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
0b21ab27f6
|
|
@ -282,6 +282,15 @@ 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.
|
||||
|
||||
mars0.1stable59
|
||||
* Major fix: "marsadm up" did not work when sync could not
|
||||
be started. Now does "best effort".
|
||||
* Minor fix: marsadm system interface was active when
|
||||
not activated.
|
||||
* Minor usability improvement: new repliaction state "Orphaned"
|
||||
indicates that logfiles are missing, and thus replication
|
||||
is stuck.
|
||||
|
||||
mars0.1stable58
|
||||
* Major fix for Football / split-cluster: for safety,
|
||||
cron deletes some blocking left-overs.
|
||||
|
|
|
|||
|
|
@ -25,6 +25,38 @@ Actions for resource migration:
|
|||
Remove old / currently unused LV replicas from MARS and deallocate
|
||||
from LVM.
|
||||
|
||||
Actions for inplace FS shrinking:
|
||||
|
||||
./football.sh shrink <resource> <percent>
|
||||
Run the sequence shrink_prepare ; shrink_finish ; shrink_cleanup.
|
||||
|
||||
./football.sh shrink_prepare <resource> [<percent>]
|
||||
Allocate temporary LVM space (when possible) and create initial
|
||||
raw FS copy.
|
||||
Default percent value(when left out) is 85.
|
||||
|
||||
./football.sh shrink_finish <resource>
|
||||
Incrementally update the FS copy, swap old <=> new copy with
|
||||
small downtime.
|
||||
|
||||
./football.sh shrink_cleanup <resource>
|
||||
Remove old FS copy from LVM.
|
||||
|
||||
Actions for inplace FS extension:
|
||||
|
||||
./football.sh extend <resource> <percent>
|
||||
|
||||
Combined actions:
|
||||
|
||||
./football.sh migrate+shrink <resource> <target_primary> [<target_secondary>] [<percent>]
|
||||
Similar to migrate ; shrink but produces less network traffic.
|
||||
Default percent value (when left out) is 85.
|
||||
|
||||
./football.sh migrate+shrink+back <resource> <tmp_primary> [<percent>]
|
||||
Migrate temporarily to <tmp_primary>, then shrink there,
|
||||
finally migrate back to old primary and secondaries.
|
||||
Default percent value (when left out) is 85.
|
||||
|
||||
Actions for (manual) repair in emergency situations:
|
||||
|
||||
./football.sh manual_migrate_config <resource> <target_primary> [<target_secondary>]
|
||||
|
|
@ -60,37 +92,10 @@ Actions for (manual) repair in emergency situations:
|
|||
get the customers online again, while buying the downsides of this
|
||||
command.
|
||||
|
||||
Actions for inplace FS shrinking:
|
||||
|
||||
./football.sh shrink <resource> <percent>
|
||||
Run the sequence shrink_prepare ; shrink_finish ; shrink_cleanup.
|
||||
|
||||
./football.sh shrink_prepare <resource> [<percent>]
|
||||
Allocate temporary LVM space (when possible) and create initial
|
||||
raw FS copy.
|
||||
Default percent value(when left out) is 85.
|
||||
|
||||
./football.sh shrink_finish <resource>
|
||||
Incrementally update the FS copy, swap old <=> new copy with
|
||||
small downtime.
|
||||
|
||||
./football.sh shrink_cleanup <resource>
|
||||
Remove old FS copy from LVM.
|
||||
|
||||
Actions for inplace FS extension:
|
||||
|
||||
./football.sh extend <resource> <percent>
|
||||
|
||||
Combined actions:
|
||||
|
||||
./football.sh migrate+shrink <resource> <target_primary> [<target_secondary>] [<percent>]
|
||||
Similar to migrate ; shrink but produces less network traffic.
|
||||
Default percent value (when left out) is 85.
|
||||
|
||||
./football.sh migrate+shrink+back <resource> <tmp_primary> [<percent>]
|
||||
Migrate temporarily to <tmp_primary>, then shrink there,
|
||||
finally migrate back to old primary and secondaries.
|
||||
Default percent value (when left out) is 85.
|
||||
./football.sh manual_lock <item> <host_list>
|
||||
./football.sh manual_unlock <item> <host_list>
|
||||
Manually lock or unlock an item at all of the given hosts, in
|
||||
an atomic fashion. In most cases, use "ALL" for the item.
|
||||
|
||||
Global maintenance:
|
||||
|
||||
|
|
@ -119,9 +124,20 @@ General features:
|
|||
attaches to the sessions and presses the RETURN key.
|
||||
|
||||
## football_includes
|
||||
# List of directories where football-*.conf files can be found.
|
||||
# List of directories where football-*.sh and football-*.conf
|
||||
# files can be found.
|
||||
football_includes="${football_includes:-/usr/lib/mars/plugins /etc/mars/plugins $script_dir/plugins $HOME/.mars/plugins ./plugins}"
|
||||
|
||||
## football_confs
|
||||
# Another list of directories where football-*.conf files can be found.
|
||||
# These are sourced in a second pass after $football_includes.
|
||||
# Thus you can change this during the first pass.
|
||||
football_confs="${football_confs:-/usr/lib/mars/confs /etc/mars/confs $script_dir/confs $HOME/.mars/confs ./confs}"
|
||||
|
||||
## football_creds
|
||||
# List of directories where various credential files can be found.
|
||||
football_creds="${football_creds:-/usr/lib/mars/creds /etc/mars/creds $script_dir/creds $script_dir $HOME/.mars/creds ./creds}"
|
||||
|
||||
## dry_run
|
||||
# When set, actions are only simulated.
|
||||
dry_run=${dry_run:-0}
|
||||
|
|
@ -195,6 +211,10 @@ General features:
|
|||
rsync_repeat_prepare="${rsync_repeat_prepare:-5}"
|
||||
rsync_repeat_hot="${rsync_repeat_hot:-3}"
|
||||
|
||||
## rsync_skip_lines
|
||||
# Number of rsync lines to skip in output (avoid overflow of logfiles).
|
||||
rsync_skip_lines="${rsync_skip_lines:-1000}"
|
||||
|
||||
## wait_timeout
|
||||
# Avoid infinite loops upon waiting.
|
||||
wait_timeout="${wait_timeout:-$(( 24 * 60 ))}" # Minutes
|
||||
|
|
@ -214,11 +234,24 @@ General features:
|
|||
serious_status="${serious_status:-198}"
|
||||
|
||||
## pre_hand or --pre-hand=
|
||||
# Set this to do an ordinary to a new start position before doing
|
||||
# anything else. This may be used for handover to a different datacenter
|
||||
# and running Football there.
|
||||
# Set this to do an ordinary handover to a new start position
|
||||
# (in the source cluster) before doing anything else.
|
||||
# This may be used for handover to a different datacenter,
|
||||
# in order to minimize cross traffic between datacenters.
|
||||
pre_hand="${pre_hand:-}"
|
||||
|
||||
## post_hand or --post-hand=
|
||||
# Set this to do an ordinary handover to a final position
|
||||
# (in the target cluster) after everything has successfully finished.
|
||||
# This may be used to establish a uniform default running location.
|
||||
post_hand="${post_hand:-}"
|
||||
|
||||
## lock_break_timeout
|
||||
# When remote ssh commands are failing, remote locks may sustain forever.
|
||||
# Avoid deadlocks by breaking remote locks after this timeout has elapsed.
|
||||
# NOTICE: these type of locks are only intended for short-term locking.
|
||||
lock_break_timeout="${lock_break_timeout:-3600}" # seconds
|
||||
|
||||
## startup_when_locked
|
||||
# When == 0:
|
||||
# Don't abort and don't wait when a lock is detected at startup.
|
||||
|
|
@ -237,338 +270,16 @@ General features:
|
|||
export user_name="${user_name:-$(get_real_ssh_user)}"
|
||||
export user_name="${user_name:-$LOGNAME}"
|
||||
|
||||
|
||||
PLUGIN football-cm3
|
||||
|
||||
1&1 specfic plugin for dealing with the cm3 cluster manager
|
||||
and its concrete operating enviroment (singleton instance).
|
||||
|
||||
Current maximum cluster size limit:
|
||||
|
||||
Maximum #syncs running before migration can start:
|
||||
|
||||
Following marsadm --version must be installed:
|
||||
|
||||
Following mars kernel modules must be loaded:
|
||||
|
||||
## enable_cm3
|
||||
# ShaHoLin-specifc plugin for working with the infong platform
|
||||
# (istore, icpu, infong) via 1&1-specific clustermanager cm3
|
||||
# and related toolsets. Much of it is bound to a singleton database
|
||||
# instance (clustermw & siblings).
|
||||
enable_cm3="${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="${date_lock:-}"
|
||||
|
||||
## workaround_firewall
|
||||
# Documentation of technical debt for later generations:
|
||||
# This is needed since July 2017. In the many years before, no firewalling
|
||||
# was effective at the replication network, because it is a physically
|
||||
# separate network from the rest of the networking infrastructure.
|
||||
# An attacker would first need to gain root access to the _hypervisor_
|
||||
# (not only to the LXC container and/or to KVM) before gaining access to
|
||||
# those physical replication network interfaces.
|
||||
# Since about that time, which is about the same time when the requirements
|
||||
# for Container Football had been communicated, somebody introduced some
|
||||
# unnecessary firewall rules, based on "security arguments".
|
||||
# These arguments were however explicitly _not_ required by the _real_
|
||||
# security responsible person, and explicitly _not_ recommended by him.
|
||||
# Now the problem is that it is almost politically impossible to get
|
||||
# rid of suchalike "security feature".
|
||||
# Until the problem is resolved, Container Football requires
|
||||
# the _entire_ local firewall to be _temporarily_ shut down in order to
|
||||
# allow marsadm commands over ssh to work.
|
||||
# Notice: this is _not_ increasing the general security in any way.
|
||||
# LONGTERM solution / TODO: future versions of mars should no longer
|
||||
# depend on ssh.
|
||||
# Then this "feature" can be turned off.
|
||||
workaround_firewall="${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}"
|
||||
|
||||
## 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:-$(shopt -u nullglob; ls *.password | head -1 | cut -d. -f1)}" || echo "cannot find a password file *.password for clustermw: you MUST supply the credentials via default curl config files (see man page)"
|
||||
|
||||
## clustertool_passwd
|
||||
# Here you can supply the encrpted password.
|
||||
# By default, a file $clustertool_user.password is used
|
||||
# containing the encrypted password.
|
||||
clustertool_passwd="${clustertool_passwd:-$([[ -r $clustertool_user.password ]] && cat $clustertool_user.password)}"
|
||||
|
||||
## do_migrate
|
||||
# Keep this enabled. Only disable for testing.
|
||||
do_migrate="${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}"
|
||||
|
||||
## backup_dir
|
||||
# Directory for keeping JSON backups of clustermw.
|
||||
backup_dir="${backup_dir:-.}"
|
||||
|
||||
## enable_mod_deflate
|
||||
# Internal, for support.
|
||||
enable_mod_deflate="${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:-25007}"
|
||||
|
||||
## override_hvt_id
|
||||
# When necessary, override this from $include_dir/plugins/*.conf
|
||||
override_hvt_id="${override_hvt_id:-8059}"
|
||||
|
||||
## 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="${shaholin_action:-}"
|
||||
## replace_ssh_id_file
|
||||
# When set, replace current ssh user with this one.
|
||||
# The new user should hot have a passphrase.
|
||||
# Useful for logging out the original user (interrupting the original
|
||||
# ssh agent chain).
|
||||
replace_ssh_id_file="${replace_ssh_id_file:-}"
|
||||
|
||||
|
||||
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="${basic_mnt_dir:-/mnt}"
|
||||
|
||||
|
||||
PLUGIN football-motd
|
||||
|
||||
Generic plugin for motd. Communicate that Football is running
|
||||
at login via motd.
|
||||
|
||||
## enable_motd
|
||||
# whether to use the motd plugin.
|
||||
enable_motd="${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
|
||||
PLUGIN football-1and1config
|
||||
|
||||
1&1 specfic plugin for dealing with the cm3 clusters
|
||||
and its concrete configuration .
|
||||
\end{verbatim}
|
||||
|
|
|
|||
|
|
@ -24,6 +24,38 @@ Actions for resource migration:
|
|||
Remove old / currently unused LV replicas from MARS and deallocate
|
||||
from LVM.
|
||||
|
||||
Actions for inplace FS shrinking:
|
||||
|
||||
./football.sh shrink <resource> <percent>
|
||||
Run the sequence shrink_prepare ; shrink_finish ; shrink_cleanup.
|
||||
|
||||
./football.sh shrink_prepare <resource> [<percent>]
|
||||
Allocate temporary LVM space (when possible) and create initial
|
||||
raw FS copy.
|
||||
Default percent value(when left out) is 85.
|
||||
|
||||
./football.sh shrink_finish <resource>
|
||||
Incrementally update the FS copy, swap old <=> new copy with
|
||||
small downtime.
|
||||
|
||||
./football.sh shrink_cleanup <resource>
|
||||
Remove old FS copy from LVM.
|
||||
|
||||
Actions for inplace FS extension:
|
||||
|
||||
./football.sh extend <resource> <percent>
|
||||
|
||||
Combined actions:
|
||||
|
||||
./football.sh migrate+shrink <resource> <target_primary> [<target_secondary>] [<percent>]
|
||||
Similar to migrate ; shrink but produces less network traffic.
|
||||
Default percent value (when left out) is 85.
|
||||
|
||||
./football.sh migrate+shrink+back <resource> <tmp_primary> [<percent>]
|
||||
Migrate temporarily to <tmp_primary>, then shrink there,
|
||||
finally migrate back to old primary and secondaries.
|
||||
Default percent value (when left out) is 85.
|
||||
|
||||
Actions for (manual) repair in emergency situations:
|
||||
|
||||
./football.sh manual_migrate_config <resource> <target_primary> [<target_secondary>]
|
||||
|
|
@ -59,37 +91,10 @@ Actions for (manual) repair in emergency situations:
|
|||
get the customers online again, while buying the downsides of this
|
||||
command.
|
||||
|
||||
Actions for inplace FS shrinking:
|
||||
|
||||
./football.sh shrink <resource> <percent>
|
||||
Run the sequence shrink_prepare ; shrink_finish ; shrink_cleanup.
|
||||
|
||||
./football.sh shrink_prepare <resource> [<percent>]
|
||||
Allocate temporary LVM space (when possible) and create initial
|
||||
raw FS copy.
|
||||
Default percent value(when left out) is 85.
|
||||
|
||||
./football.sh shrink_finish <resource>
|
||||
Incrementally update the FS copy, swap old <=> new copy with
|
||||
small downtime.
|
||||
|
||||
./football.sh shrink_cleanup <resource>
|
||||
Remove old FS copy from LVM.
|
||||
|
||||
Actions for inplace FS extension:
|
||||
|
||||
./football.sh extend <resource> <percent>
|
||||
|
||||
Combined actions:
|
||||
|
||||
./football.sh migrate+shrink <resource> <target_primary> [<target_secondary>] [<percent>]
|
||||
Similar to migrate ; shrink but produces less network traffic.
|
||||
Default percent value (when left out) is 85.
|
||||
|
||||
./football.sh migrate+shrink+back <resource> <tmp_primary> [<percent>]
|
||||
Migrate temporarily to <tmp_primary>, then shrink there,
|
||||
finally migrate back to old primary and secondaries.
|
||||
Default percent value (when left out) is 85.
|
||||
./football.sh manual_lock <item> <host_list>
|
||||
./football.sh manual_unlock <item> <host_list>
|
||||
Manually lock or unlock an item at all of the given hosts, in
|
||||
an atomic fashion. In most cases, use "ALL" for the item.
|
||||
|
||||
Global maintenance:
|
||||
|
||||
|
|
@ -118,6 +123,11 @@ General features:
|
|||
attaches to the sessions and presses the RETURN key.
|
||||
|
||||
|
||||
PLUGIN football-1and1config
|
||||
|
||||
1&1 specfic plugin for dealing with the cm3 clusters
|
||||
and its concrete configuration .
|
||||
|
||||
PLUGIN football-cm3
|
||||
|
||||
1&1 specfic plugin for dealing with the cm3 cluster manager
|
||||
|
|
|
|||
|
|
@ -141,7 +141,7 @@ tst@1und1.de
|
|||
\end_layout
|
||||
|
||||
\begin_layout Date
|
||||
Version 0.1a-11
|
||||
Version 0.1a-12
|
||||
\end_layout
|
||||
|
||||
\begin_layout Lowertitleback
|
||||
|
|
@ -18773,6 +18773,22 @@ restore your backup.
|
|||
\begin_layout Labeling
|
||||
\labelwidthstring 00.00.0000
|
||||
|
||||
\family typewriter
|
||||
Orphan
|
||||
\family default
|
||||
The secondary cannot replay data anymore, because it has been kicked out
|
||||
for avoidance of emergency mode.
|
||||
The data is not recent anymore.
|
||||
Typically,
|
||||
\family typewriter
|
||||
marsadm invalidate
|
||||
\family default
|
||||
needs to be done.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Labeling
|
||||
\labelwidthstring 00.00.0000
|
||||
|
||||
\family typewriter
|
||||
NoAttach
|
||||
\family default
|
||||
|
|
@ -19348,6 +19364,22 @@ PrimaryUnreachable
|
|||
\begin_layout Labeling
|
||||
\labelwidthstring 00.00.0000
|
||||
|
||||
\family typewriter
|
||||
Orphan
|
||||
\family default
|
||||
The secondary cannot replay data anymore, because it has been kicked out
|
||||
for avoidance of emergency mode.
|
||||
The data is not recent anymore.
|
||||
Typically,
|
||||
\family typewriter
|
||||
marsadm invalidate
|
||||
\family default
|
||||
needs to be done.
|
||||
\end_layout
|
||||
|
||||
\begin_layout Labeling
|
||||
\labelwidthstring 00.00.0000
|
||||
|
||||
\family typewriter
|
||||
Replaying
|
||||
\family default
|
||||
|
|
|
|||
Binary file not shown.
|
|
@ -541,7 +541,7 @@ marsadm [<global_options>] view[-<macroname>] [<resource_name> | all ]
|
|||
get-resource-{fat,err,wrn}{,-count}
|
||||
get-{disk,device}
|
||||
is-{alive}
|
||||
is-{split-brain,consistent,emergency}
|
||||
is-{split-brain,consistent,emergency,orphan}
|
||||
occupied-size
|
||||
present-{disk,device}
|
||||
(deprecated, use *-present instead)
|
||||
|
|
@ -567,4 +567,5 @@ 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}
|
||||
|
|
|
|||
|
|
@ -185,9 +185,15 @@ Options:
|
|||
--help --verbose
|
||||
Show all overridable shell variables, also for plugins.
|
||||
|
||||
## football_includes
|
||||
## screener_includes
|
||||
# List of directories where screener-*.conf files can be found.
|
||||
football_includes="${football_includes:-/usr/lib/mars/plugins /etc/mars/plugins $script_dir/plugins $HOME/.mars/plugins ./plugins}"
|
||||
screener_includes="${screener_includes:-/usr/lib/mars/plugins /etc/mars/plugins $script_dir/plugins $HOME/.mars/plugins ./plugins}"
|
||||
|
||||
## screener_confs
|
||||
# Another list of directories where screener-*.conf files can be found.
|
||||
# These are sourced in a second pass after $screener_includes.
|
||||
# Thus you can change this during the first pass.
|
||||
screener_confs="${screener_confs:-/usr/lib/mars/confs /etc/mars/confs $script_dir/confs $HOME/.mars/confs ./confs}"
|
||||
|
||||
## title
|
||||
# Used as a title for startup of screen sessions, and later for
|
||||
|
|
|
|||
|
|
@ -419,6 +419,13 @@ sub systemd_activate {
|
|||
system($ctl_cmd) and lwarn "command '$ctl_cmd' failed\n";
|
||||
}
|
||||
|
||||
sub _systemd_op {
|
||||
my ($op, $unit) = @_;
|
||||
if (!system("$systemctl cat '$unit' > /dev/null 2>&1")) {
|
||||
system("$systemctl $op '$unit'");
|
||||
}
|
||||
}
|
||||
|
||||
sub systemd_trigger {
|
||||
my ($cmd) = @_;
|
||||
# Remember old instances
|
||||
|
|
@ -499,9 +506,7 @@ sub systemd_trigger {
|
|||
if ($count + $deleted) {
|
||||
lprint "==== Restart systemd\n"if $verbose;
|
||||
foreach my $unit (@systemctl_enable) {
|
||||
if (!system("$systemctl cat '$unit' > /dev/null 2>&1")) {
|
||||
system("$systemctl enable '$unit'");
|
||||
}
|
||||
_systemd_op("enable", $unit);
|
||||
}
|
||||
system("$systemctl daemon-reload");
|
||||
}
|
||||
|
|
@ -510,7 +515,7 @@ sub systemd_trigger {
|
|||
my $unit = `basename "$unit_path"`;
|
||||
chomp $unit;
|
||||
lprint "==== Activate path watcher '$unit'\n"if $verbose;
|
||||
system("$systemctl start \"$unit\"");
|
||||
_systemd_op("start", $unit);
|
||||
}
|
||||
# Activate the listed units.
|
||||
foreach my $res (@res_list) {
|
||||
|
|
@ -518,9 +523,7 @@ sub systemd_trigger {
|
|||
}
|
||||
# Start standard units
|
||||
foreach my $unit (@systemctl_start) {
|
||||
if (!system("$systemctl cat '$unit' > /dev/null 2>&1")) {
|
||||
system("$systemctl start '$unit'");
|
||||
}
|
||||
_systemd_op("start", $unit);
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -3095,7 +3098,10 @@ sub up_res_phase1 {
|
|||
} else {
|
||||
attach_res_phase1("attach", $res);
|
||||
fetch_local_res("resume-fetch-local", $res);
|
||||
pause_sync_local_res("resume-sync-local", $res);
|
||||
# ignore ldie on sync, just do all the rest
|
||||
eval {
|
||||
pause_sync_local_res("resume-sync-local", $res);
|
||||
};
|
||||
pause_replay_local_res("resume-replay-local", $res);
|
||||
}
|
||||
}
|
||||
|
|
@ -3204,12 +3210,14 @@ sub primary_phase0 {
|
|||
set_link($new, $want_path);
|
||||
my $unit_path = "$mars/resource-$res/systemd-$oper-unit";
|
||||
my $unit = get_link($unit_path, 2);
|
||||
lprint "IMPORTANT: Relying on systemd for $oper of unit '$unit'\n";
|
||||
lprint "IMPORTANT: unit '$unit' wanted at '$new'\n";
|
||||
finish_links();
|
||||
_systemd_trigger($cmd);
|
||||
_trigger(3);
|
||||
return;
|
||||
if ($unit) {
|
||||
lprint "IMPORTANT: Relying on systemd for $oper of unit '$unit'\n";
|
||||
lprint "IMPORTANT: unit '$unit' wanted at '$new'\n";
|
||||
finish_links();
|
||||
_systemd_trigger($cmd);
|
||||
_trigger(3);
|
||||
return;
|
||||
}
|
||||
}
|
||||
return if ($old eq $host and $cmd eq "primary");
|
||||
return if $old eq "(none)";
|
||||
|
|
@ -4113,6 +4121,17 @@ sub eval_fn {
|
|||
my $lnk = "$mars/alive-$peer";
|
||||
return get_link_stamp($lnk);
|
||||
}
|
||||
if (/^is[-_]?orphan$/) {
|
||||
my $peer = parse_macro($arg1, $env);
|
||||
$peer = $$env{"host"} unless $peer;
|
||||
my $replay = get_link($$env{"resdir"} . "/replay-$peer", 1);
|
||||
$replay =~ m/^(log-[^,]+),/;
|
||||
my $logfile = $$env{"resdir"} . "/" . $1;
|
||||
if (-r $logfile) {
|
||||
return 0;
|
||||
}
|
||||
return 1;
|
||||
}
|
||||
if (/^is[-_]?(almost[-_]?)?consistent$/) {
|
||||
my $almost = $1;
|
||||
# has sync finished?
|
||||
|
|
@ -4750,6 +4769,8 @@ my %complex_macros =
|
|||
. "}"
|
||||
. "}{%and{%replay-code{}}{%<{%replay-code{}}{0}}}{"
|
||||
. "DefectiveLog[%errno-text{%replay-code{}}]"
|
||||
. "}{%is-orphan{}}{"
|
||||
. "Orphan"
|
||||
. "}{%not{%is-attach{}}}{"
|
||||
. "NoAttach"
|
||||
. "}{%not{%is-consistent{}}}{"
|
||||
|
|
@ -4823,6 +4844,8 @@ my %complex_macros =
|
|||
. "NoPrimaryDesignated"
|
||||
. "}{%not{%is-alive{}}}{"
|
||||
. "PrimaryUnreachable"
|
||||
. "}{%is-orphan{}}{"
|
||||
. "Orphan"
|
||||
. "}{"
|
||||
. "Replaying"
|
||||
. "}"
|
||||
|
|
@ -5148,7 +5171,7 @@ my %trivial_globs =
|
|||
=> "",
|
||||
"{is,todo}-{attach,sync,fetch,replay,primary}"
|
||||
=> "",
|
||||
"is-{split-brain,consistent,emergency}"
|
||||
"is-{split-brain,consistent,emergency,orphan}"
|
||||
=> "",
|
||||
"rest-space"
|
||||
=> "",
|
||||
|
|
|
|||
Loading…
Reference in New Issue