Megatest

Changes On Branch a160c138d8a43b60
Login

Changes In Branch v1.65-experiment Through [a160c138d8] Excluding Merge-Ins

This is equivalent to a diff from 0cbf1a0b26 to a160c138d8

2020-09-08
10:12
Added testplan section to manual. NOTE: Passes ext-tests without any re-runs, seems like a sweet spot. ==24.9/2.2/1201/WARN/mars== check-in: 0d4dd9a19f user: mrwellan tags: v1.65
2020-09-07
23:29
Added query throttle.

Fully tested and passes ext-tests on sles11 and Ubuntu. Closed-Leaf check-in: 70a65ade2a user: matt tags: v1.65-rmt-call-throttle-orig

11:39
Better flagging with LAUNCHING state. NOTE: itemwait subrun items are re-running when they perhaps should not. check-in: 5d2d0fddc3 user: matt tags: v1.65-experiment
2020-09-05
23:59
Cache testdat. Not sure yet this is a good idea but it sure cuts down on queries that seem unnecessary. check-in: a160c138d8 user: matt tags: v1.65-experiment
21:51
Merged the prereq attempt to rate gate check-in: 9dfe6cbfa1 user: matt tags: v1.65-experiment
13:41
Try reduced frequency queries for prereq not met. ==/3.5/0.83/PASS/1201/mars/== check-in: 275adb0d10 user: matt tags: v1.65-prereq-qry-freq
11:17
Merged cleanup branch back to v1.65 ==9.4/2.2/1201/WARN/mars== check-in: 0cbf1a0b26 user: matt tags: v1.65
2020-09-04
16:34
Change ERROR to INFO on directories in logs dir NOTE: Use this version as baseline: ext-tests gives full PASS, obfusc-skel test gives full PASS and no exn= in logs dir (but there are exn= in tests). check-in: 5c063e3452 user: mrwellan tags: v1.65-cleanup, v1.6568, v1.6565a
2020-08-25
15:08
Added get-intercept and get-delay functions for load monitoring ==/FAIL/orion,zeus/== check-in: 85b652d5a1 user: jmoon18 tags: v1.65

Modified db.scm from [2f649dc1fb] to [a8d9328753].

3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
	  -1 "-" "-"))

;;
;; 1. cache tests-match-qry
;; 2. compile qry and store in hash
;; 3. convert for-each-row to fold
;;
(define (db:get-tests-for-run-state-status dbstruct run-id testpatt)
  (db:with-db
   dbstruct run-id #f
   (lambda (db)
     (let* ((res            '())
	    (stmt-cache      (dbr:dbstruct-stmt-cache dbstruct))
	    (stmth           (let* ((sh (db:hoh-get stmt-cache db testpatt)))
			       (or sh







|







3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
	  -1 "-" "-"))

;;
;; 1. cache tests-match-qry
;; 2. compile qry and store in hash
;; 3. convert for-each-row to fold
;;
#;(define (db:get-tests-for-run-state-status dbstruct run-id testpatt)
  (db:with-db
   dbstruct run-id #f
   (lambda (db)
     (let* ((res            '())
	    (stmt-cache      (dbr:dbstruct-stmt-cache dbstruct))
	    (stmth           (let* ((sh (db:hoh-get stmt-cache db testpatt)))
			       (or sh

Modified runs.scm from [030b929939] to [f581c02f6f].

58
59
60
61
62
63
64
65




66
67
68
69
70
71
72
  (last-load-check-time    0)
  (last-jobs-check-time    0)
  )

(defstruct runs:testdat
  hed tal reg reruns  test-record
  test-name item-path jobgroup
  waitons testmode  newtal itemmaps prereqs-not-met)




  
;; look in the $MT_RUN_AREA_HOME/.softlocks directory for key-host-pid.softlock files
;;  - remove any that are over 3600 seconds old
;;  - if there are any that are younger than 10 seconds
;;      * sleep 10 seconds
;;      * touch my key-host-pid.softlock file
;;      * return







|
>
>
>
>







58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
  (last-load-check-time    0)
  (last-jobs-check-time    0)
  )

(defstruct runs:testdat
  hed tal reg reruns  test-record
  test-name item-path jobgroup
  waitons testmode  newtal
  itemmaps
  (prereqs-not-met '())
  (last-update 0) ;; 
  )
  
;; look in the $MT_RUN_AREA_HOME/.softlocks directory for key-host-pid.softlock files
;;  - remove any that are over 3600 seconds old
;;  - if there are any that are younger than 10 seconds
;;      * sleep 10 seconds
;;      * touch my key-host-pid.softlock file
;;      * return
827
828
829
830
831
832
833






















834
835
836
837
838
839
840
841
842
843

844

845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
;;    => review of a previously seen test is higher priority of never visited test
;; reg - list of previously visited tests
;; tal - list of never visited tests
;;   prefer next hed to be from reg than tal.

(define runs:nothing-left-in-queue-count 0)























;;======================================================================
;; runs:expand-items is called by runs:run-tests-queue
;;======================================================================
;;
;; return value of runs:expand-items is passed back to runs-tests-queue and is fed to named loop with this signature:
;;    (let loop ((hed         (car sorted-test-names))
;;	         (tal         (cdr sorted-test-names))
;;	         (reg         '()) ;; registered, put these at the head of tal 
;;	         (reruns      '()))
(define (runs:expand-items hed tal reg reruns regfull newtal jobgroup max-concurrent-jobs run-id waitons item-path testmode test-record can-run-more items runname tconfig reglen test-registry test-records itemmaps)

  (let* ((loop-list       (list hed tal reg reruns))

	 (prereqs-not-met (let ((res (rmt:get-prereqs-not-met run-id waitons hed item-path mode: testmode itemmaps: itemmaps)))
			    (if (list? res)
				res
				(begin
				  (debug:print 0 *default-log-port*
					       "ERROR: rmt:get-prereqs-not-met returned non-list!\n"
					       "  res=" res " run-id=" run-id " waitons=" waitons " hed=" hed " item-path=" item-path " testmode=" testmode " itemmaps=" itemmaps)
				  '()))))
         (have-itemized (not (null? (lset-intersection eq? testmode '(itemmatch itemwait)))))
	 ;; (prereqs-not-met (mt:lazy-get-prereqs-not-met run-id waitons item-path mode: testmode itemmap: itemmap))
	 (fails           (runs:calc-fails prereqs-not-met))
	 (prereq-fails    (runs:calc-prereq-fail prereqs-not-met))
	 (non-completed   (runs:calc-not-completed prereqs-not-met))
	 (runnables       (runs:calc-runnable prereqs-not-met))
         (unexpanded-prereqs
          (filter (lambda (testname)







>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>









|
>

>
|






|
|







831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
;;    => review of a previously seen test is higher priority of never visited test
;; reg - list of previously visited tests
;; tal - list of never visited tests
;;   prefer next hed to be from reg than tal.

(define runs:nothing-left-in-queue-count 0)

(define (runs:lazy-get-prereqs-not-met  testdat run-id waitons hed item-path #!key (mode '(normal))(itemmaps #f)) ;; mode: testmode itemmaps: itemmaps)
  (if (< (- (current-seconds) (runs:testdat-last-update testdat)) 10) ;; only refresh for this test if it has been at least 10 seconds
      (begin
	;; (debug:print 0 *default-log-port* "last-update=" (runs:testdat-last-update testdat) "(current-seconds)=" (current-seconds))
	(runs:testdat-prereqs-not-met testdat))
      ;;                     (rmt:get-prereqs-not-met 46     '("r1") "y1" ""       mode: '(itemmatch) itemmaps: #f) 
      (let* ((res (let ((res (rmt:get-prereqs-not-met run-id waitons hed item-path mode: mode         itemmaps: itemmaps)))
		    (debug:print 4 *default-log-port* "Get prereqs for " hed ", have " (length res)
				 " prereqs. last-update=" (runs:testdat-last-update testdat) " current-seconds=" (current-seconds)
				 " delta=" (- (current-seconds) (runs:testdat-last-update testdat)))
		    (if (list? res)
			res
			(begin
			  (debug:print 0 *default-log-port*
				       "ERROR: rmt:get-prereqs-not-met returned non-list!\n"
				       "  res=" res " run-id=" run-id " waitons=" waitons " hed=" hed
				       " item-path=" item-path " testmode=" mode " itemmaps=" itemmaps)
			  '())))))
	(runs:testdat-prereqs-not-met-set! testdat res)
	(runs:testdat-last-update-set! testdat (current-seconds))
	res)))
	   
;;======================================================================
;; runs:expand-items is called by runs:run-tests-queue
;;======================================================================
;;
;; return value of runs:expand-items is passed back to runs-tests-queue and is fed to named loop with this signature:
;;    (let loop ((hed         (car sorted-test-names))
;;	         (tal         (cdr sorted-test-names))
;;	         (reg         '()) ;; registered, put these at the head of tal 
;;	         (reruns      '()))
(define (runs:expand-items hed tal reg reruns regfull newtal jobgroup max-concurrent-jobs run-id waitons item-path testmode test-record
			   can-run-more items runname tconfig reglen test-registry test-records itemmaps testdat)
  (let* ((loop-list       (list hed tal reg reruns))
	 (prereqs-not-met (runs:lazy-get-prereqs-not-met testdat run-id waitons hed item-path mode: testmode itemmaps: itemmaps))
	  #;(let ((res (rmt:get-prereqs-not-met run-id waitons hed item-path mode: testmode itemmaps: itemmaps)))
			    (if (list? res)
				res
				(begin
				  (debug:print 0 *default-log-port*
					       "ERROR: rmt:get-prereqs-not-met returned non-list!\n"
					       "  res=" res " run-id=" run-id " waitons=" waitons " hed=" hed " item-path=" item-path " testmode=" testmode " itemmaps=" itemmaps)
				  '())))
	 (have-itemized   (not (null? (lset-intersection eq? testmode '(itemmatch itemwait)))))
	 ;; (prereqs-not-met (mt:lazy-get-prereqs-not-met run-id waitons item-path mode: testmode itemmap: itemmap))
	 (fails           (runs:calc-fails prereqs-not-met))
	 (prereq-fails    (runs:calc-prereq-fail prereqs-not-met))
	 (non-completed   (runs:calc-not-completed prereqs-not-met))
	 (runnables       (runs:calc-runnable prereqs-not-met))
         (unexpanded-prereqs
          (filter (lambda (testname)
1440
1441
1442
1443
1444
1445
1446
1447


1448
1449
1450
1451
1452
1453
1454

;; every time though the loop increment the test/itempatt val.
;; when the min is > max-allowed and none running then force exit
;;
(define *max-tries-hash* (make-hash-table))

(define (runs:pretty-long-list lst)
   (if (> (length lst) 8)(append (take lst 3)(list "...")) lst))



;;======================================================================
;; runs:run-tests-queue is called by runs:run-tests
;;======================================================================
;;
;; test-records is a hash table testname:item_path => vector < testname testconfig waitons priority items-info ... >
(define (runs:run-tests-queue run-id runname test-records keyvals flags test-patts required-tests reglen-in all-tests-registry)







|
>
>







1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484

;; every time though the loop increment the test/itempatt val.
;; when the min is > max-allowed and none running then force exit
;;
(define *max-tries-hash* (make-hash-table))

(define (runs:pretty-long-list lst)
  (if (> (length lst) 8)(append (take lst 3)(list "...")) lst))

(define *runs-testdat-cache* (make-hash-table)) ;; full/testname => testdat

;;======================================================================
;; runs:run-tests-queue is called by runs:run-tests
;;======================================================================
;;
;; test-records is a hash table testname:item_path => vector < testname testconfig waitons priority items-info ... >
(define (runs:run-tests-queue run-id runname test-records keyvals flags test-patts required-tests reglen-in all-tests-registry)
1564
1565
1566
1567
1568
1569
1570
















1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585


1586
1587
1588
1589
1590
1591
1592
				   extras)
				  extras)
				'())))
	     (waitons     (delete-duplicates (append (tests:testqueue-get-waitons test-record) extra-waits) equal?))
	     (newtal      (append tal (list hed)))
	     (regfull     (>= (length reg) reglen))
	     (num-running (rmt:get-count-tests-running-for-run-id run-id #t)) ;; fastmode=yes
















	     (testdat     (make-runs:testdat
			   hed: hed
			   tal: tal
			   reg: reg
			   reruns: reruns
			   test-record: test-record
			   test-name:   test-name
			   item-path:   item-path
			   jobgroup:    jobgroup
			   waitons:     waitons
			   testmode:    testmode
			   newtal:      newtal
			   itemmaps:    itemmaps
			   ;; prereqs-not-met: prereqs-not-met
			   )))


	(runs:dat-regfull-set! runsdat regfull)
    
	(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)))
            (hash-table-set! *max-tries-hash* tfullname (+ (hash-table-ref/default *max-tries-hash* tfullname 0) 1)))







>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
>
>







1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
				   extras)
				  extras)
				'())))
	     (waitons     (delete-duplicates (append (tests:testqueue-get-waitons test-record) extra-waits) equal?))
	     (newtal      (append tal (list hed)))
	     (regfull     (>= (length reg) reglen))
	     (num-running (rmt:get-count-tests-running-for-run-id run-id #t)) ;; fastmode=yes
	     (testdat     (let ((oldtestdat (hash-table-ref/default *runs-testdat-cache* tfullname #f)))
			    (if oldtestdat
				(begin
				  (runs:testdat-hed-set!         oldtestdat hed)
				  (runs:testdat-tal-set!         oldtestdat tal)
				  (runs:testdat-reg-set!         oldtestdat reg)
				  (runs:testdat-reruns-set!      oldtestdat reruns)
				  (runs:testdat-test-record-set! oldtestdat test-record)
				  (runs:testdat-newtal-set!      oldtestdat newtal)
				  
				  (if (not (equal? (runs:testdat-waitons oldtestdat) waitons))
				      (debug:print 0 *default-log-port* " waitons changed for runs:testdat"))
				  (if (not (equal? (runs:testdat-itemmaps oldtestdat) itemmaps))
				      (debug:print 0 *default-log-port* " itemmaps changed for runs:testdat"))
				  
				  oldtestdat)
				(let ((newtestdat (make-runs:testdat
						   hed: hed
						   tal: tal
						   reg: reg
						   reruns: reruns
						   test-record: test-record
						   test-name:   test-name
						   item-path:   item-path
						   jobgroup:    jobgroup
						   waitons:     waitons
						   testmode:    testmode
						   newtal:      newtal
						   itemmaps:    itemmaps
						   ;; prereqs-not-met: prereqs-not-met
						   )))
				  (hash-table-set! *runs-testdat-cache* tfullname newtestdat)
				  newtestdat)))))
	(runs:dat-regfull-set! runsdat regfull)
    
	(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)))
            (hash-table-set! *max-tries-hash* tfullname (+ (hash-table-ref/default *max-tries-hash* tfullname 0) 1)))
1713
1714
1715
1716
1717
1718
1719


1720
1721
1722
1723
1724
1725
1726
1727
				  ;; wait for load here
				  (if (runs:dat-load-mgmt-function runsdat)((runs:dat-load-mgmt-function runsdat)))
				  (loop-can-run-more (runs:can-run-more-tests runsdat run-id jobgroup max-concurrent-jobs)
						     (- remtries 1)))))))
		       )))))

	  ;; I'm not clear on why prereqs are gathered here TODO: verfiy this is needed


	  (runs:testdat-prereqs-not-met-set! testdat (rmt:get-prereqs-not-met run-id waitons hed item-path mode: testmode itemmaps: itemmaps))

	  ;; I'm not clear on why we'd capture running job counts here TODO: verify this is needed
	  (runs:dat-can-run-more-tests-set! runsdat (runs:can-run-more-tests runsdat run-id jobgroup max-concurrent-jobs))

	  (let ((loop-list (runs:process-expanded-tests runsdat testdat))) ;; in process-expanded-tests ultimately run:test -> launch-test -> test actually running
            (if loop-list (apply loop loop-list))))








>
>
|







1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
				  ;; wait for load here
				  (if (runs:dat-load-mgmt-function runsdat)((runs:dat-load-mgmt-function runsdat)))
				  (loop-can-run-more (runs:can-run-more-tests runsdat run-id jobgroup max-concurrent-jobs)
						     (- remtries 1)))))))
		       )))))

	  ;; I'm not clear on why prereqs are gathered here TODO: verfiy this is needed
	  (runs:lazy-get-prereqs-not-met testdat run-id waitons hed item-path
					 mode: testmode
					 itemmaps: itemmaps)

	  ;; I'm not clear on why we'd capture running job counts here TODO: verify this is needed
	  (runs:dat-can-run-more-tests-set! runsdat (runs:can-run-more-tests runsdat run-id jobgroup max-concurrent-jobs))

	  (let ((loop-list (runs:process-expanded-tests runsdat testdat))) ;; in process-expanded-tests ultimately run:test -> launch-test -> test actually running
            (if loop-list (apply loop loop-list))))

1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
         
	 ;; if items is a proc then need to run items:get-items-from-config, get the list and loop 
	 ;;    - but only do that if resources exist to kick off the job
	 ;; EXPAND ITEMS
	 ((or (procedure? items)(eq? items 'have-procedure))
          (debug:print-info 4 *default-log-port* "cond branch - "  "rtq-4")
	  (let ((can-run-more    #f)) ;; (runs:can-run-more-tests runsdat run-id jobgroup max-concurrent-jobs)))
	    (if (not can-run-more) #;(and (list? can-run-more)
		(car can-run-more))
		(let ((loop-list (runs:expand-items hed tal reg reruns regfull newtal jobgroup max-concurrent-jobs run-id waitons item-path testmode test-record can-run-more items runname tconfig reglen test-registry test-records itemmaps))) ;; itemized test expanded here
		  (if loop-list
		      (apply loop loop-list)
                      (debug:print-info 4 *default-log-port* " -- Can't expand hed="hed)
                      )
                  )
		;; if can't run more just loop with next possible test
		(loop (car newtal)(cdr newtal) reg reruns))))







|

|







1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
         
	 ;; if items is a proc then need to run items:get-items-from-config, get the list and loop 
	 ;;    - but only do that if resources exist to kick off the job
	 ;; EXPAND ITEMS
	 ((or (procedure? items)(eq? items 'have-procedure))
          (debug:print-info 4 *default-log-port* "cond branch - "  "rtq-4")
	  (let ((can-run-more    #f)) ;; (runs:can-run-more-tests runsdat run-id jobgroup max-concurrent-jobs)))
	    (if (not can-run-more) #;(and (list? can-run-more) ;; IDEA, this mechanism may have had some value, make it configurable to test pros/cons TODO
		(car can-run-more))
		(let ((loop-list (runs:expand-items hed tal reg reruns regfull newtal jobgroup max-concurrent-jobs run-id waitons item-path testmode test-record can-run-more items runname tconfig reglen test-registry test-records itemmaps testdat))) ;; itemized test expanded here
		  (if loop-list
		      (apply loop loop-list)
                      (debug:print-info 4 *default-log-port* " -- Can't expand hed="hed)
                      )
                  )
		;; if can't run more just loop with next possible test
		(loop (car newtal)(cdr newtal) reg reruns))))