Enhance collect to support collecting from subclouds

This update introduces a new collect command line
option --subcloud (or -sc) to support the collect
of subclouds from the system controller.

This update also

- defaults to a 1 month dated collect
- defaults to parallel collect ; instead of one by one
- introduces an --inline or -in option to collect hosts
  or subclouds one by one ; i.e. the legacy collect mode
  before the parallel collect was introduced.
- adds a check_host_reachable access test to each host
  or subcloud to verify access before trying to collect.
- adds collect --continue support for collecting a large
  number of subclouds when there is not enough scratch
  space to hold them all in one go.
- scale subcloud collect timeout with number of subclouds
- show early initial progress for subcloud collect
- improved speed of subcloud name verification for large
  number of listed subclouds
- improved scratch space management on final tar create

Test Plan:

Orchestrated subcloud(s) collect ; parallel and inline:

PASS: Verify single subcloud collect
PASS: Verify listed subcloud collect ; one and several
PASS: Verify named subcloud collect (-sc -a -p -n <name>)
PASS: Verify all subcloud collect in parallel
PASS: Verify subcloud collect continue option handling

Active controller host(s) collect ; parallel and inline:

PASS: Verify single host collect
PASS: Verify listed host collect  ; one and several
PASS: Verify named collect
PASS: Verify all hosts collect

Misc New Features:

PASS: Verify new defaulted 1 month dated collect
PASS: Verify new --file option for subcloud collect
PASS: Verify collect --clean for local and remote hosts
             and subclouds
PASS: Verify collect tar cleanup on hosts and subclouds
             following collect
PASS: Verify parallel collect early progress with .'s
PASS: Verify subcloud collect continue warning message

Failure Cases:

PASS: Verify subcloud collect with failing dcmanager process
PASS: Verify subcloud collect with no provisioned subclouds
PASS: Verify fault handling surrounding use of new --file option
PASS: Verify partial collect after one or more subcloud collect
             errors or timeouts
PASS: Verify subcloud collect is only accepted on a system controller
PASS: Verify handling of unreachable host or subcloud
PASS: Verify handling of host or subcloud that reboots during collect
PASS: Verify collect of subcloud with a lot of /var/log
PASS: Verify collect handling when remote host or subcloud
             runs out of space
PASS: Verify subcloud collect handling when system controller
             runs out of space
PASS: Verify host collect handling when active controller
             runs out of space
PASS: Verify all report_error case handling for collect subcloud
PASS: Verify subcloud collect timeout on remote subcloud is
             reported as a subcloud timeout
PASS: Verify host or subcloud collect with no valid hosts or
             subclouds found or specified
PASS: Verify collect continue option failure handling

Regression:

PASS: Verify host and subcloud specification options (-a -l … , … )
PASS: Verify --all option overrides --list option
PASS: Verify collect drops duplicate or unknown host/subclouds
PASS: Verify host or subcloud collect clean option behavior
PASS: Verify host or subcloud collect reject with -lt 25% free
             scratch space
PASS: Verify permission and incorrect password error handling
PASS: Verify collect handling for unresponsive host or subcloud
PASS: Verify subcloud collect clean of unresponsive host or subcloud

PASS: Verify handling of 'control c' during collect
PASS: Verify collect logging on all hosts and subclouds
PASS: Verify shellcheck static analysis
PASS: Verify bashate static analysis

Change-Id: Ie76bfc86b1ee5eab83f42b65b643ccdf13ad7580
Story: 2009055
Task: 42836
Signed-off-by: Eric MacDonald <eric.macdonald@windriver.com>

tools/collector/scripts/collect_utils

@@ -27,6 +27,8 @@ FAIL_TIMEOUT7=17
 FAIL_TIMEOUT8=18
 FAIL_TIMEOUT9=19
 
+FAIL_SUBCLOUD_TIMEOUT=20
+
 FAIL_PASSWORD=30
 FAIL_PERMISSION=31
 FAIL_CLEANUP=32
@@ -39,10 +41,29 @@ FAIL_INSUFFICIENT_SPACE=38
 FAIL_INTERNAL=39
 FAIL_NO_TARDIR=40
 FAIL_NO_TARBALLS=41
+FAIL_NO_FILE_SPECIFIED=42
+FAIL_FILE_NOT_FOUND=43
+FAIL_FILE_EMPTY=44
+FAIL_PASSWORD_PROMPT=45
+FAIL_MISSING_PARAMETER=46
+FAIL_DATE_FORMAT=47
+FAIL_NO_HOSTS=48
+FAIL_FILE_COPY=49
+FAIL_SUBCLOUD=50
+FAIL_CONTINUE=51
+FAIL_SUBCLOUDNAME=52
+FAIL_NO_SUBCLOUDS=53
+FAIL_NOT_SYSTEMCONTROLLER=54
+
 
 # Warnings are above 200
 WARN_WARNING=200
 WARN_HOSTNAME=201
+WARN_SUBCLOUD=202
+
+COLLECT_ERROR="Error:"
+COLLECT_DEBUG="Debug:"
+COLLECT_WARN="Warning:"
 
 # Failure Strings
 FAIL_NOT_ENOUGH_SPACE_STR="Not enough /scratch filesystem space"
@@ -51,12 +72,38 @@ FAIL_TAR_OUT_OF_SPACE_STR="tar: Error is not recoverable"
 FAIL_INSUFFICIENT_SPACE_STR="Not enough space on device"
 FAIL_UNREACHABLE_STR="Unreachable"
 
+FAIL_TIMEOUT_STR="operation timeout"
+FAIL_SUBCLOUD_TIMEOUT_STR="subcloud collect timeout"
+
+FAIL_NO_FILE_SPECIFIED_STR="no file specified"
+FAIL_FILE_NOT_FOUND_STR="no such file or directory"
+FAIL_FILE_EMPTY_STR="file is empty"
+FAIL_PASSWORD_PROMPT_STR="password for"
+
+FAIL_DATE_FORMAT_STR="date format"
+FAIL_INACTIVE_STR="not active"
+FAIL_NO_HOSTS_STR="empty host list"
+FAIL_NO_SUBCLOUDS_STR="empty subcloud list"
+FAIL_MISSING_PARAMETER_STR="missing parameter"
+FAIL_FILE_COPY_STR="failed to copy"
+FAIL_CONTINUE_STR="cannot continue"
+
 # The minimum amount of % free space on /scratch to allow collect to proceed
 MIN_PERCENT_SPACE_REQUIRED=75
 
+# Subcloud collect stops when avail scratch drops below this threshold.
+# Use collect -sc --continue to tell collect to continue collecting subclouds
+# from where it left off.
+# 2Gib in K blocks rounded up
+declare -i COLLECT_BASE_DIR_FULL_THRESHOLD=2147484 # 2Gib in K blocks rounded up
+
 # Log file path/names
 COLLECT_LOG=/var/log/collect.log
 COLLECT_ERROR_LOG=/tmp/collect_error.log
+HOST_COLLECT_ERROR_LOG="/tmp/host_collect_error.log"
+
+DCROLE_SYSTEMCONTROLLER="systemcontroller"
+DCROLE_SUBCLOUD="subcloud"
 
 function source_openrc_if_needed
 {
@@ -79,7 +126,7 @@ function source_openrc_if_needed
         OPENRC="/etc/platform/openrc"
         if [ -e "${OPENRC}" ] ; then
             OS_PASSWORD=""
-            source ${OPENRC}
+            source ${OPENRC} 2>/dev/null 1>/dev/null
             if [ "${OS_PASSWORD}" != "" ] ; then
                 ACTIVE=true
             fi
@@ -99,6 +146,7 @@ cmd_done_file="/usr/local/sbin/expect_done"
 TAR_ZIP_CMD="tar -cvzf"
 TAR_UZIP_CMD="tar -xvzf"
 TAR_CMD="tar -cvhf"
+TAR_CMD_APPEND="tar -rvhf"
 UNTAR_CMD="tar -xvf"
 ZIP_CMD="gzip"
 NICE_CMD="/usr/bin/nice -n19"
@@ -128,14 +176,14 @@ function ilog
 
 function elog
 {
-    echo "Error: $@"
-    logger -t ${COLLECT_TAG} "Error: $@"
+    echo "${COLLECT_ERROR} $@"
+    logger -t ${COLLECT_TAG} "${COLLECT_ERROR} $@"
 }
 
 function wlog
 {
-    echo "Warning: $@"
-    logger -t ${COLLECT_TAG} "Warning: $@"
+    echo "${COLLECT_WARN} $@"
+    logger -t ${COLLECT_TAG} "${COLLECT_WARN} $@"
 }
 
 function set_debug_mode()
@@ -146,8 +194,8 @@ function set_debug_mode()
 function dlog()
 {
     if [ "$DEBUG" == true ] ; then
-        logger -t ${COLLECT_TAG} "Debug: $@"
-        echo "$(date) Debug: $@"
+        logger -t ${COLLECT_TAG} "${COLLECT_DEBUG} $@"
+        echo "$(date) ${COLLECT_DEBUG} $@"
     fi
 }
 
@@ -214,8 +262,7 @@ function collect_errors()
 
         ## now loop through known space related error strings
         index=0
-        while [ "x${listOfOutOfSpaceErrors[index]}" != "x" ]
-        do
+        while [ "x${listOfOutOfSpaceErrors[index]}" != "x" ] ; do
             grep -q "${listOfOutOfSpaceErrors[index]}" ${COLLECT_ERROR_LOG}
             if [ "$?" == "0" ] ; then