wip

Add --migrate feature: near-live migrate between clusters

.gitignore

@@ -0,0 +1 @@
+eve4pve-barc

README.md

@@ -2,7 +2,7 @@
 
 [![License](https://img.shields.io/github/license/EnterpriseVE/eve4pve-barc.svg)](https://www.gnu.org/licenses/gpl-3.0.en.html)
 
-Cross-Pool (live) Replication and near-live migration for Proxmox VE
+Cross-Pool asynchronous online-replication and near-live migration for Proxmox VE
 
 
 ```text
@@ -11,32 +11,43 @@ ______
 |   --|  _| . |_ -|_ -| . | | | -_|  _|
 |_____|_| |___|___|___|___|\_/|___|_|  
 
-Cross Pool (live) replication and near-live migration for Proxmox VE  
+Cross Pool asynchronous online-replication and near-live migration for Proxmox VE  
 
 Usage:
     crossover <COMMAND> [ARGS] [OPTIONS]
     crossover help
     crossover version
  
-    crossover mirror     --vmid=<string> --destination=<destionationhost> --pool=<targetpool> --keeplocal=n --keepremote=n
+    crossover mirror     --vmid=<string> --destination=<destionationhost> --pool=<targetpool> --keeplocal=[n][d|s] --keepremote=[n][d|s]
 Commands:
     version              Show version program
     help                 Show help program
     mirror               Replicate a stopped VM to another Cluster (full clone)
 
 Options:
-    --vmid               The source+target ID of the VM/CT, comma separated (eg. --vmid=100:100,101:101), 
-    --destination        'Target PVE Host in target pool. e.g. --destination=pve04
-    --pool               'Ceph pool name in target pool. e.g. --pool=data
-    --keeplocal          'How many additional Snapshots to keep locally. e.g. --keeplocal=2
-    --keepremote         'How many additional Snapshots to keep remote. e.g. --keepremote=2
-    --online             'Allow online Copy
-    --nolock             'Don't lock source VM on Transfer (mainly for test purposes)
-    --keep-slock         'Keep source VM locked on Transfer
-    --keep-dlock         'Keep VM locked after transfer on Destination
-    --overwrite          'Overwrite Destination
-    --protect            'Protect Ceph Snapshots
-    --debug              'Show Debug Output
+    --sshcipher          SSH Cipher to use for transfer (default: aes128-gcm@openssh.com,aes128-cbc)
+    --vmid               The source+target ID of the VM, comma separated (eg. --vmid=100:100,101:101)
+                         (The possibility to specify a different Target VMID is to not interfere with VMIDs on the
+                         target cluster, or mark mirrored VMs on the destination)
+    --prefixid           Prefix for VMID's on target System [optional]
+    --excludevmids       Exclusde VM IDs when using --vmid==all
+    --destination        Target PVE Host in target pool. e.g. --destination=pve04
+    --pool               Ceph pool name in target pool. e.g. --pool=data
+    --keeplocal          How many additional Snapshots to keep locally, specified in seconds or day. e.g. --keeplocal=2d
+    --keepremote         How many additional Snapshots to keep remote, specified in seconds or day. e.g. --keepremote=7d
+    --rewrite            PCRE Regex to rewrite the Config Files (eg. --rewrite='s/(net0:)(.*)tag=([0-9]+)/\1\2tag=1/g' would
+                         change the VLAN tag from 5 to 1 for net0.
+    --influxurl          Influx API url (e.g. --influxurl=https://your-influxserver.com/api/)
+    --influxtoken        Influx API token with write permission
+    --influxbucket       Influx Bucket to write to (e.g. --influxbucket=telegraf/autogen)
+Switches:    
+    --online             Allow online Copy
+    --nolock             Don't lock source VM on Transfer (mainly for test purposes)
+    --keep-slock         Keep source VM locked on Transfer
+    --keep-dlock         Keep VM locked after transfer on Destination
+    --overwrite          Overwrite Destination
+    --protect            Protect Ceph Snapshots
+    --debug              Show Debug Output
 
 Report bugs to the Github repo at https://github.com/lephisto/crossover/
 ```
@@ -75,17 +86,13 @@ It'll work according this scheme:
 * Can keep multiple backup
 * Retention policy: (eg. keep x snapshots on the source and y snapshots in the destination cluster)
 * Rewrites VM configurations so they match the new VMID and/or poolname on the destination
-
-## Protected / unprotected snapshot
-
-!TBD!
-You can protect Ceph Snapshots by the according Ceph/RDB flag, to avoid accidental deletion
-and thus damaging your chain. Keep in mind that Proxmox won't let you delete VM's then, because
-it's not aware of that paramter.
+* Secure an encrypted transfer (SSH), so it's safe to mirror between datacenter without an additional VPN
+* Near live-migrate: To move a VM from one Cluster to another, make an initial copy and re-run with --migrate. This will shutdown the VM on the source cluster and start it on the destination cluster.
 
 ## Installation of prerequisites
 
-```apt install git
+```
+apt install git pv gawk jq curl
 
 ## Install the Script somewhere, eg to /opt
 
@@ -93,54 +100,141 @@ git clone https://github.com/lephisto/crossover/ /opt
 
 ```
 
-## Usage
+Ensure that you can freely ssh from the Node you plan to mirror _from_ to _all_ nodes in the destination cluster, as well as localhost.
 
-Mirror VM to another Cluster:
+## Continuous replication between Clusters
+
+Example 1: Mirror VM to another Cluster:
 
 ```
-root@pve01:~/crossover# ./crossover mirror --vmid=100:10100 --destination=pve04 --pool=data2 --keeplocal=4 --keepremote=8 --overwrite --keep-dlock --online
-
-Start mirror 2022-10-21 18:09:36
-Transmitting Config for VM 100 to desination 10100
-update VM 100: -lock backup
-update VM 10100: -lock backup
-VM 100 - Issuing fsfreeze-freeze to 100 on pve01
-2
-VM 100 - Creating snapshot data/vm-100-disk-0@mirror-20221021180936
-Creating snap: 100% complete...done.
-VM 100 - Creating snapshot data/vm-100-disk-1@mirror-20221021180936
-Creating snap: 100% complete...done.
-VM 100 - Issuing fsfreeze-thaw to 100 on pve01
-2
-Exporting image: 100% complete...done.
-Importing image diff: 100% complete...done.
-Houskeeping localhost data vm-100-disk-0, keeping previous 4 Snapshots
-Removing snap: 100% complete...done.
-Houskeeping pve04 data2 vm-10100-disk-0, keeping previous 8 Snapshots
-Exporting image: 100% complete...done.
-Importing image diff: 100% complete...done.
-Houskeeping localhost data vm-100-disk-1, keeping previous 4 Snapshots
-Removing snap: 100% complete...done.
-Houskeeping pve04 data2 vm-10100-disk-1, keeping previous 8 Snapshots
-Unlocking source VM 100
-root@pve01:~/crossover#
+root@pve01:~/crossover# ./crossover mirror --vmid=all --prefixid=99 --excludevmids=101 --destination=pve04 --pool=data2 --overwrite --online 
+ACTION: Onlinemirror
+Start mirror 2022-11-01 19:21:44
+VM 100 - Starting mirror for testubuntu
+VM 100 - Checking for VM 99100 on Destination Host pve04 /etc/pve/nodes/*/qemu-server
+VM 100 - Transmitting Config for to destination pve04 VMID 99100
+VM 100 - locked 100 [rc:0]
+VM 99100 - locked 99100 [rc:0]
+VM 100 - Creating snapshot data/vm-100-disk-0@mirror-20221101192144
+VM 100 - Creating snapshot data/vm-100-disk-1@mirror-20221101192144
+VM 100 - unlocked source VM 100 [rc:0]
+VM 100 - I data/vm-100-disk-0@mirror-20221101192144: e:0:00:01 c:[ 227KiB/s] a:[ 227KiB/s]  372KiB
+VM 100 - Housekeeping: localhost data/vm-100-disk-0, keeping Snapshots for 0s
+VM 100 - Removing Snapshot localhost data/vm-100-disk-0@mirror-20221101192032 (106s) [rc:0]
+VM 100 - Housekeeping: pve04 data2/vm-99100-disk-0-data, keeping Snapshots for 0s
+VM 100 - Removing Snapshot pve04 data2/vm-99100-disk-0-data@mirror-20221101192032 (108s) [rc:0]
+VM 100 - Disk Summary: Took 2 Seconds to transfer 372.89 KiB in a incremental run
+VM 100 - I data/vm-100-disk-1@mirror-20221101192144: e:0:00:00 c:[ 346 B/s] a:[ 346 B/s] 74.0 B
+VM 100 - Housekeeping: localhost data/vm-100-disk-1, keeping Snapshots for 0s
+VM 100 - Removing Snapshot localhost data/vm-100-disk-1@mirror-20221101192032 (114s) [rc:0]
+VM 100 - Housekeeping: pve04 data2/vm-99100-disk-1-data, keeping Snapshots for 0s
+VM 100 - Removing Snapshot pve04 data2/vm-99100-disk-1-data@mirror-20221101192032 (115s) [rc:0]
+VM 100 - Disk Summary: Took 1 Seconds to transfer 372.96 KiB in a incremental run
+VM 99100 - Unlocking destination VM 99100
+Finnished mirror 2022-11-01 19:22:30
+Job Summary: Bytes transferd 2 bytes for 2 Disks on 1 VMs in 00 hours 00 minutes 46 seconds
+VM Freeze OK/failed...: 1/0
+RBD Snapshot OK/failed: 2/0
+Full xmitted..........: 0 byte
+Differential Bytes ...: 372.96 KiB
 
 ```
+
 This example creates a mirror of VM 100 (in the source cluster) as VM 10100 (in the destination cluster) using the ceph pool "data2" for storing all attached disks. It will keep 4 Ceph snapshots prior the latest (in total 5) and 8 snapshots on the remote cluster. It will keep the VM on the target Cluster locked to avoid an accidental start (thus causing split brain issues), and will do it even if the source VM is running. 
 
 The use case is that you might want to keep a cold-standby copy of a certain VM on another Cluster. If you need to start it on the target cluster you just have to unlock it with `qm unlock VMID` there.
 
 Another usecase could be that you want to migrate a VM from one cluster to another with the least downtime possible. Real live migration that you are used to inside one cluster is hard to achive cross-cluster, but you can easily make an initial migration while the VM is still running on the source cluster (fully transferring the block devices), shut it down on source, run the mirror process again (which is much faster now because it only needs to transfer the diff since the initial snapshot) and start it up on the target cluster. This way the migration basically takes one boot plus a few seconds for transferring the incremental snapshot.
 
+## Near-live Migration 
+
+To minimize downtime and achive a near-live Migration from one Cluster to another it's recommended to do an initial Sync of a VM from the source to the destination cluster. After that, run the job again, and add the --migrate switch. This causes the source VM to be shut down prior snapshot + transfer, and be restarted on the destination cluster as soon as the incremental transfer is complete. Using --migrate will always try to start the VM on the destination cluster.
+
+Example 2: Near-live migrate VM from one cluster to another (Run initial replication first, which works online, then run with --migrate to shutdown on source, incrematally copy and start on destination):
+
+```
+root@pve01:~/crossover# ./crossover mirror --jobname=migrate --vmid=100 --destination=pve04 --pool=data2 --online
+ACTION: Onlinemirror
+Start mirror 2023-04-26 15:02:24
+VM 100 - Starting mirror for testubuntu
+VM 100 - Checking for VM 100 on destination cluster pve04 /etc/pve/nodes/*/qemu-server
+VM 100 - Transmitting Config for to destination pve04 VMID 100
+VM 100 - locked 100 [rc:0] on source
+VM 100 - locked 100 [rc:0] on destination
+VM 100 - Creating snapshot data/vm-100-disk-0@mirror-20230426150224
+VM 100 - Creating snapshot data/vm-100-disk-1@mirror-20230426150224
+VM 100 - unlocked source VM 100 [rc:0]
+VM 100 - F data/vm-100-disk-0@mirror-20230426150224: e:0:09:20 r:            c:[36.6MiB/s] a:[36.6MiB/s] 20.0GiB [===============================>] 100%
+VM 100 - created snapshot on 100 [rc:0]
+VM 100 - Disk Summary: Took 560 Seconds to transfer 20.00 GiB in a full run
+VM 100 - F data/vm-100-disk-1@mirror-20230426150224: e:0:00:40 r:            c:[50.7MiB/s] a:[50.7MiB/s] 2.00GiB [===============================>] 100%
+VM 100 - created snapshot on 100 [rc:0]
+VM 100 - Disk Summary: Took 40 Seconds to transfer 22.00 GiB in a full run
+VM 100 - Unlocking destination VM 100
+Finnished mirror 2023-04-26 15:13:47
+Job Summary: Bytes transferred 22.00 GiB for 2 Disks on 1 VMs in 00 hours 11 minutes 23 seconds
+VM Freeze OK/failed.......: 1/0
+RBD Snapshot OK/failed....: 2/0
+RBD export-full OK/failed.: 2/0
+RBD export-diff OK/failed.: 0/0
+Full xmitted..............: 22.00 GiB
+Differential Bytes .......: 0 Bytes
+
+root@pve01:~/crossover# ./crossover mirror --jobname=migrate --vmid=100 --destination=pve04 --pool=data2 --online --migrate
+ACTION: Onlinemirror
+Start mirror 2023-04-26 15:22:35
+VM 100 - Starting mirror for testubuntu
+VM 100 - Checking for VM 100 on destination cluster pve04 /etc/pve/nodes/*/qemu-server
+VM 100 - Migration requested, shutting down VM on pve01
+VM 100 - locked 100 [rc:0] on source
+VM 100 - locked 100 [rc:0] on destination
+VM 100 - Creating snapshot data/vm-100-disk-0@mirror-20230426152235
+VM 100 - Creating snapshot data/vm-100-disk-1@mirror-20230426152235
+VM 100 - I data/vm-100-disk-0@mirror-20230426152235: e:0:00:03 c:[1.29MiB/s] a:[1.29MiB/s] 4.38MiB
+VM 100 - Housekeeping: localhost data/vm-100-disk-0, keeping Snapshots for 0s
+VM 100 - Removing Snapshot localhost data/vm-100-disk-0@mirror-20230323162532 (2930293s) [rc:0]
+VM 100 - Removing Snapshot localhost data/vm-100-disk-0@mirror-20230426144911 (2076s) [rc:0]
+VM 100 - Removing Snapshot localhost data/vm-100-disk-0@mirror-20230426145632 (1637s) [rc:0]
+VM 100 - Removing Snapshot localhost data/vm-100-disk-0@mirror-20230426145859 (1492s) [rc:0]
+VM 100 - Removing Snapshot localhost data/vm-100-disk-0@mirror-20230426150224 (1290s) [rc:0]
+VM 100 - Housekeeping: pve04 data2/vm-100-disk-0-data, keeping Snapshots for 0s
+VM 100 - Removing Snapshot pve04 data2/vm-100-disk-0-data@mirror-20230426150224 (1293s) [rc:0]
+VM 100 - Disk Summary: Took 4 Seconds to transfer 4.37 MiB in a incremental run
+VM 100 - I data/vm-100-disk-1@mirror-20230426152235: e:0:00:00 c:[ 227 B/s] a:[ 227 B/s] 74.0 B
+VM 100 - Housekeeping: localhost data/vm-100-disk-1, keeping Snapshots for 0s
+VM 100 - Removing Snapshot localhost data/vm-100-disk-1@mirror-20230323162532 (2930315s) [rc:0]
+VM 100 - Removing Snapshot localhost data/vm-100-disk-1@mirror-20230426144911 (2098s) [rc:0]
+VM 100 - Removing Snapshot localhost data/vm-100-disk-1@mirror-20230426145632 (1659s) [rc:0]
+VM 100 - Removing Snapshot localhost data/vm-100-disk-1@mirror-20230426145859 (1513s) [rc:0]
+VM 100 - Removing Snapshot localhost data/vm-100-disk-1@mirror-20230426150224 (1310s) [rc:0]
+VM 100 - Housekeeping: pve04 data2/vm-100-disk-1-data, keeping Snapshots for 0s
+VM 100 - Removing Snapshot pve04 data2/vm-100-disk-1-data@mirror-20230426150224 (1313s) [rc:0]
+VM 100 - Disk Summary: Took 2 Seconds to transfer 4.37 MiB in a incremental run
+VM 100 - Unlocking destination VM 100
+VM 100 - Starting VM on pve01
+Finnished mirror 2023-04-26 15:24:25
+Job Summary: Bytes transferred 4.37 MiB for 2 Disks on 1 VMs in 00 hours 01 minutes 50 seconds
+VM Freeze OK/failed.......: 0/0
+RBD Snapshot OK/failed....: 2/0
+RBD export-full OK/failed.: 0/0
+RBD export-diff OK/failed.: 2/0
+Full xmitted..............: 0 Bytes
+Differential Bytes .......: 4.37 MiB
+```
+
 ## Things to check
 
-From Proxmox VE Hosts you want to backup you need to be able to ssh passwordless to all other Cluster hosts, that may hold VM's or Containers. This goes for the source and for the destination Cluster.
+From Proxmox VE Hosts you want to backup you need to be able to ssh passwordless to all other Cluster hosts, that may hold VM's or Containers. This goes for the source and for the destination Cluster. Doublecheck this.
 
 This is required for using the free/unfreeze and the lock/unlock function, which has to be called locally from that Host the guest is currently running on. Usually this works out of the box for the source cluster, but you may want to make sure that you can "ssh root@pvehost1...n" from every host to every other host in the cluster.
 
-For the Destination Cluster you need to copy your ssh-key to the first host in the cluster, and login once to every node
-in your cluster.
+For the Destination Cluster you need to copy your ssh-key to the first host in the cluster, and login once to every node in your cluster.
 
+Currently preflight checks don't include the check for enough resources in the destination cluster. Check beforehand that you don't exceed the maximum safe size of ceph in the destination cluster.
+
+## Unique Disk names
+
+There are cases, when the Source VM has Disks on different ceph pools. Now, in theory you can have identical image names for different disks. Since all disk images are migrated to one destination pool, they need to be unique. This tool detects this in Preflight checks, and skips these VMs and issues a warning. To solve this, give them unique names, like vm-100-disk-0, vm,100-disk-1 and so on. `rbd mv` will help you.
 
 ## Some words about Snapshot consistency and what qemu-guest-agent can do for you
 
@@ -283,3 +377,4 @@ Ceph Documentation:
 
 Proxmox Wiki:
 https://pve.proxmox.com/wiki/
+

crossover

@@ -1,30 +1,77 @@
 #!/bin/bash
 
-#set -x
-
 # Cross Pool Migration and incremental replication Tool for Proxmox VMs using Ceph.
 # Author: Bastian Mäuser <bma@netz.org>        
 
-declare -r VERSION=0.3
-declare -r NAME=$(basename "$0")
-declare -r PROGNAME=${NAME%.*}
+LC_ALL="en_US.UTF-8"
 
+source rainbow.sh
+
+# Predefine if you want
+declare opt_influx_api_url=''
+declare opt_influx_token=''
+declare opt_influx_bucket=''
+declare opt_influx_api_org=''
+declare opt_influx_jobname=''
+declare opt_influx_job_metrics='crossover_xmit'
+declare opt_influx_summary_metrics='crossover_jobs'
+
+name=$(basename "$0")
+# readonly variables
+declare -r NAME=$name
+declare -r VERSION=0.9
+declare -r PROGNAME=${NAME%.*}
 declare -r PVE_DIR="/etc/pve"
 declare -r PVE_NODES="$PVE_DIR/nodes"
 declare -r QEMU='qemu-server'
 declare -r QEMU_CONF_CLUSTER="$PVE_NODES/*/$QEMU"
 declare -r EXT_CONF='.conf'
+declare -r PVFORMAT_FULL='e:%t r:%e c:%r a:%a %b %p'
+declare -r PVFORMAT_SNAP='e:%t c:%r a:%a %b'
+logfile=$(mktemp)
+declare -r LOG_FILE=$logfile
 
-declare -r LOG_FILE=$(mktemp)
-
+# associative global arrays 
 declare -A -g pvnode
 declare -A -g dstpvnode
 declare -A -g svmids
 declare -A -g dvmids
 
+declare -g scluster
+declare -g dcluster
+declare -g scephversion
+declare -g dcephversion
+
+# global integers
+declare -g -i perf_freeze_ok=0
+declare -g -i perf_freeze_failed=0
+declare -g -i perf_ss_ok=0
+declare -g -i perf_ss_failed=0
+declare -g -i perf_ss_ok=0
+declare -g -i perf_ss_failed=0
+declare -g -i perf_full_ok=0
+declare -g -i perf_full_failed=0
+declare -g -i perf_diff_ok=0
+declare -g -i perf_diff_failed=0
+declare -g -i perf_bytes_full=0
+declare -g -i perf_bytes_diff=0
+declare -g -i perf_bytes_total=0
+declare -g -i perf_vm_running=0
+declare -g -i perf_vm_stopped=0
+declare -g -i perf_snaps_removed=0
+declare -g -i perf_vm_total=0
+declare -g -i perf_vm_ok=0
+
+# commandline parameters
 declare opt_destination
 declare opt_vm_ids=''
 declare opt_snapshot_prefix='mirror-'
+declare opt_rewrite=''
+declare opt_pool='rbd'
+declare opt_sshcipher='aes128-gcm@openssh.com,aes128-cbc'
+declare opt_tag=''
+declare -i opt_prefix_id
+declare opt_exclude_vmids=''
 declare -i opt_debug=0
 declare -i opt_dry_run=0
 declare -i opt_syslog=0
@@ -33,11 +80,17 @@ declare -i opt_keepslock=0
 declare -i opt_keepdlock=0
 declare -i opt_overwrite=0
 declare -i opt_online=0
-declare -i opt_keep_local=0
-declare -i opt_keep_remote=0
+declare -i opt_migrate=0
+declare -i opt_noconfirm=0
+declare opt_keep_local='0s'
+declare opt_keep_remote='0s'
+
 
 declare -r redstconf='^\/etc\/pve\/nodes\/(.*)\/qemu-server\/([0-9]+).conf$'
 declare -r recephimg='([a-zA-Z0-9]+)\:(.*)'
+declare -r restripsnapshots='/^$/,$d'
+declare -r redateex='^([0-9]{4})([0-9]{2})([0-9]{2})([0-9]{2})([0-9]{2})([0-9]{2})$'
+declare -r restripansicolor='s/\x1b\[[0-9;]*m//g'
 
 function usage(){
    shift
@@ -47,7 +100,7 @@ function usage(){
  _____                                 
 |     |___ ___ ___ ___ ___ _ _ ___ ___ 
 |   --|  _| . |_ -|_ -| . | | | -_|  _|
-|_____|_| |___|___|___|___|\_/|___|_|  
+|_____|_| |___|___|___|___|\_/|___|_|   v$VERSION
 
 EOF
     fi
@@ -67,22 +120,35 @@ Commands:
     mirror               Replicate a stopped VM to another Cluster (full clone)
 
 Options:
-    --vmid               The source+target ID of the VM/CT, comma separated (eg. --vmid=100:100,101:101), 
-    --destination        'Target PVE Host in target pool. e.g. --destination=pve04
-    --pool               'Ceph pool name in target pool. e.g. --pool=data
-    --keeplocal          'How many additional Snapshots to keep locally. e.g. --keeplocal=2
-    --keepremote         'How many additional Snapshots to keep remote. e.g. --keepremote=2
-    --online             'Allow online Copy
-    --nolock             'Don't lock source VM on Transfer (mainly for test purposes)
-    --keep-slock         'Keep source VM locked on Transfer
-    --keep-dlock         'Keep VM locked after transfer on Destination
-    --overwrite          'Overwrite Destination
-    --debug              'Show Debug Output
+    --sshcipher          SSH Cipher to use for transfer (default: aes128-gcm@openssh.com,aes128-cbc)
+    --tag                Include all VMs with a specific tag set in the Proxmox UI (if set, implies vmid=all)
+    --vmid               The source+target ID of the VM/CT, comma separated (eg. --vmid=100:100,101:101), or all for all
+    --prefixid           Prefix for VMID's on target System [optional]
+    --excludevmids       Exclusde VM IDs when using --vmid==all
+    --destination        Target PVE Host in target pool. e.g. --destination=pve04
+    --pool               Ceph pool name in target pool. e.g. --pool=data [default=rbd]
+    --keeplocal          How many additional Snapshots to keep locally. e.g. --keeplocal=2d
+    --keepremote         How many additional Snapshots to keep remote. e.g. --keepremote=7d
+    --rewrite            PCRE Regex to rewrite the Config Files (eg. --rewrite='s/(net0:)(.*)tag=([0-9]+)/\1\2tag=1/g' would
+                         change the VLAN tag from 5 to 1 for net0.
+    --influxurl          Influx API url (e.g. --influxurl=https://your-influxserver.com/api/)
+    --influxtoken        Influx API token with write permission
+    --influxbucket       Influx Bucket to write to (e.g. --influxbucket=telegraf/autogen)
+    --jobname            Descriptive name for the job, used in Statistics
+    --mail               Mail address to send report to, comma-seperated (e.g. --mail=admin@test.com,admin2@test.com)
+Switches:
+    --online             Allow online Copy
+    --migrate            Stop VM on Source Cluster before final Transfer and start on destination Cluster
+    --nolock             Don't lock source VM on Transfer (mainly for test purposes)
+    --keep-slock         Keep source VM locked on Transfer
+    --keep-dlock         Keep VM locked after transfer on Destination
+    --overwrite          Overwrite Destination
+    --noconfirm          Don't ask for confirmation before starting --migrate mode (use with care!)
+    --debug              Show Debug Output
 
 Report bugs to <mephisto@mephis.to>
 
 EOF
-    exit 1
 }
 
 function parse_opts(){
@@ -92,7 +158,7 @@ function parse_opts(){
     local args
     args=$(getopt \
            --options '' \
-           --longoptions=vmid:,destination:,pool:,keeplocal:,keepremote:,online,nolock,keep-slock,keep-dlock,overwrite,dry-run,debug \
+           --longoptions=sshcipher:,tag:,vmid:,prefixid:,excludevmids:,destination:,pool:,keeplocal:,keepremote:,rewrite:,influxurl:,influxorg:,influxtoken:,influxbucket:,jobname:,mail:,online,migrate,nolock,keep-slock,keep-dlock,overwrite,dry-run,noconfirm,debug,syslog \
            --name "$PROGNAME" \
            -- "$@") \
            || end_process 128
@@ -101,18 +167,32 @@ function parse_opts(){
 
     while true; do    
       case "$1" in
+        --sshcipher) opt_sshcipher=$2; shift 2;;
+        --tag) opt_tag=$2; shift 2;;
         --vmid) opt_vm_ids=$2; shift 2;;
+        --prefixid) opt_prefix_id=$2; shift 2;;
+        --excludevmids) opt_exclude_vmids=$2; shift 2;;
         --destination) opt_destination=$2; shift 2;;
         --pool) opt_pool=$2; shift 2;;
         --keeplocal) opt_keep_local=$2; shift 2;;
         --keepremote) opt_keep_remote=$2; shift 2;;
-        --online) opt_online=1; shift 2;;
+        --rewrite) opt_rewrite=$2; shift 2;;
+        --influxurl) opt_influx_api_url=$2; shift 2;;
+        --influxorg) opt_influx_api_org=$2; shift 2;;
+        --influxtoken) opt_influx_token=$2; shift 2;;
+        --influxbucket) opt_influx_bucket=$2; shift 2;;
+        --jobname) opt_influx_jobname=$2; shift 2;;
+        --mail) opt_addr_mail="$2"; shift 2;;
+        --online) opt_online=1; shift ;;
+        --migrate) opt_migrate=1; shift ;;
         --dry-run) opt_dry_run=1; shift;;
+        --noconfirm) opt_noconfirm=1; shift;;
         --debug) opt_debug=1; shift;;
         --nolock) opt_lock=0; shift;;
         --keep-slock) opt_keepslock=1; shift;;
         --keep-dlock) opt_keepdlock=1; shift;;
         --overwrite) opt_overwrite=1; shift;;
+        --syslog) opt_syslog=1; shift;;
         --) shift; break;;
         *) break;;
       esac
@@ -121,18 +201,85 @@ function parse_opts(){
     if [ $opt_debug -eq 1 ]; then
         log info "============================================"
         log info "Proxmox Crosspool Migration: $VERSION";
+        log info "pid: $(cat /var/run/"$PROGNAME".pid)"
         log info "============================================"
         log info "Proxmox VE Version:"
 
-        pveversion
+        echowhite "$(pveversion)"
 
         log info "============================================"
     fi
 
+
+    [ -z "$opt_influx_jobname" ] && { log info "Jobname is not set."; end_process 1; }
+
+    if [ -n "$opt_keep_local" ]; then
+        if ! [[ ${opt_keep_local:(-1)} == "s" || ${opt_keep_local:(-1)} == "d" ]]; then
+            echo "--keeplocal: Parameter malformed. suffix s or d missing"
+            end_process 255
+        fi
+    fi
+
+    if [ -n "$opt_keep_remote" ]; then
+        if ! [[ ${opt_keep_remote:(-1)} == "s" || ${opt_keep_remote:(-1)} == "d" ]]; then
+            echo "--keepremote: Parameter malformed. suffix s or d missing"
+            end_process 255
+        fi
+    fi
+
+    if [ $opt_keepdlock -eq 1 ] && [ $opt_migrate -eq 1 ]; then
+        log error "--keepdlock/--migrate: Invalid parameter Combination: you can't keep the destination locked in near-live migration mode"
+        end_process 255
+    fi
+
+    if [ -n "$opt_tag" ] && [ -n "$opt_vm_ids" ] && [ "$opt_vm_ids" != "all" ]; then
+        log error "You can't use --tag and --vmid at the same time"
+        end_process 255
+    fi
+
+    [ -n "$opt_tag" ] && [ -z $opt_vm_ids ] && opt_vm_ids="all"
+
     [ -z "$opt_vm_ids" ] && { log info "VM id is not set."; end_process 1; }
 
-    vm_ids=$(echo "$opt_vm_ids" | tr ',' "\n")
+    if [ "$opt_vm_ids" = "all" ]; then
+        local all=''
+        local data=''
+        local cnt=''
+        local ids=''
 
+        all=$(get_vm_ids "$QEMU_CONF_CLUSTER/*$EXT_CONF" "$LXC_CONF_CLUSTER/*$EXT_CONF")
+        log debug "all: $all"
+        all=$(echo "$all" | tr ',' "\n")
+        opt_exclude_vmids=$(echo "$opt_exclude_vmids" | tr ',' "\n")
+        for id in $all; do
+            cnt=$(echo $opt_exclude_vmids | grep -o $id|wc -w)
+            if [ $cnt == 0 ]; then
+                vm_ids=$(echo "$vm_ids$id:$opt_prefix_id$id,")
+            fi
+        done
+        vm_ids=$(echo "$vm_ids" | tr ',' "\n")
+    else
+        if [ ! -z $opt_prefix_id ]; then
+            ids=$(echo "$opt_vm_ids" | tr ',' "\n")
+            for id in $ids; do
+                vm_ids=$(echo "$vm_ids$id:$opt_prefix_id$id,")
+            done
+            vm_ids=$(echo "$vm_ids" | tr ',' "\n")
+        else
+            vm_ids=$(echo "$opt_vm_ids" | tr ',' "\n")
+        fi
+    fi
+    
+}
+
+human_readable() {
+    b=${1:-0}; d=''; s=0; S=(Bytes {K,M,G,T,P,E,Z,Y}iB)
+    while ((b > 1024)); do
+        d="$(printf ".%02d" $((b % 1024 * 100 / 1024)))"
+        b=$((b / 1024))
+        let s++
+    done
+    echo "$b$d ${S[$s]}"
 }
 
 function map_vmids_to_host(){
@@ -166,7 +313,14 @@ function exist_file(){
 function lookupcephpool() {
     pvehost=$1
     pvepoolname=$2
-    res=$(ssh $pvehost cat /etc/pve/storage.cfg | sed -n "/rbd: $pvepoolname/,/^$/p" | grep pool | cut -d " " -f 2)
+    res=$(ssh $pvehost cat /etc/pve/storage.cfg | sed -n "/rbd: $pvepoolname/,/^$/p" | grep -E "\s+pool\s" | cut -d " " -f 2)
+    echo $res
+}
+
+function lookupdatapool() {
+    pvehost=$1
+    pvepoolname=$2
+    res=$(ssh $pvehost cat /etc/pve/storage.cfg | sed -n "/rbd: $pvepoolname/,/^$/p" | grep -E "\s+data-pool\s" | cut -d " " -f 2)
     echo $res
 }
 
@@ -177,7 +331,9 @@ function get_vm_ids(){
     while [ $# -gt 0 ]; do
         for conf in $1; do
             [ ! -e "$conf" ] && break
-
+            if [ -n "$opt_tag" ]  && ! grep -qE "^tags:\s.*$opt_tag(;|$)" $conf; then
+                continue
+            fi
             conf=$(basename "$conf")
             [ "$data" != '' ] && data="$data,"
             data="$data${conf%.*}"
@@ -188,20 +344,6 @@ function get_vm_ids(){
     echo "$data"
 }
 
-function get_config_file(){
-    local file_config=''
-
-    if exist_file "$QEMU_CONF_CLUSTER/$vm_id$EXT_CONF"; then
-        file_config=$(ls $QEMU_CONF_CLUSTER/$vm_id$EXT_CONF)
-
-    else
-        log error "VM $vm_id - Unknown technology or VMID not found: $QEMU_CONF_CLUSTER/$vm_id$EXT_CONF"
-        end_process 128
-    fi 
-
-    echo "$file_config"
-}
-
 function get_disks_from_config(){
     local disks;
     local file_config=$1
@@ -213,7 +355,7 @@ function get_disks_from_config(){
                 [[ "$line" == "" ]] && break
                 echo "$line" 
             done < "$file_config" | \
-            grep -P '^(?:((?:virtio|ide|scsi|sata|mp)\d+)|rootfs): ' | \
+            grep -P '^(?:((?:efidisk|virtio|ide|scsi|sata|mp|tpmstate)\d+)|rootfs): ' | \
             grep -v -P 'cdrom|none' | \
             grep -v -P 'backup=0' | \
             awk '{ split($0,a,","); split(a[1],b," "); print b[2]}')
@@ -221,10 +363,35 @@ function get_disks_from_config(){
     echo "$disks"
 }
 
+function check_unique_disk_config() {
+    local file_config=$1
+    disks=$(while read -r line; do
+                [[ "$line" == "" ]] && break
+                echo "$line" 
+            done < "$file_config" | \
+            grep -P '^(?:((?:efidisk|virtio|ide|scsi|sata|mp|tpmstate)\d+)|rootfs): ' | \
+            grep -v -P 'cdrom|none' | \
+            grep -v -P 'backup=0' | \
+            awk '{ split($0,a,","); split(a[1],b," "); print b[2]}'| wc -l)
+    echo disks            
+    uniquedisks=$(while read -r line; do
+                [[ "$line" == "" ]] && break
+                echo "$line" 
+            done < "$file_config" | \
+            grep -P '^(?:((?:efidisk|virtio|ide|scsi|sata|mp|tpmstate)\d+)|rootfs): ' | \
+            grep -v -P 'cdrom|none' | \
+            grep -v -P 'backup=0' | \
+            awk '{ split($0,a,","); split(a[1],b," "); print b[2]}'|cut -d ':' -f 2 | sort -nr | uniq | wc -l)
+    # TBD: ^(vm|ct)-([0-9]+)-([a-z]+)-[\d]+.*$
+    difference=$(expr $disks - $uniquedisks)
+    echo "$difference"
+}
+
 function log(){
     local level=$1
     shift 1
     local message=$*
+    local syslog_msg=''
 
     case $level in
         debug) 
@@ -236,26 +403,32 @@ function log(){
 
         info) 
             echo -e "$message"; 
-            echo -e "$message" >> "$LOG_FILE";
-            [ $opt_syslog -eq 1 ] && logger -t "$PROGNAME" "$message"
+            echo -e "$message" | sed -e 's/\x1b\[[0-9;]*m//g' >> "$LOG_FILE";
+            syslog_msg=$(echo -e "$message" | sed -e ${restripansicolor})
+            [ $opt_syslog -eq 1 ] && logger -t "$PROGNAME" "$syslog_msg"
             ;;
 
         warn)
-            echo "WARNING: $message" 1>&2
-            echo -e "$message" >> "$LOG_FILE";            
-            [ $opt_syslog -eq 1 ] && logger -t "$PROGNAME" -p daemon.warn "$message"
+            echo -n "$(echoyellow 'WARNING: ')"
+            echowhite "$message" 1>&2
+            echo -e "$message" | sed -e ${restripansicolor} >> "$LOG_FILE";            
+            syslog_msg=$(echo -e "$message" | sed -e ${restripansicolor})
+            [ $opt_syslog -eq 1 ] && logger -t "$PROGNAME" -p daemon.warn "$syslog_msg"
             ;;
         
         error)
-            echo "ERROR: $message" 1>&2
-            echo -e "$message" >> "$LOG_FILE";            
-            [ $opt_syslog -eq 1 ] && logger -t "$PROGNAME" -p daemon.err "$message"
+            echo -n "$(echored 'ERROR: ')"
+            echowhite "$message" 1>&2
+            echo -e "$message" | sed -e ${restripansicolor} >> "$LOG_FILE";            
+            syslog_msg=$(echo -e "$message" | sed -e ${restripansicolor})
+            [ $opt_syslog -eq 1 ] && logger -t "$PROGNAME" -p daemon.err "$syslog_msg"
             ;;
 
         *)  
             echo "$message" 1>&2
-            echo -e "$message" >> "$LOG_FILE";            
-            [ $opt_syslog -eq 1 ] && logger -t "$PROGNAME" "$message"
+            echo -e "$message" | sed -e ${restripansicolor} >> "$LOG_FILE";            
+            syslog_msg=$(echo -e "$message" | sed -e ${restripansicolor})
+            [ $opt_syslog -eq 1 ] && logger -t "$PROGNAME" "$syslog_msg"
             ;;
     esac
 }
@@ -274,9 +447,36 @@ function mirror() {
     parse_opts "$@"
 
     local timestamp; timestamp=$(date +%Y%m%d%H%M%S)
+    local xmittype
+    local humantime
+    local vmname
+    local -i xmitrc
+    local -i ssrc
+    local -i freezerc
+    local -i unfreezerc
+    local -i startdisk
+    local -i enddisk
+    local -i startjob
+    local -i endjob
+    local -i vmcount=0
+    local -i diskcount=0
+    local -i vmdiskcount=0
+    local -i skipped_vm_count=0
+    local -i startdowntime
+    local -i enddowntime
+    local -i ga_ping
 
-    log info "ACTION: Onlinemirror"
+    local disp_perf_freeze_failed
+    local disp_perf_ss_failed
+    local disp_perf_full_failed
+    local disp_perf_diff_failed
+
+    log info "ACTION: $(echowhite Onlinemirror)"
     log info "Start mirror $(date "+%F %T")"
+    startjob=$(date +%s)
+
+    get_ceph_version
+    log info "Local Ceph Version: $scephversion, Remote Ceph Version: $dcephversion"
 
     #create pid file
     local pid_file="/var/run/$PROGNAME.pid"
@@ -292,29 +492,69 @@ function mirror() {
         end_process 1
     fi
 
+    scluster=$(grep cluster_name /etc/pve/corosync.conf | cut -d " " -f 4)
+    dcluster=$(ssh "$opt_destination" grep cluster_name /etc/pve/corosync.conf | cut -d " " -f 4)
+
+    if [ $opt_migrate -eq 1 ] && [ $opt_noconfirm -eq 0 ]; then
+        echo "VM(s) $opt_vm_ids will subsequently be shutdown on [$scluster] and started on [$dcluster]"
+        read -p "Do you want to proceed? (yes/no) " yn
+        case $yn in 
+            yes ) echo ok, we will proceed;;
+            no ) echo exiting...;
+                exit;;
+            * ) echo invalid response;
+                exit 1;;
+        esac
+    fi
+
+
+
     map_source_to_destination_vmid
     map_vmids_to_host
     map_vmids_to_dsthost "$opt_destination"
 
+    if [ "$(check_pool_exist "$opt_pool")" -eq 0 ]; then
+        log error "Preflight check: Destination RBD-Pool $opt_pool does not exist."
+        end_process 255
+    fi
     for vm_id in $svmids; do
-        local file_config; file_config=$(get_config_file)
-        [ -z "$file_config" ] && continue
+        file_config="$PVE_NODES/${pvnode[$vm_id]}/$QEMU/$vm_id.conf"
+        check_unique_disk_config "$file_config"
+        end_process 255
+        if [[ $(check_unique_disk_config "$file_config") -ge 1 ]]; then
+            log error "VM $vm_id - Preflight check: VM $vm_id has duplicate disk entries - skipping to next VM. Check Documentation to learn how to avoid this."
+            (( skipped_vm_count++ ))
+            continue
+        fi
+        if ! exist_file "$file_config"; then
+            log error "VM $vm_id - Preflight check: VM $vm_id does not exist on source cluster [$scluster] - skipping to next VM."
+            (( skipped_vm_count++ ))
+            continue
+        fi
+        ga_ping=$(gaping "$vm_id")
+        log debug "ga_ping: $ga_ping"
+        if [ "$ga_ping" -eq 255 ] ; then    #vm running but no qemu-guest-agent answering
+            log error "VM $vm_id - Preflight check: VM $vm_id on source cluster [$scluster] has no qemu-guest-agent running - skipping to next VM."
+            (( skipped_vm_count++ ))
+            continue
+        fi
+        (( vmcount++ ))
         local disk=''
         dvmid=${dvmids[$vm_id]}
-
-
-        srcvmgenid=$(cat $PVE_NODES/"${pvnode[$vm_id]}"/$QEMU/"$vm_id".conf|grep vmgenid|sed -r -e 's/^vmgenid:\s(.*)/\1/')
-        dstvmgenid=$(ssh $opt_destination cat $PVE_NODES/"${dstpvnode[$dvmid]}"/$QEMU/"$dvmid".conf 2>/dev/null|grep vmgenid|sed -r -e 's/^vmgenid:\s(.*)/\1/')
-        log debug "Checking for VM $dvmid on Destination Host $opt_destination $QEMU_CONF_CLUSTER"
-        log debug "DVMID: $dvmid"
-        conf_on_destination=$(ssh $opt_destination "ls -d $QEMU_CONF_CLUSTER/$dvmid$EXT_CONF 2>/dev/null")
+        vmname=$(cat $PVE_NODES/"${pvnode[$vm_id]}"/$QEMU/"$vm_id".conf | sed -e ''$restripsnapshots'' | grep "name\:" | cut -d' ' -f 2)
+        log info "VM $vm_id - Starting mirror for $(echowhite "$vmname")"
+        srcvmgenid=$(cat $PVE_NODES/"${pvnode[$vm_id]}"/$QEMU/"$vm_id".conf | sed -e ''$restripsnapshots'' | grep vmgenid | sed -r -e 's/^vmgenid:\s(.*)/\1/')
+        dstvmgenid=$(ssh "$opt_destination" cat $PVE_NODES/"${dstpvnode[$dvmid]}"/$QEMU/"$dvmid".conf 2>/dev/null | grep vmgenid | sed -e ''$restripsnapshots'' | sed -r -e 's/^vmgenid:\s(.*)/\1/')
+        log info "VM $vm_id - Checking for VM $dvmid on destination cluster $opt_destination $QEMU_CONF_CLUSTER"
+        log debug "DVMID:$dvmid srcvmgenid:$srcvmgenid dstvmgenid:$dstvmgenid"
+        conf_on_destination=$(ssh "$opt_destination" "ls -d $QEMU_CONF_CLUSTER/$dvmid$EXT_CONF 2>/dev/null")
         [[ "$conf_on_destination" =~ $redstconf ]]
         host_on_destination=${BASH_REMATCH[1]}
 
         if [ $host_on_destination ]; then
             dststatus=$(ssh root@${dstpvnode[$dvmid]} qm status $dvmid|cut -d' ' -f 2)
             if [ $dststatus == "running" ]; then
-                log error "Destination VM is running. bailing out"
+                log error "VM is running on Destination Cluster [$dcluster]. bailing out"
                 end_process 255
             fi
         fi
@@ -330,134 +570,282 @@ function mirror() {
                 log error "Source VM genid ($srcvmgenid) doesn't match destination VM genid ($dstvmgenid). This should not happen. Bailing out.."
                 end_process 255
             fi
-            log info "Transmitting Config for VM $vm_id to desination $dvmid"
+            log info "VM $vm_id - Transmitting Config for VM $vm_id to destination $opt_destination VMID $dvmid"
             rewriteconfig $PVE_NODES/"${pvnode[$vm_id]}"/$QEMU/"$vm_id".conf $opt_destination "$opt_pool" $PVE_NODES/"$opt_destination"/$QEMU/"$dvmid".conf "$dvmid"
             map_vmids_to_dsthost "$opt_destination"
         fi
 
+        #--move so we need to shutdown and remove from ha group?
+        if [ $opt_migrate -eq 1 ]; then
+            log info "VM $vm_id - Migration requested, shutting down VM on ${pvnode[$vm_id]}"
+            if [ "$(get_ha_status "$vm_id")" == "started" ]; then
+                log info "VM $vm_id - remove from HA"
+                do_run "ha-manager remove $vm_id"
+            fi
+            do_run "ssh root@${pvnode[$vm_id]} qm shutdown $vm_id >/dev/null"
+            startdowntime=$(date +%s)
+        fi
+
         #Lock on source + destination
         if [ $opt_lock -eq 1 ]; then
-            ssh root@"${pvnode[$vm_id]}" qm set "$vm_id" --lock backup
+            do_run "ssh root@""${pvnode[$vm_id]}"" qm set ""$vm_id"" --lock backup" >/dev/null
+            log info "VM $vm_id - locked $vm_id [rc:$?] on source"
+            do_run "ssh root@""${dstpvnode[$dvmid]}"" qm set ""$dvmid"" --lock backup" >/dev/null
+            log info "VM $dvmid - locked $dvmid [rc:$?] on destination"
+        fi
+        #Freeze fs only if no migration running and qemu-guest-agent okay.
+        if [ $opt_migrate -eq 0 ] && [ $ga_ping -eq 0 ]; then
+            vm_freeze "$vm_id" "${pvnode[$vm_id]}" >/dev/null
+            freezerc=$?
+            if [ $freezerc -gt 0 ]; then
+                log warn "VM $vm_id - QEMU-Guest could not fsfreeze on guest."
+                (( perf_freeze_failed++ ))
+            else
+                (( perf_freeze_ok++ ))
             fi
-
-        if [ $opt_lock -eq 1 ]; then
-            ssh root@"${dstpvnode[$dvmid]}" qm set "$dvmid" --lock backup
         fi
-
-        #Freeze, take Rbd Snapshot then unfreeze
-        vm_freeze "$vm_id" "${pvnode[$vm_id]}"
         for disk in $(get_disks_from_config "$file_config"); do
             src_image_spec=$(get_image_spec "$disk")
-            create_snapshot "$src_image_spec@$opt_snapshot_prefix$timestamp"
+            create_snapshot "$src_image_spec@$opt_snapshot_prefix$timestamp" 2>/dev/null
+            ssrc=$?
+            if [ $ssrc -gt 0 ]; then
+                log warn "VM $vm_id - rbd snap failed."
+                (( perf_ss_failed++ ))
+            else
+                (( perf_ss_ok++ ))
+            fi
         done
-        vm_unfreeze "$vm_id" "${pvnode[$vm_id]}"
-
+        if [ $opt_migrate -eq 0 ]; then
+            vm_unfreeze "$vm_id" "${pvnode[$vm_id]}" >/dev/null
+            unfreezerc=$?
+            if [ $unfreezerc -gt 0 ]; then
+                log error "VM $vm_id - QEMU-Guest could not fsunfreeze on guest."
+            fi
+            if [ ! $opt_keepslock -eq 1 ]; then
+                do_run "ssh root@${pvnode[$vm_id]} qm unlock $vm_id" >/dev/null
+                log info "VM $vm_id - unlocked source VM $vm_id [rc:$?]"
+            fi
+        fi
         for disk in $(get_disks_from_config "$file_config"); do
-            log debug "VMID: $vm_id Disk: $disk DESTVMID: $dvmid"
+            (( diskcount++ ))
+            (( vmdiskcount++ ))
             src_image_spec=$(get_image_spec "$disk")
+            log debug "src_image_spec: $src_image_spec"
             [ -z "$src_image_spec" ] && continue
-            dst_image_spec=$(echo $src_image_spec | sed -r -e "s/([a-zA-Z0-9]+\/[a-zA-Z0-9]+\-)([0-9]+)(\-[a-zA-Z0-9]+\-[0-9]+)/\1$dvmid\3/")
+            dst_image_spec=$(echo $src_image_spec | sed -r -e "s/(.*\/[a-zA-Z0-9]+\-)([0-9]+)(\-[a-zA-Z0-9]+\-[0-9]+)/\1$dvmid\3/")
             [ -z "$dst_image_spec" ] && continue
             [[ $disk =~ $recephimg ]]
-            #src_image_pool=${BASH_REMATCH[1]}
+#	        src_image_pool_pve=${BASH_REMATCH[1]}
             src_image_pool=$(lookupcephpool "localhost" ${BASH_REMATCH[1]})
             src_image_name=${BASH_REMATCH[2]}
-            [[ $dst_image_spec =~ ^[a-zA-Z0-9]+\/(.*)$ ]]
-            dst_image_name=${BASH_REMATCH[1]}
+            [[ $dst_image_spec =~ ^.*\/(.*)$ ]]
+            dst_image_name=${BASH_REMATCH[1]} #-$src_image_pool_pve
             dst_image_pool=$(lookupcephpool $opt_destination $opt_pool)
-            echo "dst_image_pool: $dst_image_pool"
+            dst_data_pool=$(lookupdatapool $opt_destination $opt_pool)
+            if [ -n "$dst_data_pool" ]; then
+                dst_data_opt="--data-pool $dst_data_pool"
+            fi
             snapshot_name="@$opt_snapshot_prefix$timestamp"
             localsnapcount=$(rbd ls -l $src_image_pool | grep $src_image_name@$opt_snapshot_prefix | cut -d ' ' -f 1|wc -l)
             if [ $localsnapcount -ge 2 ]; then
             # we have at least 2 local snapshots, to we can make an incremental copy
                 currentlocal=$(rbd ls -l $src_image_pool | grep $src_image_name@$opt_snapshot_prefix | cut -d ' ' -f 1|tail -n 1)
-                localts=$(rbd ls -l $src_image_pool | grep $src_image_name@$opt_snapshot_prefix | cut -d ' ' -f 1 | sed -r -e 's/.*@mirror-(.*)/\1/')
+                localts=$(rbd ls -l $src_image_pool | grep $src_image_name@$opt_snapshot_prefix | cut -d ' ' -f 1 | sed -r -e 's/.*@'$opt_snapshot_prefix'(.*)/\1/')
             fi
             latestremote=$(ssh $opt_destination rbd ls -l $dst_image_pool | grep $dst_image_name@$opt_snapshot_prefix | cut -d ' ' -f 1|tail -n 1)
-            if [ $latestremote ]; then
+            if [ "$latestremote" ]; then
                 [[ $latestremote =~ ^.*@$opt_snapshot_prefix([0-9]+)$ ]]
                 latestremotets=${BASH_REMATCH[1]}
                 for ts in $localts; do
-                    if [ $ts == $latestremotets ]; then
+                    if [ "$ts" == "$latestremotets" ]; then
                         basets=$ts
                     fi
                 done
             fi
-            if [ -z $basets ]; then
+            if [ -z "$basets" ]; then
+                xmittype='full'
                 log debug "No matching Snapshot found on destination - Full Copy $src_image_pool/$src_image_name$snapshot_name to $dst_image_pool/$dst_image_name"
-                xmitjob="rbd export --rbd-concurrent-management-ops 8 $src_image_pool/$src_image_name$snapshot_name --no-progress -|pv -r|ssh $opt_destination rbd import --image-format 2 - $dst_image_pool/$dst_image_name"
+                #snapts=$(echo $currentlocal | sed -r -e 's/.*@mirror-(.*)/\1/')
+                snapshotsize=$(rbd du --pretty-format --format json $src_image_pool/$src_image_name|jq '.images[] | select (.snapshot_id == null) | {provisioned_size}.provisioned_size'|tail -1)
+                log debug "snapsize: $snapshotsize "
+                xmitjob="rbd export --rbd-concurrent-management-ops 8 $src_image_pool/$src_image_name$snapshot_name --no-progress - | tee >({ wc -c; } >/tmp/$PROGNAME.$pid.$dst_image_pool-$dst_image_name.size) | pv -s $snapshotsize -F \"VM $vm_id - F $src_image_pool/$src_image_name$snapshot_name: $PVFORMAT_FULL\" | ssh -c $opt_sshcipher $opt_destination rbd import --image-format 2 - $dst_image_pool/$dst_image_name $dst_data_opt 2>/dev/null"
                 # create initial snapshot on destination
-                if ! do_run $xmitjob; then
+                log debug "xmitjob: $xmitjob"
+                startdisk=$(date +%s)
+                do_run "$xmitjob"
+                enddisk=$(date +%s)
+                xmitrc=$?
+                if [ ! $xmitrc ]; then
                     log error "Transmitting Image failed"
+                    (( perf_full_failed++ ))
                     return 1
+                else
+                    (( perf_full_ok++ ))
                 fi
                 cmd="ssh $opt_destination rbd snap create $dst_image_pool/$dst_image_name$snapshot_name"
-                do_run $cmd
+                do_run "$cmd" 2>/dev/null
+                log info "VM $vm_id - created snapshot on $dvmid [rc:$?]"
+                perf_bytes_full=$(( perf_bytes_full + $(cat /tmp/"$PROGNAME"."$pid"."$dst_image_pool"-"$dst_image_name".size) ))
             else
+                xmittype='incremental'
                 log debug "Basecopy + snapshot on destination - let's just transfer the diff"
-                xmitjob="rbd export-diff --from-snap $opt_snapshot_prefix$basets $src_image_pool/$currentlocal - | ssh $opt_destination rbd import-diff - $dst_image_pool/$dst_image_name"
-                if ! do_run $xmitjob; then
+                log debug "sizer: rbd diff $src_image_pool/$currentlocal --from-snap $opt_snapshot_prefix$basets|gawk --bignum '{ SUM += \$2 } END { print SUM }'"
+                snapshotsize=$(rbd diff $src_image_pool/$currentlocal --from-snap $opt_snapshot_prefix$basets|gawk --bignum '{ SUM += $2 } END { print SUM }')
+                log debug "snapshotsize: $snapshotsize"
+                if [ -z "$snapshotsize" ]; then
+                    #disk was not attached, or really nothing has changed..
+                    snapshotsize=0
+                fi
+                xmitjob="rbd export-diff --no-progress --from-snap $opt_snapshot_prefix$basets $src_image_pool/$currentlocal - | tee >({ wc -c; } >/tmp/$PROGNAME.$pid.$dst_image_pool-$dst_image_name.size) | pv -F \"VM $vm_id - I $src_image_pool/$src_image_name$snapshot_name: $PVFORMAT_SNAP\" | ssh -c $opt_sshcipher $opt_destination rbd import-diff --no-progress - $dst_image_pool/$dst_image_name"
+                log debug "xmitjob: $xmitjob"
+                startdisk=$(date +%s)
+                do_run "$xmitjob"
+                enddisk=$(date +%s)
+                xmitrc=$?
+                if [ ! $xmitrc ]; then
                     log error "Transmitting Image failed"
+                    (( perf_diff_failed++ ))
                     return 1
+                else
+                    (( perf_diff_ok++ ))
                 fi
-                do_housekeeping "localhost" "$src_image_pool" "$src_image_name" $opt_keep_local
-                do_housekeeping "$opt_destination" "$dst_image_pool" "$dst_image_name" $opt_keep_remote
+                do_housekeeping "localhost" "$src_image_pool" "$src_image_name" "$opt_keep_local" "$vm_id"
+                do_housekeeping "$opt_destination" "$dst_image_pool" "$dst_image_name" "$opt_keep_remote" "$vm_id"
+                perf_bytes_diff=$(( perf_bytes_diff + $(cat /tmp/"$PROGNAME"."$pid"."$dst_image_pool"-"$dst_image_name".size) ))
             fi
+            perf_bytes_total=$(( perf_bytes_total + $(cat /tmp/"$PROGNAME"."$pid"."$dst_image_pool"-"$dst_image_name".size) ))
+            rm /tmp/"$PROGNAME"."$pid"."$dst_image_pool"-"$dst_image_name".size
+            log info "VM $vm_id - Disk Summary: Took $(( enddisk - startdisk )) Seconds to transfer $(human_readable "$perf_bytes_total" 2) in a $xmittype run"
+            if [ -n "$opt_influx_api_url" ]; then
+                log info "VM $vm_id - Logging to InfluxDB: $opt_influx_api_url"
+                influxlp="$opt_influx_job_metrics,vmname=$vmname,jobname=$opt_influx_jobname,destination=$opt_destination,srcimage=$src_image_name,dstimage=$dst_image_name,xmittype=$xmittype bytescalculated=$snapshotsize""i,bytesonwire=$perf_bytes_total""i,xmitrc=$xmitrc""i,freezerc=$freezerc""i,unfreezerc=$unfreezerc""i,basets=$basets""i"
+                log debug "InfluxLP: --->\n $influxlp"
+                cmd="curl --request POST \"$opt_influx_api_url/v2/write?org=$opt_influx_api_org&bucket=$opt_influx_bucket&precision=ns\" --header \"Authorization: Token $opt_influx_token\" --header \"Content-Type: text/plain; charset=utf-8\" --header \"Accept: application/json\" --data-binary '$influxlp'"
+                do_run "$cmd"
+            fi
+            unset basets
+            vmdiskcount=0
         done
-        if [ ! $opt_keepslock -eq 1 ]; then
-            ssh root@${pvnode[$vm_id]} qm unlock $vm_id
-            log info "Unlocking source VM $vm_id"
-        fi
         if [ $opt_keepdlock -eq 0 ]; then
             ssh root@${dstpvnode[$dvmid]} qm unlock $dvmid
-            log info "Unlocking destination VM $dvmid"
+            log info "VM $dvmid - Unlocking destination VM $dvmid"
+        fi
+        #--migrate so start on destination?
+        if [ $opt_migrate -eq 1 ]; then
+            log info "VM $dvmid - Starting VM on node ${dstpvnode[$dvmid]} in cluster [$dcluster]"
+            do_run "ssh root@""${dstpvnode[$dvmid]}"" qm start "$dvmid >/dev/null
+            enddowntime=$(date +%s)
+            log info "VM $dvmid - Downtime: $(( enddowntime - startdowntime )) Seconds"
+        fi
+
+    done
+    endjob=$(date +%s)
+    log info "Finnished mirror $(date "+%F %T")"
+    humantime=$(date -ud "@$((endjob-startjob))" +'%H hours %M minutes %S seconds')
+    log info "Job Summary: Bytes transferred $(human_readable $perf_bytes_total) for $diskcount Disks on $vmcount VMs in $humantime"
+    if [ "$perf_freeze_failed" -gt 0 ]; then disp_perf_freeze_failed="$(echored $perf_freeze_failed)"; else disp_perf_freeze_failed="$(echogreen $perf_freeze_failed)"; fi
+    if [ "$perf_ss_failed" -gt 0 ]; then disp_perf_ss_failed="$(echored $perf_ss_failed)"; else disp_perf_ss_failed="$(echogreen $perf_ss_failed)"; fi
+    if [ "$perf_full_failed" -gt 0 ]; then disp_perf_full_failed="$(echored $perf_full_failed)"; else disp_perf_full_failed="$(echogreen $perf_full_failed)"; fi
+    if [ "$perf_diff_failed" -gt 0 ]; then disp_perf_diff_failed="$(echored $perf_diff_failed)"; else disp_perf_diff_failed="$(echogreen $perf_diff_failed)"; fi
+    if [ "$skipped_vm_count" -gt 0 ]; then disp_skipped_vm_count="$(echored $skipped_vm_count)"; else disp_skipped_vm_count="$(echogreen $skipped_vm_count)"; fi
+    log info "VM Freeze OK/failed.......: $perf_freeze_ok/$disp_perf_freeze_failed"    
+    log info "RBD Snapshot OK/failed....: $perf_ss_ok/$disp_perf_ss_failed"
+    log info "RBD export-full OK/failed.: $perf_full_ok/$disp_perf_full_failed"
+    log info "RBD export-diff OK/failed.: $perf_diff_ok/$disp_perf_diff_failed"
+    log info "Full xmitted..............: $(human_readable $perf_bytes_full)"
+    log info "Differential Bytes .......: $(human_readable $perf_bytes_diff)"
+    log info "Skipped VMs ..............: $disp_skipped_vm_count"
+    if [ -n "$opt_influx_api_url" ]; then
+        log info "VM $vm_id - Logging Job summary to InfluxDB: $opt_influx_api_url"
+        influxlp="$opt_influx_summary_metrics,jobname=$opt_influx_jobname perf_bytes_diff=$perf_bytes_diff""i,perf_bytes_full=$perf_bytes_full""i,perf_bytes_total=$perf_bytes_total""i,perf_diff_failed=$perf_diff_failed""i,perf_diff_ok=$perf_diff_ok""i,perf_freeze_failed=$perf_freeze_failed""i,perf_freeze_ok=$perf_freeze_ok""i,perf_full_failed=$perf_full_failed""i,perf_full_ok=$perf_full_ok""i,perf_ss_failed=$perf_ss_failed""i,perf_ss_ok=$perf_ss_ok""i,perf_vm_running=$perf_vm_running""i,perf_vm_stopped=$perf_vm_stopped""i"
+        log debug "InfluxLP: --->\n $influxlp"
+        cmd="curl --request POST \"$opt_influx_api_url/v2/write?org=$opt_influx_api_org&bucket=$opt_influx_bucket&precision=ns\" --header \"Authorization: Token $opt_influx_token\" --header \"Content-Type: text/plain; charset=utf-8\" --header \"Accept: application/json\" --data-binary '$influxlp'"
+        do_run "$cmd"
+    fi
+    (( perf_vm_ok++ ))
+    end_process 0
+}
+
+function do_housekeeping(){
+    local horst=$1
+    local rbdpool=$2
+    local rbdimage=$3
+    local keep=$4
+    local vm=$5
+    local snap
+    local -i keeptime
+    local -i ts
+    local -i snapepoch
+    local -i age
+
+    log info "VM $vm - Housekeeping: $horst $rbdpool/$rbdimage, keeping Snapshots for $keep"
+    cmd="ssh $horst rbd ls -l $rbdpool | grep $rbdimage@$opt_snapshot_prefix | cut -d ' ' -f 1|head -n -1"
+    snapshots=$($cmd)
+    if [ "${keep:(-1)}" == "d" ]; then
+        keep=${keep%?}
+        keeptime=$(( $keep * 86400 ))
+    elif [ "${keep:(-1)}" == "s" ]; then
+        keep=${keep%?}
+        keeptime=$keep
+    fi
+    for snap in $snapshots; do
+        [[ $snap =~ ^.*@$opt_snapshot_prefix([0-9]+)$ ]]
+        ts=${BASH_REMATCH[1]}
+        [[ $ts =~ $redateex ]]
+        snapepoch=$(date --date "${BASH_REMATCH[1]}/${BASH_REMATCH[2]}/${BASH_REMATCH[3]} ${BASH_REMATCH[4]}:${BASH_REMATCH[5]}:${BASH_REMATCH[6]}" +%s)
+        age=$(($(date -u +"%s")-$snapepoch ))
+        if [ $age -gt "$keeptime" ]; then
+            cmd="ssh $horst rbd snap rm $rbdpool/$snap"
+            do_run "$cmd" 2>/dev/null
+            log info "VM $vm_id - Removing Snapshot $horst $rbdpool/$snap ($age""s) [rc:$?]"
+            if [ $rc -eq 0 ]; then
+                (( perf_snaps_removed++ ))
+            fi
         fi
     done
 }
 
-function do_housekeeping(){
-    horst=$1
-    rbdpool=$2
-    rbdimage=$3
-    keep=$4
-    snapshotstokill=$(ssh $horst rbd ls -l $rbdpool | grep $rbdimage@$opt_snapshot_prefix | cut -d ' ' -f 1|head -n -1 |head -n -$keep)
-    log info "Houskeeping $horst $rbdpool $rbdimage, keeping previous $keep Snapshots"
-    for snap in $snapshotstokill; do
-        cmd="ssh $horst rbd snap rm $rbdpool/$snap"
-        if ! do_run $cmd; then
-            log error "Housekeeping failed: $cmd"
-            return 1
-        fi
-    done
+function gaping() {
+    local vmid=$1
+    local rc
+    cmd="ssh root@${pvnode[$vmid]} qm guest cmd $vmid ping >/dev/null 2>&1"
+    eval "$cmd"
+    rc=$?
+    echo $rc
 }
 
 function create_snapshot(){
     local snap="$1"
     log info "VM $vm_id - Creating snapshot $snap"
-    if ! do_run "rbd snap create $snap"; then    
-        return 1;
-    fi
+    do_run "rbd snap create $snap"
+    rc=$?
+    log debug "create_snapshot() return $rc"
+    return $rc
 }
 
 function vm_freeze() {
     local fvm=$1;
     local fhost=$2;
-    status=$(ssh root@$fhost qm status $fvm|cut -d' ' -f 2)
+    status=$(ssh root@"$fhost" qm status "$fvm"|cut -d' ' -f 2)
     if ! [[ "$status" == "running" ]]; then
         log info "VM $fvm - Not running, skipping fsfreeze-freeze"
+        (( perf_vm_stopped++ ))
         return
+    else 
+        (( perf_vm_running++ ))
     fi
     local cmd="ssh root@$fhost /usr/sbin/qm guest cmd $fvm fsfreeze-freeze"
     log info "VM $fvm - Issuing fsfreeze-freeze to $fvm on $fhost"
     do_run "$cmd"
     rc=$?
     log debug "vm_freeze() return $rc"
+    return $rc
 }
 
 function vm_unfreeze() {
     local fvm=$1;
     local fhost=$2;
-    status=$(ssh root@$fhost qm status $fvm|cut -d' ' -f 2)
+    status=$(ssh root@"$fhost" qm status "$fvm"|cut -d' ' -f 2)
     if ! [[ "$status" == "running" ]]; then
         log info "VM $fvm - Not running, skipping fsfreeze-thaw"
         return
@@ -467,6 +855,7 @@ function vm_unfreeze() {
     do_run "$cmd"
     rc=$?
     log debug "vm_unfreeze() return $rc"
+    return $rc
 }
 
 function rewriteconfig(){
@@ -475,7 +864,13 @@ function rewriteconfig(){
     local newpool=$3
     local newconfig=$4
     local newvmid=$5
-    cat "$oldconfig" | sed -r -e "s/^(virtio|ide|scsi|sata|mp)([0-9]+):\s([a-zA-Z0-9]+):(.*)-([0-9]+)-disk-([0-9]+),(.*)$/\1\2: $newpool:\4-$newvmid-disk-\6,\7/g" | ssh $dst "cat - >$newconfig"
+    local sedcmd
+    if [ ! -z "$opt_rewrite" ]; then
+        sedcmd='sed -r -e '$opt_rewrite
+    else
+        sedcmd='sed -e /^$/,$d'
+    fi
+    cat "$oldconfig" | sed -r -e "s/^(efidisk|virtio|ide|scsi|sata|mp)([0-9]+):\s([a-zA-Z0-9]+):(.*)-([0-9]+)-disk-([0-9]+).*,(.*)$/\1\2: $newpool:\4-$newvmid-disk-\6,\7/g" | $sedcmd | sed -e '/^$/,$d' | sed -e '/ide[0-9]:.*-cloudinit,media=cdrom.*/d' | grep -v "^parent:\s.*$" | ssh "$dst" "cat - >$newconfig"
 }
 
 function checkvmid(){
@@ -483,7 +878,7 @@ function checkvmid(){
     local vmid=$2
     cmd="ssh $dst ls -l $QEMU_CONF_CLUSTER/$vmid.conf|wc -l"
     rval=$($cmd)
-    echo $rval
+    echo "$rval"
 }
 
 function do_run(){
@@ -506,23 +901,25 @@ function do_run(){
 
 function end_process(){
     local -i rc=$1;
-#    if ! [[ -z "$startts" && -z "$endts" ]]; then
-#        local -i runtime=$(expr $endts - $startts)
-#        local -i bps=$(expr $bytecount/$runtime)
-#    fi
-#    local subject="Ceph [VM:$vmok/$vmtotal SS:$snapshotok/$snapshottotal EX:$exportok/$exporttotal] [$(bytesToHuman "$bytecount")@$(bytesToHuman "$bps")/s]"
-#    [ $rc != 0 ] && subject="$subject [ERROR]"
+    local -i runtime
+    local -i bps
+    local -i ss_total
+    local subject
+    if ! [[ -z "$startjob" || -z "$endjob" ]]; then
+        runtime=$(expr $endjob - $startjob)
+        bps=$(expr $perf_bytes_total/$runtime)
+    fi
+    ss_total=$(expr $perf_ss_ok + $perf_ss_failed)
+    subject="Crossover [VM:$perf_vm_ok/$vmcount SS:$perf_ss_ok/$ss_total]"
+    [ $rc != 0 ] && subject="[ERROR] $subject" || subject="[OK] $subject"
 
-    #send email
-#    local mail;
-#    local mailhead="Backup $imgcount Images in $vmcount VMs (Bytes: $bytecount)"
-#    for mail in $(echo "$opt_addr_mail" | tr "," "\n"); do
-#        do_run "cat '$LOG_FILE' | mail -s '$subject' '$mail'"
-#    done
+    local mail;
+    for mail in $(echo "$opt_addr_mail" | tr "," "\n"); do
+        do_run "cat '$LOG_FILE' | mail -s '$subject' '$mail'"
+    done
 
     #remove log
-#    rm "$LOG_FILE"
-
+    rm "$LOG_FILE"
     exit "$rc";
 }
 
@@ -539,6 +936,29 @@ function get_image_spec(){
     echo "$image_spec"
 }
 
+function get_ha_status() {
+    local havmid="$1"
+    ha_status=$(ha-manager status| grep vm:"$havmid" | cut -d " " -f 4| sed 's/.$//')
+    echo "$ha_status"
+}
+
+function check_pool_exist() {
+    local poolname="$1"
+    local -i exists=255
+    pool_status=$(ssh $opt_destination pvesm status|grep rbd|cut -d " " -f 1|grep $poolname)
+    if [ "$pool_status" == "$poolname" ]; then
+        exists=1
+    else
+        exists=0
+    fi
+    echo $exists
+}
+
+function get_ceph_version() {
+    scephversion=$(ceph -v | cut -d " " -f 3)
+    dcephversion=$(ssh $opt_destination ceph -v | cut -d " " -f 3)
+}
+
 function main(){    
     [ $# = 0 ] && usage;
 

rainbow.sh

@@ -0,0 +1,51 @@
+
+#  https://github.com/xr09/rainbow.sh
+#  Bash helper functions to put colors on your scripts
+#
+#  Usage example:
+#  vargreen=$(echogreen "Grass is green")
+#  echo "Coming next: $vargreen"
+#
+
+__RAINBOWPALETTE="1"
+
+function __colortext()
+{
+  echo -e " \e[$__RAINBOWPALETTE;$2m$1\e[0m"
+}
+
+ 
+function echogreen() 
+{
+  echo $(__colortext "$1" "32")
+}
+
+function echored() 
+{
+  echo $(__colortext "$1" "31")
+}
+
+function echoblue() 
+{
+  echo $(__colortext "$1" "34")
+}
+
+function echopurple() 
+{
+  echo $(__colortext "$1" "35")
+}
+
+function echoyellow() 
+{
+  echo $(__colortext "$1" "33")
+}
+
+function echocyan() 
+{
+  echo $(__colortext "$1" "36")
+}
+
+function echowhite()
+{
+  echo $(__colortext "$1" "37")
+}