Index: api.scm
==================================================================
--- api.scm
+++ api.scm
@@ -118,11 +118,11 @@
 (define (api:execute-requests dbstruct dat)
   (handle-exceptions
    exn
    (let ((call-chain (get-call-chain))
          )
-     (debug:print 0 *default-log-port* "WARNING: api:execute-requests received an exception from peer")
+     (debug:print 0 *default-log-port* "WARNING: api:execute-requests received an exception from peer, dat=" dat)
      (print-call-chain (current-error-port))
      (debug:print 0 *default-log-port* " message: "  ((condition-property-accessor 'exn 'message) exn))       
      (vector #f (vector exn call-chain dat))) ;; return some stuff for debug if an exception happens
    (cond
     ((not (vector? dat))                    ;; it is an error to not receive a vector

Index: common.scm
==================================================================
--- common.scm
+++ common.scm
@@ -248,11 +248,11 @@
 ;;
 (define (common:rotate-logs)
   (if (not (directory-exists? "logs"))(create-directory "logs"))
   (directory-fold 
    (lambda (file rem)
-     (handle-exceptions
+     (common:debug-handle-exceptions #t
       exn
       (debug:print-info 0 *default-log-port* "failed to rotate log " file ", probably handled by another process.")
       (let* ((fullname (conc "logs/" file))
              (file-age (- (current-seconds)(file-modification-time fullname))))
         (if (or (and (string-match "^.*.log" file)
@@ -291,11 +291,11 @@
             (cond
              ((get-environment-variable "MT_SKIP_DB_MIGRATE") #t)
              ((and (file-exists? mtconf) (file-exists? dbfile) (not read-only)
                    (eq? (current-user-id)(file-owner mtconf))) ;; safe to run -cleanup-db
               (debug:print 0 *default-log-port* "   I see you are the owner of megatest.config, attempting to cleanup and reset to new version")
-              (handle-exceptions
+              (common:debug-handle-exceptions #t
                exn
                (begin
                  (debug:print 0 *default-log-port* "Failed to switch versions.")
                  (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
                  (print-call-chain (current-error-port))
@@ -397,13 +397,13 @@
 
 (define (common:get-megatest-exe)
   (or (getenv "MT_MEGATEST") "megatest"))
 
 (define (common:read-encoded-string instr)
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
    exn
-   (handle-exceptions
+   (common:debug-handle-exceptions #t
     exn
     (begin
       (debug:print-error 0 *default-log-port* "received bad encoded string \"" instr "\", message: " ((condition-property-accessor 'exn 'message) exn))
       (print-call-chain (current-error-port))
       #f)
@@ -840,11 +840,11 @@
 		  (loop (car tal)(cdr tal))))))))
   
 (define (common:get-install-area)
   (let ((exe-path (car (argv))))
     (if (file-exists? exe-path)
-	(handle-exceptions
+	(common:debug-handle-exceptions #t
 	 exn
 	 #f
 	 (pathname-directory
 	  (pathname-directory 
 	   (pathname-directory exe-path))))
@@ -858,11 +858,11 @@
       (let loop ((hed (car dirs))
 		 (tal (cdr dirs)))
 	(let ((res (or (and (directory? hed)
 			    (file-write-access? hed)
 			    hed)
-		       (handle-exceptions
+		       (common:debug-handle-exceptions #t
 			exn
 			#f
 			(create-directory hed #t)))))
 	  (if (and (string? res)
 		   (directory? res))
@@ -874,18 +874,18 @@
 ;; return the youngest timestamp . filename
 ;;
 (define (common:get-youngest glob-list)
   (let ((all-files (apply append
 			  (map (lambda (patt)
-				 (handle-exceptions
+				 (common:debug-handle-exceptions #t
 				     exn
 				     '()
 				   (glob patt)))
 			       glob-list))))
     (fold (lambda (fname res)
 	    (let ((last-mod (car res))
-		  (curmod   (handle-exceptions
+		  (curmod   (common:debug-handle-exceptions #t
 				exn
 				0
 			      (file-modification-time fname))))
 	      (if (> curmod last-mod)
 		  (list curmod fname)
@@ -1202,23 +1202,23 @@
 
 ;; lazy-safe get file mod time. on any error (file not existing etc.) return 0
 ;;
 (define (common:lazy-modification-time fpath)
   (handle-exceptions
-   exn
-   0
-   (file-modification-time fpath)))
+      exn
+      0
+    (file-modification-time fpath)))
 
 ;; find timestamp of newest file associated with a sqlite db file
 (define (common:lazy-sqlite-db-modification-time fpath)
   (let* ((glob-list (handle-exceptions
-                    exn
-                    '("/no/such/file")
-                    (glob (conc fpath "*"))))
+			exn
+			`(,(conc "/no/such/file, message: " ((condition-property-accessor 'exn 'message) exn)))
+		      (glob (conc fpath "*"))))
          (file-list (if (eq? 0 (length glob-list))
-                        '("/no/such/file")
-                        glob-list)))
+			'("/no/such/file")
+			glob-list)))
   (apply max
    (map
     common:lazy-modification-time 
     file-list))))
 
@@ -1233,11 +1233,11 @@
 
 ;; make "nice-path" available in config files and the repl
 (define nice-path common:nice-path)
 
 (define (common:read-link-f path)
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
       exn
       (begin
 	(debug:print-error 0 *default-log-port* "command \"/bin/readlink -f " path "\" failed.")
 	path) ;; just give up
     (with-input-from-pipe

Index: common_records.scm
==================================================================
--- common_records.scm
+++ common_records.scm
@@ -26,13 +26,27 @@
 (define-syntax define-simple-syntax
   (syntax-rules ()
     ((_ (name arg ...) body ...)
      (define-syntax name (syntax-rules () ((name arg ...) (begin body ...)))))))
 
+;; (define-syntax common:handle-exceptions
+;;   (syntax-rules ()
+;;     ((_ exn-in errstmt ...)(common:debug-handle-exceptions #t exn-in errstmt ...))))
+
+(define-syntax common:debug-handle-exceptions
+  (syntax-rules ()
+    ((_ debug exn errstmt body ...)
+     (if debug
+	 (begin body ...)
+	 (handle-exceptions exn errstmt body ...)))))
+
 (define-syntax common:handle-exceptions
   (syntax-rules ()
-    ((_ exn-in errstmt ...)(handle-exceptions exn-in errstmt ...))))
+    ((_ exn errstmt body ...)
+     (begin body ...))))
+
+;; (define handle-exceptions common:handle-exceptions)
 
 ;; iup callbacks are not dumping the stack, this is a work-around
 ;;
 (define-simple-syntax (debug:catch-and-dump proc procname)
   (handle-exceptions
@@ -97,11 +111,11 @@
 	 (list? n))
     (not (null? (lset-intersection! eq? *verbosity* n))))
    ((and (number? *verbosity*)
 	 (list? n))
     (member *verbosity* n))))
-      
+
 (define (debug:setup)
   (let ((debugstr (or (args:get-arg "-debug")
 		      (getenv "MT_DEBUG_MODE"))))
     (set! *verbosity* (debug:calc-verbosity debugstr))
     (debug:check-verbosity *verbosity* debugstr)

Index: configf.scm
==================================================================
--- configf.scm
+++ configf.scm
@@ -49,11 +49,11 @@
 		   (config:assoc-safe-add
 		    (hash-table-ref/default cfgdat section-name '())
 		    var value metadata: metadata)))
 
 (define (config:eval-string-in-environment str)
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
    exn
    (begin
      (debug:print-error 0 *default-log-port* "problem evaluating \"" str "\" in the shell environment")
      #f)
    (let ((cmdres (process:cmd-run->list (conc "echo " str))))
@@ -109,11 +109,11 @@
 				   (conc "(lambda (ht)(config-lookup ht \"" sect "\" \"" var "\"))")))
 				((runconfigs-get rget) (conc "(lambda (ht)(runconfigs-get ht \"" cmd "\"))"))
 				;; ((rget)           (conc "(lambda (ht)(runconfigs-get ht \"" cmd "\"))"))
 				(else "(lambda (ht)(print \"ERROR\") \"ERROR\")"))))
 		;; (print "fullcmd=" fullcmd)
-		(handle-exceptions
+		(common:debug-handle-exceptions #t
 		 exn
 		 (begin
 		   (debug:print 0 *default-log-port* "WARNING: failed to process config input \"" l "\"")
 		   (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
 		   ;; (print "exn=" (condition->list exn))
@@ -653,19 +653,31 @@
      (lambda (section)
        (hash-table-set! ht (car section)(cdr section)))
      adat)
     ht))
 
+;; if 
 (define (configf:read-alist fname)
-  (configf:alist->config
-   (with-input-from-file fname read)))
+  (handle-exceptions
+      exn
+      #f
+    (configf:alist->config
+     (with-input-from-file fname read))))
 
 (define (configf:write-alist cdat fname)
-  (with-output-to-file fname
-    (lambda ()
-      (pp (configf:config->alist cdat)))))
-     
+  (let ((dat  (configf:config->alist cdat)))
+    (with-output-to-file fname ;; first write out the file
+      (lambda ()
+	(pp dat)))
+    (if (file-exists? fname)   ;; now verify it is readable
+	(if (configf:read-alist fname)
+	    #t ;; data is good.
+	    (begin
+	      (delete-file fname)
+	      (debug:print 0 *default-log-port* "WARNING: content " dat " for cache " fname " is not readable. Deleting generated file.")
+	      #f))
+	#f)))
 
 ;; convert hierarchial list to ini format
 ;;
 (define (configf:config->ini data)
   (map 

Index: dashboard-tests.scm
==================================================================
--- dashboard-tests.scm
+++ dashboard-tests.scm
@@ -465,22 +465,22 @@
 	       (item-path  (db:test-get-item-path testdat))
 	       ;; this next block was added to fix a bug where variables were
                ;; needed. Revisit this.
 	       (runconfig  (let ((runconfigf (conc  *toppath* "/runconfigs.config"))) ;; no rush but it would be good to convert this call to use runconfig:read
 	 		     (if (file-exists? runconfigf)
-	 			 (handle-exceptions
+	 			 (common:debug-handle-exceptions #t
                                    exn
                                    #f  ;; do nothing, just keep on trucking ....
                                    (setup-env-defaults runconfigf run-id (make-hash-table) keydat environ-patt: keystring))
 	 			 (make-hash-table))))
 	       (testconfig    (begin
 				;; (runs:set-megatest-env-vars run-id inrunname: runname testname: test-name itempath: item-path)
 				(runs:set-megatest-env-vars run-id inkeyvals: keydat inrunname: runname intarget: keystring testname: testname itempath: item-path) ;; these may be needed by the launching process
-				(handle-exceptions
-				 exn
+				(common:debug-handle-exceptions #t
+				 exn  ;; NOTE: I've no idea why this was written this way. Research, study and fix needed!
 				 (tests:get-testconfig (db:test-get-testname testdat) (db:test-get-item-path testdat) test-registry #f)
-				 (tests:get-testconfig (db:test-get-testname testdat) test-registry #t))))
+				 (tests:get-testconfig (db:test-get-testname testdat) item-path test-registry #t))))
 	       (viewlog    (lambda (x)
 			     (if (file-exists? logfile)
 					;(system (conc "firefox " logfile "&"))
 				 (dashboard-tests:run-html-viewer logfile)
 				 (message-window (conc "File " logfile " not found")))))
@@ -513,11 +513,11 @@
 							    (> (current-milliseconds)(+ last-update 250))) ;; every half seconds if db touched
 						       (> (current-milliseconds)(+ last-update 10000))     ;; force update even 10 seconds
 						       request-update))
 				    (newtestdat (if need-update 
 						    ;; NOTE: BUG HIDER, try to eliminate this exception handler
-						    (handle-exceptions
+						    (common:debug-handle-exceptions #t
 						     exn 
 						     (debug:print-info 0 *default-log-port* "test db access issue in examine test for run-id " run-id ", test-id " test-id ": " ((condition-property-accessor 'exn 'message) exn))
 						     (rmt:get-test-info-by-id run-id test-id )))))
 			       ;; (print "INFO: need-update= " need-update " curr-mod-time = " curr-mod-time)
 			       (cond

Index: dashboard.scm
==================================================================
--- dashboard.scm
+++ dashboard.scm
@@ -1899,11 +1899,11 @@
 	 (viewgen (configf:lookup views-cfgdat view-name "viewgen"))
 	 (updater (configf:lookup views-cfgdat view-name "updater"))
 	 (result-child #f))
     (if (and (file-exists? source)
 	     (file-read-access? source))
-	(handle-exceptions
+	(common:debug-handle-exceptions #t
 	 exn
 	 (begin
 	   (print-call-chain)
 	   (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
 	   (debug:print 0 *default-log-port* "ERROR: failed to load " source ", try loading in the repl: megatest -repl")
@@ -1911,11 +1911,11 @@
 	 (load source))
 	(begin
 	  (debug:print 0 *default-log-port* "ERROR: cannot find file to load: \"" source "\" for user view " view-name)))
     ;; now run the user supplied definition for the tab view
     (if success
-	(handle-exceptions
+	(common:debug-handle-exceptions #t
 	 exn
 	 (begin
 	   (print-call-chain)
 	   (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
 	   (debug:print 0 *default-log-port* "ERROR: failed call procedure " viewgen
@@ -1928,11 +1928,11 @@
 	       ((eval (string->symbol viewgen)) commondat tabs tab-num view-name views-cfgdat *configdat*))))
     ;; and finally set the updater
     (if success
 	(dboard:commondat-add-updater commondat
 				      (lambda ()
-					(handle-exceptions
+					(common:debug-handle-exceptions #t
 					 exn
 					 (begin
 					   (print-call-chain)
 					   (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
 					   (debug:print 0 *default-log-port* "ERROR: failed call procedure \"" updater
@@ -2712,14 +2712,14 @@
 
 ;; (define *monitor-db-path* #f)
 (define *last-monitor-update-time* 0)
 
 ;; Force creation of the db in case it isn't already there.
-(tasks:open-db)
+;; (tasks:open-db)
 
 (define (dashboard:get-youngest-run-db-mod-time dbdir)
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
    exn
    (begin
      (debug:print 0 *default-log-port* "WARNING: error in accessing databases in get-youngest-run-db-mod-time: " ((condition-property-accessor 'exn 'message) exn) " db-dir="dbdir)
      (current-seconds)) ;; something went wrong - just print an error and return current-seconds
    (common:max (map (lambda (filen)
@@ -3013,11 +3013,11 @@
 				      (reverse
 				       (sqlite3:fold-row
 					(lambda (res t var val)
 					  (cons (vector t var val) res))
 					'() db all-dat-qrystr)))
-		     (let ((zeropt (handle-exceptions
+		     (let ((zeropt (common:debug-handle-exceptions #t
 				    exn
 				    #f
 				    (sqlite3:first-row db all-dat-qrystr))))
 		       (if zeropt ;; NOTE: Add zeropt to the beginning of the list as the list was reversed above.
 			   (hash-table-set! res-ht

Index: datashare.scm
==================================================================
--- datashare.scm
+++ datashare.scm
@@ -228,11 +228,11 @@
 	     (file-read-access? path))
 	(let* ((dbpath    (conc path "/datashare.db"))
 	       (writeable (file-write-access? dbpath))
 	       (dbexists  (file-exists? dbpath))
 	       (handler   (make-busy-timeout 136000)))
-	  (handle-exceptions
+	  (common:debug-handle-exceptions #t
 	   exn
 	   (begin
 	     (debug:print 2 *default-log-port* "ERROR: problem accessing db " dbpath
 			  ((condition-property-accessor 'exn 'message) exn))
 	     (exit))
@@ -243,11 +243,11 @@
 		(datashare:initialize-db db)))
 	  db)
 	(print "ERROR: invalid path for storing database: " path))))
 
 (define (open-run-close-exception-handling proc idb . params)
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
    exn
    (let ((sleep-time (random 30))
          (err-status ((condition-property-accessor 'sqlite3 'status #f) exn)))
      (case err-status
        ((busy)

Index: db.scm
==================================================================
--- db.scm
+++ db.scm
@@ -74,11 +74,11 @@
     (print-call-chain (current-error-port))))
 
 ;; convert to -inline 
 ;;
 (define (db:first-result-default db stmt default . params)
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
    exn
    (let ((err-status ((condition-property-accessor 'sqlite3 'status #f) exn)))
      ;; check for (exn sqlite3) ((condition-property-accessor 'exn 'message) exn)
      (if (eq? err-status 'done)
 	 default
@@ -145,11 +145,11 @@
     (if (and use-mutex
 	     (common:low-noise-print 120 "over-50-parallel-api-requests"))
 	(debug:print-info 0 *default-log-port* *api-process-request-count* " parallel api requests being processed in process " (current-process-id) ", throttling access"))
     (if (common:low-noise-print 600 (conc "parallel-api-requests" *max-api-process-requests*))
 	(debug:print-info 2 *default-log-port* "Parallel api request count: " *api-process-request-count* " max parallel requests: " *max-api-process-requests*))
-    (handle-exceptions
+    (common:debug-handle-exceptions #t
      exn
      (begin
        (print-call-chain (current-error-port))
        (debug:print-error 0 *default-log-port* "sqlite3 issue in db:with-db, dbstruct=" dbstruct ", run-id=" run-id ", proc=" proc ", params=" params " error: " ((condition-property-accessor 'exn 'message) exn))
        ;; there is no recovering at this time. exit
@@ -190,11 +190,11 @@
 ;; 
 ;; If run-id is #f return to create and retrieve the path where the db will live.
 ;;
 (define (db:dbfile-path . junk) ;;  run-id)
   (let* ((dbdir           (common:get-db-tmp-area)))
-    (handle-exceptions
+    (common:debug-handle-exceptions #t
      exn
      (begin
        (debug:print-error 0 *default-log-port* "Couldn't create path to " dbdir)
        (exit 1))
      (if (not (directory? dbdir))(create-directory dbdir #t)))
@@ -259,11 +259,11 @@
 ;; ;; 
 ;; (define (db:open-rundb dbstruct run-id #!key (attemptnum 0)(do-not-open #f)) ;;  (conc *toppath* "/megatest.db") (car *configinfo*)))
 ;;   (let* ((dbfile       (db:dbfile-path run-id)) ;; (conc toppath "/db/" run-id ".db"))
 ;;          (dbexists     (file-exists? dbfile))
 ;;          (db           (db:lock-create-open dbfile (lambda (db)
-;;                                                      (handle-exceptions
+;;                                                      (common:debug-handle-exceptions #t
 ;;                                                       exn
 ;;                                                       (begin
 ;;                                                         ;; (release-dot-lock dbpath)
 ;;                                                         (if (> attemptnum 2)
 ;;                                                             (debug:print-error 0 *default-log-port* "tried twice, cannot create/initialize db for run-id " run-id ", at path " dbpath)
@@ -540,11 +540,11 @@
      ;; handle special cases, megatest.db and monitor.db
      ;; 
      ;;  NOPE: apply this same approach to all db files
      ;;
      (else ;; ((equal? fname "megatest.db") ;; this file can be regenerated if needed
-      (handle-exceptions
+      (common:debug-handle-exceptions #t
        exn
        (begin
 	 ;; (db:move-and-recreate-db dbdat)
 	 (if (> numtries 0)
 	     (db:repair-db dbdat numtries: (- numtries 1))
@@ -584,11 +584,11 @@
 ;; if last-update specified ("field-name" . time-in-seconds)
 ;;    then sync only records where field-name >= time-in-seconds
 ;;    IFF field-name exists
 ;;
 (define (db:sync-tables tbls last-update fromdb todb . slave-dbs)
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
    exn
    (begin
      (debug:print 0 *default-log-port* "EXCEPTION: database probably overloaded or unreadable in db:sync-tables.")
      (print-call-chain (current-error-port))
      (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
@@ -898,11 +898,10 @@
       (debug:print 0 *default-log-port* "ERROR: not able to setup up for megatest.")
       (let* ((mtdb     (dbr:dbstruct-mtdb dbstruct))
 	     (tmpdb    (db:get-db dbstruct))
              (refndb   (dbr:dbstruct-refndb dbstruct))
 	     (allow-cleanup #t) ;; (if run-ids #f #t))
-	     ;; (tdbdat  (tasks:open-db))
 	     (servers (server:get-list *toppath*)) ;; (tasks:get-all-servers (db:delay-if-busy tdbdat)))
 	     (data-synced 0)) ;; count of changed records (I hope)
     
 	;; kill servers
 	(if (member 'killservers options)
@@ -1052,11 +1051,11 @@
 	(debug:print-info 11 *default-log-port* "open-run-close-no-exception-handling END" )
 	res)
       #f))
 
 (define (open-run-close-exception-handling proc idb . params)
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
    exn
    (let ((sleep-time (random 30))
 	 (err-status ((condition-property-accessor 'sqlite3 'status #f) exn)))
      (case err-status
        ((busy)
@@ -2580,24 +2579,33 @@
 ;;  (db:delay-if-busy)
 ;;
 ;; NB// This call only operates on toplevel tests. Consider replacing it with more general call
 ;;
 (define (db:set-tests-state-status dbstruct run-id testnames currstate currstatus newstate newstatus)
-  (for-each (lambda (testname)
-	      (let ((qry (conc "UPDATE tests SET state=?,status=? WHERE "
-			       (if currstate  (conc "state='" currstate "' AND ") "")
-			       (if currstatus (conc "status='" currstatus "' AND ") "")
-			       " run_id=? AND testname LIKE ?;"))
-		    (test-id (db:get-test-id dbstruct run-id testname "")))
-		(db:with-db
-		 dbstruct
-		 run-id
-		 #t
-		 (lambda (db)
-		   (sqlite3:execute db qry newstate newstatus run-id testname)))
-		(if test-id (mt:process-triggers dbstruct run-id test-id newstate newstatus))))
-	    testnames))
+  (let ((test-ids '()))
+    (for-each
+     (lambda (testname)
+       (let ((qry (conc "UPDATE tests SET state=?,status=? WHERE "
+			(if currstate  (conc "state='" currstate "' AND ") "")
+			(if currstatus (conc "status='" currstatus "' AND ") "")
+			" run_id=? AND testname LIKE ?;"))
+	     (test-id (db:get-test-id dbstruct run-id testname "")))
+	 (db:with-db
+	  dbstruct
+	  run-id
+	  #t
+	  (lambda (db)
+	    (sqlite3:execute db qry
+			     (or newstate  currstate "NOT_STARTED")
+			     (or newstatus currstate "UNKNOWN")
+			     run-id testname)))
+	 (if test-id
+	     (begin
+	       (set! test-ids (cons test-id test-ids))
+	       (mt:process-triggers dbstruct run-id test-id newstate newstatus)))))
+     testnames)
+    test-ids))
 
 ;; ;; speed up for common cases with a little logic
 ;; ;; NB// Ultimately this will be deprecated in deference to mt:test-set-state-status-by-id
 ;;
 ;;      NOTE: run-id is not used
@@ -3668,11 +3676,11 @@
       (and dbdat (db:dbdat-get-db dbdat))
       (if dbdat
 	  (let* ((dbpath (db:dbdat-get-path dbdat))
 		 (db     (db:dbdat-get-db   dbdat)) ;; we'll return this so (db:delay--if-busy can be called inline
 		 (dbfj   (conc dbpath "-journal")))
-	    (if (handle-exceptions
+	    (if (common:debug-handle-exceptions #t
 		 exn
 		 (begin
 		   (debug:print-info 0 *default-log-port* "WARNING: failed to test for existance of " dbfj)
 		   (thread-sleep! 1)
 		   (db:delay-if-busy count (- count 1))) 

Index: dcommon.scm
==================================================================
--- dcommon.scm
+++ dcommon.scm
@@ -609,12 +609,11 @@
     (iup:vbox
      ;; (iup:label "Run statistics"  #:expand "HORIZONTAL")
      stats-matrix)))
 
 (define (dcommon:servers-table commondat tabdat)
-  (let* ((tdbdat         (tasks:open-db))
-	 (colnum         0)
+  (let* ((colnum         0)
 	 (rownum         0)
 	 (servers-matrix (iup:matrix #:expand "YES"
 				     #:numcol 7
 				     #:numcol-visible 7
 				     #:numlin-visible 5
@@ -621,11 +620,10 @@
 				     ))
 	 (colnames       (list "Id" "MTver" "Pid" "Host" "Interface:OutPort" "RunTime" "State" "RunId"))
 	 (updater        (lambda ()
 			   (if (dashboard:monitor-changed? commondat tabdat)
 			       (let ((servers  (server:get-list *toppath* limit: 10)))
-				 ;; (tasks:get-all-servers (db:delay-if-busy tdbdat))))
 				 (iup:attribute-set! servers-matrix "NUMLIN" (length servers))
 				 ;; (set! colnum 0)
 				 ;; (for-each (lambda (colname)
 				 ;;    	 ;; (print "colnum: " colnum " colname: " colname)
 				 ;;    	 (iup:attribute-set! servers-matrix (conc "0:" colnum) colname)

Index: http-transport.scm
==================================================================
--- http-transport.scm
+++ http-transport.scm
@@ -112,40 +112,40 @@
 ;;
 (define (http-transport:try-start-server ipaddrstr portnum)
   (let ((config-hostname (configf:lookup *configdat* "server" "hostname")))
     (debug:print-info 0 *default-log-port* "http-transport:try-start-server time=" (seconds->time-string (current-seconds)) " ipaddrsstr=" ipaddrstr " portnum=" portnum " config-hostname=" config-hostname)
     (handle-exceptions
-     exn
-     (begin
-       (print-error-message exn)
-       (if (< portnum 64000)
-	   (begin 
-	     (debug:print 0 *default-log-port* "WARNING: attempt to start server failed. Trying again ...")
-	     (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
-	     (debug:print 0 *default-log-port* "exn=" (condition->list exn))
-	     (portlogger:open-run-close portlogger:set-failed portnum)
-	     (debug:print 0 *default-log-port* "WARNING: failed to start on portnum: " portnum ", trying next port")
-	     (thread-sleep! 0.1)
-
-	     ;; get_next_port goes here
-	     (http-transport:try-start-server ipaddrstr
-					      (portlogger:open-run-close portlogger:find-port)))
-	   (begin
-	     (print "ERROR: Tried and tried but could not start the server"))))
-     ;; any error in following steps will result in a retry
-     (set! *server-info* (list ipaddrstr portnum))
-     (debug:print 0 *default-log-port* "INFO: Trying to start server on " ipaddrstr ":" portnum)
-     ;; This starts the spiffy server
-     ;; NEED WAY TO SET IP TO #f TO BIND ALL
-     ;; (start-server bind-address: ipaddrstr port: portnum)
-     (if config-hostname ;; this is a hint to bind directly
-	 (start-server port: portnum bind-address: (if (equal? config-hostname "-")
-						       ipaddrstr
-						       config-hostname))
-	 (start-server port: portnum))
-     (portlogger:open-run-close portlogger:set-port portnum "released")
-     (debug:print 1 *default-log-port* "INFO: server has been stopped"))))
+	exn
+	(begin
+	  (print-error-message exn)
+	  (if (< portnum 64000)
+	      (begin 
+		(debug:print 0 *default-log-port* "WARNING: attempt to start server failed. Trying again ...")
+		(debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
+		(debug:print 0 *default-log-port* "exn=" (condition->list exn))
+		(portlogger:open-run-close portlogger:set-failed portnum)
+		(debug:print 0 *default-log-port* "WARNING: failed to start on portnum: " portnum ", trying next port")
+		(thread-sleep! 0.1)
+		
+		;; get_next_port goes here
+		(http-transport:try-start-server ipaddrstr
+						 (portlogger:open-run-close portlogger:find-port)))
+	      (begin
+		(print "ERROR: Tried and tried but could not start the server"))))
+      ;; any error in following steps will result in a retry
+      (set! *server-info* (list ipaddrstr portnum))
+      (debug:print 0 *default-log-port* "INFO: Trying to start server on " ipaddrstr ":" portnum)
+      ;; This starts the spiffy server
+      ;; NEED WAY TO SET IP TO #f TO BIND ALL
+      ;; (start-server bind-address: ipaddrstr port: portnum)
+      (if config-hostname ;; this is a hint to bind directly
+	  (start-server port: portnum bind-address: (if (equal? config-hostname "-")
+							ipaddrstr
+							config-hostname))
+	  (start-server port: portnum))
+      (portlogger:open-run-close portlogger:set-port portnum "released")
+      (debug:print 1 *default-log-port* "INFO: server has been stopped"))))
 
 ;;======================================================================
 ;; S E R V E R   U T I L I T I E S 
 ;;======================================================================
 
@@ -229,30 +229,30 @@
 			      ;;					       ((exn http client-error) e (print e)))
 			      (set! res (vector
 					 success
 					 (db:string->obj 
 					  (handle-exceptions
-					   exn
-					   (begin
-					     (set! success #f)
-					     (debug:print 0 *default-log-port* "WARNING: failure in with-input-from-request to " fullurl ".")
-					     (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
-					     (if runremote
-                                                 (remote-conndat-set! runremote #f))
-					     ;; Killing associated server to allow clean retry.")
-					     ;; (tasks:kill-server-run-id run-id)  ;; better to kill the server in the logic that called this routine?
-					     (mutex-unlock! *http-mutex*)
+					      exn
+					      (begin
+						(set! success #f)
+						(debug:print 0 *default-log-port* "WARNING: failure in with-input-from-request to " fullurl ".")
+						(debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
+						(if runremote
+						    (remote-conndat-set! runremote #f))
+						;; Killing associated server to allow clean retry.")
+						;; (tasks:kill-server-run-id run-id)  ;; better to kill the server in the logic that called this routine?
+						(mutex-unlock! *http-mutex*)
 					     ;;; (signal (make-composite-condition
 					     ;;;          (make-property-condition 'commfail 'message "failed to connect to server")))
 					     ;;; "communications failed"
-					     (db:obj->string #f))
-					   (with-input-from-request ;; was dat
-					    fullurl 
-					    (list (cons 'key "thekey")
-						  (cons 'cmd cmd)
-						  (cons 'params sparams))
-					    read-string))
+						(db:obj->string #f))
+					    (with-input-from-request ;; was dat
+					     fullurl 
+					     (list (cons 'key "thekey")
+						   (cons 'cmd cmd)
+						   (cons 'params sparams))
+					     read-string))
 					  transport: 'http)
                                          0)) ;; added this speculatively
 			      ;; Shouldn't this be a call to the managed call-all-connections stuff above?
 			      (close-all-connections!)
 			      (mutex-unlock! *http-mutex*)
@@ -440,17 +440,16 @@
          (else
           (debug:print-info 0 *default-log-port* "Server timed out. seconds since last db access: " (- (current-seconds) last-access))
           (http-transport:server-shutdown port)))))))
 
 (define (http-transport:server-shutdown port)
-  (let ((tdbdat (tasks:open-db)))
+  (begin
     ;;(BB> "http-transport:server-shutdown called")
     (debug:print-info 0 *default-log-port* "Starting to shutdown the server. pid="(current-process-id))
     ;;
     ;; start_shutdown
     ;;
-    ;; (tasks:server-set-state! (db:delay-if-busy tdbdat) server-id "shutting-down")
     (set! *time-to-exit* #t) ;; tell on-exit to be fast as we've already cleaned up
     (portlogger:open-run-close portlogger:set-port port "released")
     (thread-sleep! 1)
 
     ;; (debug:print-info 0 *default-log-port* "Max cached queries was    " *max-cache-size*)

Index: launch.scm
==================================================================
--- launch.scm
+++ launch.scm
@@ -363,11 +363,11 @@
 		     (pids (delete-duplicates (filter number? (list pid1 pid2)))))
 		(if (not (null? pids))
 		    (begin
 		      (for-each
 		       (lambda (pid)
-			 (handle-exceptions
+			 (common:debug-handle-exceptions #t
 			  exn
 			  (begin
 			    (debug:print-info 0 *default-log-port* "Unable to kill process with pid " pid ", possibly already killed.")
 			    (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn)))
 			  (debug:print 0 *default-log-port* "WARNING: Request received to kill job " pid) ;;  " (attempt # " kill-tries ")")
@@ -378,11 +378,11 @@
 				 (process-signal pid-num signal/term))
 			       (process:get-sub-pids pid))
 			  (thread-sleep! 5)
 			  ;; (if (process:process-alive? pid)
 			  (map (lambda (pid-num)
-				 (handle-exceptions
+				 (common:debug-handle-exceptions #t
 				  exn
 				  #f
 				  (process-signal pid-num signal/kill)))
 			       (process:get-sub-pids pid))))
 		       ;;    (debug:print-info 0 *default-log-port* "not killing process " pid " as it is not alive"))))
@@ -846,18 +846,18 @@
 			 (if *configdat* (configf:lookup *configdat* "setup" "linktree") #f))))
       (if linktree
 	  (begin
 	    (if (not (file-exists? linktree))
 		(begin
-		  (handle-exceptions
+		  (common:debug-handle-exceptions #t
 		   exn
 		   (begin
 		     (debug:print-error 0 *default-log-port* "Something went wrong when trying to create linktree dir at " linktree)
 		     (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
 		     (exit 1))
 		   (create-directory linktree #t))))
-	    (handle-exceptions
+	    (common:debug-handle-exceptions #t
 	     exn
 	     (begin
 	       (debug:print-error 0 *default-log-port* "Something went wrong when trying to create link to linktree at " *toppath*)
 	       (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn)))
 	     (let ((tlink (conc *toppath* "/lt")))
@@ -952,11 +952,11 @@
 	  (debug:print 0 *default-log-port* "WARNING: linktree did not exist! Creating it now at " linktree)
 	  (create-directory linktree #t))) ;; (system (conc "mkdir -p " linktree))))
     ;; create the directory for the tests dir links, this is needed no matter what...
     (if (and (not (directory-exists? lnkbase))
 	     (not (file-exists? lnkbase)))
-	(handle-exceptions
+	(common:debug-handle-exceptions #t
 	 exn
 	 (begin
 	   (debug:print-error 0 *default-log-port* "Problem creating linktree base at " lnkbase)
 	   (print-error-message exn (current-error-port)))
 	 (create-directory lnkbase #t)))
@@ -971,28 +971,28 @@
     ;; to the iteration. use pathname-directory to trim the path by one
     ;; level
     (if (not not-iterated) ;; i.e. iterated
 	(let ((iterated-parent  (pathname-directory (conc lnkpath "/" item-path))))
 	  (debug:print-info 2 *default-log-port* "Creating iterated parent " iterated-parent)
-	  (handle-exceptions
+	  (common:debug-handle-exceptions #t
 	   exn
 	   (begin
 	     (debug:print-error 0 *default-log-port* " Failed to create directory " iterated-parent ((condition-property-accessor 'exn 'message) exn) ", exiting")
 	     (exit 1))
 	   (create-directory iterated-parent #t))))
 
     (if (symbolic-link? lnkpath) 
-	(handle-exceptions
+	(common:debug-handle-exceptions #t
 	 exn
 	 (begin
 	   (debug:print-error 0 *default-log-port* " Failed to remove symlink " lnkpath ((condition-property-accessor 'exn 'message) exn) ", exiting")
 	   (exit 1))
 	 (delete-file lnkpath)))
 
     (if (not (or (file-exists? lnkpath)
 		 (symbolic-link? lnkpath)))
-	(handle-exceptions
+	(common:debug-handle-exceptions #t
 	 exn
 	 (begin
 	   (debug:print-error 0 *default-log-port* " Failed to create symlink " lnkpath ((condition-property-accessor 'exn 'message) exn) ", exiting")
 	   (exit 1))
 	 (create-symbolic-link toptest-path lnkpath)))
@@ -1021,11 +1021,11 @@
 	  ;; (rmt:general-call 'test-set-rundir run-id lnkpath testname "") ;; toptest-path)
 	  (if (or (not curr-test-path)
 		  (not (directory-exists? toptest-path)))
 	      (begin
 		(debug:print-info 2 *default-log-port* "Creating " toptest-path " and link " lnkpath)
-		(handle-exceptions
+		(common:debug-handle-exceptions #t
 		 exn
 		 #f ;; don't care to catch and deal with errors here for now.
 		 (create-directory toptest-path #t))
 		(hash-table-set! *toptest-paths* testname toptest-path)))))
 
@@ -1033,11 +1033,11 @@
     ;; been created. Now, if this is an iterated test the real test dir must be created
     (if (not not-iterated) ;; this is an iterated test
 	(begin ;; (let ((lnktarget (conc lnkpath "/" item-path)))
 	  (debug:print 2 *default-log-port* "Setting up sub test run area")
 	  (debug:print 2 *default-log-port* " - creating run area in " test-path)
-	  (handle-exceptions
+	  (common:debug-handle-exceptions #t
 	   exn
 	   (begin
 	     (debug:print-error 0 *default-log-port* " Failed to create directory " test-path ((condition-property-accessor 'exn 'message) exn) ", exiting")
 	     (exit 1))
 	   (create-directory test-path #t))
@@ -1044,11 +1044,11 @@
 	  (debug:print 2 *default-log-port* 
 		       " - creating link from: " test-path "\n"
 		       "                   to: " lnktarget)
 
 	  ;; If there is already a symlink delete it and recreate it.
-	  (handle-exceptions
+	  (common:debug-handle-exceptions #t
 	   exn
 	   (begin
 	     (debug:print-error 0 *default-log-port* " Failed to re-create link " lnktarget ((condition-property-accessor 'exn 'message) exn) ", exiting")
 	     (exit))
 	   (if (symbolic-link? lnktarget)     (delete-file lnktarget))

Index: lock-queue.scm
==================================================================
--- lock-queue.scm
+++ lock-queue.scm
@@ -39,11 +39,11 @@
 	 (db       (sqlite3:open-database actualfname))
 	 (handler  (make-busy-timeout 136000)))
     (if dbexists
 	(vector db actualfname)
 	(begin
-	  (handle-exceptions
+	  (common:debug-handle-exceptions #t
 	   exn
 	   (begin
 	     (thread-sleep! 10)
 	     (if (> count 0)
 		 (lock-queue:open-db fname count: (- count 1))
@@ -69,11 +69,11 @@
     (sqlite3:set-busy-handler! db handler)
     (vector db actualfname)))
 
 (define (lock-queue:set-state dbdat test-id newstate #!key (remtries 10))
   (tasks:wait-on-journal (lock-queue:db-dat-get-path dbdat) 1200)
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
    exn
    (if (> remtries 0)
        (begin
 	 (debug:print 0 *default-log-port* "WARNING: exception on lock-queue:set-state. Trying again in 30 seconds.")
 	 (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
@@ -87,11 +87,11 @@
 		    test-id)))
 
 (define (lock-queue:any-younger? dbdat mystart test-id #!key (remtries 10))
   ;; no need to wait on journal on read only queries
   ;; (tasks:wait-on-journal (lock-queue:db-dat-get-path dbdat) 1200)
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
    exn
    (if (> remtries 0)
        (begin
 	 (debug:print 0 *default-log-port* "WARNING: exception on lock-queue:any-younger. Removing lockdb and trying again in 5 seconds.")
 	 (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
@@ -116,11 +116,11 @@
   (let* ((res       #f)
 	 (db        (lock-queue:db-dat-get-db dbdat))
 	 (lckqry    (sqlite3:prepare db "SELECT test_id,run_lock FROM runlocks WHERE run_lock='locked';"))
 	 (mklckqry  (sqlite3:prepare db "INSERT INTO runlocks (test_id,run_lock) VALUES (?,'locked');")))
     (let ((result 
-	   (handle-exceptions
+	   (common:debug-handle-exceptions #t
 	    exn
 	    (begin
 	      (debug:print 0 *default-log-port* "WARNING: failed to get queue lock. Removing lock db and returning fail") ;; Will try again in a few seconds")
 	      (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
 	      (thread-sleep! 10)
@@ -148,11 +148,11 @@
       result)))
 
 (define (lock-queue:release-lock fname test-id #!key (count 10))
   (let* ((dbdat (lock-queue:open-db fname)))
     (tasks:wait-on-journal (lock-queue:db-dat-get-path dbdat) 1200 "lock-queue:release-lock; waiting on journal")
-    (handle-exceptions
+    (common:debug-handle-exceptions #t
      exn
      (begin
        (debug:print 0 *default-log-port* "WARNING: Failed to release queue lock. Will try again in few seconds")
        (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
        (thread-sleep! (/ count 10))
@@ -161,11 +161,11 @@
 	     (sqlite3:finalize! (lock-queue:db-dat-get-db dbdat))
 	     (lock-queue:release-lock fname test-id count: (- count 1)))
 	   (let ((journal (conc fname "-journal")))
 	     ;; If we've tried ten times and failed there is a serious problem
 	     ;; try to remove the lock db and allow it to be recreated
-	     (handle-exceptions
+	     (common:debug-handle-exceptions #t
 	      exn
 	      #f
 	      (if (file-exists? journal)(delete-file journal))
 	      (if (file-exists? fname)  (delete-file fname))
 	      #f))))
@@ -173,11 +173,11 @@
      (sqlite3:finalize! (lock-queue:db-dat-get-db dbdat)))))
 
 (define (lock-queue:steal-lock dbdat test-id #!key (count 10))
   (debug:print-info 0 *default-log-port* "Attempting to steal lock at " (lock-queue:db-dat-get-path dbdat))
   (tasks:wait-on-journal (lock-queue:db-dat-get-path dbdat) 1200 "lock-queue:steal-lock; waiting on journal")
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
    exn
    (begin
      (debug:print 0 *default-log-port* "WARNING: Failed to steal queue lock. Will try again in few seconds")
      (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
      (thread-sleep! 10)
@@ -194,11 +194,11 @@
 (define (lock-queue:wait-turn fname test-id #!key (count 10)(waiting-msg #f))
   (let* ((dbdat   (lock-queue:open-db fname))
 	 (mystart (current-seconds))
 	 (db      (lock-queue:db-dat-get-db dbdat)))
     ;; (tasks:wait-on-journal (lock-queue:db-dat-get-path dbdat) 1200 waiting-msg: "lock-queue:wait-turn; waiting on journal file")
-    (handle-exceptions
+    (common:debug-handle-exceptions #t
      exn
      (begin
        (debug:print 0 *default-log-port* "WARNING: Failed to find out if it is ok to skip the wait queue. Will try again in few seconds")
        (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
        (print-call-chain (current-error-port))

Index: megatest.scm
==================================================================
--- megatest.scm
+++ megatest.scm
@@ -467,11 +467,11 @@
       (exit-handler (lambda (#!optional (exit-code 0))
 		      (printf "Preparing to exit with exit code ~A ...\n" exit-code)
 		      (for-each
 		       
 		       (lambda (pid)
-			 (handle-exceptions
+			 (common:debug-handle-exceptions #t
 			  exn
 			  #t
 			  (let-values (((pid-val exit-status exit-code) (process-wait pid #t)))
 				      (if (or (eq? pid-val pid)
 					      (eq? pid-val 0))
@@ -538,11 +538,11 @@
 		    (debug:print-info 0 *default-log-port* "No cached megatest or runconfigs files found. None removed.")
 		    (begin
 		      (debug:print-info 0 *default-log-port* "Removing cached files:\n    " (string-intersperse files "\n    "))
 		      (for-each 
 		       (lambda (f)
-			 (handle-exceptions
+			 (common:debug-handle-exceptions #t
 			     exn
 			     (debug:print 0 *default-log-port* "WARNING: Failed to remove file " f)
 			   (delete-file f)))
 		       files))))
 	      (debug:print-error 0 *default-log-port* "-clean-cache requires -runname."))
@@ -781,12 +781,11 @@
 (if (or (args:get-arg "-list-servers")
 	(args:get-arg "-stop-server")
         (args:get-arg "-kill-server"))
     (let ((tl (launch:setup)))
       (if tl 
-	  (let* ((tdbdat  (tasks:open-db))
-		 (servers (tasks:get-all-servers (db:delay-if-busy tdbdat)))
+	  (let* ((servers (server:get-list *toppath*))
 		 (fmtstr  "~5a~12a~8a~20a~24a~10a~10a~10a~10a\n")
 		 (servers-to-kill '())
                  (kill-switch  (if (args:get-arg "-kill-server") "-9" ""))
                  (killinfo   (or (args:get-arg "-stop-server") (args:get-arg "-kill-server") ))
 		 (khost-port (if killinfo (if (substring-index ":" killinfo)(string-split ":") #f) #f))
@@ -810,15 +809,15 @@
 		      (killed     #f)
 		      (status     (< last-update 20)))
 		 ;;   (zmq-sockets (if status (server:client-connect hostname port) #f)))
 		 ;; no need to login as status of #t indicates we are connecting to correct 
 		 ;; server
-		 (if (equal? state "dead")
-		     (if (> last-update (* 25 60 60)) ;; keep records around for slighly over a day.
-			 (tasks:server-deregister (db:delay-if-busy tdbdat) hostname pullport: pullport pid: pid action: 'delete))
-		     (if (> last-update 20)        ;; Mark as dead if not updated in last 20 seconds
-			 (tasks:server-deregister (db:delay-if-busy tdbdat) hostname pullport: pullport pid: pid)))
+		;; (if (equal? state "dead")
+		;;     (if (> last-update (* 25 60 60)) ;; keep records around for slighly over a day.
+		;; 	 (tasks:server-deregister (db:delay-if-busy tdbdat) hostname pullport: pullport pid: pid action: 'delete))
+		;;     (if (> last-update 20)        ;; Mark as dead if not updated in last 20 seconds
+		;; 	 (tasks:server-deregister (db:delay-if-busy tdbdat) hostname pullport: pullport pid: pid)))
 		 (format #t fmtstr id mt-ver pid hostname (conc interface ":" pullport) pubport last-update
 			 (if status "alive" "dead") transport)
 		 (if (or (equal? id sid)
 			 (equal? sid 0)) ;; kill all/any
 		     (begin
@@ -1179,11 +1178,11 @@
 			       runs-spec)
 			      (newline)))))
 		       
 		     (for-each 
 		      (lambda (test)
-		      	(handle-exceptions
+		      	(common:debug-handle-exceptions #f
 			 exn
 			 (begin
 			   (debug:print-error 0 *default-log-port* "Bad data in test record? " test)
 			   (print "exn=" (condition->list exn))
 			   (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))

Index: mtut.scm
==================================================================
--- mtut.scm
+++ mtut.scm
@@ -201,15 +201,15 @@
 				  (or (configf:lookup torun contour runkey)
 				      '()))))
 
 (define (fossil:clone-or-sync url name dest-dir)
   (let ((targ-file (conc dest-dir "/" name))) ;; do not force usage of .fossil extension
-    (handle-exceptions
+    (common:debug-handle-exceptions #t
 	exn
 	(print "ERROR: failed to create directory " dest-dir " message: " ((condition-property-accessor 'exn 'message) exn))
       (create-directory dest-dir #t))
-    (handle-exceptions
+    (common:debug-handle-exceptions #t
 	exn
 	(print "ERROR: failed to clone or sync 1ossil " url " message: " ((condition-property-accessor 'exn 'message) exn))
       (if (file-exists? targ-file)
 	  (system (conc "fossil pull --once " url " -R " targ-file))
 	  (system (conc "fossil clone " url " " targ-file))
@@ -216,19 +216,19 @@
 	  ))))
 
 (define (fossil:last-change-node-and-time fossils-dir fossil-name branch)
   (let* ((fossil-file   (conc fossils-dir "/" fossil-name))
 	 (timeline-port (if (file-read-access? fossil-file)
-			    (handle-exceptions
+			    (common:debug-handle-exceptions #t
 				exn
 				(begin
 				  (print "ERROR: failed to get timeline from " fossil-file " message: " ((condition-property-accessor 'exn 'message) exn))
 				  #f)
 			      (open-input-pipe (conc "fossil timeline -t ci -W 0 -n 0 -R " fossil-file)))
 			    #f))
 	 (get-line      (lambda ()
-			  (handle-exceptions
+			  (common:debug-handle-exceptions #t
 			      exn
 			      (begin
 				(print "ERROR: failed to read from file " fossil-file " message: "  ((condition-property-accessor 'exn 'message) exn))
 				#f)
 			    (read-line timeline-port))))
@@ -391,11 +391,12 @@
 		     ((number? sched-in) sched-in)
 		     (else     (current-seconds))))
 	 (args-data (if args-alist
 			args-alist
 			(hash-table->alist args:arg-hash)))
-	 (alldat    (apply append (list 'a action
+	 (alldat    (apply append (list 'T "cmd"
+					'a action
 					'U (current-user-name)
 					'D sched)
 			   (map (lambda (x)
 				  (let* ((param (car x))
 					 (value (cdr x))
@@ -449,11 +450,11 @@
 	 (new-target (if area-xlatr
 			 (let ((xlatr-key (string->symbol area-xlatr)))
 			   (if (alist-ref xlatr-key *target-mappers*)
 			       (begin
 				 (print "Using target mapper: " area-xlatr)
-				 (handle-exceptions
+				 (common:debug-handle-exceptions #t
 				     exn
 				     (begin
 				       (print "FAILED TO RUN TARGET MAPPER FOR " area ", called " area-xlatr)
 				       (print "   function is: " (alist-ref xlatr-key *target-mappers*))
 				       (print " message: " ((condition-property-accessor 'exn 'message) exn))
@@ -594,11 +595,11 @@
 		       (lambda (cmd)
 			 (print "cmd: " cmd)
 			 (let* ((script (car cmd))
 				(params (cdr cmd))
 				(cmd    (conc script " " contour " " runkey " " std-runname " " action " " params))
-				(res    (handle-exceptions
+				(res    (common:debug-handle-exceptions #t
 					    exn
 					    #f
 					  (print "Running " cmd)
 					  (with-input-from-pipe cmd read-lines))))
 			   (if (and res (not (null? res)))
@@ -787,11 +788,11 @@
 ;;
 (define (dispatch-commands mtconf toppath)
   ;; we are expecting a directory "logs", check and create it, create the log in /tmp if not able to create logs dir
   (let ((logdir
 	 (if (if (not (directory? "logs"))
-		 (handle-exceptions
+		 (common:debug-handle-exceptions #t
 		     exn
 		     #f
 		   (create-directory "logs")
 		   #t)
 		 #t)

Index: portlogger.scm
==================================================================
--- portlogger.scm
+++ portlogger.scm
@@ -50,25 +50,29 @@
     db))
 
 (define (portlogger:open-run-close proc . params)
   (let* ((fname  (conc "/tmp/." (current-user-name) "-portlogger.db"))
 	 (avail  (tasks:wait-on-journal fname 10))) ;; wait up to about 10 seconds for the journal to go away
-    (handle-exceptions
-     exn
-     (begin
-       ;; (release-dot-lock fname)
-       (debug:print-error 0 *default-log-port* "portlogger:open-run-close failed. " proc " " params)
-       (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
-       (debug:print 0 *default-log-port* "exn=" (condition->list exn))
-       (if (file-exists? fname)(delete-file fname)) ;; brutally get rid of it
-       (print-call-chain (current-error-port)))
+    ;;(common:debug-handle-exceptions #t
+    ;; exn
+    ;; (begin
+    ;;   ;; (release-dot-lock fname)
+    ;;   (debug:print-error 0 *default-log-port* "portlogger:open-run-close failed. " proc " " params)
+    ;;   (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
+    ;;   (debug:print 0 *default-log-port* "exn=" (condition->list exn))
+    ;;   (if (file-exists? fname)
+    ;;	   (begin
+    ;;	     (debug:print 0 *default-log-port* "Removing portlogger database file " fname)
+    ;;	     (delete-file fname))) ;; just get rid of the portlogger file
+    ;;   (print-call-chain (current-error-port)))
      (let* (;; (lock   (obtain-dot-lock fname 2 9 10))
 	    (db     (portlogger:open-db fname))
 	    (res    (apply proc db params)))
        (sqlite3:finalize! db)
        ;; (release-dot-lock fname)
-       res))))
+       res)))
+;; )
 
 ;; (fold-row PROC INIT DATABASE SQL . PARAMETERS) 
 (define (portlogger:take-port db portnum)
   (let* ((qry1 (sqlite3:prepare db "INSERT INTO ports (port,state) VALUES (?,?);"))
 	 (qry2 (sqlite3:prepare db "UPDATE ports SET state=?,update_time=strftime('%s','now') WHERE port=?;"))
@@ -99,24 +103,24 @@
     (sqlite3:finalize! qry3)
     res))
 
 (define (portlogger:get-prev-used-port db)
   (handle-exceptions
-   exn
-   (begin
-     (debug:print 0 *default-log-port* "EXCEPTION: portlogger database probably overloaded or unreadable. If you see this message again remove /tmp/.$USER-portlogger.db")
-     (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
-     (debug:print 0 *default-log-port* "exn=" (condition->list exn))
-     (print-call-chain (current-error-port))
-     (debug:print 0 *default-log-port* "Continuing anyway.")
-     #f)
-   (sqlite3:fold-row
-    (lambda (var curr)
-      (or curr var curr))
-    #f
-    db
-    "SELECT (port) FROM ports WHERE state='released' LIMIT 1;")))
+      exn
+      (begin
+	(debug:print 0 *default-log-port* "EXCEPTION: portlogger database probably overloaded or unreadable. If you see this message again remove /tmp/.$USER-portlogger.db")
+	(debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
+	(debug:print 0 *default-log-port* "exn=" (condition->list exn))
+	(print-call-chain (current-error-port))
+	(debug:print 0 *default-log-port* "Continuing anyway.")
+	#f)
+    (sqlite3:fold-row
+     (lambda (var curr)
+       (or curr var curr))
+     #f
+     db
+     "SELECT (port) FROM ports WHERE state='released' LIMIT 1;")))
 
 (define (portlogger:find-port db)
   (let* ((lowport (let ((val (configf:lookup *configdat* "server" "lowport")))
 		    (if (and val 
 			     (string->number val))
@@ -153,11 +157,11 @@
 (define (portlogger:main . args)
   (let* ((dbfname (conc "/tmp/." (current-user-name) "-portlogger.db"))
 	 (db      (portlogger:open-db dbfname))
 	 (numargs (length args))
 	 (result  
-	  (handle-exceptions
+	  (common:debug-handle-exceptions #t
 	   exn
 	   (begin
 	     (debug:print 0 *default-log-port* "EXCEPTION: portlogger database at " dbfname " probably overloaded or unreadable. Try removing it.")
 	     (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
 	     (print "exn=" (condition->list exn))

Index: process.scm
==================================================================
--- process.scm
+++ process.scm
@@ -23,11 +23,11 @@
 	(loop (conc res (read-char port)))
 	res)))
 
 (define (process:cmd-run-with-stderr->list cmd . params)
   ;; (print "Called with cmd=" cmd ", proc=" proc ", params=" params)
-;;  (handle-exceptions
+;;  (common:debug-handle-exceptions #t
 ;;   exn
 ;;   (begin
 ;;     (print "ERROR:  Failed to run command: " cmd " " (string-intersperse params " "))
 ;;     (print "       " ((condition-property-accessor 'exn 'message) exn))
 ;;     #f)
@@ -48,11 +48,11 @@
 	     (close-output-port fho)
 	     result))))) ;; )
 
 (define (process:cmd-run-proc-each-line cmd proc . params)
   ;; (print "Called with cmd=" cmd ", proc=" proc ", params=" params)
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
    exn
    (begin
      (print "ERROR:  Failed to run command: " cmd " " (string-intersperse params " "))
      (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
      (print "exn=" (condition->list exn))
@@ -140,21 +140,21 @@
 	   (let ((pid (string->number inl)))
 	     (if proc (proc pid))
 	     (loop (read-line) (cons pid res))))))))
 
 (define (process:alive? pid)
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
    exn
    ;; possibly pid is a process not a child, look in /proc to see if it is running still
    (file-exists? (conc "/proc/" pid))
    (let-values (((rpid exit-type exit-signal)(process-wait pid #t)))
        (and (number? rpid)
 	    (equal? rpid pid)))))
 
 (define (process:alive-on-host? host pid)
   (let ((cmd (conc "ssh " host " ps -o pid= -p " pid)))
-    (handle-exceptions
+    (common:debug-handle-exceptions #t
      exn
      #f ;; anything goes wrong - assume the process in NOT running.
      (with-input-from-pipe 
       cmd
       (lambda ()

Index: rmt.scm
==================================================================
--- rmt.scm
+++ rmt.scm
@@ -194,11 +194,11 @@
 	      (server:start-and-wait *toppath*)
 	      (rmt:send-receive cmd rid params attemptnum: (+ attemptnum 1)))))))))
 
 ;; (define (rmt:update-db-stats run-id rawcmd params duration)
 ;;   (mutex-lock! *db-stats-mutex*)
-;;   (handle-exceptions
+;;   (common:debug-handle-exceptions #t
 ;;    exn
 ;;    (begin
 ;;      (debug:print 0 *default-log-port* "WARNING: stats collection failed in update-db-stats")
 ;;      (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
 ;;      (print "exn=" (condition->list exn))
@@ -293,11 +293,11 @@
                 (mutex-unlock! *db-multi-sync-mutex*)))))
     res))
 
 (define (rmt:send-receive-no-auto-client-setup connection-info cmd run-id params)
   (let* ((run-id   (if run-id run-id 0))
-	 (res  	   (handle-exceptions
+	 (res  	   (common:debug-handle-exceptions #t
 		    exn
 		    #f
 		    (http-transport:client-api-send-receive run-id connection-info cmd params))))
     (if (and res (vector-ref res 0))
 	(vector-ref res 1) ;;; YES!! THIS IS CORRECT!! CHANGE IT HERE, THEN CHANGE rmt:send-receive ALSO!!!
@@ -446,11 +446,11 @@
 
 ;; WARNING: This currently bypasses the transaction wrapped writes system
 (define (rmt:test-set-state-status-by-id run-id test-id newstate newstatus newcomment)
   (rmt:send-receive 'test-set-state-status-by-id run-id (list run-id test-id newstate newstatus newcomment)))
 
-(define (rmt:set-tests-state-status run-id testnames currstate currstatus newstate newstatus)
+(define (rmt:set-tests-state-status run-id                      testnames currstate currstatus newstate newstatus)
   (rmt:send-receive 'set-tests-state-status run-id (list run-id testnames currstate currstatus newstate newstatus)))
 
 (define (rmt:get-tests-for-run run-id testpatt states statuses offset limit not-in sort-by sort-order qryvals last-update mode)
   (if (number? run-id)
       (rmt:send-receive 'get-tests-for-run run-id (list run-id testpatt states statuses offset limit not-in sort-by sort-order qryvals last-update mode))

Index: rpc-transport.scm
==================================================================
--- rpc-transport.scm
+++ rpc-transport.scm
@@ -24,11 +24,11 @@
 (include "common_records.scm")
 (include "db_records.scm")
 
 ;; procstr is the name of the procedure to be called as a string
 (define (rpc-transport:autoremote procstr params)
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
    exn
    (begin
      (debug:print 1 *default-log-port* "Remote failed for " proc " " params)
      (apply (eval (string->symbol procstr)) params))
    ;; (if *runremote*
@@ -136,21 +136,21 @@
 	      (debug:print-info 0 *default-log-port* "Max cached queries was " *max-cache-size*)
 	      (debug:print-info 0 *default-log-port* "Server shutdown complete. Exiting")
 	      ))))))
 
 (define (rpc-transport:find-free-port-and-open port)
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
    exn
 	  (begin
      (print "Failed to bind to port " (rpc:default-server-port) ", trying next port")
      (rpc-transport:find-free-port-and-open (+ port 1)))
    (rpc:default-server-port port)
    (tcp-read-timeout 240000)
    (tcp-listen (rpc:default-server-port) 10000)))
 
 (define (rpc-transport:ping run-id host port)
-  (handle-exceptions
+  (common:debug-handle-exceptions #t
    exn
    (begin
      (print "SERVER_NOT_FOUND")
      (exit 1))
    (let ((login-res ((rpc:procedure 'server:login host port) *toppath*)))
@@ -204,11 +204,11 @@
 ;; 	     (port     (if (and hostinfo (> (length hostdat) 1))(cadr hostdat) #f)))
 ;; 	(if (and port
 ;; 		 (string->number port))
 ;; 	    (let ((portn (string->number port)))
 ;; 	      (debug:print-info 2 *default-log-port* "Setting up to connect to host " host ":" port)
-;; 	      (handle-exceptions
+;; 	      (common:debug-handle-exceptions #t
 ;; 	       exn
 ;; 	       (begin
 ;; 		 (debug:print-error 0 *default-log-port* "Failed to open a connection to the server at host: " host " port: " port)
 ;; 		 (debug:print 0 *default-log-port* "   EXCEPTION: " ((condition-property-accessor 'exn 'message) exn))
 ;; 		 ;; (open-run-close 

Index: runs.scm
==================================================================
--- runs.scm
+++ runs.scm
@@ -211,11 +211,11 @@
 	 (all-tests-registry #f)  ;; (tests:get-all)) ;; (tests:get-valid-tests (make-hash-table) test-search-path)) ;; all valid tests to check waiton names
 	 (all-test-names     #f)  ;; (hash-table-keys all-tests-registry))
 	 (test-names         #f)  ;; Generated by a call to (tests:filter-test-names all-test-names test-patts))
 	 (required-tests     #f)  ;; Put fully qualified test/testpath names in this list to be done
 	 (task-key           (conc (hash-table->alist flags) " " (get-host-name) " " (current-process-id)))
-	 (tdbdat             (tasks:open-db))
+	 ;; (tdbdat             (tasks:open-db))
 	 (config-reruns      (let ((x (configf:lookup *configdat* "setup" "reruns")))
 			       (if x (string->number x) #f)))
 	 (allowed-tests      #f))
 
     ;; check if readonly
@@ -237,12 +237,12 @@
     (let ((sighand (lambda (signum)
 		     ;; (signal-mask! signum) ;; to mask or not? seems to cause issues in exiting
 		     (set! *time-to-exit* #t)
 		     (print "Received signal " signum ", cleaning up before exit. Please wait...")
 		     (let ((th1 (make-thread (lambda ()
-					       (let ((tdbdat (tasks:open-db)))
-						 (rmt:tasks-set-state-given-param-key task-key "killed"))
+					       ;; (let ((tdbdat (tasks:open-db)))
+						 (rmt:tasks-set-state-given-param-key task-key "killed") ;; )
 					       (print "Killed by signal " signum ". Exiting")
 					       (thread-sleep! 3)
 					       (exit))))
 			   (th2 (make-thread (lambda ()
 					       (thread-sleep! 5)
@@ -318,13 +318,18 @@
 	  ;;
 	  ;; (rmt:general-call 'delete-tests-in-state run-id "NOT_STARTED")
 	  
 	  ;; Now convert anything in allow-auto-rerun to NOT_STARTED
 	  ;;
-	  (for-each (lambda (state)
-		      (rmt:set-tests-state-status run-id test-names state #f "NOT_STARTED" state))
-		    (string-split (or (configf:lookup *configdat* "setup" "allow-auto-rerun") "")))))
+	  (for-each
+	   (lambda (state-status)
+	     (let* ((ss-lst (string-split-fields "/" state-status #:infix))
+		    (state  (if (> (length ss-lst) 0)(car  ss-lst) #f))
+		    (status (if (> (length ss-lst) 1)(cadr ss-lst) #f)))
+	       (rmt:set-tests-state-status run-id test-names state status "NOT_STARTED" status)))
+	   ;; list of state/status pairs separated by spaces
+	   (string-split (or (configf:lookup *configdat* "setup" "allow-auto-rerun") "")))))
 
     ;; Ensure all tests are registered in the test_meta table
     (runs:update-all-test_meta #f)
 
     ;; now add non-directly referenced dependencies (i.e. waiton)
@@ -422,11 +427,11 @@
       (if (> (length (hash-table-keys test-records)) 0)
 	  (let* ((keep-going        #t)
 		 (run-queue-retries 5)
 		 (th1        (make-thread (lambda ()
 					    (runs:run-tests-queue run-id runname test-records keyvals flags test-patts required-tests (any->number reglen) all-tests-registry))
-					    ;; (handle-exceptions
+					    ;; (common:debug-handle-exceptions #t
 					    ;;  exn
 					    ;;  (begin
 					    ;;    (print-call-chain (current-error-port))
 					    ;;    (debug:print-error 0 *default-log-port* "failure in runs:run-tests-queue thread, error: " ((condition-property-accessor 'exn 'message) exn))
 					    ;;    (if (> run-queue-retries 0)
@@ -438,11 +443,11 @@
 		 (th2        (make-thread (lambda ()				    
 					    ;; (rmt:find-and-mark-incomplete-all-runs))))) CAN'T INTERRUPT IT ...
 					    (let ((run-ids (rmt:get-all-run-ids)))
 					      (for-each (lambda (run-id)
 							  (if keep-going
-							      (handle-exceptions
+							      (common:debug-handle-exceptions #t
 							       exn
 							       (debug:print 0 *default-log-port* "error in calling find-and-mark-incomplete for run-id " run-id)
 							       (rmt:find-and-mark-incomplete run-id #f)))) ;; ovr-deadtime)))
 							run-ids)))
 					  "runs: mark-incompletes")))
@@ -1075,11 +1080,11 @@
 				     (string->number mcj)
 				     1))) ;; length of the register queue ahead
 	(reglen                (if (number? reglen-in) reglen-in 1))
 	(last-time-incomplete  (- (current-seconds) 900)) ;; force at least one clean up cycle
 	(last-time-some-running (current-seconds))
-	(tdbdat                (tasks:open-db))
+	;; (tdbdat                (tasks:open-db))
 	(runsdat (make-runs:dat
 		  ;; hed: hed
 		  ;; tal: tal
 		  ;; reg: reg
 		  ;; reruns: reruns
@@ -1170,13 +1175,13 @@
 			   itemmaps:    itemmaps
 			   ;; prereqs-not-met: prereqs-not-met
 			   )))
 	(runs:dat-regfull-set! runsdat regfull)
 	;; every couple minutes verify the server is there for this run
-	(if (and (common:low-noise-print 60 "try start server"  run-id)
-		 (tasks:need-server run-id))
-	    (tasks:start-and-wait-for-server tdbdat run-id 10)) ;; NOTE: delay and wait is done under the hood
+	;; (if (and (common:low-noise-print 60 "try start server"  run-id)
+	;; 	 (tasks:need-server run-id))
+	;;     (tasks:start-and-wait-for-server tdbdat run-id 10)) ;; NOTE: delay and wait is done under the hood
 	
 	(if (> num-running 0)
 	  (set! last-time-some-running (current-seconds)))
 
       (if (> (current-seconds)(+ last-time-some-running (or (configf:lookup *configdat* "setup" "give-up-waiting") 36000)))
@@ -1647,11 +1652,11 @@
 ;; NB// should pass in keys?
 ;;
 (define (runs:operate-on action target runnamepatt testpatt #!key (state #f)(status #f)(new-state-status #f)(mode 'remove-all)(options '()))
   (common:clear-caches) ;; clear all caches
   (let* ((db           #f)
-	 (tdbdat       (tasks:open-db))
+	 ;; (tdbdat       (tasks:open-db))
 	 (keys         (rmt:get-keys))
 	 (rundat       (mt:get-runs-by-patt keys runnamepatt target))
 	 (header       (vector-ref rundat 0))
 	 (runs         (vector-ref rundat 1))
 	 (states       (if state  (string-split state  ",") '()))
@@ -1705,11 +1710,11 @@
 		    (tasks:kill-runner target run-name testpatt)
 		    
 		    ;; (debug:print 0 *default-log-port* "not attempting to kill any run launcher processes as testpatt is " testpatt))
 		    (debug:print 1 *default-log-port* "Removing tests for run: " runkey " " (db:get-value-by-header run header "runname")))
 		   ((set-state-status)
-		    (if (tasks:need-server run-id)(tasks:start-and-wait-for-server tdbdat run-id 10))
+		    ;; (if (tasks:need-server run-id)(tasks:start-and-wait-for-server tdbdat run-id 10))
 		    (debug:print 1 *default-log-port* "Modifying state and staus for tests for run: " runkey " " (db:get-value-by-header run header "runname")))
 		   ((print-run)
 		    (debug:print 1 *default-log-port* "Printing info for run " runkey ", run=" run ", tests=" tests ", header=" header)
 		    action)
 		   ((run-wait)
@@ -1872,18 +1877,18 @@
 	    (debug:print 0 *default-log-port* "WARNING: directory " real-dir " does not exist")
 	    (debug:print 0 *default-log-port* "WARNING: no real directory corrosponding to link " run-dir ", nothing done")))
     (if (symbolic-link? run-dir)
 	(begin
 	  (debug:print-info 1 *default-log-port* "Removing symlink " run-dir)
-	  (handle-exceptions
+	  (common:debug-handle-exceptions #t
 	   exn
 	   (debug:print-error 0 *default-log-port* " Failed to remove symlink " run-dir ((condition-property-accessor 'exn 'message) exn) ", attempting to continue")
 	   (delete-file run-dir)))
 	(if (directory? run-dir)
 	    (if (> (directory-fold (lambda (f x)(+ 1 x)) 0 run-dir) 0)
 		(debug:print 0 *default-log-port* "WARNING: refusing to remove " run-dir " as it is not empty")
-		(handle-exceptions
+		(common:debug-handle-exceptions #t
 		 exn
 		 (debug:print-error 0 *default-log-port* " Failed to remove directory " run-dir ((condition-property-accessor 'exn 'message) exn) ", attempting to continue")
 		 (delete-directory run-dir)))
 	    (if (and run-dir
 		     (not (member run-dir (list "n/a" "/tmp/badname"))))

Index: server.scm
==================================================================
--- server.scm
+++ server.scm
@@ -183,11 +183,11 @@
 	  (if (null? server-logs)
 	      '()
 	      (let loop ((hed  (car server-logs))
 			 (tal  (cdr server-logs))
 			 (res '()))
-		(let* ((mod-time  (handle-exceptions
+		(let* ((mod-time  (common:debug-handle-exceptions #t
                                    exn
                                    0
                                    (file-modification-time hed))) ;; default to *very* old so log gets ignored if deleted
 		       (down-time (- (current-seconds) mod-time))
 		       (serv-dat  (if (or (< num-serv-logs 10)
@@ -287,11 +287,11 @@
 (define server:try-running server:run) ;; there is no more per-run servers ;; REMOVE ME. BUG.
 
 (define (server:dotserver-age-seconds areapath)
   (let ((server-file (conc areapath "/.server")))
     (begin
-      (handle-exceptions
+      (common:debug-handle-exceptions #t
        exn
        #f
        (- (current-seconds)
           (file-modification-time server-file))))))
     

Index: sharedat.scm
==================================================================
--- sharedat.scm
+++ sharedat.scm
@@ -112,11 +112,11 @@
 	     (directory? path)
 	     (file-read-access? path))
 	(let* ((dbpath    (conc path "/spublish.db"))
 	       (writeable (file-write-access? dbpath))
 	       (dbexists  (file-exists? dbpath)))
-	  (handle-exceptions
+	  (common:debug-handle-exceptions #t
 	   exn
 	   (begin
 	     (debug:print 2 *default-log-port* "ERROR: problem accessing db " dbpath
 			  ((condition-property-accessor 'exn 'message) exn))
 	     (exit 1))

Index: spublish.scm
==================================================================
--- spublish.scm
+++ spublish.scm
@@ -112,11 +112,11 @@
 	     (directory? path)
 	     (file-read-access? path))
 	(let* ((dbpath    (conc path "/spublish.db"))
 	       (writeable (file-write-access? dbpath))
 	       (dbexists  (file-exists? dbpath)))
-	  (handle-exceptions
+	  (common:debug-handle-exceptions #t
 	   exn
 	   (begin
 	     (debug:print 2 *default-log-port* "ERROR: problem accessing db " dbpath
 			  ((condition-property-accessor 'exn 'message) exn))
 	     (exit 1))

Index: sretrieve.scm
==================================================================
--- sretrieve.scm
+++ sretrieve.scm
@@ -121,11 +121,11 @@
 	     (directory? path)
 	     (file-read-access? path))
 	(let* ((dbpath    (conc path "/" *exe-name* ".db"))
 	       (writeable (file-write-access? dbpath))
 	       (dbexists  (file-exists? dbpath)))
-	  (handle-exceptions
+	  (common:debug-handle-exceptions #t
 	   exn
 	   (begin
 	     (debug:print 2 *default-log-port* "ERROR: problem accessing db " dbpath
 			  ((condition-property-accessor 'exn 'message) exn))
 	     (exit 1))
@@ -485,11 +485,11 @@
     ;;   <packages-metadir>/<package-type>.config file using
     ;;   <upstream-file> as an input
     (if (file-exists? upstream-file)
 	(if (or (not (file-exists? package-config)) ;; if not created call the updater, otherwise call only if upstream newer
 		(> (file-modification-time upstream-file)(file-modification-time package-config)))
-	    (handle-exceptions
+	    (common:debug-handle-exceptions #t
 	     exn
 	     (debug:print-error 0 *default-log-port* "failed to run script " conversion-script " with params " upstream-file " " package-config)
 	     (let ((pid (process-run conversion-script (list upstream-file package-config))))
 	       (process-wait pid)))
 	    (debug:print 0 *default-log-port* "Skipping update of " package-config " from " upstream-file))

Index: tasks.scm
==================================================================
--- tasks.scm
+++ tasks.scm
@@ -52,19 +52,20 @@
 		     (begin
 		       (thread-sleep! 1)
 		       (loop (file-exists? fullpath)
 			     (- count 1)))
 		     (begin
+		       (debug:print 0 *default-log-port* "ERROR: removing the journal file " fullpath ", this is not good. Look for disk full, write access and other issues.")
 		       (if remove (system (conc "rm -rf " fullpath)))
 		       #f)))
 	       #t))))))
 
 (define (tasks:get-task-db-path)
   (let ((dbdir  (or (configf:lookup *configdat* "setup" "monitordir")
 		    (configf:lookup *configdat* "setup" "dbdir")
 		    (conc (configf:lookup *configdat* "setup" "linktree") "/.db"))))
-    (handle-exceptions
+    (common:debug-handle-exceptions #t
      exn
      (begin
        (debug:print-error 0 *default-log-port* "Couldn't create path to " dbdir)
        (exit 1))
      (if (not (directory? dbdir))(create-directory dbdir #t)))
@@ -80,11 +81,11 @@
 ;;    ==> open in-mem version
 ;;
 (define (tasks:open-db #!key (numretries 4))
   (if *task-db*
       *task-db*
-      (handle-exceptions
+      (common:debug-handle-exceptions #t
        exn
        (if (> numretries 0)
 	   (begin
 	     (print-call-chain (current-error-port))
 	     (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
@@ -93,11 +94,11 @@
 	     (tasks:open-db numretries (- numretries 1)))
 	   (begin
 	     (print-call-chain (current-error-port))
 	     (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
 	     (debug:print 0 *default-log-port* " exn=" (condition->list exn))))
-       (let* ((dbpath       (tasks:get-task-db-path))
+       (let* ((dbpath        (db:dbfile-path )) ;; (tasks:get-task-db-path))
 	      (dbfile       (conc dbpath "/monitor.db"))
 	      (avail        (tasks:wait-on-journal dbpath 10)) ;; wait up to about 10 seconds for the journal to go away
 	      (exists       (file-exists? dbpath))
 	      (write-access (file-write-access? dbpath))
 	      (mdb          (cond ;; what the hek is *toppath* doing here?
@@ -468,11 +469,11 @@
 
 (define (tasks:param-key->id dbstruct task-params)
   (db:with-db
    dbstruct #f #f
    (lambda (db)
-     (handle-exceptions
+     (common:debug-handle-exceptions #t
       exn
       #f
       (sqlite3:first-result db "SELECT id FROM tasks_queue WHERE params LIKE ?;"
 			    task-params)))))
 
@@ -484,19 +485,19 @@
 
 (define (tasks:get-records-given-param-key dbstruct param-key state-patt action-patt test-patt)
   (db:with-db
    dbstruct #f #f
    (lambda (db)
-     (handle-exceptions
+     (common:debug-handle-exceptions #t
       exn
       '()
       (sqlite3:first-row db "SELECT id,action,owner,state,target,name,testpatt,keylock,params WHERE
                                params LIKE ? AND state LIKE ? AND action LIKE ? AND testpatt LIKE ?;"
 			 param-key state-patt action-patt test-patt)))))
 
 (define (tasks:find-task-queue-records dbstruct target run-name test-patt state-patt action-patt)
-  ;; (handle-exceptions
+  ;; (common:debug-handle-exceptions #t
   ;;  exn
   ;;  '()
   ;;  (sqlite3:first-row
   (let ((db (db:delay-if-busy (db:get-db dbstruct)))
 	(res '()))
@@ -528,11 +529,11 @@
 		   (pid       (string->number (caddr match-dat))))
 	       (debug:print 0 *default-log-port* "Sending SIGINT to process " pid " on host " hostname)
 	       (if (equal? (get-host-name) hostname)
 		   (if (process:alive? pid)
 		       (begin
-			 (handle-exceptions
+			 (common:debug-handle-exceptions #t
 			  exn
 			  (begin
 			    (debug:print 0 *default-log-port* "Kill of process " pid " on host " hostname " failed.")
 			    (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
 			    #t)
@@ -593,11 +594,11 @@
 ;;
 (define (tasks:set-area dbh configdat #!key (toppath #f)) ;; could I safely put *toppath* in for the default for toppath? when would it be evaluated?
   (let loop ((area-name (or (configf:lookup configdat "setup" "area-name")
 			    (common:get-area-name)))
 	     (modifier  'none))
-    (let ((success (handle-exceptions
+    (let ((success (common:debug-handle-exceptions #t
 		       exn
 		       (begin
 			 (debug:print 0 *default-log-port* "ERROR: cannot create area entry, " ((condition-property-accessor 'exn 'message) exn))
 			 #f) ;; FIXME: I don't care for now but I should look at *why* there was an exception
 		     (pgdb:add-area dbh area-name (or toppath *toppath*)))))
@@ -639,11 +640,11 @@
 		(pgdb:refresh-run-info
 		 dbh
 		 new-run-id
 		 state status owner event-time comment fail-count pass-count)
 		new-run-id)
-	      (if (handle-exceptions
+	      (if (common:debug-handle-exceptions #t
 		      exn
 		      (begin (print-call-chain) #f)
 		    (pgdb:insert-run
 		     dbh
 		     spec-id target run-name state status owner event-time comment fail-count pass-count)) ;; area-id))

Index: tdb.scm
==================================================================
--- tdb.scm
+++ tdb.scm
@@ -52,11 +52,11 @@
 	   (directory? work-area)
 	   (file-read-access? work-area))
       (let* ((dbpath              (conc work-area "/testdat.db"))
 	     (dbexists            (file-exists? dbpath))
 	     (work-area-writeable (file-write-access? work-area))
-	     (db                  (handle-exceptions  ;; open the db if area writeable or db pre-existing. open in-mem otherwise. if exception, open in-mem
+	     (db                  (common:debug-handle-exceptions #t  ;; open the db if area writeable or db pre-existing. open in-mem otherwise. if exception, open in-mem
 				   exn
 				   (begin
 				     (print-call-chain (current-error-port))
 				     (debug:print 2 *default-log-port* "ERROR: problem accessing test db " work-area ", you probably should clean and re-run this test"
 						  ((condition-property-accessor 'exn 'message) exn))
@@ -81,11 +81,11 @@
 	      (debug:print-info 11 *default-log-port* "Initialized test database " dbpath)
 	      (tdb:testdb-initialize db)))
 	;; (sqlite3:execute db "PRAGMA synchronous = 0;")
 	(debug:print-info 11 *default-log-port* "open-test-db END (sucessful)" work-area)
 	;; now let's test that everything is correct
-	(handle-exceptions
+	(common:debug-handle-exceptions #t
 	 exn
 	 (begin
 	   (print-call-chain (current-error-port))
 	   (debug:print-error 0 *default-log-port* "problem accessing test db " work-area ", you probably should clean and re-run this test or remove the file " 
 			dbpath ".\n  "

Index: tests.scm
==================================================================
--- tests.scm
+++ tests.scm
@@ -1098,11 +1098,11 @@
     (if fnamepatt
 	(apply append 
 	       (map (lambda (p)
 		      (if (directory-exists? p)
 			  (let ((glob-query (conc p "/" fnamepatt)))
-			    (handle-exceptions
+			    (common:debug-handle-exceptions #t
 				exn
 				(with-input-from-pipe
 				    (conc "echo " glob-query)
 				  read-lines)  ;; we aren't going to try too hard. If glob breaks it is likely because someone tried to do */*/*.log or similar
 			      (glob glob-query)))
@@ -1151,11 +1151,11 @@
 	 (cache-exists (and cache-file
 			    (not force-create)  ;; if force-create then pretend there is no cache to read
 			    (file-exists? cache-file)))
 	 (cached-dat   (if (and (not force-create)
 				cache-exists)
-			   (handle-exceptions
+			   (common:debug-handle-exceptions #t
 			    exn
 			    #f ;; any issues, just give up with the cached version and re-read
 			    (configf:read-alist cache-file))
 			   #f))
          (test-full-name (if (and item-path (not (string-null? item-path)))
@@ -1529,11 +1529,11 @@
 ;; (define (tests:set-partial-meta-info test-id run-id minutes work-area)
 (define (tests:set-partial-meta-info test-id run-id minutes work-area remtries)
   (let* ((cpuload  (get-cpu-load))
 	 (diskfree (get-df (current-directory)))
 	 (remtries 10))
-    (handle-exceptions
+    (common:debug-handle-exceptions #t
      exn
      (if (> remtries 0)
 	 (begin
 	   (print-call-chain (current-error-port))
 	   (debug:print-info 0 *default-log-port* "WARNING: failed to set meta info. Will try " remtries " more times")

Index: tests/fullrun/megatest.config
==================================================================
--- tests/fullrun/megatest.config
+++ tests/fullrun/megatest.config
@@ -99,12 +99,12 @@
 # htmlviewercmd firefox -new-window 
 htmlviewercmd arora
 
 # -runtests automatically deletes the records for tests with the listed states on starting up a run allowing them to re-run
 #     (nb// this is in addition to NOT_STARTED which is automatically re-run)
-#
-allow-auto-rerun INCOMPLETE ZERO_ITEMS
+# format is STATE/STATUS
+allow-auto-rerun /INCOMPLETE /ZERO_ITEMS
 # could add: STUCK STUCK/DEAD UNKNOWN KILLED KILLREQ PREQ_DISCARD
 
 [validvalues]
 state start end 0 1 - 2
 status pass fail n/a 0 1 running - 2