sync_replica.sh #25

  • //
  • guest/
  • russell_jackson/
  • sdp/
  • Server/
  • Unix/
  • p4/
  • common/
  • bin/
  • sync_replica.sh
  • View
  • Commits
  • Open Download .zip Download (4 KB)
#!/bin/bash
# Intended to be run on a replica machine to sync replica from its corresponding master
export SDP_INSTANCE=${SDP_INSTANCE:-Undefined} 
export SDP_INSTANCE=${1:-$SDP_INSTANCE} 
if [[ $SDP_INSTANCE == Undefined ]]; then 
   echo "Instance parameter not supplied." 
   echo "You must supply the Perforce instance as a parameter to this script." 
   exit 1 
fi 

. /p4/common/bin/p4_vars $SDP_INSTANCE
. /p4/common/bin/backup_functions.sh
LOGFILE=$LOGS/sync_replica.log

######### Start of Script ##########
check_vars
set_vars
get_journalnum
ckp_running
rotate_last_run_logs
log "Starting sync_replica.sh"

if [[ "${P4REPLICA}" == "FALSE" ]]; then
  die "Error: sync_replica can only be run a read only or forwarding replica." 
fi

check_uid

# You must set up a public keypair using "ssh-keygen -t rsa" in order for this to work.
# You need to paste your CLIENT ~/.ssh/id_rsa.pub contents into the REMOTE ~/ssh/authorized_keys file. 
if [[ "$SHAREDDATA" == "FALSE" ]]; then
  rsync -avz --delete ${RSYNCUSER}@${P4MASTERHOST}:$CHECKPOINTS/ $CHECKPOINTS >> $LOGFILE 2>&1
  rsync_exit_code=$?
  if [[ $rsync_exit_code -ne 0 ]]; then
    rsync -avz --delete ${RSYNCUSER}@${P4MASTERHOST}:$CHECKPOINTS/ $CHECKPOINTS >> $LOGFILE 2>&1
    rsync_exit_code=$?
    if [[ $rsync_exit_code -ne 0 ]]; then
      die "Error: Failed to pull $CHECKPOINTS from host $P4MASTERHOST.  The rsync exit code was: $rsync_exit_code.  Aborting."
    fi
  fi
fi

if [[ "$SHAREDDATA" == "FALSE" ]]; then
  rsync -avz --delete ${RSYNCUSER}@${P4MASTERHOST}:$JOURNALS/ $JOURNALS >> $LOGFILE 2>&1
  rsync_exit_code=$?
  if [[ $rsync_exit_code -ne 0 ]]; then
    rsync -avz --delete ${RSYNCUSER}@${P4MASTERHOST}:$JOURNALS/ $JOURNALS >> $LOGFILE 2>&1
    rsync_exit_code=$?
    if [[ $rsync_exit_code -ne 0 ]]; then
      die "Error: Failed to pull $JOURNALS from host $P4MASTERHOST.  The rsync exit code was: $rsync_exit_code.  Aborting."
    fi
  fi
fi

recreate_offline_db_files
get_journalnum
# Reduce the journal number by 1 since the rotated journals in offline will be 1 less than
# the active journal number.
JOURNALNUM=$((JOURNALNUM - 1))
get_offline_journal_num
replay_journals_to_offline_db
CHECKPOINTS_ORIG=${CHECKPOINTS}
CHECKPOINTS=${P4HOME}/journals.rep
replay_journals_to_offline_db
CHECKPOINTS=$CHECKPOINTS_ORIG
get_journalnum

# LASTJOURNALNUM is the highest numbered journal number in the checkpoints directory.
if [[ $JOURNALNUM -lt $LASTJOURNALNUM ]]; then
  stop_p4d >> $LOGFILE 2>&1
  exit_code=$?

  if [[ $exit_code -ne 0 ]]; then
    die "Error: Server failed to shut down.  Aborting."
  fi

  log "Server should be down now."
  log "Moving offline db into root."
  get_journalnum
  get_offline_journal_num
  replay_journals_to_offline_db
  CHECKPOINTS_ORIG=${CHECKPOINTS}
  CHECKPOINTS=${P4HOME}/journals.rep
  replay_journals_to_offline_db
  CHECKPOINTS=$CHECKPOINTS_ORIG
  switch_db_files

  log "Remove replication files to reset replication to beginning of current master journal."
  rm -f ${OFFLINE_DB}/state* >> $LOGFILE 2>&1
  rm -f ${OFFLINE_DB}/rdb.lbr >> $LOGFILE 2>&1
  rm -f ${P4ROOT}/state* >> $LOGFILE 2>&1
  rm -f ${P4ROOT}/rdb.lbr >> $LOGFILE 2>&1
  rm -f ${LOGS}/journal* >> $LOGFILE 2>&1

  start_p4d >> $LOGFILE 2>&1
  $P4CBIN/p4login

  log "Server should be back up now."

  $P4BIN pull -lj >> $LOGFILE
  rm -f ${OFFLINE_DB}/save/db.* >> $LOGFILE 2>&1
  rm -f ${P4ROOT}/save/db.* >> $LOGFILE 2>&1
fi

$P4CBIN/p4login
remove_old_logs
remove_old_checkpoints_and_journals
if [[ -d ${P4HOME}/journals.rep ]]; then
   cd ${P4HOME}/journals.rep
   rm $(ls -t | awk 'NR>3') > /dev/null 2>&1
fi
ckp_complete
log "End $P4SERVER sync replica"

# Change User Description Committed
#31 30716 Russell C. Jackson (Rusty) Corrected the name of the logs variable.
#30 30714 Russell C. Jackson (Rusty) Add clean up of replica structured logs.
#29 30534 Russell C. Jackson (Rusty) Added journal directories to replication reset cleanup.
#28 30226 Russell C. Jackson (Rusty) Switched order of journals.rotated and journals.rep
#27 30166 Russell C. Jackson (Rusty) Fixed logic with replays to handle the different journal locations.
#26 30081 Russell C. Jackson (Rusty) Updated for sync_replica.sh to reduce noise and handle multiple journal folders.
#25 29965 Russell C. Jackson (Rusty) Changes to directories, commands and journalPrefix to implement new process to keep journal rotation to the same volume as the logs volume, but to still move journals to the checkpoints directory so they get backed up.
Also compresses journals to save space.
#24 29760 Russell C. Jackson (Rusty) Added code to replay journals.rep folders to offline_db as well.
#23 29758 Russell C. Jackson (Rusty) Increased number of journals to keep.
#22 29051 Russell C. Jackson (Rusty) Removed check for offline db usable since it is going to get recreated.
#21 29021 Russell C. Jackson (Rusty) Added checkpoint running checks to prevent multiple runs of scripts from overlapping.
#20 29016 Russell C. Jackson (Rusty) Fix for trying to replay a journal that doesn't exist.
#19 27627 Russell C. Jackson (Rusty) Changed P4MASTER to P4MASTERHOST
#18 27277 Russell C. Jackson (Rusty) Fixed redirect not to overwrite the log file.
#17 27166 Russell C. Jackson (Rusty) Changed RC stop/start to stop_p4d and start_p4d
#16 26960 Russell C. Jackson (Rusty) Added removal of save db.* files
#15 26958 Russell C. Jackson (Rusty) Replaced switch with code from the recreate script to cover everything.
#14 26956 Russell C. Jackson (Rusty) Add stop/start
#13 26935 Russell C. Jackson (Rusty) Fixed replay of offline journals and add switch of db if the replica is out of sync.
#12 26794 Russell C. Jackson (Rusty) Added journals.rep cleanup
#11 25866 Russell C. Jackson (Rusty) Changes to work with updated backup_functions.sh
#10 25857 Russell C. Jackson (Rusty) Added 2nd rsync to cover journal files getting deleted during the rsync.
#9 24858 Russell C. Jackson (Rusty) Set rpl.journalcopy.location=1 and removed all journals.rep references since it won't be needed anymore.
#8 23680 Russell C. Jackson (Rusty) New script to copy over shelved files that verify -t schedules incorrectly.
Defaulted RSYNCUSER to OSUSER to eliminate the need to check to see if RSYNCUSER is set.
#7 23541 Russell C. Jackson (Rusty) Added handling for a different OSUSER on the master than on the replica for rsync.
Just add RSYNCUSER to the p4_1.vars file to enable.
#6 22981 Russell C. Jackson (Rusty) Made files writeable so they are easier to update once on the server.
#5 22869 Russell C. Jackson (Rusty) Updated to only send email on error.
#4 22757 Russell C. Jackson (Rusty) Added P4SVRPORT to use to make the server listen on just the port number.

Changed P4PORT to include the hostname to eliminate a bug where the ticket is not
issued by the master as it should be when rpl.forward.login is set up.

Created a p4login_master and updated appropriate scripts to use it. This actually
isn't necessary with the change to include the hostname in P4PORT since the ticket
will be valid on all servers in the group, but this covers configurations that aren't
using rpl.forward.login.
#3 22697 Russell C. Jackson (Rusty) Handle existing rotated logs, and remove check_disk_space from log reports since people monitor disk space with monitoring systems.
#2 22696 Russell C. Jackson (Rusty) Updates to support using journalnum in rotate_last_run_logs.
#1 22693 Russell C. Jackson (Rusty) Branched a Unix only version of the SDP.
Removed extra items to create a cleaner tree.
Moved a few items around to make more sense without Windows in the mix.
//guest/perforce_software/sdp/dev/Server/Unix/p4/common/bin/sync_replica.sh
#16 20940 Russell C. Jackson (Rusty) Drop JOURNALNUM from the rotated log names because it forces you to wait to rotate
the prior logs until you get the journal number and creates a problem where the error
that you couldn't get the journal number ends up at the end of the previous days log
file, and that is what gets email out. That causes confusion for the person trying
to see what the error is.

Moved all rotate_last_run_logs up to the point right after we set the environment.
#15 20937 Russell C. Jackson (Rusty) Added check to exit if we are not on a replica server.
#14 20749 C. Thomas Tyler Approved and committed, but I believe that the shared data setting is always set to false on the master and we should look at fixing that in another change.

Enhanced p4login again.

Improvements:
Default behavior with no arguments gives the desired results.
For example, if run on a master, we login on the super user P4USER to
P4PORT.  If run on a replica/edge and auth.id is set, we login P4USER
to the P4TARGET port of the replica.

All other login functionality, such as logging in the replication
service user on a replica, logging in supplemental automation users,
is now accessed via new flags.

A usage message is now available via '-h' and '-man' options.  The
new synopsys is:
p4login [<instance>] [-p <port> | -service] [-automation] [-all]

The <instance> parameter is the only non-flag positional parameter,
and can be ommitted if SDP_INSTANCE is already defined (as is typical
when called by scripts).

With this change, several other scripts calling either the 'p4login'
script or 'p4 login' commands were normalized to call p4login as
appropriate given the new usage.

Reviewer Note:  Review p4login first, then other files.  Most changes
are in p4login.

In other scripts callling p4login, calls similar to:
$P4BIN -u $P4USER -p $P4PORT login < /path/to/pwd
are replaced with: $P4CBIN/p4login

In other scritps calling p4login, calls similar to:
$P4BIN -p $P4MASTERPORT login < /path/to/pwd
are replaced with: $P4CBIN/p4login -p $P4MASTERPORT

Note that, if auth.id is set, calling 'p4login' actually has the
same behavior as 'p4login -p $P4MASTERPORT', since p4login
called on a replica with auth.id set will just login to the master
port anyway.

Depending on intent, sometimes $P4BIN/p4login -service
is used.

== Misc Cleanup ==

In doing the cleanup:
* Fixed a hard-coding-to-instance-1 bug in broker_rotate.sh.
* Fixed an inconsistency in recreate_db_sync_replica.sh, where
it did just a regular login rather than a login -a as done in other
places for (for compatibility with some multi-interface NIC card
configs).

== p4login Call Normalization ==
Code cleanup was done to normalize calls to p4login, such that:
1) the call starts with $P4CBIN/p4login (not the hard-coded path),
and 2) logic to redirect sdtout/stderr to /dev/null was removed,
since it's not necessary with p4login.  (And if p4login ever
does generate any unwanted output, we only fix it in one place).

== Tweak to instance_vars.template ==
This change includes a tweak to set P4MASTERPORT dynamically
on a replica to ensure the value precisely matches P4TARGET
for the given replica.  This will reduce a source of problems
when SSL is used, as it is particularly sensitive to the precise
P4PORT values used, and will also help for environments which
have not yet set auth.id.  If the port cannot be determined
dynamically, we fall back to the old logic using the assigned
value.

== Tweak to SDP_ALWAYS_LOGIN behavior ==
This used to default to 1, now it defaults to 0.  At this
point we should no longer need to force logins, and in fact
doing so can get into a 'p4 login' hang situation with
auth.id set.  Best to avoid unnecessary logins if we
already have a valid ticket.  (I think the need to force a
login may have gone away with p4d patches).

== Obsolete Script ==
With this change, svclogin.sh is now obsolete.  All it was doing
was a few redundant 'p4 login' commands followed by a call to
p4login anyway.

== Testing ==
Our test suite doesn't fully cover this change, so additional
manual testing was done in the Battle School lab environment.
#13 20708 C. Thomas Tyler Per discussion: s/checkpoints.rep/journals.rep/g

This directory name changed, used in the journalPrefix configurable, is
intended to clarify that the should be targeted to for a FAST volume
for use with journalcopy, rather than the LARGE volume as would be
implied when using a directory with "checkpoints" in the name.
#12 20170 Russell C. Jackson (Rusty) Moved password and users into the config directory to allow for instance specific
users and passwords. Ran into a case where two different teams were sharing the same
server hardware and needed this type of differentiation. Surprised that we haven't hit
this sooner.

Also defaulted mkdirs to use the numeric ports since this is the most common
installation.
#11 18587 Russell C. Jackson (Rusty) Reworked the log rotation stuff in backup_functions.sh to make it cleaner and
handle the new log from recreate_offline_db.sh.

Modified recreate_offline_db.sh to add comments about a bad checkpoint. Also
made it create its own log file since it isn't doing a checkpoint. Removed the
log rotation for the same reason.

Moved the LOGFILE setting out to all of scripts to make it more obvious for future
scripts that you need to set that variable in your script so that it doesn't just
default to checkpoint.log.

Moved the functions in weekly_backup.sh and recreate_offline_db.sh into backup_functions.sh
where they belong for consistency.

Modified backup_functions.sh to use a consistent naming convention for all the
rotated log files rather than checkpoint.log being unique.

Replaced all back ticks with the newer bash $() method.

Removed all of the line wrapping since I am pretty sure that none of us are working on an
80 character terminal these days and it is easier to read this way.
#10 16335 C. Thomas Tyler Routine Merge Down to dev from main using:
p4 merge -b perforce_software-sdp-dev
#9 16029 C. Thomas Tyler Routine merge to dev from main using:
p4 merge -b perforce_software-sdp-dev
#8 15778 C. Thomas Tyler Routine Merge Down to dev from main.
#7 15701 C. Thomas Tyler Routine merge down using 'p4 merge -b perforce_software-sdp-dev'.
#6 15374 adrian_waters - Ensure backup scripts are run as the OSUSER (to prevent accidental running as root); 
- in scripts where LOGFILE value is changed from the 'checkpoint.log'  set by set_vars, ensure the new assignment is before check_dirs is called, otherwise errors could be written to the 'wrong' log
- in 'die()' - detect if running from terminal & also send output to stderr
#5 13906 C. Thomas Tyler Normalized P4INSTANCE to SDP_INSTANCE to get Unix/Windows
implementations in sync.

Reasons:
1. Things that interact with SDP in both Unix and Windows
environments shoudn't have to account for this obscure
SDP difference between Unix and Windows.  (I came across
this doing CBD work).

2. The Windows and Unix scripts have different variable
names for defining the same concept, the SDP instance.
Unix uses P4INSTANCE, while Windows uses SDP_INSTANCE.

3. This instance tag, a data set identifier, is an SDP concept.
I prefer the SDP_INSTANCE name over P4INSTANCE, so I prpose
to normalize to SDP_INSTANCE.

4. The P4INSTANCE name makes it look like a setting that might be
recognized by the p4d itself, which it is not.  (There are other
such things such as P4SERVER that could perhaps be renamed as
a separate task; but I'm not sure we want to totally disallow
the P4 prefix for variable names. It looks too right to be wrong
in same cases, like P4BIN and P4DBIN.  That's a discussion for
another day, outside the scope of this task).

Meanwhile:
* Fixed a bug in the Windows 2013.3 upgrade script that
was referencing undefined P4INSTANCE, as the Windows
environment defined only SDP_INSTANCE.

* Had P4INSTANCE been removed completely, this change would
likely cause trouble for users doing updates for existing
SDP installations.  So, though it involves slight technical debt,
I opted to keep a redundant definition of P4INSTANCE
in p4_vars.template, with comments indicating SDP_INSTANCE should be
used in favor of P4INSTANCE, with a warning that P4INSTANCE
may go away in a future release.  This should avoid unnecessary
upgrade pain.

* In mkdirs.sh, the varialbe name was INSTANCE rather than
SDP_INSTANCE.  I changed that as well.  That required manual
change rather than sub/replace to avoid corrupting other similar
varialbe names (e.g.  MASTERINSTANCE).

This is a trivial change technically (a substitute/replace, plus
tweaks in p4_vars.template), but impacts many files.
#4 12169 Russell C. Jackson (Rusty) Updated copyright date to 2015

 Updated shell scripts to require an instance parameter to eliminate the need
 for calling p4master_run.    Python and Perl still need it since you have to set the
environment for them to run in.

 Incorporated comments from reviewers. Left the . instead of source as that seems
more common in the field and has the same functionality.
#3 12107 C. Thomas Tyler Routine merge down from 'main' to 'dev', resolved with
'p4 resolve -as'.
#2 12028 C. Thomas Tyler Refreshed SDP dev branch, merging down from main.
#1 10638 C. Thomas Tyler Populate perforce_software-sdp-dev.
//guest/perforce_software/sdp/main/Server/Unix/p4/common/bin/sync_replica.sh
#1 10148 C. Thomas Tyler Promoted the Perforce Server Deployment Package to The Workshop.