#!/bin/bash #------------------------------------------------------------------------------ # Copyright (c) Perforce Software, Inc., 2007-2015. All rights reserved # # Redistribution and use in source and binary forms, with or without # modification, are permitted provided that the following conditions are met: # # 1 Redistributions of source code must retain the above copyright # notice, this list of conditions and the following disclaimer. # # 2. Redistributions in binary form must reproduce the above copyright # notice, this list of conditions and the following disclaimer in the # documentation and/or other materials provided with the distribution. # # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS # FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL PERFORCE # SOFTWARE, INC. BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, # SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT # LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, # DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON # ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR # TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF # THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH # DAMAGE. #------------------------------------------------------------------------------ # 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 $SDP_INSTANCE . /p4/common/bin/backup_functions.sh ######### Start of Script ########## check_vars set_vars LOGFILE=$LOGS/sync_replica.log check_uid $P4BIN -u $P4USER -p ${SSL_PREFIX}${P4MASTER}:${P4MASTERPORTNUM} login < /p4/common/bin/adminpass > /dev/null 2>&1 JOURNALNUM=`$P4BIN -u $P4USER -p ${SSL_PREFIX}${P4MASTER}:${P4MASTERPORTNUM} counter journal` if [[ "$JOURNALNUM" == "" ]]; then die "Error: Couldn't get journal number from master. Aborting." fi rotate_last_run_logs log "Starting sync_replica.sh" # 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 ${OSUSER}@${P4MASTER}:$CHECKPOINTS/ $CHECKPOINTS > $LOGFILE 2>&1 rsync_exit_code=$? if [[ $rsync_exit_code -ne 0 ]]; then die "Error: Failed to pull $CHECKPOINTS from host $P4MASTER. The rsync exit code was: $rsync_exit_code. Aborting." fi fi recreate_weekly_offline_db_files get_offline_journal_num replay_journals_to_offline_db $P4BIN -p ${SSL_PREFIX}${P4MASTERPORTNUM} login < /p4/common/bin/adminpass > /dev/null 2>&1 check_disk_space remove_old_logs export CHECKPOINTS=${P4HOME}/checkpoints.rep remove_old_checkpoints_and_journals log "End $P4SERVER sync replica" mail_log_file "$HOSTNAME $P4SERVER Daily sync replica log."
# | Change | User | Description | Committed | |
---|---|---|---|---|---|
#25 | 30267 | Robert Cowham |
Copy files to be dumped via p4d -jd to tmp dir first to avoid locks on P4ROOT (or offline_db) SDP-1087 |
||
#24 | 30182 | C. Thomas Tyler | Added change to rsync to avoid issues with .nfs* files on NFS. | ||
#23 | 29798 | C. Thomas Tyler |
sync_replica.sh: Enhanced to silence spurious p4d output generated when scanning db.config to get the target host for the rsync. Also improved error checking and error messages. |
||
#22 | 29590 | C. Thomas Tyler |
Another refinement of sync_replica.sh logic to handle all intended use cases: * HA of commit server, with and without NFS sharing (SHAREDDATA). * HA of edge server, with and without NFS sharing (SHAREDDATA). When NFS sharing, the rsync from the target server is disabled, as before. When rsycing for full replicas (not NFS-sharing, metadata-only replicas), the sync_replica.sh script now always rsyncs from a checkpoints directory based on the journalPrefix of the P4TARGET server. This is correct for all scenarios. If that cannot be determined, the script now does a die() call to avoid rsyncing to a possibly incorrect path. When rebuilding the local offline_db, the checkpoints directory based on the journalPrefix of the P4TARGET server is always used. This directory should exist, whether due to rsync from the target, or NFS-sharing. Logic to remove old checkpoints and journals now only cleans in folders written to by the local replica, to avoid removing files on an NFS-shared upstream server. Auditability of checkpoint operations in backup_functions.sh is improved. #review-29591 |
||
#21 | 29576 | C. Thomas Tyler |
Enhanced sync_replica.sh to support operation on a 'ham' type replica (HA, Metadata-only). A 'ham' type replica replicates only metadata, and shares the /hxdepots volume (via NFS) with its target server. In this configuration, the SHAREDDATA=TRUE value is set, and this corresponds to a p4d configuration setting for the replica of lbr.replication=shared. In this configuration, the journalPrefix value of the replica server will differ from that of its target server. For example, the commit server will may have the First Form jour the journalPrefix, while an HA of the commit will have the Second Form. See 'The journalPrefix Standard': https://swarm.workshop.perforce.com/projects/perforce-software-sdp/view/main/doc/SDP_Guide.Unix.html#_the_journalprefix_standard As another example, for an edge server and HA of that edge, both servers will use the Second Form of the journalPrefix, the form which incorporates a shortened form of the ServerID into the journalPrefix value. But since the ServerIDs are different, the actual journalPrefix values will be different, even though both are of the Second Form. The common pattern is that, when configured for NFS sharing, the sync_replica.sh script should use the journalPrefix of its target server when determining where to look for a checkpoint and numbered journal to load into the offline_db. #review @mark_zinthefer @robert_cowham |
||
#20 | 28621 | C. Thomas Tyler |
Added support to sync_replica.sh for operation on a replica of an edge server. Fixed related error with erroneous output in backup_functions.sh. #review-28622 |
||
#19 | 26718 | Robert Cowham |
Rename P4MASTER to P4MASTERHOST for clarity with comments in: - mkdirs.cfg/mkdirs.sh - p4_<instance>.vars - other files which reference Remove unnecessary sed for p4p.template |
||
#18 | 26156 | C. Thomas Tyler |
Shellcheck v0.6.0 and style compliance changes. Fixed minor bugs related to capturing output, driven by shellcheck changes. Fixed sync_replica.sh for standby replicas with the configurable rpl.journalcopy.location=1 (SDP-424), removing an unnecessary and broken check. Fixed test for pre-existing checkpoints in function recreate_offline_db_files() so that it checks only for the master server, fixing an issue where it would report "No checkpoints found - run live_checkpoint.sh" when used on a replica where checkpoints might legatimately not exist. Also fixed the actual test itself. Replaced P4COMMITSERVER variable with P4MASTERPORT to support daisy chain scenarios, removing the assumption that all servers target only the master. (This assumption was made only in journal_watch.sh). Enhanced check_vars() to report individual missing environment variables, and to add more info on how to fix environment problems (e.g. adding to p4_vars or p4_N.vars files). Fixed bug in check_dirs() where a missing directory check intended to result in a die() call would result in a syntax error instead. These files have been field tested. |
||
#17 | 23130 | C. Thomas Tyler |
Changed rsync commands to avoid using compression when transferring checkpoints, which are already compressed. Fixed logging issue where log was truncated in mid-script. |
||
#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. |