Add --jobname as mandatory parameter

.gitignore

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

README.md

@@ -11,71 +11,85 @@ ______
 |   --|  _| . |_ -|_ -| . | | | -_|  _|
 |_____|_| |___|___|___|___|\_/|___|_|  
 
-Cross Pool (live) replication and near-live migration forProxmox VE  
+Cross Pool (live) 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
+    --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/
 ```
 
 ## Introduction
 
-When working with hyperconverges Proxmox HA Clusters you sometimes need to get VMs migrated 
-to another cluster, or have a cold-standby copy of a VM ready to start there. Crossover implements
-functions that enable you to do the following:
+When working with hyperconverged Proxmox HA Clusters you sometimes need to get VMs migrated to another cluster, or have a cold-standby copy of a VM ready to start there in case your main Datacenter goes boom. Crossover implements functionality that enables you to do the following:
 
 - Transfer a non-running VM to another Cluster
 - Transfer a running VM to another Cluster
 - Continuously update a previously tranferred VM in another Cluster with incemental snapshots
 
-Backup And Restore Ceph for Proxmox VE with retention. This solution implements
-a snapshotbackup for Ceph cluster exporting to specific directory. The mechanism using
-Ceph snapshot, export and export differential. In backup export image and config
-file VM/CT.
-
 Currently this only works with Ceph based storage backends, since the incremental logic heavily
 relies on Rados block device features.
 
+It'll work according this scheme:
+
+```
+.:::::::::.                                                           .:::::::::. 
+|Cluster-A|                                                           |Cluster-B|
+|         |                                                           |         |
+| _______ |  rbd export-diff [..] | ssh pve04 | rbd import-diff [..]  | _______ |
+|  pve01 -|-----------------------------------------------------------|->pve04  |
+| _______ |                                                           | _______ |
+|  pve02  |                                                           |  pve05  |
+| _______ |                                                           | _______ |
+|  pve03  |                                                           |  pve06  |
+| _______ |                                                           | _______ |
+|         |                                                           |         |
+|:::::::::|                                                           |:::::::::|
+```
+
 ## Main features
 
 * Currently only for KVM. I might add LXC support when I need to.
 * 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
 
 ## Installation of prerequisites
 
-```apt install git
+```apt install git pv gawk jq
 
 ## Install the Script somewhere, eg to /opt
 
@@ -83,12 +97,44 @@ 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.
+
+## Examples
 
 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
+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. 
 

crossover

@@ -1,11 +1,22 @@
 #!/bin/bash
 
-#set -x
+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'
 
 # Cross Pool Migration and incremental replication Tool for Proxmox VMs using Ceph.
 # Author: Bastian Mäuser <bma@netz.org>        
 
-declare -r VERSION=0.2
+declare -r VERSION=0.5
 declare -r NAME=$(basename "$0")
 declare -r PROGNAME=${NAME%.*}
 
@@ -14,6 +25,8 @@ 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'
 
 declare -r LOG_FILE=$(mktemp)
 
@@ -22,9 +35,29 @@ declare -A -g dstpvnode
 declare -A -g svmids
 declare -A -g dvmids
 
+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 opt_destination
 declare opt_vm_ids=''
 declare opt_snapshot_prefix='mirror-'
+declare opt_rewrite=''
+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 +66,14 @@ 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 opt_keep_local='0s'
+declare opt_keep_remote='0s'
+
 
 declare -r redstconf='^\/etc\/pve\/nodes\/(.*)\/qemu-server\/([0-9]+).conf$'
 declare -r recephimg='([a-zA-Z0-9]+)\:(.*)'
+declare -r restripsnapshots='/^$/,$d'
+declare -r redateex='^([0-9]{4})([0-9]{2})([0-9]{2})([0-9]{2})([0-9]{2})([0-9]{2})$'
 
 function usage(){
    shift
@@ -47,7 +83,7 @@ function usage(){
  _____                                 
 |     |___ ___ ___ ___ ___ _ _ ___ ___ 
 |   --|  _| . |_ -|_ -| . | | | -_|  _|
-|_____|_| |___|___|___|___|\_/|___|_|  
+|_____|_| |___|___|___|___|\_/|___|_|   v$VERSION
 
 EOF
     fi
@@ -67,17 +103,26 @@ 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
+    --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
+    --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
+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
+    --debug              Show Debug Output
 
 Report bugs to <mephisto@mephis.to>
 
@@ -92,7 +137,7 @@ function parse_opts(){
     local args
     args=$(getopt \
            --options '' \
-           --longoptions=vmid:,destination:,pool:,keeplocal:,keepremote:,online,nolock,keep-slock,keep-dlock,overwrite,dry-run,debug \
+           --longoptions=vmid:,prefixid:,excludevmids:,destination:,pool:,keeplocal:,keepremote:,rewrite:,influxurl:,influxorg:,influxtoken:,influxbucket:,jobname:,online,nolock,keep-slock,keep-dlock,overwrite,dry-run,debug \
            --name "$PROGNAME" \
            -- "$@") \
            || end_process 128
@@ -102,10 +147,19 @@ function parse_opts(){
     while true; do    
       case "$1" in
         --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;;
+        --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;;
+
         --online) opt_online=1; shift 2;;
         --dry-run) opt_dry_run=1; shift;;
         --debug) opt_debug=1; shift;;
@@ -121,18 +175,61 @@ 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_vm_ids" ] && { log info "VM id is not set."; end_process 1; }
 
-    vm_ids=$(echo "$opt_vm_ids" | tr ',' "\n")
+    [ -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_vm_ids" = "all" ]; then
+        local all=''
+        local data=''
+        local cnt=''
+
+        all=$(get_vm_ids "$QEMU_CONF_CLUSTER/*$EXT_CONF" "$LXC_CONF_CLUSTER/*$EXT_CONF")
+        all=$(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
+        vm_ids=$(echo "$opt_vm_ids" | tr ',' "\n")
+    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(){
@@ -163,6 +260,13 @@ function exist_file(){
     done
 }
 
+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)
+    echo $res
+}
+
 function get_vm_ids(){
     local data=''
     local conf=''
@@ -234,13 +338,15 @@ function log(){
             ;;
 
         warn)
-            echo "WARNING: $message" 1>&2
+            echo -n $(echoyellow "WARNING: ")
+            echo $(echowhite "$message") 1>&2
             echo -e "$message" >> "$LOG_FILE";            
             [ $opt_syslog -eq 1 ] && logger -t "$PROGNAME" -p daemon.warn "$message"
             ;;
         
         error)
-            echo "ERROR: $message" 1>&2
+            echo -n $(echored "ERROR: ")
+            echo $(echowhite "$message") 1>&2
             echo -e "$message" >> "$LOG_FILE";            
             [ $opt_syslog -eq 1 ] && logger -t "$PROGNAME" -p daemon.err "$message"
             ;;
@@ -267,9 +373,28 @@ function mirror() {
     parse_opts "$@"
 
     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
 
-    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)
 
     #create pid file
     local pid_file="/var/run/$PROGNAME.pid"
@@ -285,21 +410,24 @@ function mirror() {
         end_process 1
     fi
 
+    
+
     map_source_to_destination_vmid
     map_vmids_to_host
     map_vmids_to_dsthost "$opt_destination"
 
     for vm_id in $svmids; do
+        (( vmcount++ ))
         local file_config; file_config=$(get_config_file)
         [ -z "$file_config" ] && continue
         local disk=''
         dvmid=${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: $dvmid"
+        vmname=$(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 Host $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]}
@@ -323,96 +451,205 @@ 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 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
 
         #Lock on source + destination
         if [ $opt_lock -eq 1 ]; then
-            ssh root@"${pvnode[$vm_id]}" qm set "$vm_id" --lock backup
-            ssh root@"${dstpvnode[$dvmid]}" qm set "$dvmid" --lock backup
+            do_run "ssh root@"${pvnode[$vm_id]}" qm set "$vm_id" --lock backup" >/dev/null
+            log info "VM $vm_id - locked $vm_id [rc:$?]"
+            do_run "ssh root@"${dstpvnode[$dvmid]}" qm set "$dvmid" --lock backup" >/dev/null
+            log info "VM $dvmid - locked $dvmid [rc:$?]"
         fi
 
-        #Freeze, take Rbd Snapshot then unfreeze
-        vm_freeze "$vm_id" "${pvnode[$vm_id]}"
+        vm_freeze "$vm_id" "${pvnode[$vm_id]}" >/dev/null
+        freezerc=$?
+        if [ $freezerc -gt 0 ]; then
+            log error "VM $vm_id - QEMU-Guest could not fsfreeze on guest."
+            (( perf_freeze_failed++ ))
+        else
+            (( perf_freeze_ok++ ))
+        fi
         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 error "VM $vm_id - rbd snap failed."
+                (( perf_ss_failed++ ))
+            else
+                (( perf_ss_ok++ ))
+            fi
         done
-        vm_unfreeze "$vm_id" "${pvnode[$vm_id]}"
+        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
 
         for disk in $(get_disks_from_config "$file_config"); do
+            (( diskcount++ ))
             log debug "VMID: $vm_id Disk: $disk DESTVMID: $dvmid"
             src_image_spec=$(get_image_spec "$disk")
             [ -z "$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 $opt_pool)
             snapshot_name="@$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 $opt_pool | grep $dst_image_name@$opt_snapshot_prefix | cut -d ' ' -f 1|tail -n 1)
-            if [ $latestremote ]; then
+            latestremote=$(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
                 [[ $latestremote =~ ^.*@$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
-                log debug "No matching Snapshot found on destination - Full Copy $src_image_pool/$src_image_name$snapshot_name to $opt_pool/$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 - $opt_pool/$dst_image_name"
+            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"
+                #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 $opt_destination rbd import --image-format 2 - $dst_image_pool/$dst_image_name  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
-                fi
-                cmd="ssh $opt_destination rbd snap create $opt_pool/$dst_image_name$snapshot_name"
-                do_run $cmd
                 else
+                    (( perf_full_ok++ ))
+                fi
+                cmd="ssh $opt_destination rbd snap create $dst_image_pool/$dst_image_name$snapshot_name"
+                do_run "$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 - $opt_pool/$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 $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" "$opt_pool" "$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
         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 $dvmid"
         fi
     done
+    endjob=$(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
+    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 $perf_bytes_diff)"
+    if [ -n "$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
 }
 
 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
+    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"
-        if ! do_run $cmd; then
-            log error "Housekeeping failed: $cmd"
-            return 1
+            do_run "$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
 }
@@ -420,30 +657,35 @@ function do_housekeeping(){
 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 $fvm - Not running, skipping fsfreeze-freeze"
         return
+        (( perf_vm_stopped++ ))
+    else 
+        (( perf_vm_running++ ))
     fi
     local cmd="ssh root@$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 $fvm - Not running, skipping fsfreeze-thaw"
         return
@@ -453,6 +695,7 @@ function vm_unfreeze() {
     do_run "$cmd"
     rc=$?
     log debug "vm_unfreeze() return $rc"
+    return $rc
 }
 
 function rewriteconfig(){
@@ -461,7 +704,13 @@ 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 "$oldconfig" | sed -r -e "s/^(virtio|ide|scsi|sata|mp)([0-9]+):\s([a-zA-Z0-9]+):(.*)-([0-9]+)-disk-([0-9]+).*,(.*)$/\1\2: $newpool:\4-$newvmid-disk-\6-\3,\7/g" | $sedcmd | sed -e '/^$/,$d' | grep -v "^parent:\s.*$" | ssh "$dst" "cat - >$newconfig"
 }
 
 function checkvmid(){
@@ -469,7 +718,7 @@ 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(){

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")
+}