Megatest

Check-in [0c24209eae]
Login
Overview
Comment:Removed the thread doing rmt:find-and-mark-incomplete, changed an ERROR to INFO message
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | v1.70
Files: files | file ages | folders
SHA1: 0c24209eae89b2837dd799cc0961b85acc11029c
User & Date: mmgraham on 2024-03-20 17:26:45
Other Links: branch diff | manifest | tags
Context
2024-03-20
17:27
Changed version to v1.7016 check-in: 727d573ad0 user: mmgraham tags: v1.70, v1.7016
17:26
Removed the thread doing rmt:find-and-mark-incomplete, changed an ERROR to INFO message check-in: 0c24209eae user: mmgraham tags: v1.70
2023-07-20
16:12
Changed version to v1.7015 check-in: 3152edd3b0 user: mmgraham tags: v1.70, v1.7015
Changes

Modified rmt.scm from [cecfc0934e] to [2253771ff5].

333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
    (debug:print-info 13 *default-log-port* "rmt:send-receive, case  9. conninfo=" conninfo " dat=" dat " runremote = " runremote)
    (mutex-unlock! *rmt-mutex*)
    (if success ;; success only tells us that the transport was
	;; successful, have to examine the data to see if
	;; there was a detected issue at the other end
	(extras-transport-succeded *default-log-port* *rmt-mutex* attemptnum runremote res params rid cmd)
	(begin
           (debug:print-error 2 *default-log-port* " dat=" dat) 
           (extras-transport-failed *default-log-port* *rmt-mutex* attemptnum runremote cmd rid params))
	)))

(define (rmt:print-db-stats)
  (let ((fmtstr "~40a~7-d~9-d~20,2-f")) ;; "~20,2-f"
    (debug:print 18 *default-log-port* "DB Stats\n========")
    (debug:print 18 *default-log-port* (format #f "~40a~8a~10a~10a" "Cmd" "Count" "TotTime" "Avg"))







|







333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
    (debug:print-info 13 *default-log-port* "rmt:send-receive, case  9. conninfo=" conninfo " dat=" dat " runremote = " runremote)
    (mutex-unlock! *rmt-mutex*)
    (if success ;; success only tells us that the transport was
	;; successful, have to examine the data to see if
	;; there was a detected issue at the other end
	(extras-transport-succeded *default-log-port* *rmt-mutex* attemptnum runremote res params rid cmd)
	(begin
           (debug:print-info 0 *default-log-port* "Bad return data from Megatest server: dat=" dat) 
           (extras-transport-failed *default-log-port* *rmt-mutex* attemptnum runremote cmd rid params))
	)))

(define (rmt:print-db-stats)
  (let ((fmtstr "~40a~7-d~9-d~20,2-f")) ;; "~20,2-f"
    (debug:print 18 *default-log-port* "DB Stats\n========")
    (debug:print 18 *default-log-port* (format #f "~40a~8a~10a~10a" "Cmd" "Count" "TotTime" "Avg"))

Modified runs.scm from [6164fa6d2a] to [d6ca8ef849].

797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850

    (if (not (null? required-tests))
	(debug:print-info 1 *default-log-port* "Adding \"" (string-intersperse required-tests " ") "\" to the run queue"))
    ;; NOTE: these are all parent tests, items are not expanded yet.
    (debug:print-info 4 *default-log-port* "test-records=" (hash-table->alist test-records))
    (let ((reglen (configf:lookup *configdat* "setup" "runqueue")))
      (if (> (length (hash-table-keys test-records)) 0)
	  (let* ((keep-going        #t)
		 (run-queue-retries 5)
		;; (th1        (make-thread (lambda ()
		;; 			    (handle-exceptions
		;; 				exn
		;; 				(begin
		;; 				  (print-call-chain)
		;; 				  (print " message: " ((condition-property-accessor 'exn 'message) exn)))
		;; 			      (runs:run-tests-queue run-id runname test-records keyvals flags test-patts required-tests
		;; 						    (any->number reglen) all-tests-registry)))
		;; 			  "runs:run-tests-queue"))
		 (th2        (make-thread (lambda ()			 ;; BBQ: why are we visiting ALL runs here?	    
					    ;; (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
							       exn
							       (debug:print 0 *default-log-port* "error in calling find-and-mark-incomplete for run-id " run-id ", exn=" exn)
							       (rmt:find-and-mark-incomplete run-id #f)))) ;; ovr-deadtime))) ;; could be root of https://hsdes.intel.com/appstore/article/#/220546828/main -- Title: Megatest jobs show DEAD even though they are still running (1.64/27)
							run-ids)))
					  "runs: mark-incompletes")))
	    ;; (thread-start! th1)
	    (thread-start! th2)
	    ;; (thread-join! th1)
	    ;; just do the main stuff in the main thread
	    (runs:run-tests-queue run-id runname test-records keyvals flags test-patts required-tests
								    (any->number reglen) all-tests-registry)
	    (set! keep-going #f)
	    (thread-join! th2)
	    ;; if run-count > 0 call, set -preclean and -rerun STUCK/DEAD
	    (if (> run-count 0) ;; handle reruns
		(begin
		  (if (not (hash-table-ref/default flags "-preclean" #f))
		      (hash-table-set! flags "-preclean" #t))
		  (if (not (hash-table-ref/default flags "-rerun" #f))
		      (hash-table-set! flags "-rerun" "ABORT,STUCK/DEAD,n/a,ZERO_ITEMS"))
		  ;; recursive call to self
      (runs:run-tests target runname test-patts user flags run-count: (- run-count 1)))
                  (launch:end-of-run-check run-id)))
	  (debug:print-info 0 *default-log-port* "No tests to run")))
    (debug:print-info 4 *default-log-port* "All done by here")
    ;; TODO: try putting post hook call here
      
    ;  (debug:print-info 2 *default-log-port* " run-count " run-count)
    ;  (runs:run-post-hook run-id))
    ;  (debug:print-info 2 *default-log-port* "Not calling post hook runcount = " run-count ))   







|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<



<
<








|
|







797
798
799
800
801
802
803
804
























805
806
807


808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824

    (if (not (null? required-tests))
	(debug:print-info 1 *default-log-port* "Adding \"" (string-intersperse required-tests " ") "\" to the run queue"))
    ;; NOTE: these are all parent tests, items are not expanded yet.
    (debug:print-info 4 *default-log-port* "test-records=" (hash-table->alist test-records))
    (let ((reglen (configf:lookup *configdat* "setup" "runqueue")))
      (if (> (length (hash-table-keys test-records)) 0)
	  (let* ()
























	    ;; just do the main stuff in the main thread
	    (runs:run-tests-queue run-id runname test-records keyvals flags test-patts required-tests
								    (any->number reglen) all-tests-registry)


	    ;; if run-count > 0 call, set -preclean and -rerun STUCK/DEAD
	    (if (> run-count 0) ;; handle reruns
		(begin
		  (if (not (hash-table-ref/default flags "-preclean" #f))
		      (hash-table-set! flags "-preclean" #t))
		  (if (not (hash-table-ref/default flags "-rerun" #f))
		      (hash-table-set! flags "-rerun" "ABORT,STUCK/DEAD,n/a,ZERO_ITEMS"))
		  ;; recursive call to self
                  (runs:run-tests target runname test-patts user flags run-count: (- run-count 1)))
                 (launch:end-of-run-check run-id)))
	  (debug:print-info 0 *default-log-port* "No tests to run")))
    (debug:print-info 4 *default-log-port* "All done by here")
    ;; TODO: try putting post hook call here
      
    ;  (debug:print-info 2 *default-log-port* " run-count " run-count)
    ;  (runs:run-post-hook run-id))
    ;  (debug:print-info 2 *default-log-port* "Not calling post hook runcount = " run-count ))