @@
|
|||
#FIG 3.2 Produced by xfig version 3.2.5c
|
||||
Landscape
|
||||
Center
|
||||
Metric
|
||||
A4
|
||||
100.00
|
||||
Single
|
||||
-2
|
||||
1200 2
|
||||
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 4
|
||||
450 1800 1800 0 3150 1800 450 1800
|
||||
2 1 0 3 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
|
||||
1800 0 3150 1800
|
||||
4 0 0 50 -1 18 12 0.0000 4 195 1515 2115 90 C = Consistency\001
|
||||
4 0 0 50 -1 18 12 0.0000 4 195 1410 405 2115 A = Availability\001
|
||||
4 0 0 50 -1 18 12 0.0000 4 195 2445 3060 2070 P = Partitioning Tolerance\001
|
||||
4 0 4 50 -1 18 40 0.0000 4 480 435 450 2025 X\001
|
||||
|
|
@ -0,0 +1,17 @@
|
|||
#FIG 3.2 Produced by xfig version 3.2.5c
|
||||
Landscape
|
||||
Center
|
||||
Metric
|
||||
A4
|
||||
100.00
|
||||
Single
|
||||
-2
|
||||
1200 2
|
||||
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 4
|
||||
450 1800 1800 0 3150 1800 450 1800
|
||||
2 1 0 3 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
|
||||
3150 1800 450 1800
|
||||
4 0 0 50 -1 18 12 0.0000 4 195 1515 2115 90 C = Consistency\001
|
||||
4 0 0 50 -1 18 12 0.0000 4 195 1410 405 2115 A = Availability\001
|
||||
4 0 0 50 -1 18 12 0.0000 4 195 2445 3060 2070 P = Partitioning Tolerance\001
|
||||
4 0 4 50 -1 18 40 0.0000 4 480 435 1755 360 X\001
|
||||
|
|
@ -0,0 +1,16 @@
|
|||
#FIG 3.2 Produced by xfig version 3.2.5c
|
||||
Landscape
|
||||
Center
|
||||
Metric
|
||||
A4
|
||||
100.00
|
||||
Single
|
||||
-2
|
||||
1200 2
|
||||
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 4
|
||||
450 1800 1800 0 3150 1800 450 1800
|
||||
2 1 0 3 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
|
||||
1800 0 450 1800
|
||||
4 0 0 50 -1 18 12 0.0000 4 195 1515 2115 90 C = Consistency\001
|
||||
4 0 0 50 -1 18 12 0.0000 4 195 1410 405 2115 A = Availability\001
|
||||
4 0 0 50 -1 18 12 0.0000 4 195 2445 3060 2070 P = Partitioning Tolerance\001
|
||||
|
|
@ -0,0 +1,16 @@
|
|||
#FIG 3.2 Produced by xfig version 3.2.5c
|
||||
Landscape
|
||||
Center
|
||||
Metric
|
||||
A4
|
||||
100.00
|
||||
Single
|
||||
-2
|
||||
1200 2
|
||||
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 4
|
||||
450 1800 1800 0 3150 1800 450 1800
|
||||
2 1 0 3 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
|
||||
3150 1800 450 1800
|
||||
4 0 0 50 -1 18 12 0.0000 4 195 1410 405 2115 A = Availability\001
|
||||
4 0 0 50 -1 18 12 0.0000 4 195 2445 3060 2070 P = Partitioning Tolerance\001
|
||||
4 0 0 50 -1 18 12 0.0000 4 195 1515 2115 90 C = Consistency\001
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
#FIG 3.2 Produced by xfig version 3.2.5c
|
||||
Landscape
|
||||
Center
|
||||
Metric
|
||||
A4
|
||||
100.00
|
||||
Single
|
||||
-2
|
||||
1200 2
|
||||
2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 4
|
||||
450 1800 1800 0 3150 1800 450 1800
|
||||
4 0 0 50 -1 18 12 0.0000 4 195 1515 2115 90 C = Consistency\001
|
||||
4 0 0 50 -1 18 12 0.0000 4 195 1410 405 2115 A = Availability\001
|
||||
4 0 0 50 -1 18 12 0.0000 4 195 2445 3060 2070 P = Partitioning Tolerance\001
|
||||
1533
docu/mars-manual.lyx
1533
docu/mars-manual.lyx
File diff suppressed because it is too large
Load Diff
|
|
@ -13,6 +13,10 @@ marsadm [<global_options>] view[-<macroname>] [<resource_name> | all ]
|
|||
Use this only when you really know what you are doing!
|
||||
Warning! This is dangerous! First try --dry-run.
|
||||
Not combinable with 'all'.
|
||||
--ignore-sync
|
||||
Allow primary handover even when some sync is running somewhere.
|
||||
This is less rude than --force because it checks for all else
|
||||
preconditions.
|
||||
--dry-run
|
||||
Don't modify the symlink tree, but tell what would be done.
|
||||
Use this before starting potentially harmful actions such as
|
||||
|
|
@ -567,5 +571,4 @@ marsadm [<global_options>] view[-<macroname>] [<resource_name> | all ]
|
|||
{sync,fetch,replay,work}-{rest,{almost-,threshold-,}reached,percent,permille,vector}
|
||||
{sync,fetch,replay}-{rate,remain}
|
||||
{time,real-time}
|
||||
{tree,features}-version
|
||||
\end{verbatim}
|
||||
|
|
|
|||
|
|
@ -106,7 +106,7 @@ sub lwarn {
|
|||
|
||||
my $Id = '$Id$ ';
|
||||
my $user_version = 0.1;
|
||||
my $marsadm_version = 2.3; # some rough hint at newer features
|
||||
my $marsadm_version = 2.4; # some rough hint at newer features
|
||||
my $mars = "/mars";
|
||||
my $host = `uname -n` or ldie "cannot determine my network node name\n";
|
||||
chomp $host;
|
||||
|
|
@ -114,6 +114,7 @@ check_id($host);
|
|||
my $real_host = $host;
|
||||
my $backup_dir = "$mars/backups-" . time();
|
||||
my $force = 0;
|
||||
my $ignore_sync = 0;
|
||||
my $cron_mode = 0;
|
||||
my $timeout = -1;
|
||||
my $ip = "";
|
||||
|
|
@ -2623,7 +2624,7 @@ sub split_cluster {
|
|||
$cmd .= "shopt -s nullglob; ";
|
||||
$cmd .= "for i in $mars/resource-*; do if ! [[ -e \$i/data-$peer ]] && ! [[ -e \$i/replay-$peer ]]; then rm -rf $backup_dir/\${i##*/}; mv \$i $backup_dir/; fi; done; ";
|
||||
$cmd .= "mkdir -p $mars/ips; ";
|
||||
my $sub_list = "{ for i in \$(ls $mars/resource-*/data-$peer | cut -d/ -f1-3 | sort -u); do (cd \$i; ls data-*); done; echo x-$peer; }";
|
||||
my $sub_list = "{ for dir in $mars/resource-*/data-$peer; do (cd \${dir%/*} && for i in data-*; do echo \$i; done); done; echo x-$peer; }";
|
||||
my $sub_cmd = "echo RESTORE IP \$j; cp -a $ips_backup/ip-\$j $mars/ips/";
|
||||
$cmd .= "for j in \$($sub_list | cut -d- -f2- | sort -u); do $sub_cmd; done";
|
||||
lprint "$cmd\n";
|
||||
|
|
@ -3172,16 +3173,19 @@ sub primary_phase0 {
|
|||
lprint "Current designated primary: $old\n";
|
||||
if ($cmd eq "primary") {
|
||||
if ($host ne $old) {
|
||||
check_sync_finished($res, $host);
|
||||
lprint "Allowing handover in cases of sync: ignore_sync=$ignore_sync\n" if $ignore_sync;
|
||||
check_sync_finished($res, $host, $ignore_sync);
|
||||
# also check that other secondaries won't loose their sync primary
|
||||
my @names = glob("$mars/resource-$res/data-*");
|
||||
# for k <= 2 replicas, the previous check must have been sufficient
|
||||
if (scalar(@names) > 2) {
|
||||
my $allow_anyway = ($force || $ignore_sync);
|
||||
lprint "Allowing handover in cases of sync: force=$force ignore_sync=$ignore_sync\n" if $allow_anyway;
|
||||
foreach my $name (@names) {
|
||||
$name =~ m:/data-(.+):;
|
||||
my $peer = $1;
|
||||
next if ($peer eq $old || $peer eq $host);
|
||||
check_sync_finished($res, $peer, $force);
|
||||
check_sync_finished($res, $peer, $allow_anyway);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -6120,6 +6124,10 @@ marsadm [<global_options>] view[-<macroname>] [<resource_names> | all ]
|
|||
Use this only when you really know what you are doing!
|
||||
Warning! This is dangerous! First try --dry-run.
|
||||
Not combinable with 'all'.
|
||||
--ignore-sync
|
||||
Allow primary handover even when some sync is running somewhere.
|
||||
This is less rude than --force because it checks for all else
|
||||
preconditions.
|
||||
--dry-run
|
||||
Don't modify the symlink tree, but tell what would be done.
|
||||
Use this before starting potentially harmful actions such as
|
||||
|
|
@ -6237,6 +6245,9 @@ foreach my $arg (@ARGV) {
|
|||
if ($arg eq "--force" || $arg eq "-f") {
|
||||
$force++;
|
||||
next;
|
||||
} elsif ($arg eq "--ignore-sync") {
|
||||
$ignore_sync++;
|
||||
next;
|
||||
} elsif ($arg eq "--dry-run" || $arg eq "-d") {
|
||||
$dry_run++;
|
||||
next;
|
||||
|
|
|
|||
Loading…
Reference in New Issue