Megatest

Changes On Branch 57cd3416b18e388c
Login

Changes In Branch v1.65 Through [57cd3416b1] Excluding Merge-Ins

This is equivalent to a diff from 57b5fb07d6 to 57cd3416b1

2022-02-20
19:17
Added dbmod.scm and build support check-in: 996af79a27 user: matt tags: v1.65
17:57
Added back MT_STEP_NAMES check-in: 57cd3416b1 user: mmgraham tags: v1.65
2022-02-17
16:20
Fixed few things broken by the cherrypicks check-in: b4346350c4 user: mrwellan tags: v1.65
2021-04-06
10:31
Fixed typo Closed-Leaf check-in: 8283307ec9 user: matt tags: v1.65-real
2021-03-14
05:41
Redo inter-test-delay. Leaf check-in: 262ea69800 user: matt tags: v1.65-real-redo-inter-test-delay
2021-03-11
17:52
updated delay to kind-run check-in: dd2cea12eb user: pjhatwal tags: v1.65, THIS-IS-REAL-1.65
2021-03-09
21:03
Very odd, missing egg in server.scm, util. check-in: 57b5fb07d6 user: matt tags: v1.65-real
18:48
changed version to 1.6584 check-in: b6403cb822 user: mmgraham tags: v1.65-real

Modified common.scm from [82673dacdb] to [526a2263d9].

815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
    (11 "PREQ_DISCARDED")
    (12 "ABORT")))

(define *common:ended-states*       ;; states which indicate the test is stopped and will not proceed
  '("COMPLETED" "ARCHIVED" "KILLED" "KILLREQ" "STUCK" "INCOMPLETE" ))

(define *common:badly-ended-states* ;; these roll up as CHECK, i.e. results need to be checked
  '("KILLED" "KILLREQ" "STUCK" "INCOMPLETE" "DEAD"))

(define *common:well-ended-states* ;; an item's prereq in this state allows item to proceed
  '("PASS" "WARN" "CHECK" "WAIVED" "SKIP"))

;; BBnote: *common:running-states* used from db:set-state-status-and-roll-up-items
(define *common:running-states*     ;; test is either running or can be run
  '("RUNNING" "REMOTEHOSTSTART" "LAUNCHED" "STARTED"))

(define *common:cant-run-states*    ;; These are stopping conditions that prevent a test from being run
  '("COMPLETED" "KILLED" "UNKNOWN" "INCOMPLETE" "ARCHIVED"))







|


|







815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
    (11 "PREQ_DISCARDED")
    (12 "ABORT")))

(define *common:ended-states*       ;; states which indicate the test is stopped and will not proceed
  '("COMPLETED" "ARCHIVED" "KILLED" "KILLREQ" "STUCK" "INCOMPLETE" ))

(define *common:badly-ended-states* ;; these roll up as CHECK, i.e. results need to be checked
  '("KILLED" "KILLREQ" "STUCK" "INCOMPLETE" "DEAD" "CHECK"))

(define *common:well-ended-states* ;; an item's prereq in this state allows item to proceed
  '("PASS" "WARN" "WAIVED" "SKIP"))

;; BBnote: *common:running-states* used from db:set-state-status-and-roll-up-items
(define *common:running-states*     ;; test is either running or can be run
  '("RUNNING" "REMOTEHOSTSTART" "LAUNCHED" "STARTED"))

(define *common:cant-run-states*    ;; These are stopping conditions that prevent a test from being run
  '("COMPLETED" "KILLED" "UNKNOWN" "INCOMPLETE" "ARCHIVED"))
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
;;   count     - count down to zero, at some point we'd give up if the load never drops
;;   num-tries - count down to zero number tries to get numcpus
;;
(define (common:wait-for-cpuload maxnormload numcpus-in
				 #!key (count 1000)
				 (msg #f)(remote-host #f)(num-tries 5))
  (let* ((loadavg     (common:get-cpu-load remote-host))
	  ;; not possible to have zero.  If we get 1, it's possible that we got the previous default, and we should check again
	 (numcpus     (if (<= 1 numcpus-in)
			  (common:get-num-cpus remote-host)
			  numcpus-in))
	 (first       (car loadavg))
	 (next        (cadr loadavg))
	 (adjmaxload  (* maxnormload (max 1 numcpus))) ;; possible bug
						   ;; where numcpus
						   ;; (or could be
						   ;; maxload) is
						   ;; zero, crude
						   ;; fallback is to
						   ;; at least use 1
	 ;; effective load accounts for load jumps, this should elminate all the first-next-avg, adjwait, load-jump-limit
	 ;; etc.
	 (effective-load    (common:get-intercept first next))
	 (recommended-delay (common:get-delay effective-load numcpus))
	 (effective-host    (or remote-host "localhost"))
	 (normalized-effective-load (/ effective-load numcpus))
	 (will-wait                 (> normalized-effective-load maxnormload)))
    (if (> recommended-delay 1) 
	(let* ((actual-delay (min recommended-delay 30)))
	  (if (common:low-noise-print 30 (conc (round actual-delay) "-safe-load"))
	      (debug:print-info 0 *default-log-port* "Load control, delaying "
				actual-delay " seconds to maintain safe load. current normalized effective load is "
				normalized-effective-load". maxnormload = " maxnormload " numcpus = " numcpus " loadavg = " loadavg " effective-load = " effective-load))
	  (thread-sleep! actual-delay)))
    
    (cond
     ;; bad data, try again to get the data
     ((not will-wait)
      (if (common:low-noise-print 3600 (conc (round normalized-effective-load) "-load-acceptable-" effective-host))
      	  (debug:print 0 *default-log-port* "Effective load on " effective-host " is acceptable at " effective-load " continuing.")))








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


|







2206
2207
2208
2209
2210
2211
2212
2213
2214
2215

2216
2217
2218




2219

2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
;;   count     - count down to zero, at some point we'd give up if the load never drops
;;   num-tries - count down to zero number tries to get numcpus
;;
(define (common:wait-for-cpuload maxnormload numcpus-in
				 #!key (count 1000)
				 (msg #f)(remote-host #f)(num-tries 5))
  (let* ((loadavg     (common:get-cpu-load remote-host))
    ;; not possible to have zero.  If we get 1, it's possible that we got the previous default, and we should check again
    (numcpus     (if (<= 1 numcpus-in)
    (common:get-num-cpus remote-host) numcpus-in))

    (first       (car loadavg))
    (next        (cadr loadavg))
    (adjmaxload  (* maxnormload (max 1 numcpus))) ;; possible bug where numcpus (or could be maxload) is zero, crude




						  ;; fallback is to at least use 1

    ;; effective load accounts for load jumps, this should elminate all the first-next-avg, adjwait, load-jump-limit
    ;; etc.
    (effective-load    (common:get-intercept first next))
    (recommended-delay (common:get-delay effective-load numcpus))
    (effective-host    (or remote-host "localhost"))
    (normalized-effective-load (/ effective-load numcpus))
    (will-wait                 (> normalized-effective-load maxnormload)))
    (if (and will-wait (> recommended-delay 1)) 
      (let* ((actual-delay (min recommended-delay 30)))
        (if (common:low-noise-print 30 (conc (round actual-delay) "-safe-load"))
          (debug:print-info 0 *default-log-port* "Load control, delaying "
				actual-delay " seconds to maintain safe load. current normalized effective load is "
				normalized-effective-load". maxnormload = " maxnormload " numcpus = " numcpus " loadavg = " loadavg " effective-load = " effective-load))
	(thread-sleep! actual-delay)))
    
    (cond
     ;; bad data, try again to get the data
     ((not will-wait)
      (if (common:low-noise-print 3600 (conc (round normalized-effective-load) "-load-acceptable-" effective-host))
      	  (debug:print 0 *default-log-port* "Effective load on " effective-host " is acceptable at " effective-load " continuing.")))

Modified configf.scm from [15f0835800] to [b768bf346e].

50
51
52
53
54
55
56




57
58
59
60
61
62
63

(define (configf:assoc-safe-add alist key val #!key (metadata #f))
  (let ((newalist (filter (lambda (x)(not (equal? key (car x)))) alist)))
    (append newalist (list (if metadata
			       (list key val metadata)
			       (list key val))))))





(define (configf:section-var-set! cfgdat section-name var value #!key (metadata #f))
  (hash-table-set! cfgdat section-name
		   (configf:assoc-safe-add
		    (hash-table-ref/default cfgdat section-name '())
		    var value metadata: metadata)))

(define (configf:eval-string-in-environment str)







>
>
>
>







50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67

(define (configf:assoc-safe-add alist key val #!key (metadata #f))
  (let ((newalist (filter (lambda (x)(not (equal? key (car x)))) alist)))
    (append newalist (list (if metadata
			       (list key val metadata)
			       (list key val))))))

;; this is used in megatestqa/ext.scm.
;; remove it from here and there by 12/31/21
;; (define config:assoc-safe-add configf:assoc-safe-add)

(define (configf:section-var-set! cfgdat section-name var value #!key (metadata #f))
  (hash-table-set! cfgdat section-name
		   (configf:assoc-safe-add
		    (hash-table-ref/default cfgdat section-name '())
		    var value metadata: metadata)))

(define (configf:eval-string-in-environment str)
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
		       (lambda ()
			 (set! result ((eval (read)) ht))))
		     (set! result (conc "#{(" cmdtype ") "  cmd "}"))))
		(case cmdsym
		  ((system shell scheme)
		   (let ((delta (- (current-seconds) start-time)))
		     (if (> delta 2)
			 (debug:print-info 0 *default-log-port* "for line \"" l "\"\n command:  " cmd " took " delta " seconds to run with output:\n   " result)
			 (debug:print-info 9 *default-log-port* "for line \"" l "\"\n command:  " cmd " took " delta " seconds to run with output:\n   " result)))))
		(loop (conc prestr result poststr)))
	      res))
	res)))

;; Run a shell command and return the output as a string
(define (shell cmd)







|







146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
		       (lambda ()
			 (set! result ((eval (read)) ht))))
		     (set! result (conc "#{(" cmdtype ") "  cmd "}"))))
		(case cmdsym
		  ((system shell scheme)
		   (let ((delta (- (current-seconds) start-time)))
		     (if (> delta 2)
			 (debug:print-info 2 *default-log-port* "for line \"" l "\"\n command:  " cmd " took " delta " seconds to run with output:\n   " result)
			 (debug:print-info 9 *default-log-port* "for line \"" l "\"\n command:  " cmd " took " delta " seconds to run with output:\n   " result)))))
		(loop (conc prestr result poststr)))
	      res))
	res)))

;; Run a shell command and return the output as a string
(define (shell cmd)
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
;; redefines
(define config-lookup configf:lookup)
(define configf:read-file read-config)

;; safely look up a value that is expected to be a number, return
;; a default (#f unless provided)
;;
(define (configf:lookup-number cfdat section varname #!key (default #f))
  (let* ((val (configf:lookup *configdat* section varname))
         (res (if val
                  (string->number (string-substitute "\\s+" "" val #t))
                  #f)))
    (cond
     (res  res)
     (val  (debug:print 0 *default-log-port* "ERROR: no number found for [" section "], " varname ", got: " val))
     (else default))))







|
|







533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
;; redefines
(define config-lookup configf:lookup)
(define configf:read-file read-config)

;; safely look up a value that is expected to be a number, return
;; a default (#f unless provided)
;;
(define (configf:lookup-number cfgdat section varname #!key (default #f))
  (let* ((val (configf:lookup cfgdat section varname))
         (res (if val
                  (string->number (string-substitute "\\s+" "" val #t))
                  #f)))
    (cond
     (res  res)
     (val  (debug:print 0 *default-log-port* "ERROR: no number found for [" section "], " varname ", got: " val))
     (else default))))

Modified db.scm from [ed256dd44f] to [65246b91b8].

4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678

4679
4680
4681
4682
4683
4684
4685
		(loop (car tal)(cdr tal) newr)))))))




;; the new prereqs calculation, looks also at itempath if specified
;; all prereqs must be met
;;    if prereq test with itempath='' is COMPLETED and PASS, WARN, CHECK, or WAIVED then prereq is met
;;    if prereq test with itempath=ref-item-path and COMPLETED with PASS, WARN, CHECK, or WAIVED then prereq is met
;;
;; Note: mode 'normal means that tests must be COMPLETED and ok (i.e. PASS, WARN, CHECK, SKIP or WAIVED)
;;       mode 'toplevel means that tests must be COMPLETED only
;;       mode 'itemmatch or 'itemwait means that tests items must be COMPLETED and (PASS|WARN|WAIVED|CHECK) [[ NB// NOT IMPLEMENTED YET ]]
;;       mode 'exclusive means this test/item cannot run if the same test/item is LAUNCHED,REMOTEHOSTSTART or RUNNING
;;
;; IDEA for consideration:
;;    1. collect all tests "upstream"
;;    2. any NOT completed and good? if yes => return those as prereqs not met, if no => return null list
;; 
;; (define (db:get-prereqs-not-met dbstruct run-id waitons ref-item-path mode)
(define (db:get-prereqs-not-met dbstruct run-id waitons ref-test-name ref-item-path mode itemmaps) ;; #!key (mode '(normal))(itemmap #f))
  ;; BBnote - rollup of an itemized test's overall state/status done in db:set-state-status-and-roll-up-items

  (append
   (if (member 'exclusive mode)
       (let ((running-tests (db:get-tests-for-run dbstruct
						  #f  ;; run-id of #f means for all runs. 
						  (if (string=? ref-item-path "")   ;; testpatt
						      ref-test-name
						      (conc ref-test-name "/" ref-item-path))







|














>







4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
		(loop (car tal)(cdr tal) newr)))))))




;; the new prereqs calculation, looks also at itempath if specified
;; all prereqs must be met
;;    if prereq test with itempath='' is in common:well-ended-states, then prereq is met
;;    if prereq test with itempath=ref-item-path and COMPLETED with PASS, WARN, CHECK, or WAIVED then prereq is met
;;
;; Note: mode 'normal means that tests must be COMPLETED and ok (i.e. PASS, WARN, CHECK, SKIP or WAIVED)
;;       mode 'toplevel means that tests must be COMPLETED only
;;       mode 'itemmatch or 'itemwait means that tests items must be COMPLETED and (PASS|WARN|WAIVED|CHECK) [[ NB// NOT IMPLEMENTED YET ]]
;;       mode 'exclusive means this test/item cannot run if the same test/item is LAUNCHED,REMOTEHOSTSTART or RUNNING
;;
;; IDEA for consideration:
;;    1. collect all tests "upstream"
;;    2. any NOT completed and good? if yes => return those as prereqs not met, if no => return null list
;; 
;; (define (db:get-prereqs-not-met dbstruct run-id waitons ref-item-path mode)
(define (db:get-prereqs-not-met dbstruct run-id waitons ref-test-name ref-item-path mode itemmaps) ;; #!key (mode '(normal))(itemmap #f))
  ;; BBnote - rollup of an itemized test's overall state/status done in db:set-state-status-and-roll-up-items
  (debug:print 4 *default-log-port* "db:get-prereqs-not-met: " waitons)
  (append
   (if (member 'exclusive mode)
       (let ((running-tests (db:get-tests-for-run dbstruct
						  #f  ;; run-id of #f means for all runs. 
						  (if (string=? ref-item-path "")   ;; testpatt
						      ref-test-name
						      (conc ref-test-name "/" ref-item-path))
4698
4699
4700
4701
4702
4703
4704


4705
4706
4707
4708
4709
4710
4711
	;;	(if (equal? (db:test-get-item-path testdat) "")
	;;	    (db:test-get-testname testdat)
	;;	    (conc (db:test-get-testname testdat)
	;;		  "/"
	;;		  (db:test-get-item-path testdat))))
	 running-tests) ;; calling functions want the entire data
       '())



   ;; collection of: for each waiton -
   ;;   if this ref-test-name is an item in an itemized test and mode is itemwait/itemmatch:
   ;;     if waiton is not itemized - if waiton is not both completed and in ok status, add as unmet prerequisite
   ;;     if waiton is itemized:
   ;;           and waiton's items are not expanded, add as unmet prerequisite
   ;;           else if matching waiton item is not both completed and in an ok status, add as unmet prerequisite







>
>







4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
	;;	(if (equal? (db:test-get-item-path testdat) "")
	;;	    (db:test-get-testname testdat)
	;;	    (conc (db:test-get-testname testdat)
	;;		  "/"
	;;		  (db:test-get-item-path testdat))))
	 running-tests) ;; calling functions want the entire data
       '())



   ;; collection of: for each waiton -
   ;;   if this ref-test-name is an item in an itemized test and mode is itemwait/itemmatch:
   ;;     if waiton is not itemized - if waiton is not both completed and in ok status, add as unmet prerequisite
   ;;     if waiton is itemized:
   ;;           and waiton's items are not expanded, add as unmet prerequisite
   ;;           else if matching waiton item is not both completed and in an ok status, add as unmet prerequisite

Modified docs/manual/Makefile from [ec9633c3d9] to [759e8c25e6].

28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46

# design_spec.html : $(SRCFILES) $(CSVFILES)
#         asciidoc -b html5 -a icons -a iconsdir=$(DISPATH)/images/icons -a toc2 design_spec.txt
#

all : server.ps megatest_manual.html client.ps complex-itemmap.png megatest_manual.pdf

megatest_manual.html : megatest_manual.txt  *.txt installation.txt *png
	asciidoc  -b html5 -a icons -a iconsdir=$(DISPATH)/images/icons -a toc2 megatest_manual.txt
#	dos2unix megatest_manual.html

megatest_manual.pdf : megatest_manual.txt *.txt *png
	a2x -a toc -f pdf megatest_manual.txt

server.ps : server.dot
	dot -Tps server.dot > server.ps

client.ps : client.dot
	dot -Tps client.dot > client.ps







|



|







28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46

# design_spec.html : $(SRCFILES) $(CSVFILES)
#         asciidoc -b html5 -a icons -a iconsdir=$(DISPATH)/images/icons -a toc2 design_spec.txt
#

all : server.ps megatest_manual.html client.ps complex-itemmap.png megatest_manual.pdf

megatest_manual.html : megatest_manual.txt  *.txt installation.txt *png *.dot
	asciidoc  -b html5 -a icons -a iconsdir=$(DISPATH)/images/icons -a toc2 megatest_manual.txt
#	dos2unix megatest_manual.html

megatest_manual.pdf : megatest_manual.txt *.txt *png *.dot
	a2x -a toc -f pdf megatest_manual.txt

server.ps : server.dot
	dot -Tps server.dot > server.ps

client.ps : client.dot
	dot -Tps client.dot > client.ps

Added docs/manual/bisecting.dot version [01396be470].































































>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
//  Copyright 2021, Matthew Welland.
// 
// This file is part of Megatest.
// 
//     Megatest is free software: you can redistribute it and/or modify
//     it under the terms of the GNU General Public License as published by
//     the Free Software Foundation, either version 3 of the License, or
//     (at your option) any later version.
// 
//     Megatest is distributed in the hope that it will be useful,
//     but WITHOUT ANY WARRANTY; without even the implied warranty of
//     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
//     GNU General Public License for more details.
// 
//     You should have received a copy of the GNU General Public License
//     along with Megatest.  If not, see <http://www.gnu.org/licenses/>.
//
digraph G {
    rankdir=LR
    subgraph cluster_1 {
        node [style=filled,shape=box];

	B [label="B\nProblem is here"];
	E [label="E\nProblem manifests here"];
	A -> B;
	B -> C;
	C -> D;
	D -> E;
    }

}

Added docs/manual/bisecting.png version [81573d185b].

cannot compute difference between binary files

Added docs/manual/debugging.txt version [731079995f].





















































































































































































































































































































































































































































































































































































































































>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
//  Copyright 2021, Matthew Welland.
// 
// This file is part of Megatest.
// 
//     Megatest is free software: you can redistribute it and/or modify
//     it under the terms of the GNU General Public License as published by
//     the Free Software Foundation, either version 3 of the License, or
//     (at your option) any later version.
// 
//     Megatest is distributed in the hope that it will be useful,
//     but WITHOUT ANY WARRANTY; without even the implied warranty of
//     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
//     GNU General Public License for more details.
// 
//     You should have received a copy of the GNU General Public License
//     along with Megatest.  If not, see <http://www.gnu.org/licenses/>.

Debugging
---------

Well Written Tests
~~~~~~~~~~~~~~~~~~

Test Design and Surfacing Errors
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Design your tests to surface errors. Ensure that all logs are
processed by logpro (or a custom log processing tool) and can be
reached by a mouse click or two from the test control panel.

To illustrate, here is a set of scripts with nested calls where script1.sh calls script2.sh which calls script3.sh which finally calls the Cadence EDA tool virtuoso:

.script1.sh
..............................
#!/bin/bash
code ...
script2.sh some parameters > script2.log
more code ...
..............................

.script2.sh
..............................
#!/bin/bash
code ...
script3.sh some more parameters > script3.log
more code ...
..............................

.script3.sh
..............................
#!/bin/bash
code ...
virtuoso params and switches ...
more code ...
..............................

The log files script2.log, script3.log and the log output from
virtuoso are not accessible from the test control panel. It would be
much better for future users of your automation to use steps more
fully. One easy option would be to post process the logs in downstream
additional steps:

.testconfig
..............................
[ezsteps]
step1 script1.sh
step2 cat script2.log
step3 cat script3.log

[logpro]
step1 ;; some logpro rules
  (expect:required in "LogFileBody" > 0 "Expect this output" #/something expected/)
step2 ;; some logpro rules for script2.sh
step3 ;; some logpro rules for script3.sh

[scripts]
script1.sh #!/bin/bash
 code ...

...
..............................

With the above testconfig the logs for every critical part of the
automation are fully surfaced and rules can be created to flag errors,
warnings, aborts and to ignore false errors. A user of your automation
will be able to see the important error with two mouse clicks from the
runs view.

An even better would be to eliminate the nesting if possible. As a
general statement with layers - less is usually more. By flattening
the automation into a sequence of steps you can use the test control
panel to re-run a step with a single click or from the test xterm run
only the errant step from the command line.

The message here is make debugging and maintenace easy for future
users (and yourself) by keeping clicks-to-error in mind.

Examining The Test Logs and Environment
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Test Control Panel - xterm
^^^^^^^^^^^^^^^^^^^^^^^^^^

From the dashboard click on a test PASS/FAIL button. This brings up a
test control panel. Aproximately near the center left of the window
there is a button "Start Xterm". Push this to get an xterm with the
full context and environment loaded for that test. You can run scripts
or ezsteps by copying from the testconfig (hint, load up the
testconfig in a separate text editor window).

With more recent versions of Megatest you can step through your test
from the test control panel. Click on the cell labeled "rerun this
step" to only rerun the step or click on "restart from here" to rerun
that step and downstream steps.

NOTE 1: visual feedback can take some time, give it a few seconds and
you will see the step change color to blue as it starts running.

NOTE 2: steping through only works if you are using ezsteps.

A word on Bisecting
~~~~~~~~~~~~~~~~~~~

Bisecting is a debug strategy intended to speed up finding the root
cause of some bug.

.A complex process with a problem found in stage "E"
["graphviz", "bisecting.png"]
----------------------------------------------------------------------
include::bisecting.dot[]
----------------------------------------------------------------------

It is common to start debugging where the problem was observed and
then work back. However by inspecting the output at stage "C" in the
example above you would potentially save a lot of debug effort, this
is similar to the feature in source control tools like git and fossil
called biseceting.

Tough Bugs
~~~~~~~~~~

Most bugs in Megatest based automation will be in the scripts called
in your test steps and if you utilize the good design practice
described above should be fairly easy for you to reproduce, isolate
and find.

Some bugs however will come from subtle and hard to detect
interactions between Megatest and your OS and Unix environment. This
includes things like constructed variables that are legal in one
context (e.g. tcsh) but illegal in another context (e.g. bash),
variables that come from your login scripts and access and permissions
issues (e.g. a script that silently fails due to no access to needed
data). Other bugs might be due to Megatest itself.

To isolate bugs like this you may need to look at the log files at
various stages in the execution process of your run and tests.

.A simplified diagram of the stages Megatest goes through to run a test.
["graphviz", "megatest-test-stages.png"]
----------------------------------------------------------------------
include::megatest-test-stages.dot[]
----------------------------------------------------------------------

.How to check variable values and inspect logs at each stage
[width="80%",cols="<,2m,2m",frame="topbot",options="header"]
|======================
|Stage	                    | How to inspect                               | Watch for or try ...
|A: post config processing  | megatest -show-config -target your/target	   | #f (failed var processing)
|B: post runconfig          | megatest -show-runconfig -target your/target | Add -debug 0,9 to see which file your settings come from
|C: processing testconfigs  | inspect output from "megatest -run ..."      | Messages indicating issues process configs, dependency problems
|D: process testconfig for test launch | inspect output from megatest runner | Zero items (items expansion yielded no items)
|E,F: launching test        | start test xterm, look at mt_launch.log      | Did your batch system accept the job? Has the job landed on a machine? 
|G: starting test           | look at your batch systems logs for the process | Did the megatest -execute process start and run? Extract the "megatest -execute ..." command and run it from your xterm.
|H,H1,H2: step exectution   | look at <stepname>.log, <stepname>.html and your own internal logs | Do you have sufficiently tight logpro rules? You must always have a "required" rule! 
|======================

Bisecting megatest.csh/sh
^^^^^^^^^^^^^^^^^^^^^^^^^

Sometimes finding the environment variable that is causing the problem
can be very difficult. Bisection can be applied.

Edit the megatest.csh or megatest.sh file and comment out 50% per
round, source in fresh xterm and run the test.

This idea can also be applied to your .cshrc, .bashrc, .aliases and
other similar files.

csh and -f
^^^^^^^^^^

A common issue when tcsh or csh shells are used for scripting is to
forget or choose to not use -f in your #! line.

.Not good
..............................
#!/bin/tcsh
...
..............................

.Good
..............................
#!/bin/tcsh -f
...
..............................


Config File Processing
^^^^^^^^^^^^^^^^^^^^^^

As described above it is often helpful to know the content of
variables in various contexts as Megatest works through the actions
needed to run your tests. A handy technique is to force the startup of
an xterm in the context being examined.

For example, if an item list is not being generated as expected you
can inject the startup of an xterm as if it were an item:

.Original items table
-----------------
[items]
CELLNAME [system getcellname.sh]
-----------------

.Items table modified for debug
-----------------
[items]
DEBUG [system xterm]
CELLNAME [system getcellnames.sh]
-----------------

When this test is run an xterm will pop up. In that xterm the
environment is exactly that in which the script "getcellnames.sh"
would run. You can now debug the script to find out why it isn't
working as expected.

Similarly in a script just call the xterm.
NOTE: This technique can be very helpful in debugging running of EDA tools in Perl, Ruby, Python or tcl scripts:

.Perl example
..............................
some_code();
$cmdline="virtuoso -some-switches and params ...";
print "$cmdline"; # print the command line so you can paste it into the xterm that pops up
system("xterm");  # this line is added for the debug and removed when done
system($cmdline);
more_code();
..............................

Misc Other Debugging Hints
~~~~~~~~~~~~~~~~~~~~~~~~~~

Annotating scripts and config files
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Run the "env" command to record the environment:

env | sort > stagename.log

In a config file:

.megatest.config, runconfigs.config and testconfig
...................
#{shell env | sort > stagename.log}

# or

[system env | sort > stagename.log]
...................

In scripts just insert the commands, this example helps you identify
if "some commands ..." changed any environment variables.:

.myscript.sh
..............................
env | sort > somefile-before.log
some commands ...
env | sort > somefile-after.log
..............................

.Use meld to examine the differences
..............................
meld somefile-before.log somefile-after.log
..............................

Oneshot Modifying a Variable
^^^^^^^^^^^^^^^^^^^^^^^^^^^^

To try various values for a variable without mutating the current value

.within a bash shell
..............................
SOMEVAR=123 runcmd.sh
..............................

.within csh
..............................
(setenv SOMEVAR 123;runcmd.sh)

# OR

env SOMEVAR=123 runcmd.sh
..............................

Capturing output from a command
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

.Use the "script" utility
..............................
script -c "virtuoso -params and switches ..."
..............................



Modified docs/manual/howto.txt from [5266978039] to [1b987427fd].

108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
[jobtools]
launcher bsub
# if defined and not "no" flexi-launcher will bypass launcher unless there is no
# match.
flexi-launcher yes
------------------------

Tricks
------

This section is a compendium of a various useful tricks for debugging,
configuring and generally getting the most out of Megatest.

Limiting your running jobs
~~~~~~~~~~~~~~~~~~~~~~~~~~

The following example will limit a test in the jobgroup "group1" to no more than 10 tests simultaneously.

In your testconfig:







|
|

|
|







108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
[jobtools]
launcher bsub
# if defined and not "no" flexi-launcher will bypass launcher unless there is no
# match.
flexi-launcher yes
------------------------

Tricks and Tips
---------------

This section is a collection of a various useful tricks for that
didn't quite fit elsewhere.

Limiting your running jobs
~~~~~~~~~~~~~~~~~~~~~~~~~~

The following example will limit a test in the jobgroup "group1" to no more than 10 tests simultaneously.

In your testconfig:
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187

---------------
[jobgroups]
group1 10
custdes 4
---------------

Debugging Tricks
----------------

Examining The Environment
~~~~~~~~~~~~~~~~~~~~~~~~~

Test Control Panel - xterm
^^^^^^^^^^^^^^^^^^^^^^^^^^

From the dashboard click on a test PASS/FAIL button. This brings up a test control panel. Aproximately near the center left of the 
window there is a button "Start Xterm". Push this to get an xterm with the full context and environment loaded for that test. You can run
scripts or ezsteps by copying from the testconfig (hint, load up the testconfig in a separate gvim or emacs window). This is the easiest way
to debug your tests.

During Config File Processing
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

It is often helpful to know the content of variables in various
contexts as Megatest does the actions needed to run your tests. A handy technique is to force the startup of an xterm in the context being examined.

For example, if an item list is not being generated as expected you
can inject the startup of an xterm as if it were an item:

.Original items table
-----------------
[items]
CELLNAME [system getcellname.sh]
-----------------

.Items table modified for debug
-----------------
[items]
DEBUG [system xterm]
CELLNAME [system getcellnames.sh]
-----------------

When this test is run an xterm will pop up. In that xterm the
environment is exactly that in which the script "getcellnames.sh"
would run. You can now debug the script to find out why it isn't
working as expected.

Organising Your Tests and Tasks
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

The default location "tests" for storing tests can be extended by
adding to your tests-paths section.








<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<







134
135
136
137
138
139
140








































141
142
143
144
145
146
147

---------------
[jobgroups]
group1 10
custdes 4
---------------










































Organising Your Tests and Tasks
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

The default location "tests" for storing tests can be extended by
adding to your tests-paths section.

Added docs/manual/megatest-test-stages.dot version [41d7d6e43f].





















































































>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
//  Copyright 2021, Matthew Welland.
// 
// This file is part of Megatest.
// 
//     Megatest is free software: you can redistribute it and/or modify
//     it under the terms of the GNU General Public License as published by
//     the Free Software Foundation, either version 3 of the License, or
//     (at your option) any later version.
// 
//     Megatest is distributed in the hope that it will be useful,
//     but WITHOUT ANY WARRANTY; without even the implied warranty of
//     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
//     GNU General Public License for more details.
// 
//     You should have received a copy of the GNU General Public License
//     along with Megatest.  If not, see <http://www.gnu.org/licenses/>.
//
digraph G {
    // rankdir=LR
    subgraph cluster_1 {
        node [style=filled,shape=box];
	A [label="A: Process megatest.config"]
	B [label="B: Process runconfig.config"]
	A -> B [label="resolve vars"]
	B2 [label="B2: Resolve variables"]
	B -> B2 -> A
	C [label="C: Process testconfigs (find tests to run)"]
	D [label="D: Process testconfig for test of interest"]
	E [label="E: Set vars for launching test"]
	F [label="F: Launch into batch system, ssh, batch system\nand different hosts can all \nimpact variable values"]
	G [label="G: Process testconfig again with all available variables"]
	H [label="H: Start test"]
	H1 [label="H1: Start step"]
	H2 [label="H2: Execute step script"]
	I [label="I: End step, process logfile with logpro"]
	I -> H [label="Run remaining steps"]
	H-> H1 -> H2 -> I
	B->C->D->E->F->G->H
	I->D
    }

}

Added docs/manual/megatest-test-stages.png version [e53ee8abbe].

cannot compute difference between binary files

Modified docs/manual/megatest_manual.html from [a02a70016f] to [e1b85635a3].

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
    along with Megatest.  If not, see &lt;http://www.gnu.org/licenses/&gt;.</pre>
</div></div>
</div>
</div>
<div class="sect1">
<h2 id="_why_megatest">Why Megatest?</h2>
<div class="sectionbody">
<div class="paragraph"><p>The Megatest project was started for two reasons, the first was an
immediate and pressing need for a generalized tool to manage a suite
of regression tests and the second was the fact that I had written or

maintained several such tools at different companies over the years. I
thought a single open source tool, flexible enough to meet the needs
of any team doing continuous integration and or running a complex
suite of tests for release qualification would solve some problems for
me and for others.</p></div>
<div class="literalblock">
<div class="content monospaced">
<pre>-- Matt Welland, original author of the Megatest tool suite.</pre>
</div></div>
</div>
</div>
<div class="sect1">
<h2 id="_megatest_design_philosophy">Megatest Design Philosophy</h2>
<div class="sectionbody">
<div class="paragraph"><p>Megatest is a distributed system intended to provide the minimum needed
resources to make writing a suite of tests and tasks for implementing







|
<
|
>
|
|
|
<
|
<
<
<
<







806
807
808
809
810
811
812
813

814
815
816
817
818

819




820
821
822
823
824
825
826
    along with Megatest.  If not, see &lt;http://www.gnu.org/licenses/&gt;.</pre>
</div></div>
</div>
</div>
<div class="sect1">
<h2 id="_why_megatest">Why Megatest?</h2>
<div class="sectionbody">
<div class="paragraph"><p>Megatest was created to provide a generalized tool for managing suites

of regression tests and to provide a multi-host, distributed
alternative to "make". The EDA world is littered with proprietory,
company-specific tools for this purpose and by going open source and
keeping the tool flexible the hope is that Megatest could be useful to
any team at any company for continuous integration and almost any

other general automation tasks.</p></div>




</div>
</div>
<div class="sect1">
<h2 id="_megatest_design_philosophy">Megatest Design Philosophy</h2>
<div class="sectionbody">
<div class="paragraph"><p>Megatest is a distributed system intended to provide the minimum needed
resources to make writing a suite of tests and tasks for implementing
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
<div class="imageblock">
<div class="content">
<img src="megatest-system-architecture.png" alt="Static">
</div>
</div>
</div>
</div>
</div>
<div class="sect1">
<h2 id="_road_map">Road Map</h2>
<div class="sectionbody">
</div>
</div>
<div class="sect1">
<h2 id="_todo_road_map">TODO / Road Map</h2>
<div class="sectionbody">
<div class="paragraph"><p>Note: This road-map is a wish list and not a formal plan. Items are in
rough priority but are subject to change. Development is driven by
user requests, developer "itch" and bug reports. Please contact







<
<
<
<
<







952
953
954
955
956
957
958





959
960
961
962
963
964
965
<div class="imageblock">
<div class="content">
<img src="megatest-system-architecture.png" alt="Static">
</div>
</div>
</div>
</div>





</div>
<div class="sect1">
<h2 id="_todo_road_map">TODO / Road Map</h2>
<div class="sectionbody">
<div class="paragraph"><p>Note: This road-map is a wish list and not a formal plan. Items are in
rough priority but are subject to change. Development is driven by
user requests, developer "itch" and bug reports. Please contact
1939
1940
1941
1942
1943
1944
1945












































































































































































































































































































1946
1947
1948
1949
1950
1951
1952
reviewed never</pre>
</div></div>
<div class="paragraph"><p>This test runs a single step called "stepname1" which runs a script
"stepname.sh". Note that although it is common to put the actions
needed for a test step into a script it is not necessary.</p></div>
</div>
</div>












































































































































































































































































































</div>
<div class="sect1">
<h2 id="_how_to_do_things">How To Do Things</h2>
<div class="sectionbody">
<div class="sect2">
<h3 id="_process_runs">Process Runs</h3>
<div class="sect3">







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







1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
reviewed never</pre>
</div></div>
<div class="paragraph"><p>This test runs a single step called "stepname1" which runs a script
"stepname.sh". Note that although it is common to put the actions
needed for a test step into a script it is not necessary.</p></div>
</div>
</div>
</div>
<div class="sect1">
<h2 id="_debugging">Debugging</h2>
<div class="sectionbody">
<div class="sect2">
<h3 id="_well_written_tests">Well Written Tests</h3>
<div class="sect3">
<h4 id="_test_design_and_surfacing_errors">Test Design and Surfacing Errors</h4>
<div class="paragraph"><p>Design your tests to surface errors. Ensure that all logs are
processed by logpro (or a custom log processing tool) and can be
reached by a mouse click or two from the test control panel.</p></div>
<div class="paragraph"><p>To illustrate, here is a set of scripts with nested calls where script1.sh calls script2.sh which calls script3.sh which finally calls the Cadence EDA tool virtuoso:</p></div>
<div class="literalblock">
<div class="title">script1.sh</div>
<div class="content monospaced">
<pre>#!/bin/bash
code ...
script2.sh some parameters &gt; script2.log
more code ...</pre>
</div></div>
<div class="literalblock">
<div class="title">script2.sh</div>
<div class="content monospaced">
<pre>#!/bin/bash
code ...
script3.sh some more parameters &gt; script3.log
more code ...</pre>
</div></div>
<div class="literalblock">
<div class="title">script3.sh</div>
<div class="content monospaced">
<pre>#!/bin/bash
code ...
virtuoso params and switches ...
more code ...</pre>
</div></div>
<div class="paragraph"><p>The log files script2.log, script3.log and the log output from
virtuoso are not accessible from the test control panel. It would be
much better for future users of your automation to use steps more
fully. One easy option would be to post process the logs in downstream
additional steps:</p></div>
<div class="literalblock">
<div class="title">testconfig</div>
<div class="content monospaced">
<pre>[ezsteps]
step1 script1.sh
step2 cat script2.log
step3 cat script3.log

[logpro]
step1 ;; some logpro rules
  (expect:required in "LogFileBody" &gt; 0 "Expect this output" #/something expected/)
step2 ;; some logpro rules for script2.sh
step3 ;; some logpro rules for script3.sh

[scripts]
script1.sh #!/bin/bash
 code ...

...</pre>
</div></div>
<div class="paragraph"><p>With the above testconfig the logs for every critical part of the
automation are fully surfaced and rules can be created to flag errors,
warnings, aborts and to ignore false errors. A user of your automation
will be able to see the important error with two mouse clicks from the
runs view.</p></div>
<div class="paragraph"><p>An even better would be to eliminate the nesting if possible. As a
general statement with layers - less is usually more. By flattening
the automation into a sequence of steps you can use the test control
panel to re-run a step with a single click or from the test xterm run
only the errant step from the command line.</p></div>
<div class="paragraph"><p>The message here is make debugging and maintenace easy for future
users (and yourself) by keeping clicks-to-error in mind.</p></div>
</div>
</div>
<div class="sect2">
<h3 id="_examining_the_test_logs_and_environment">Examining The Test Logs and Environment</h3>
<div class="sect3">
<h4 id="_test_control_panel_xterm">Test Control Panel - xterm</h4>
<div class="paragraph"><p>From the dashboard click on a test PASS/FAIL button. This brings up a
test control panel. Aproximately near the center left of the window
there is a button "Start Xterm". Push this to get an xterm with the
full context and environment loaded for that test. You can run scripts
or ezsteps by copying from the testconfig (hint, load up the
testconfig in a separate text editor window).</p></div>
<div class="paragraph"><p>With more recent versions of Megatest you can step through your test
from the test control panel. Click on the cell labeled "rerun this
step" to only rerun the step or click on "restart from here" to rerun
that step and downstream steps.</p></div>
<div class="paragraph"><p>NOTE 1: visual feedback can take some time, give it a few seconds and
you will see the step change color to blue as it starts running.</p></div>
<div class="paragraph"><p>NOTE 2: steping through only works if you are using ezsteps.</p></div>
</div>
</div>
<div class="sect2">
<h3 id="_a_word_on_bisecting">A word on Bisecting</h3>
<div class="paragraph"><p>Bisecting is a debug strategy intended to speed up finding the root
cause of some bug.</p></div>
<div class="imageblock graphviz">
<div class="content">
<img src="bisecting.png" alt="bisecting.png">
</div>
<div class="title">Figure 1. A complex process with a problem found in stage "E"</div>
</div>
<div class="paragraph"><p>It is common to start debugging where the problem was observed and
then work back. However by inspecting the output at stage "C" in the
example above you would potentially save a lot of debug effort, this
is similar to the feature in source control tools like git and fossil
called biseceting.</p></div>
</div>
<div class="sect2">
<h3 id="_tough_bugs">Tough Bugs</h3>
<div class="paragraph"><p>Most bugs in Megatest based automation will be in the scripts called
in your test steps and if you utilize the good design practice
described above should be fairly easy for you to reproduce, isolate
and find.</p></div>
<div class="paragraph"><p>Some bugs however will come from subtle and hard to detect
interactions between Megatest and your OS and Unix environment. This
includes things like constructed variables that are legal in one
context (e.g. tcsh) but illegal in another context (e.g. bash),
variables that come from your login scripts and access and permissions
issues (e.g. a script that silently fails due to no access to needed
data). Other bugs might be due to Megatest itself.</p></div>
<div class="paragraph"><p>To isolate bugs like this you may need to look at the log files at
various stages in the execution process of your run and tests.</p></div>
<div class="imageblock graphviz">
<div class="content">
<img src="megatest-test-stages.png" alt="megatest-test-stages.png">
</div>
<div class="title">Figure 2. A simplified diagram of the stages Megatest goes through to run a test.</div>
</div>
<table class="tableblock frame-topbot grid-all"
style="
width:80%;
">
<caption class="title">Table 2. How to check variable values and inspect logs at each stage</caption>
<col style="width:20%;">
<col style="width:40%;">
<col style="width:40%;">
<thead>
<tr>
<th class="tableblock halign-left valign-top" >Stage                      </th>
<th class="tableblock halign-left valign-top" > How to inspect                               </th>
<th class="tableblock halign-left valign-top" > Watch for or try &#8230;</th>
</tr>
</thead>
<tbody>
<tr>
<td class="tableblock halign-left valign-top" ><p class="tableblock">A: post config processing</p></td>
<td class="tableblock halign-left valign-top" ><p class="tableblock monospaced">megatest -show-config -target your/target</p></td>
<td class="tableblock halign-left valign-top" ><p class="tableblock monospaced">#f (failed var processing)</p></td>
</tr>
<tr>
<td class="tableblock halign-left valign-top" ><p class="tableblock">B: post runconfig</p></td>
<td class="tableblock halign-left valign-top" ><p class="tableblock monospaced">megatest -show-runconfig -target your/target</p></td>
<td class="tableblock halign-left valign-top" ><p class="tableblock monospaced">Add -debug 0,9 to see which file your settings come from</p></td>
</tr>
<tr>
<td class="tableblock halign-left valign-top" ><p class="tableblock">C: processing testconfigs</p></td>
<td class="tableblock halign-left valign-top" ><p class="tableblock monospaced">inspect output from "megatest -run &#8230;"</p></td>
<td class="tableblock halign-left valign-top" ><p class="tableblock monospaced">Messages indicating issues process configs, dependency problems</p></td>
</tr>
<tr>
<td class="tableblock halign-left valign-top" ><p class="tableblock">D: process testconfig for test launch</p></td>
<td class="tableblock halign-left valign-top" ><p class="tableblock monospaced">inspect output from megatest runner</p></td>
<td class="tableblock halign-left valign-top" ><p class="tableblock monospaced">Zero items (items expansion yielded no items)</p></td>
</tr>
<tr>
<td class="tableblock halign-left valign-top" ><p class="tableblock">E,F: launching test</p></td>
<td class="tableblock halign-left valign-top" ><p class="tableblock monospaced">start test xterm, look at mt_launch.log</p></td>
<td class="tableblock halign-left valign-top" ><p class="tableblock monospaced">Did your batch system accept the job? Has the job landed on a machine?</p></td>
</tr>
<tr>
<td class="tableblock halign-left valign-top" ><p class="tableblock">G: starting test</p></td>
<td class="tableblock halign-left valign-top" ><p class="tableblock monospaced">look at your batch systems logs for the process</p></td>
<td class="tableblock halign-left valign-top" ><p class="tableblock monospaced">Did the megatest -execute process start and run? Extract the "megatest -execute &#8230;" command and run it from your xterm.</p></td>
</tr>
<tr>
<td class="tableblock halign-left valign-top" ><p class="tableblock">H,H1,H2: step exectution</p></td>
<td class="tableblock halign-left valign-top" ><p class="tableblock monospaced">look at &lt;stepname&gt;.log, &lt;stepname&gt;.html and your own internal logs</p></td>
<td class="tableblock halign-left valign-top" ><p class="tableblock monospaced">Do you have sufficiently tight logpro rules? You must always have a "required" rule!</p></td>
</tr>
</tbody>
</table>
<div class="sect3">
<h4 id="_bisecting_megatest_csh_sh">Bisecting megatest.csh/sh</h4>
<div class="paragraph"><p>Sometimes finding the environment variable that is causing the problem
can be very difficult. Bisection can be applied.</p></div>
<div class="paragraph"><p>Edit the megatest.csh or megatest.sh file and comment out 50% per
round, source in fresh xterm and run the test.</p></div>
<div class="paragraph"><p>This idea can also be applied to your .cshrc, .bashrc, .aliases and
other similar files.</p></div>
</div>
<div class="sect3">
<h4 id="_csh_and_f">csh and -f</h4>
<div class="paragraph"><p>A common issue when tcsh or csh shells are used for scripting is to
forget or choose to not use -f in your #! line.</p></div>
<div class="literalblock">
<div class="title">Not good</div>
<div class="content monospaced">
<pre>#!/bin/tcsh
...</pre>
</div></div>
<div class="literalblock">
<div class="title">Good</div>
<div class="content monospaced">
<pre>#!/bin/tcsh -f
...</pre>
</div></div>
</div>
<div class="sect3">
<h4 id="_config_file_processing">Config File Processing</h4>
<div class="paragraph"><p>As described above it is often helpful to know the content of
variables in various contexts as Megatest works through the actions
needed to run your tests. A handy technique is to force the startup of
an xterm in the context being examined.</p></div>
<div class="paragraph"><p>For example, if an item list is not being generated as expected you
can inject the startup of an xterm as if it were an item:</p></div>
<div class="listingblock">
<div class="title">Original items table</div>
<div class="content monospaced">
<pre>[items]
CELLNAME [system getcellname.sh]</pre>
</div></div>
<div class="listingblock">
<div class="title">Items table modified for debug</div>
<div class="content monospaced">
<pre>[items]
DEBUG [system xterm]
CELLNAME [system getcellnames.sh]</pre>
</div></div>
<div class="paragraph"><p>When this test is run an xterm will pop up. In that xterm the
environment is exactly that in which the script "getcellnames.sh"
would run. You can now debug the script to find out why it isn&#8217;t
working as expected.</p></div>
<div class="paragraph"><p>Similarly in a script just call the xterm.
NOTE: This technique can be very helpful in debugging running of EDA tools in Perl, Ruby, Python or tcl scripts:</p></div>
<div class="literalblock">
<div class="title">Perl example</div>
<div class="content monospaced">
<pre>some_code();
$cmdline="virtuoso -some-switches and params ...";
print "$cmdline"; # print the command line so you can paste it into the xterm that pops up
system("xterm");  # this line is added for the debug and removed when done
system($cmdline);
more_code();</pre>
</div></div>
</div>
</div>
<div class="sect2">
<h3 id="_misc_other_debugging_hints">Misc Other Debugging Hints</h3>
<div class="sect3">
<h4 id="_annotating_scripts_and_config_files">Annotating scripts and config files</h4>
<div class="paragraph"><p>Run the "env" command to record the environment:</p></div>
<div class="paragraph"><p>env | sort &gt; stagename.log</p></div>
<div class="paragraph"><p>In a config file:</p></div>
<div class="literalblock">
<div class="title">megatest.config, runconfigs.config and testconfig</div>
<div class="content monospaced">
<pre>#{shell env | sort &gt; stagename.log}

# or

[system env | sort &gt; stagename.log]</pre>
</div></div>
<div class="paragraph"><p>In scripts just insert the commands, this example helps you identify
if "some commands &#8230;" changed any environment variables.:</p></div>
<div class="literalblock">
<div class="title">myscript.sh</div>
<div class="content monospaced">
<pre>env | sort &gt; somefile-before.log
some commands ...
env | sort &gt; somefile-after.log</pre>
</div></div>
<div class="literalblock">
<div class="title">Use meld to examine the differences</div>
<div class="content monospaced">
<pre>meld somefile-before.log somefile-after.log</pre>
</div></div>
</div>
<div class="sect3">
<h4 id="_oneshot_modifying_a_variable">Oneshot Modifying a Variable</h4>
<div class="paragraph"><p>To try various values for a variable without mutating the current value</p></div>
<div class="literalblock">
<div class="title">within a bash shell</div>
<div class="content monospaced">
<pre>SOMEVAR=123 runcmd.sh</pre>
</div></div>
<div class="literalblock">
<div class="title">within csh</div>
<div class="content monospaced">
<pre>(setenv SOMEVAR 123;runcmd.sh)

# OR

env SOMEVAR=123 runcmd.sh</pre>
</div></div>
</div>
</div>
</div>
</div>
<div class="sect1">
<h2 id="_how_to_do_things">How To Do Things</h2>
<div class="sectionbody">
<div class="sect2">
<h3 id="_process_runs">Process Runs</h3>
<div class="sect3">
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
# match.
flexi-launcher yes</pre>
</div></div>
</div>
</div>
</div>
<div class="sect1">
<h2 id="_tricks">Tricks</h2>
<div class="sectionbody">
<div class="paragraph"><p>This section is a compendium of a various useful tricks for debugging,
configuring and generally getting the most out of Megatest.</p></div>
<div class="sect2">
<h3 id="_limiting_your_running_jobs">Limiting your running jobs</h3>
<div class="paragraph"><p>The following example will limit a test in the jobgroup "group1" to no more than 10 tests simultaneously.</p></div>
<div class="paragraph"><p>In your testconfig:</p></div>
<div class="listingblock">
<div class="content monospaced">
<pre>[test_meta]
jobgroup group1</pre>
</div></div>
<div class="paragraph"><p>In your megatest.config:</p></div>
<div class="listingblock">
<div class="content monospaced">
<pre>[jobgroups]
group1 10
custdes 4</pre>
</div></div>
</div>
</div>
</div>
<div class="sect1">
<h2 id="_debugging_tricks">Debugging Tricks</h2>
<div class="sectionbody">
<div class="sect2">
<h3 id="_examining_the_environment">Examining The Environment</h3>
<div class="sect3">
<h4 id="_test_control_panel_xterm">Test Control Panel - xterm</h4>
<div class="paragraph"><p>From the dashboard click on a test PASS/FAIL button. This brings up a test control panel. Aproximately near the center left of the
window there is a button "Start Xterm". Push this to get an xterm with the full context and environment loaded for that test. You can run
scripts or ezsteps by copying from the testconfig (hint, load up the testconfig in a separate gvim or emacs window). This is the easiest way
to debug your tests.</p></div>
</div>
<div class="sect3">
<h4 id="_during_config_file_processing">During Config File Processing</h4>
<div class="paragraph"><p>It is often helpful to know the content of variables in various
contexts as Megatest does the actions needed to run your tests. A handy technique is to force the startup of an xterm in the context being examined.</p></div>
<div class="paragraph"><p>For example, if an item list is not being generated as expected you
can inject the startup of an xterm as if it were an item:</p></div>
<div class="listingblock">
<div class="title">Original items table</div>
<div class="content monospaced">
<pre>[items]
CELLNAME [system getcellname.sh]</pre>
</div></div>
<div class="listingblock">
<div class="title">Items table modified for debug</div>
<div class="content monospaced">
<pre>[items]
DEBUG [system xterm]
CELLNAME [system getcellnames.sh]</pre>
</div></div>
<div class="paragraph"><p>When this test is run an xterm will pop up. In that xterm the
environment is exactly that in which the script "getcellnames.sh"
would run. You can now debug the script to find out why it isn&#8217;t
working as expected.</p></div>
</div>
<div class="sect3">
<h4 id="_organising_your_tests_and_tasks">Organising Your Tests and Tasks</h4>
<div class="paragraph"><p>The default location "tests" for storing tests can be extended by
adding to your tests-paths section.</p></div>
<div class="listingblock">
<div class="content monospaced">
<pre>[misc]







|

|
|
















<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<







2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350







































2351
2352
2353
2354
2355
2356
2357
# match.
flexi-launcher yes</pre>
</div></div>
</div>
</div>
</div>
<div class="sect1">
<h2 id="_tricks_and_tips">Tricks and Tips</h2>
<div class="sectionbody">
<div class="paragraph"><p>This section is a collection of a various useful tricks for that
didn&#8217;t quite fit elsewhere.</p></div>
<div class="sect2">
<h3 id="_limiting_your_running_jobs">Limiting your running jobs</h3>
<div class="paragraph"><p>The following example will limit a test in the jobgroup "group1" to no more than 10 tests simultaneously.</p></div>
<div class="paragraph"><p>In your testconfig:</p></div>
<div class="listingblock">
<div class="content monospaced">
<pre>[test_meta]
jobgroup group1</pre>
</div></div>
<div class="paragraph"><p>In your megatest.config:</p></div>
<div class="listingblock">
<div class="content monospaced">
<pre>[jobgroups]
group1 10
custdes 4</pre>
</div></div>







































<div class="sect3">
<h4 id="_organising_your_tests_and_tasks">Organising Your Tests and Tasks</h4>
<div class="paragraph"><p>The default location "tests" for storing tests can be extended by
adding to your tests-paths section.</p></div>
<div class="listingblock">
<div class="content monospaced">
<pre>[misc]
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
<div class="sectionbody">
<div class="sect2">
<h3 id="_megatest_use_modes">Megatest Use Modes</h3>
<table class="tableblock frame-topbot grid-all"
style="
width:80%;
">
<caption class="title">Table 2. Base commands</caption>
<col style="width:20%;">
<col style="width:40%;">
<col style="width:40%;">
<thead>
<tr>
<th class="tableblock halign-center valign-top" >Use case                </th>
<th class="tableblock halign-left valign-top" > Megatest command     </th>







|







2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
<div class="sectionbody">
<div class="sect2">
<h3 id="_megatest_use_modes">Megatest Use Modes</h3>
<table class="tableblock frame-topbot grid-all"
style="
width:80%;
">
<caption class="title">Table 3. Base commands</caption>
<col style="width:20%;">
<col style="width:40%;">
<col style="width:40%;">
<thead>
<tr>
<th class="tableblock halign-center valign-top" >Use case                </th>
<th class="tableblock halign-left valign-top" > Megatest command     </th>
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
<div class="sect2">
<h3 id="_config_file_helpers">Config File Helpers</h3>
<div class="paragraph"><p>Various helpers for more advanced config files.</p></div>
<table class="tableblock frame-topbot grid-all"
style="
width:80%;
">
<caption class="title">Table 3. Helpers</caption>
<col style="width:14%;">
<col style="width:28%;">
<col style="width:28%;">
<col style="width:28%;">
<thead>
<tr>
<th class="tableblock halign-center valign-top" >Helper                      </th>







|







2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
<div class="sect2">
<h3 id="_config_file_helpers">Config File Helpers</h3>
<div class="paragraph"><p>Various helpers for more advanced config files.</p></div>
<table class="tableblock frame-topbot grid-all"
style="
width:80%;
">
<caption class="title">Table 4. Helpers</caption>
<col style="width:14%;">
<col style="width:28%;">
<col style="width:28%;">
<col style="width:28%;">
<thead>
<tr>
<th class="tableblock halign-center valign-top" >Helper                      </th>
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
</div>
<div class="sect2">
<h3 id="_database_settings">Database settings</h3>
<table class="tableblock frame-topbot grid-all"
style="
width:70%;
">
<caption class="title">Table 4. Database config settings in [setup] section of megatest.config</caption>
<col style="width:14%;">
<col style="width:28%;">
<col style="width:28%;">
<col style="width:28%;">
<thead>
<tr>
<th class="tableblock halign-center valign-top" >Var                       </th>







|







2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
</div>
<div class="sect2">
<h3 id="_database_settings">Database settings</h3>
<table class="tableblock frame-topbot grid-all"
style="
width:70%;
">
<caption class="title">Table 5. Database config settings in [setup] section of megatest.config</caption>
<col style="width:14%;">
<col style="width:28%;">
<col style="width:28%;">
<col style="width:28%;">
<thead>
<tr>
<th class="tableblock halign-center valign-top" >Var                       </th>
3006
3007
3008
3009
3010
3011
3012




3013
3014
3015
3016
3017
3018
3019

[logpro]
lookittmp ;; Note: config file format supports multi-line entries where leading whitespace is removed from each line
  ;;     a blank line indicates the end of the block of text
  (expect:required in "LogFileBody" &gt; 0 "A file name that should never exist!" #/This is a awfully stupid file name that should never be found in the temp dir/)</pre>
</div></div>
<div class="paragraph"><p>To transfer the environment to the next step you can do the following:</p></div>




<div class="listingblock">
<div class="title">Propagate environment to next step</div>
<div class="content monospaced">
<pre>$MT_MEGATEST -env2file .ezsteps/${stepname}</pre>
</div></div>
</div>
<div class="sect2">







>
>
>
>







3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274

[logpro]
lookittmp ;; Note: config file format supports multi-line entries where leading whitespace is removed from each line
  ;;     a blank line indicates the end of the block of text
  (expect:required in "LogFileBody" &gt; 0 "A file name that should never exist!" #/This is a awfully stupid file name that should never be found in the temp dir/)</pre>
</div></div>
<div class="paragraph"><p>To transfer the environment to the next step you can do the following:</p></div>
# if your upstream file is csh you can force csh like this
# if your upstream is bash
loadenv     source $REF/ourenviron.sh

<div class="listingblock">
<div class="title">Propagate environment to next step</div>
<div class="content monospaced">
<pre>$MT_MEGATEST -env2file .ezsteps/${stepname}</pre>
</div></div>
</div>
<div class="sect2">
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
but since triggers can be called in various contexts not all variables are
available at all times. The trigger script should check for the variable and
fail gracefully if it doesn&#8217;t exist.</p></div>
<table class="tableblock frame-topbot grid-all"
style="
width:90%;
">
<caption class="title">Table 5. Environment variables visible to the trigger script</caption>
<col style="width:50%;">
<col style="width:50%;">
<thead>
<tr>
<th class="tableblock halign-left valign-top" > Variable            </th>
<th class="tableblock halign-left valign-top" > Purpose</th>
</tr>







|







3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
but since triggers can be called in various contexts not all variables are
available at all times. The trigger script should check for the variable and
fail gracefully if it doesn&#8217;t exist.</p></div>
<table class="tableblock frame-topbot grid-all"
style="
width:90%;
">
<caption class="title">Table 6. Environment variables visible to the trigger script</caption>
<col style="width:50%;">
<col style="width:50%;">
<thead>
<tr>
<th class="tableblock halign-left valign-top" > Variable            </th>
<th class="tableblock halign-left valign-top" > Purpose</th>
</tr>
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
<h2 id="_programming_api">Programming API</h2>
<div class="sectionbody">
<div class="paragraph"><p>These routines can be called from the megatest repl.</p></div>
<table class="tableblock frame-topbot grid-all"
style="
width:70%;
">
<caption class="title">Table 6. API Keys Related Calls</caption>
<col style="width:14%;">
<col style="width:28%;">
<col style="width:28%;">
<col style="width:28%;">
<thead>
<tr>
<th class="tableblock halign-center valign-top" >API Call                        </th>







|







3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
<h2 id="_programming_api">Programming API</h2>
<div class="sectionbody">
<div class="paragraph"><p>These routines can be called from the megatest repl.</p></div>
<table class="tableblock frame-topbot grid-all"
style="
width:70%;
">
<caption class="title">Table 7. API Keys Related Calls</caption>
<col style="width:14%;">
<col style="width:28%;">
<col style="width:28%;">
<col style="width:28%;">
<thead>
<tr>
<th class="tableblock halign-center valign-top" >API Call                        </th>

Added docs/manual/megatest_manual.pdf version [8fe19d594b].

cannot compute difference between binary files

Modified docs/manual/megatest_manual.txt from [cb5cc67576] to [5b54398387].

31
32
33
34
35
36
37
38
39
40

41
42
43
44
45
46
47
48
49
50
51
52
53
54
    along with Megatest.  If not, see <http://www.gnu.org/licenses/>.

----------------------------

Why Megatest?
-------------

The Megatest project was started for two reasons, the first was an
immediate and pressing need for a generalized tool to manage a suite
of regression tests and the second was the fact that I had written or

maintained several such tools at different companies over the years. I
thought a single open source tool, flexible enough to meet the needs
of any team doing continuous integration and or running a complex
suite of tests for release qualification would solve some problems for
me and for others.

 -- Matt Welland, original author of the Megatest tool suite.

Megatest Design Philosophy
--------------------------

Megatest is a distributed system intended to provide the minimum needed
resources to make writing a suite of tests and tasks for implementing
continuous build for software, design engineering or process control (via







<
|
|
>
|
|
|
<
<
|
<







31
32
33
34
35
36
37

38
39
40
41
42
43


44

45
46
47
48
49
50
51
    along with Megatest.  If not, see <http://www.gnu.org/licenses/>.

----------------------------

Why Megatest?
-------------


Megatest was created to provide a generalized tool for managing suites
of regression tests and to provide a multi-host, distributed
alternative to "make". The EDA world is littered with proprietory,
company-specific tools for this purpose and by going open source and
keeping the tool flexible the hope is that Megatest could be useful to
any team at any company for continuous integration and almost any


other general automation tasks.


Megatest Design Philosophy
--------------------------

Megatest is a distributed system intended to provide the minimum needed
resources to make writing a suite of tests and tasks for implementing
continuous build for software, design engineering or process control (via
96
97
98
99
100
101
102


103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
Tests are launched using the launching system available for the
distributed compute platform in use. A template script is provided
which can launch jobs on local and remote Linux hosts. Currently
megatest uses the network filesystem to call home to your master
sqlite3 database. Megatest has been used with the Intel Netbatch and
lsf (also known as openlava) batch systems and it should be
straightforward to use it with other similar systems.



include::overview.txt[]

include::plan.txt[]

include::installation.txt[]

include::getting_started.txt[]

include::study_plan.txt[]

// :leveloffset: 0

include::writing_tests.txt[]

include::howto.txt[]

include::reference.txt[]

include::testplan.txt[]








>
>




|






|

|







93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
Tests are launched using the launching system available for the
distributed compute platform in use. A template script is provided
which can launch jobs on local and remote Linux hosts. Currently
megatest uses the network filesystem to call home to your master
sqlite3 database. Megatest has been used with the Intel Netbatch and
lsf (also known as openlava) batch systems and it should be
straightforward to use it with other similar systems.

// :leveloffset: 0

include::overview.txt[]

include::plan.txt[]
 
include::installation.txt[]

include::getting_started.txt[]

include::study_plan.txt[]

include::writing_tests.txt[]

include::debugging.txt[]

include::howto.txt[]

include::reference.txt[]

include::testplan.txt[]

Modified docs/manual/plan.txt from [84407a87ee] to [5f519e210f].

1
2
3
4
5
6
7
8
9
10
Road Map
--------

// This file is part of Megatest.
// 
//     Megatest is free software: you can redistribute it and/or modify
//     it under the terms of the GNU General Public License as published by
//     the Free Software Foundation, either version 3 of the License, or
//     (at your option) any later version.
// 
<
<
<










1
2
3
4
5
6
7



// This file is part of Megatest.
// 
//     Megatest is free software: you can redistribute it and/or modify
//     it under the terms of the GNU General Public License as published by
//     the Free Software Foundation, either version 3 of the License, or
//     (at your option) any later version.
// 

Modified docs/manual/reference.txt from [6aa04b6eea] to [7adc3533c3].

203
204
205
206
207
208
209

















210
211
212
213
214
215
216

-----------------
[setup]
# this will automatically kill the test if it runs for more than 1h 2m and 3s
runtimelim 1h 2m 3s
-----------------


















Tests browser view
~~~~~~~~~~~~~~~~~~

The tests browser (see the Run Control tab on the dashboard) has two views for displaying the tests. 

. Dot (graphviz) based tree
. No dot, plain listing







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







203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233

-----------------
[setup]
# this will automatically kill the test if it runs for more than 1h 2m and 3s
runtimelim 1h 2m 3s
-----------------

Post Run Hook
+++++++++++++

This runs script to-run.sh after all tests have been completed. It is
not necessary to use -run-wait as each test will check for other
running tests on completion and if there are none it will call the
post run hook.

Note that the output from the script call will be placed in a log file
in the logs directory with a file name derived by replacing / with _
in post-hook-<target>-<runname>.log.

-------------------
[runs]
post-hook /path/to/script/to-run.sh
-------------------

Tests browser view
~~~~~~~~~~~~~~~~~~

The tests browser (see the Run Control tab on the dashboard) has two views for displaying the tests. 

. Dot (graphviz) based tree
. No dot, plain listing
718
719
720
721
722
723
724




725
726
727
728
729
730
731
lookittmp ;; Note: config file format supports multi-line entries where leading whitespace is removed from each line
  ;;     a blank line indicates the end of the block of text 
  (expect:required in "LogFileBody" > 0 "A file name that should never exist!" #/This is a awfully stupid file name that should never be found in the temp dir/)

-----------------

To transfer the environment to the next step you can do the following:





.Propagate environment to next step
----------------------------
$MT_MEGATEST -env2file .ezsteps/${stepname}	  
----------------------------

Scripts







>
>
>
>







735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
lookittmp ;; Note: config file format supports multi-line entries where leading whitespace is removed from each line
  ;;     a blank line indicates the end of the block of text 
  (expect:required in "LogFileBody" > 0 "A file name that should never exist!" #/This is a awfully stupid file name that should never be found in the temp dir/)

-----------------

To transfer the environment to the next step you can do the following:
# if your upstream file is csh you can force csh like this
# if your upstream is bash 
loadenv     source $REF/ourenviron.sh


.Propagate environment to next step
----------------------------
$MT_MEGATEST -env2file .ezsteps/${stepname}	  
----------------------------

Scripts

Added docs/megatest-debug-tutorial.odp version [bfd2483cd2].

cannot compute difference between binary files

Modified ezsteps.scm from [5de5d166c7] to [0c12b39167].

102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
     (lambda () ;; (process-run "/bin/bash" "-c" "exec ls -l /tmp/foobar > /tmp/delme-more.log 2>&1")
       (let* ((cmd (conc stepcmd " > " stepname ".log 2>&1")) ;; >outfile 2>&1 
	      (pid #f))
	 (let ((proc (lambda ()
		       (set! pid (process-run "/bin/bash" (list "-c" cmd))))))
	   (if subrun
               (begin
                 (debug:print-info 0 *default-log-port* "Running without MT_.* environment variables.")
                 (common:without-vars proc "^MT_.*"))
	       (proc)))
	 
         (with-output-to-file "Makefile.ezsteps"
           (lambda ()
             (print stepname ".log :")
             (print "\t" cmd)







|







102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
     (lambda () ;; (process-run "/bin/bash" "-c" "exec ls -l /tmp/foobar > /tmp/delme-more.log 2>&1")
       (let* ((cmd (conc stepcmd " > " stepname ".log 2>&1")) ;; >outfile 2>&1 
	      (pid #f))
	 (let ((proc (lambda ()
		       (set! pid (process-run "/bin/bash" (list "-c" cmd))))))
	   (if subrun
               (begin
                 (debug:print-info 0 *default-log-port* "Running "cmd" without MT_.* environment variables.")
                 (common:without-vars proc "^MT_.*"))
	       (proc)))
	 
         (with-output-to-file "Makefile.ezsteps"
           (lambda ()
             (print stepname ".log :")
             (print "\t" cmd)

Modified launch.scm from [7e65ac64d4] to [b55ae6d40b].

157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177


178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
	;; 3. fix target
	;; 4. fix runname
	;; 5. fix testpatt or calculate it from contour
	;; 6. launch the run
	;; 7. roll up the run result and or roll up the logpro processed result
	(when (configf:lookup testconfig "subrun" "runwait") ;; we use runwait as the flag that a subrun is requested
            (subrun:initialize-toprun-test testconfig test-run-dir)
	    (let* ((mt-cmd (subrun:launch-cmd test-run-dir)))
              (debug:print-info 0 *default-log-port* "Subrun command is \"" mt-cmd "\"")
              (set! ezsteps #t) ;; set the needed flag
	      (set! ezstepslst
                    (append (or ezstepslst '())
                            (list (list "subrun" (conc "{subrun=true} " mt-cmd)))))))

	;; process the ezsteps
	(if ezsteps
	    (let* ((all-steps-dat (make-hash-table))) ;; keep all the info around as stepname ==> alist; where  'params is the params list (add other stuff as needed)
	      (if (not (common:file-exists? ".ezsteps"))(create-directory ".ezsteps"))
	      ;; if ezsteps was defined then we are sure to have at least one step but check anyway
	      (if (not (> (length ezstepslst) 0))
		  (debug:print-error 0 *default-log-port* "ezsteps defined but ezstepslst is zero length")


		  (let loop ((ezstep (car ezstepslst))
			     (tal    (cdr ezstepslst))
			     (prevstep #f))
                    (debug:print-info 0 *default-log-port* "Processing ezstep \"" (string-intersperse ezstep " ") "\"")
		    ;; check exit-info (vector-ref exit-info 1)
		    (if (launch:einf-exit-status exit-info) ;; (vector-ref exit-info 1)
			(let* ((logpro-used (launch:runstep ezstep run-id test-id exit-info m tal testconfig all-steps-dat))
			       (stepname    (car ezstep))
			       (stepparms   (hash-table-ref all-steps-dat stepname)))
			  (setenv "MT_STEP_NAME" stepname)
			  (pp (hash-table->alist all-steps-dat))
			  ;; if logpro-used read in the stepname.dat file
			  (if (and logpro-used (common:file-exists? (conc stepname ".dat")))
			      (launch:load-logpro-dat run-id test-id stepname))
			  (if (steprun-good? logpro-used (launch:einf-exit-code exit-info) stepparms)
			      (if (not (null? tal))
				  (loop (car tal) (cdr tal) stepname))
			      (debug:print 0 *default-log-port* "WARNING: step " (car ezstep) " failed. Stopping")))
			(debug:print 0 *default-log-port* "WARNING: a prior step failed, stopping at " ezstep)))))))))

(define (launch:monitor-job run-id test-id item-path fullrunscript ezsteps test-name tconfigreg exit-info m work-area runtlim misc-flags)
  (let* ((update-period (string->number (or (configf:lookup *configdat* "setup" "test-stats-update-period") "30")))
         (start-seconds (current-seconds))
	 (calc-minutes  (lambda ()
			  (inexact->exact 
			   (round 







|













>
>
|

















|







157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
	;; 3. fix target
	;; 4. fix runname
	;; 5. fix testpatt or calculate it from contour
	;; 6. launch the run
	;; 7. roll up the run result and or roll up the logpro processed result
	(when (configf:lookup testconfig "subrun" "runwait") ;; we use runwait as the flag that a subrun is requested
            (subrun:initialize-toprun-test testconfig test-run-dir)
	    (let* ((mt-cmd (subrun:launch-cmd test-run-dir (configf:lookup testconfig "subrun" "runwait"))))
              (debug:print-info 0 *default-log-port* "Subrun command is \"" mt-cmd "\"")
              (set! ezsteps #t) ;; set the needed flag
	      (set! ezstepslst
                    (append (or ezstepslst '())
                            (list (list "subrun" (conc "{subrun=true} " mt-cmd)))))))

	;; process the ezsteps
	(if ezsteps
	    (let* ((all-steps-dat (make-hash-table))) ;; keep all the info around as stepname ==> alist; where  'params is the params list (add other stuff as needed)
	      (if (not (common:file-exists? ".ezsteps"))(create-directory ".ezsteps"))
	      ;; if ezsteps was defined then we are sure to have at least one step but check anyway
	      (if (not (> (length ezstepslst) 0))
		  (debug:print-error 0 *default-log-port* "ezsteps defined but ezstepslst is zero length")
                  (let ((all-step-names (map car ezstepslst)))
		   (setenv "MT_STEP_NAMES" (string-intersperse all-step-names " "))
		   (let loop ((ezstep (car ezstepslst))
			     (tal    (cdr ezstepslst))
			     (prevstep #f))
                    (debug:print-info 0 *default-log-port* "Processing ezstep \"" (string-intersperse ezstep " ") "\"")
		    ;; check exit-info (vector-ref exit-info 1)
		    (if (launch:einf-exit-status exit-info) ;; (vector-ref exit-info 1)
			(let* ((logpro-used (launch:runstep ezstep run-id test-id exit-info m tal testconfig all-steps-dat))
			       (stepname    (car ezstep))
			       (stepparms   (hash-table-ref all-steps-dat stepname)))
			  (setenv "MT_STEP_NAME" stepname)
			  (pp (hash-table->alist all-steps-dat))
			  ;; if logpro-used read in the stepname.dat file
			  (if (and logpro-used (common:file-exists? (conc stepname ".dat")))
			      (launch:load-logpro-dat run-id test-id stepname))
			  (if (steprun-good? logpro-used (launch:einf-exit-code exit-info) stepparms)
			      (if (not (null? tal))
				  (loop (car tal) (cdr tal) stepname))
			      (debug:print 0 *default-log-port* "WARNING: step " (car ezstep) " failed. Stopping")))
			(debug:print 0 *default-log-port* "WARNING: a prior step failed, stopping at " ezstep))))))))))

(define (launch:monitor-job run-id test-id item-path fullrunscript ezsteps test-name tconfigreg exit-info m work-area runtlim misc-flags)
  (let* ((update-period (string->number (or (configf:lookup *configdat* "setup" "test-stats-update-period") "30")))
         (start-seconds (current-seconds))
	 (calc-minutes  (lambda ()
			  (inexact->exact 
			   (round 
474
475
476
477
478
479
480
481
482
483

484
485
486
487
488
489
490

491
492
493
494
495
496
497
498

              (rmt:general-call 'set-test-start-time #f test-id)
              (rmt:test-set-state-status run-id test-id "REMOTEHOSTSTART" "n/a" #f)
	      ) ;; prime it for running
	     ((member (db:test-get-state test-info) '("RUNNING" "REMOTEHOSTSTART"))
	      (if (process:alive-on-host? test-host test-pid)
		  (debug:print-error 0 *default-log-port* "test state is "  (db:test-get-state test-info) " and process " test-pid " is still running on host " test-host ", cannot proceed")
		  (exit)))
	     ((member (db:test-get-state test-info) '("COMPLETED"))  ;; we do NOT want to re-run COMPLETED jobs. Mark as NOT_STARTED to run!
	      (debug:print-error 0 *default-log-port* "test state is " (db:test-get-state test-info) ", cannot proceed")

	      (exit))
	     ((not (member (db:test-get-state test-info) '("REMOVING" "REMOTEHOSTSTART" "RUNNING" "KILLREQ")))
	      ;; (tests:test-force-state-status! run-id test-id "REMOTEHOSTSTART" "n/a")
              (rmt:general-call 'set-test-start-time #f test-id)
	      (rmt:test-set-state-status run-id test-id "REMOTEHOSTSTART" "n/a" #f))
	     (else ;; (member (db:test-get-state test-info) '("REMOVING" "REMOTEHOSTSTART" "RUNNING" "KILLREQ"))
	      (debug:print-error 0 *default-log-port* "test state is " (db:test-get-state test-info) ", cannot proceed")

	      (exit))))

          ;; cleanup prior execution's steps
          (rmt:delete-steps-for-test! run-id test-id)
          
	  (debug:print 2 *default-log-port* "Executing " test-name " (id: " test-id ") on " (get-host-name))
	  (set! keys       (rmt:get-keys))
	  ;; (runs:set-megatest-env-vars run-id inkeys: keys inkeyvals: keyvals) ;; these may be needed by the launching process







|

|
>
|





|
>
|







476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502

              (rmt:general-call 'set-test-start-time #f test-id)
              (rmt:test-set-state-status run-id test-id "REMOTEHOSTSTART" "n/a" #f)
	      ) ;; prime it for running
	     ((member (db:test-get-state test-info) '("RUNNING" "REMOTEHOSTSTART"))
	      (if (process:alive-on-host? test-host test-pid)
		  (debug:print-error 0 *default-log-port* "test state is "  (db:test-get-state test-info) " and process " test-pid " is still running on host " test-host ", cannot proceed")
		  (exit 1)))
	     ((member (db:test-get-state test-info) '("COMPLETED"))  ;; we do NOT want to re-run COMPLETED jobs. Mark as NOT_STARTED to run!
	      (debug:print 0 *default-log-port* "test state is " (db:test-get-state test-info) ", cannot proceed")
	      (debug:print 0 *default-log-port* "exiting with status 1")
	      (exit 1))
	     ((not (member (db:test-get-state test-info) '("REMOVING" "REMOTEHOSTSTART" "RUNNING" "KILLREQ")))
	      ;; (tests:test-force-state-status! run-id test-id "REMOTEHOSTSTART" "n/a")
              (rmt:general-call 'set-test-start-time #f test-id)
	      (rmt:test-set-state-status run-id test-id "REMOTEHOSTSTART" "n/a" #f))
	     (else ;; (member (db:test-get-state test-info) '("REMOVING" "REMOTEHOSTSTART" "RUNNING" "KILLREQ"))
	      (debug:print 0 *default-log-port* "test state is " (db:test-get-state test-info) ", cannot proceed")
	      (debug:print 0 *default-log-port* "exiting with status 1")
	      (exit 1))))

          ;; cleanup prior execution's steps
          (rmt:delete-steps-for-test! run-id test-id)
          
	  (debug:print 2 *default-log-port* "Executing " test-name " (id: " test-id ") on " (get-host-name))
	  (set! keys       (rmt:get-keys))
	  ;; (runs:set-megatest-env-vars run-id inkeys: keys inkeyvals: keyvals) ;; these may be needed by the launching process
641
642
643
644
645
646
647
648

649
650
651
652
653
654
655
656
657
658
659
660
661
662





663
664
665
666
667

668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692

693
694
695
696
697
698
699
700
701
702
703
704
705


706

707
708
709
710
711
712
713

714
715
716
717













718
719
720
721
722
723
724
		       (with-output-to-file name
			 (lambda ()
			   (print content)
			   (change-file-mode name (bitwise-ior perm/irwxg perm/irwxu)))))
		      (else
		       (debug:print-info 0 "Invalid script definiton found in [scripts] section of testconfig. \"" scriptdat "\""))))
	     scripts))
	  ;; 

	  (let* ((m            (make-mutex))
		 (kill-job?    #f)
		 (exit-info    (make-launch:einf pid: #t exit-status: #t exit-code: #t rollup-status: 0)) ;; pid exit-status exit-code (i.e. process was successfully run) rollup-status
		 (job-thread   #f)
		 ;; (keep-going   #t)
		 (misc-flags   (let ((ht (make-hash-table)))
				 (hash-table-set! ht 'keep-going #t)
				 ht))
		 (runit        (lambda ()
				 (launch:manage-steps run-id test-id item-path fullrunscript ezsteps subrun test-name tconfigreg exit-info m)))
		 (monitorjob   (lambda ()
				 (launch:monitor-job  run-id test-id item-path fullrunscript ezsteps test-name tconfigreg exit-info m work-area runtlim misc-flags)))
		 (th1          (make-thread monitorjob "monitor job"))
		 (th2          (make-thread runit "run job")))





	    (set! job-thread th2)
	    (thread-start! th1)
	    (thread-start! th2)
	    (thread-join! th2)
	    (debug:print-info 0 *default-log-port* "Megatest exectute of test " test-name ", item path " item-path " complete. Notifying the db ...")

	    (hash-table-set! misc-flags 'keep-going #f)
	    (thread-join! th1)
	    (thread-sleep! 1)       ;; givbe thread th1 a chance to be done TODO: Verify this is needed. At 0.1 I was getting fail to stop, increased to total of 1.1 sec.
	    (mutex-lock! m)
	    (let* ((item-path (item-list->path itemdat))
		   ;; only state and status needed - use lazy routine
		   (testinfo  (rmt:get-testinfo-state-status run-id test-id)))
	      ;; Am I completed?
	      (if (member (db:test-get-state testinfo) '("REMOTEHOSTSTART" "RUNNING")) ;; NOTE: It should *not* be REMOTEHOSTSTART but for reasons I don't yet understand it sometimes gets stuck in that state ;; (not (equal? (db:test-get-state testinfo) "COMPLETED"))
		  (let ((new-state  (if kill-job? "KILLED" "COMPLETED") ;; (if (eq? (vector-ref exit-info 2) 0) ;; exited with "good" status
				                                        ;; "COMPLETED"							                ;; (db:test-get-state testinfo)))   ;; else preseve the state as set within the test
				    )
			(new-status (cond
				     ((not (launch:einf-exit-status exit-info)) "FAIL") ;; job failed to run ... (vector-ref exit-info 1)
				     ((eq? (launch:einf-rollup-status exit-info) 0)     ;; (vector-ref exit-info 3)
				      ;; if the current status is AUTO then defer to the calculated value (i.e. leave this AUTO)
				      (if (equal? (db:test-get-status testinfo) "AUTO") "AUTO" "PASS"))
				     ((eq? (launch:einf-rollup-status exit-info) 1) "FAIL")  ;; (vector-ref exit-info 3)
				     ((eq? (launch:einf-rollup-status exit-info) 2)	     ;;	(vector-ref exit-info 3)
				      ;; if the current status is AUTO the defer to the calculated value but qualify (i.e. make this AUTO-WARN)
				      (if (equal? (db:test-get-status testinfo) "AUTO") "AUTO-WARN" "WARN"))
				     ((eq? (launch:einf-rollup-status exit-info) 3) "CHECK")
				     ((eq? (launch:einf-rollup-status exit-info) 4) "WAIVED")
				     ((eq? (launch:einf-rollup-status exit-info) 5) "ABORT")
				     ((eq? (launch:einf-rollup-status exit-info) 6) "SKIP")

				     (else "FAIL")))) ;; (db:test-get-status testinfo)))
		    (debug:print-info 1 *default-log-port* "Test exited in state=" (db:test-get-state testinfo) ", setting state/status based on exit code of " (launch:einf-exit-status exit-info) " and rollup-status of " (launch:einf-rollup-status exit-info))
   
        ;; Leave a .final-status file for each sub-test
        (tests:save-final-status run-id test-id)

		    (tests:test-set-status! run-id 
					    test-id 
					    new-state
					    new-status
					    (args:get-arg "-m") #f)
		    ;; need to update the top test record if PASS or FAIL and this is a subtest
		    ;; NO NEED TO CALL set-state-status-and-roll-up-items HERE, THIS IS DONE IN set-state-status-and-roll-up-items called by tests:test-set-status!


		    ))

	      ;; for automated creation of the rollup html file this is a good place...
	      (if (not (equal? item-path ""))
		      (tests:summarize-items run-id test-id test-name #f))
	      (tests:summarize-test run-id test-id)  ;; don't force - just update if no
        ;; Leave a .final-status file for the top level test
        (tests:save-final-status run-id test-id)
	      (rmt:update-run-stats run-id (rmt:get-raw-run-stats run-id)))

	    (mutex-unlock! m)
            (launch:end-of-run-check run-id )
	    (debug:print 2 *default-log-port* "Output from running " fullrunscript ", pid " (launch:einf-pid exit-info) " in work area " 
			 work-area ":\n====\n exit code " (launch:einf-exit-code exit-info) "\n" "====\n")













	    (if (not (launch:einf-exit-status exit-info))
		(exit 4))))
        )))

;; Spec for End of test
;; At end of each test call, after marking self as COMPLETED do run-state-status-rollup
;; At transition to run COMPLETED/X do hooks







|
>













|
>
>
>
>
>




|
>








|
|
<
<
|












>
|
|

|
|








>
>
|
>




|
|
|
>




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







645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688


689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
		       (with-output-to-file name
			 (lambda ()
			   (print content)
			   (change-file-mode name (bitwise-ior perm/irwxg perm/irwxu)))))
		      (else
		       (debug:print-info 0 "Invalid script definiton found in [scripts] section of testconfig. \"" scriptdat "\""))))
	     scripts))
	  ;;

	  (let* ((m            (make-mutex))
		 (kill-job?    #f)
		 (exit-info    (make-launch:einf pid: #t exit-status: #t exit-code: #t rollup-status: 0)) ;; pid exit-status exit-code (i.e. process was successfully run) rollup-status
		 (job-thread   #f)
		 ;; (keep-going   #t)
		 (misc-flags   (let ((ht (make-hash-table)))
				 (hash-table-set! ht 'keep-going #t)
				 ht))
		 (runit        (lambda ()
				 (launch:manage-steps run-id test-id item-path fullrunscript ezsteps subrun test-name tconfigreg exit-info m)))
		 (monitorjob   (lambda ()
				 (launch:monitor-job  run-id test-id item-path fullrunscript ezsteps test-name tconfigreg exit-info m work-area runtlim misc-flags)))
		 (th1          (make-thread monitorjob "monitor job"))
		 (th2          (make-thread runit "run job"))
                 (tconfig         (tests:get-testconfig test-name item-path tconfigreg #t))
                 (propagate-exit-code (configf:lookup *configdat* "setup" "propagate-exit-code"))
                 (propagate-status-list '("FAIL" "KILLED" "ABORT" "DEAD" "CHECK" "SKIP" "WAIVED"))
                 (test-status "not set")
                 )
	    (set! job-thread th2)
	    (thread-start! th1)
	    (thread-start! th2)
	    (thread-join! th2)
	    (debug:print-info 0 *default-log-port* "Megatest execute of test " test-name ", item path " item-path " complete. Notifying the db ...")
            (debug:print-info 2 *default-log-port* "exit-info = " exit-info)
	    (hash-table-set! misc-flags 'keep-going #f)
	    (thread-join! th1)
	    (thread-sleep! 1)       ;; givbe thread th1 a chance to be done TODO: Verify this is needed. At 0.1 I was getting fail to stop, increased to total of 1.1 sec.
	    (mutex-lock! m)
	    (let* ((item-path (item-list->path itemdat))
		   ;; only state and status needed - use lazy routine
		   (testinfo  (rmt:get-testinfo-state-status run-id test-id)))
	      ;; Am I completed?
	      (if (member (db:test-get-state testinfo) '("REMOTEHOSTSTART" "RUNNING"))
                 (let ((new-state  (if kill-job? "KILLED" "COMPLETED"))


		        (new-status (cond
				     ((not (launch:einf-exit-status exit-info)) "FAIL") ;; job failed to run ... (vector-ref exit-info 1)
				     ((eq? (launch:einf-rollup-status exit-info) 0)     ;; (vector-ref exit-info 3)
				      ;; if the current status is AUTO then defer to the calculated value (i.e. leave this AUTO)
				      (if (equal? (db:test-get-status testinfo) "AUTO") "AUTO" "PASS"))
				     ((eq? (launch:einf-rollup-status exit-info) 1) "FAIL")  ;; (vector-ref exit-info 3)
				     ((eq? (launch:einf-rollup-status exit-info) 2)	     ;;	(vector-ref exit-info 3)
				      ;; if the current status is AUTO the defer to the calculated value but qualify (i.e. make this AUTO-WARN)
				      (if (equal? (db:test-get-status testinfo) "AUTO") "AUTO-WARN" "WARN"))
				     ((eq? (launch:einf-rollup-status exit-info) 3) "CHECK")
				     ((eq? (launch:einf-rollup-status exit-info) 4) "WAIVED")
				     ((eq? (launch:einf-rollup-status exit-info) 5) "ABORT")
				     ((eq? (launch:einf-rollup-status exit-info) 6) "SKIP")
				     (else "FAIL")))
                        ) ;; (db:test-get-status testinfo)))
		    (debug:print-info 0 *default-log-port* "Test exited in state=" (db:test-get-state testinfo) ", setting state/status based on exit code of " (launch:einf-exit-status exit-info) " and rollup-status of " (launch:einf-rollup-status exit-info))
   
                    ;; Leave a .final-status file for each sub-test
                    (tests:save-final-status run-id test-id)

		    (tests:test-set-status! run-id 
					    test-id 
					    new-state
					    new-status
					    (args:get-arg "-m") #f)
		    ;; need to update the top test record if PASS or FAIL and this is a subtest
		    ;; NO NEED TO CALL set-state-status-and-roll-up-items HERE, THIS IS DONE IN set-state-status-and-roll-up-items called by tests:test-set-status!
		 )
              )


	      ;; for automated creation of the rollup html file this is a good place...
	      (if (not (equal? item-path ""))
		      (tests:summarize-items run-id test-id test-name #f))
	      (tests:summarize-test run-id test-id)  ;; don't force - just update if no
              ;; Leave a .final-status file for the top level test
              (tests:save-final-status run-id test-id)
	      (rmt:update-run-stats run-id (rmt:get-raw-run-stats run-id))) ;; end of let*

	    (mutex-unlock! m)
            (launch:end-of-run-check run-id )
	    (debug:print 2 *default-log-port* "Output from running " fullrunscript ", pid " (launch:einf-pid exit-info) " in work area " 
			 work-area ":\n====\n exit code " (launch:einf-exit-code exit-info) "\n" "====\n")


            (set! test-status (db:test-get-status (rmt:get-testinfo-state-status run-id test-id)))

            ;; If the propagate-exit-code option has been set in the megatest config, and the test status matches the list, set the exit code to 1.

            (if (and propagate-exit-code (string=? propagate-exit-code "yes") (member test-status propagate-status-list))
               (begin
                (debug:print 1 *default-log-port* "Setting exit status to 1 because of test status of " test-status) 
                (set! *globalexitstatus* 1)
               )
            )

	    (if (not (launch:einf-exit-status exit-info))
		(exit 4))))
        )))

;; Spec for End of test
;; At end of each test call, after marking self as COMPLETED do run-state-status-rollup
;; At transition to run COMPLETED/X do hooks
766
767
768
769
770
771
772
773
774

775
776
777
778
779
780
781
782
783
784















785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
       (if (> (length not-completed-tests) 0) 
           (let loop ((running-test (car not-completed-tests))
			     (tal    (cdr not-completed-tests)))
		       (let* ((test-name (vector-ref running-test 2))
                 (item-path (vector-ref running-test 11)))
			       	(debug:print 0 *default-log-port* "test " test-name "/" item-path " not completed")
              (if (not (null? tal))
				  (loop (car tal) (cdr tal)))))))))))        
 

(define (launch:is-test-alive host pid)
  (if (and host pid (not (equal? host "n/a")))
      (let* ((cmd (conc "ssh " host " pstree -A " pid))
	     (output (with-input-from-pipe cmd read-lines)))
	(debug:print 2 *default-log-port* "Running " cmd " received " output)
	(if (eq? (length output) 0)
	   #f
	   #t))
      #t))
 















(define (launch:kill-tests-if-dead run-id)
  (let* ((running-tests (rmt:get-tests-for-run run-id "%" `("RUNNING" "LAUNCHED" "REMOTEHOSTSTART") `() #f #f #f #f #f #f #f #f)))
       (let loop ((running-test (car running-tests))
			     (tal    (cdr running-tests))
			     (kill-cnt 0))
		       (let* ((test-name (vector-ref running-test 2))
                 (item-path (vector-ref running-test 11))
								 (test-id (vector-ref running-test 0))
                 (host (vector-ref running-test 6))
                 (pid  (rmt:test-get-top-process-pid run-id test-id))   
                 (event-time (vector-ref running-test 5))
                 (duration (vector-ref running-test 12))
                 (flag 0)   
                 (curr-time (current-seconds)))
       (if (and (< (+ event-time duration 600) curr-time) (not (launch:is-test-alive host pid))) ;;test has not updated duration in last 10 min then likely its not running but confirm before marking it as killed







|
|
>
|








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







|







793
794
795
796
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
       (if (> (length not-completed-tests) 0) 
           (let loop ((running-test (car not-completed-tests))
			     (tal    (cdr not-completed-tests)))
		       (let* ((test-name (vector-ref running-test 2))
                 (item-path (vector-ref running-test 11)))
			       	(debug:print 0 *default-log-port* "test " test-name "/" item-path " not completed")
              (if (not (null? tal))
		  (loop (car tal) (cdr tal)))))))))))

;; replaced below with version that does not ssh if checking on localhost
#;(define (launch:is-test-alive host pid)
  (if (and host pid (not (equal? host "n/a")))
      (let* ((cmd (conc "ssh " host " pstree -A " pid))
	     (output (with-input-from-pipe cmd read-lines)))
	(debug:print 2 *default-log-port* "Running " cmd " received " output)
	(if (eq? (length output) 0)
	   #f
	   #t))
      #t))

(define (launch:is-test-alive host pid)
  (let* ((same-host (equal? host (get-host-name)))
	 (cmd (conc 
	       (if same-host "" (conc "ssh "host" "))
	       "pstree -A "pid)))
    (if (and host pid
	     (not (equal? host "n/a")))
	
	(let* ((output (with-input-from-pipe cmd read-lines)))
	  (debug:print 2 *default-log-port* "Running " cmd " received " output)
	  (if (eq? (length output) 0)
	      #f
	      #t))
	#t))) ;; assuming bad query is about a live test is likely not the right thing to do?

(define (launch:kill-tests-if-dead run-id)
  (let* ((running-tests (rmt:get-tests-for-run run-id "%" `("RUNNING" "LAUNCHED" "REMOTEHOSTSTART") `() #f #f #f #f #f #f #f #f)))
       (let loop ((running-test (car running-tests))
			     (tal    (cdr running-tests))
			     (kill-cnt 0))
		       (let* ((test-name (vector-ref running-test 2))
                 (item-path (vector-ref running-test 11))
		 (test-id (vector-ref running-test 0))
                 (host (vector-ref running-test 6))
                 (pid  (rmt:test-get-top-process-pid run-id test-id))   
                 (event-time (vector-ref running-test 5))
                 (duration (vector-ref running-test 12))
                 (flag 0)   
                 (curr-time (current-seconds)))
       (if (and (< (+ event-time duration 600) curr-time) (not (launch:is-test-alive host pid))) ;;test has not updated duration in last 10 min then likely its not running but confirm before marking it as killed
1511
1512
1513
1514
1515
1516
1517


1518
1519
1520
1521
1522
1523
1524
					(list 'target    mt_target)
					(list 'contour   contour)
					(list 'runtlim   (if run-time-limit (common:hms-string->seconds run-time-limit) #f))
					(list 'env-ovrd  (hash-table-ref/default *configdat* "env-override" '())) 
					(list 'set-vars  (if params (hash-table-ref/default params "-setvars" #f)))
					(list 'runname   runname)
					(list 'mt-bindir-path mt-bindir-path))))))))


      
      ;; clean out step records from previous run if they exist
      ;; (rmt:delete-test-step-records run-id test-id)
      ;; if the dir does not exist we may have a itempath where individual variables are a path, launch anyway
      (if (common:file-exists? work-area)
	  (change-directory work-area)) ;; so that log files from the launch process don't clutter the test dir
      (cond







>
>







1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
					(list 'target    mt_target)
					(list 'contour   contour)
					(list 'runtlim   (if run-time-limit (common:hms-string->seconds run-time-limit) #f))
					(list 'env-ovrd  (hash-table-ref/default *configdat* "env-override" '())) 
					(list 'set-vars  (if params (hash-table-ref/default params "-setvars" #f)))
					(list 'runname   runname)
					(list 'mt-bindir-path mt-bindir-path))))))))

        (setenv "MT_CMDINFO" cmdparms)  ;; setting this for use in nblauncher
      
      ;; clean out step records from previous run if they exist
      ;; (rmt:delete-test-step-records run-id test-id)
      ;; if the dir does not exist we may have a itempath where individual variables are a path, launch anyway
      (if (common:file-exists? work-area)
	  (change-directory work-area)) ;; so that log files from the launch process don't clutter the test dir
      (cond

Modified megatest-version.scm from [f92dc46346] to [5941e8f016].

16
17
18
19
20
21
22
23
;;     along with Megatest.  If not, see <http://www.gnu.org/licenses/>.

;; Always use two or four digit decimal
;; 1.01, 1.02...1.10,1.11,1.1101 ... 1.99,2.00..

;; (declare (unit megatest-version))

(define megatest-version 1.6584)







|
16
17
18
19
20
21
22
23
;;     along with Megatest.  If not, see <http://www.gnu.org/licenses/>.

;; Always use two or four digit decimal
;; 1.01, 1.02...1.10,1.11,1.1101 ... 1.99,2.00..

;; (declare (unit megatest-version))

(define megatest-version 1.6589)

Modified mtut.scm from [ead30f316f] to [413cf26858].

152
153
154
155
156
157
158

159
160
161
162
163
164
165

Queries:
   show [areas|contours... ] : show areas, contours or other section from megatest.config
   gendot                    : generate a graphviz dot file from pkts.

Contour actions:
   process                   : runs import, rungen and dispatch 

			     
Trigger propagation actions:
   tsend a=b,c=d...          : send trigger info to all recpients in the [listeners] section
   tlisten -port N           : listen for trigger info on port N
			     
Selectors 		     
  -immediate                 : apply this action immediately, default is to queue up actions







>







152
153
154
155
156
157
158
159
160
161
162
163
164
165
166

Queries:
   show [areas|contours... ] : show areas, contours or other section from megatest.config
   gendot                    : generate a graphviz dot file from pkts.

Contour actions:
   process                   : runs import, rungen and dispatch 
   go                        : runs import, rungen and dispatch every five minutes forever
			     
Trigger propagation actions:
   tsend a=b,c=d...          : send trigger info to all recpients in the [listeners] section
   tlisten -port N           : listen for trigger info on port N
			     
Selectors 		     
  -immediate                 : apply this action immediately, default is to queue up actions
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
			    (handle-exceptions
				exn
				(begin
				  (print-call-chain)
				  (print "FAILED TO RUN RUNNAME MAPPER " callname " FOR AREA " area)
				  (print " message: " ((condition-property-accessor 'exn 'message) exn))
				  runname)
			      (print "(mapper " (string-intersperse (list runkey runname area area-path reason contour mode-patt) ", ") ")")
			      (mapper runkey runname area area-path reason contour mode-patt))
			    (case callname
			      ((auto #f) runname)
			      (else   runtrans)))))
	 (new-target     target) ;; I believe we will want target manipulation here .. (map-targets xlatr-key runkey area contour))
	 (actual-action  (if action
			     (if (equal? action "sync-prepend")







|







772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
			    (handle-exceptions
				exn
				(begin
				  (print-call-chain)
				  (print "FAILED TO RUN RUNNAME MAPPER " callname " FOR AREA " area)
				  (print " message: " ((condition-property-accessor 'exn 'message) exn))
				  runname)
			      (print "(mapper " (string-intersperse (map conc (list runkey runname area area-path reason contour mode-patt)) ", ") ")")
			      (mapper runkey runname area area-path reason contour mode-patt))
			    (case callname
			      ((auto #f) runname)
			      (else   runtrans)))))
	 (new-target     target) ;; I believe we will want target manipulation here .. (map-targets xlatr-key runkey area contour))
	 (actual-action  (if action
			     (if (equal? action "sync-prepend")
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
	 ;;    (if (not (member key *legal-params*))
	 ;; 	(hash-table-delete! adjargs key))) ;; we need to delete any params intended for mtutil
	 ;;  (hash-table-keys adjargs))
	 (let-values (((uuid pkt)
		       (command-line->pkt *action* adjargs #f area-path: area-path new-ss: new-ss)))
           (print "run log @ " (conc (current-directory) "/" uuid "-" *action* ".log"))
	   (write-pkt pktsdir uuid pkt))))
      ((dispatch import rungen process)
       (let* ((mtconfdat (simple-setup (args:get-arg "-start-dir")))
	      (mtconf    (car mtconfdat))
	      (toppath   (configf:lookup mtconf "scratchdat" "toppath")))



	 (case (string->symbol *action*)
	   ((process)  (begin
			 (common:load-pkts-to-db mtconf)
			 (generate-run-pkts mtconf toppath)
			 (common:load-pkts-to-db mtconf)
			 (dispatch-commands mtconf toppath)))
	   ((import)   (common:load-pkts-to-db mtconf)) ;; import pkts
	   ((rungen)   (generate-run-pkts mtconf toppath))
	   ((dispatch) (dispatch-commands mtconf toppath)))))












































      ;; misc
      ((show)
       (if (> (length remargs) 0)
	   (let* ((mtconfdat (simple-setup (args:get-arg "-start-dir")))
		  (mtconf    (car mtconfdat))
		  (sect-dat (configf:get-section mtconf (car remargs))))
	     (if sect-dat







|


|
>
>
>








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







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
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
	 ;;    (if (not (member key *legal-params*))
	 ;; 	(hash-table-delete! adjargs key))) ;; we need to delete any params intended for mtutil
	 ;;  (hash-table-keys adjargs))
	 (let-values (((uuid pkt)
		       (command-line->pkt *action* adjargs #f area-path: area-path new-ss: new-ss)))
           (print "run log @ " (conc (current-directory) "/" uuid "-" *action* ".log"))
	   (write-pkt pktsdir uuid pkt))))
      ((dispatch import rungen process go)
       (let* ((mtconfdat (simple-setup (args:get-arg "-start-dir")))
	      (mtconf    (car mtconfdat))
	      (toppath   (configf:lookup mtconf "scratchdat" "toppath"))
	      (period    (configf:lookup-number mtconf "mtutil" "autorun-period" default: 300))
	      (rest-time (configf:lookup-number mtconf "mtutil" "autorun-rest"   default: 30)))
	 (print "Using period="period" and rest time="rest-time)
	 (case (string->symbol *action*)
	   ((process)  (begin
			 (common:load-pkts-to-db mtconf)
			 (generate-run-pkts mtconf toppath)
			 (common:load-pkts-to-db mtconf)
			 (dispatch-commands mtconf toppath)))
	   ((import)   (common:load-pkts-to-db mtconf)) ;; import pkts
	   ((rungen)   (generate-run-pkts mtconf toppath))
	   ((dispatch) (dispatch-commands mtconf toppath))
	   ;; [mtutil]
	   ;; # approximate interval between run processing in mtutil (seconds)
	   ;; autorun-period 300
	   ;; # minimal rest period between processing 
	   ;; autorun-rest   30
	   ((go)
	    ;; determine if I'm the boss
	    (if (file-exists? "mtutil-go.pid")
		(begin
		  (print "ERROR: mtutil go is already running under host and pid " (with-input-from-file "mtutil-go.pid" read-line)
			 ". Please kill that process and remove the file \"mutil-go.pid\" and try again.")
		  (exit)))
	    (with-output-to-file "mtutil-go.pid" (lambda ()(print (get-host-name) " " (current-process-id))))
	    (print "Starting long running import, rungen, and process loop")
	    (if (file-exists? "do-not-run-mtutil-go")
		(begin
		  (print "NOTE: Removing flag file "(current-directory)"/do-not-run-mtutil-go")
		  (delete-file* "do-not-run-mtutil-go")))
	    (let loop ((last-run (- (current-seconds) (+ period 10))) ;; fake out first time in 
		       (this-run (current-seconds)))
	      (if (file-exists? "do-not-run-mtutil-go")
		  (begin
		    (print "File do-not-run-mtutil-go exists, exiting.")
		    (delete-file* "mtutil-go.pid")
		    (exit)))
	      (let ((delta (- this-run last-run)))
		(if (>= delta period)
		    (let* ((mtconfdat (simple-setup (args:get-arg "-start-dir")))
			   (mtconf    (car mtconfdat)))
		      (print "Running import at " (current-seconds))
		      (common:load-pkts-to-db mtconf)
		      (print "Running generate run pkts at " (current-seconds))
		      (generate-run-pkts mtconf toppath)
		      (print "Running run dispatch at " (current-seconds))
		      (common:load-pkts-to-db mtconf)
		      (dispatch-commands mtconf toppath)
		      (print "Done running import, generate, and dispatch done in " (- (current-seconds) this-run))
		      (print "NOTE: touch " (current-directory) "/do-not-run-mtutil-go to kill this runner.")
		      (loop this-run (current-seconds)))
		    (let ((now (current-seconds)))
		      (print "Sleeping " rest-time " seconds, next run in aproximately " (- period (- now last-run)) " seconds")
		      (thread-sleep! rest-time)
		      (loop last-run (current-seconds))))))
	    (delete-file* "mtutil-go.pid")))))
      ;; misc
      ((show)
       (if (> (length remargs) 0)
	   (let* ((mtconfdat (simple-setup (args:get-arg "-start-dir")))
		  (mtconf    (car mtconfdat))
		  (sect-dat (configf:get-section mtconf (car remargs))))
	     (if sect-dat
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831

1832
1833

1834

1835


1836
1837
1838
1839
1840

1841

1842


1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
                                   )

                                  )

                                )))
                           (loop (nn-recv rep))))
		       (print "ERROR: Port " portnum " already in use. Try another port")))))))
      



      ((tlisten)
       (if (null? remargs)
           (print "ERROR: useage for tlisten is \"mtutil tlisten portnum\"")
           (let ((portnum (string->number (car remargs))))
              
             (if (not portnum)
                 (print "ERROR: the portnumber parameter must be a number, you gave: " (car remargs))
                 (begin
                   (if (not (is-port-in-use portnum))  
                       (let* ((rep       (start-nn-server portnum))
                              (mtconfdat (simple-setup (args:get-arg "-start-dir")))
                              (mtconf    (car mtconfdat))
                              (contact   (configf:lookup mtconf "listener" "owner"))
                              (script    (configf:lookup mtconf "listener" "script")))
                         (print "Listening on port " portnum " for messages.")
                         (set-signal-handler! signal/int  (lambda (signum) 

															(set! *time-to-exit* #t)
  														(debug:print-error 0 *default-log-port* "Received signal " signum " sending email befor exiting !!")

  														(let ((email-body (mtut:stml->string (s:body

																						(s:p (conc "Received signal " signum ". Lister has been terminated on host " (get-environment-variable "HOST") ". "))))))


             					        (sendmail contact "Listner has been terminated." email-body  use_html: #t))
                              (exit)))
															(set-signal-handler! signal/term  (lambda (signum) 
															(set! *time-to-exit* #t)
  														(debug:print-error 0 *default-log-port* "Received signal " signum " sending email befor exiting !!")

  														(let ((email-body (mtut:stml->string (s:body

																						(s:p (conc "Received signal " signum ". Lister has been terminated on host " (get-environment-variable "HOST") ". "))))))


             					        (sendmail contact "Listner has been terminated." email-body  use_html: #t))
                              (exit)))

                         ;(set-signal-handler! signal/term special-signal-handler)
                         
                         (let loop ((instr (nn-recv rep)))
                             (nn-send rep "ok")
                             (let ((ctime (date->string (current-date)))) 
                             (if  (equal? instr "time-to-die")
                              (begin 
                              (debug:print 0 *default-log-port* ctime " received '" instr "'. Time to sucide." )
                               (let ((pid  (current-process-id)))







<
<
<

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

|
|







1853
1854
1855
1856
1857
1858
1859



1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
                                   )

                                  )

                                )))
                           (loop (nn-recv rep))))
		       (print "ERROR: Port " portnum " already in use. Try another port")))))))




    ((tlisten)
     (if (null? remargs)
         (print "ERROR: useage for tlisten is \"mtutil tlisten portnum\"")
         (let ((portnum (string->number (car remargs))))
           
           (if (not portnum)
               (print "ERROR: the portnumber parameter must be a number, you gave: " (car remargs))
               (begin
                 (if (not (is-port-in-use portnum))  
                     (let* ((rep       (start-nn-server portnum))
                            (mtconfdat (simple-setup (args:get-arg "-start-dir")))
                            (mtconf    (car mtconfdat))
                            (contact   (configf:lookup mtconf "listener" "owner"))
                            (script    (configf:lookup mtconf "listener" "script")))
                       (print "Listening on port " portnum " for messages.")
                       (set-signal-handler! signal/int
					    (lambda (signum) 
					      (set! *time-to-exit* #t)
  					      (debug:print-error 0 *default-log-port* "Received signal " signum
								 " sending email befor exiting !!")
  					      (let ((email-body (mtut:stml->string
								 (s:body
								  (s:p (conc "Received signal " signum
									     ". Lister has been terminated on host "
									     (get-environment-variable "HOST") ". "))))))
             					(sendmail contact "Listner has been terminated." email-body  use_html: #t))
					      (exit)))
		       (set-signal-handler! signal/term  (lambda (signum) 
							   (set! *time-to-exit* #t)
  							   (debug:print-error 0 *default-log-port* "Received signal "
									      signum " sending email befor exiting !!")
  							   (let ((email-body (mtut:stml->string
									      (s:body
									       (s:p (conc "Received signal " signum
											  ". Lister has been terminated on host "
											  (get-environment-variable "HOST") ". "))))))
             					             (sendmail contact "Listner has been terminated." email-body  use_html: #t))
							   (exit)))

		       ;; (set-signal-handler! signal/term special-signal-handler)
                       
                         (let loop ((instr (nn-recv rep)))
                             (nn-send rep "ok")
                             (let ((ctime (date->string (current-date)))) 
                             (if  (equal? instr "time-to-die")
                              (begin 
                              (debug:print 0 *default-log-port* ctime " received '" instr "'. Time to sucide." )
                               (let ((pid  (current-process-id)))

Modified runs.scm from [2583922f1c] to [dcda6cf6d1].

499
500
501
502
503
504
505

506
507
508
509
510
511
512
;; runs:run-tests is called from megatest.scm and itself
;;======================================================================
;;
;;  test-names: Comma separated patterns same as test-patts but used in selection 
;;              of tests to run. The item portions are not respected.
;;              FIXME: error out if /patt specified
;;            

(define (runs:run-tests target runname test-patts user flags #!key (run-count 1)) ;; test-names
  (let* ((keys               (keys:config-get-fields *configdat*))
	 (keyvals            (keys:target->keyval keys target))
	 (run-id             (rmt:register-run keyvals runname "new" "n/a" user (args:get-arg "-contour")))  ;;  test-name)))
	 ;; (deferred          '()) ;; delay running these since they have a waiton clause
	 (runconfigf         (conc  *toppath* "/runconfigs.config"))
         (dbfile             (conc  *toppath* "/megatest.db"))







>







499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
;; runs:run-tests is called from megatest.scm and itself
;;======================================================================
;;
;;  test-names: Comma separated patterns same as test-patts but used in selection 
;;              of tests to run. The item portions are not respected.
;;              FIXME: error out if /patt specified
;;            
;; run-count is passed from megatest.scm as configf:lookup *configdat* "setup" "reruns", or defaults to 1.
(define (runs:run-tests target runname test-patts user flags #!key (run-count 1)) ;; test-names
  (let* ((keys               (keys:config-get-fields *configdat*))
	 (keyvals            (keys:target->keyval keys target))
	 (run-id             (rmt:register-run keyvals runname "new" "n/a" user (args:get-arg "-contour")))  ;;  test-name)))
	 ;; (deferred          '()) ;; delay running these since they have a waiton clause
	 (runconfigf         (conc  *toppath* "/runconfigs.config"))
         (dbfile             (conc  *toppath* "/megatest.db"))
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
    ;; (set! required-tests     (lset-intersection equal? test-names all-test-names))
    
    ;; look up all tests matching the comma separated list of globs in
    ;; test-patts (using % as wildcard)

    ;; (set! test-names (delete-duplicates (tests:get-valid-tests *toppath* test-patts)))
    (debug:print-info 0 *default-log-port* "tests search path: " (string-intersperse (tests:get-tests-search-path *configdat*) " "))
    (debug:print-info 0 *default-log-port* "all tests:         " (string-intersperse (sort all-test-names string<) " "))
    (debug:print-info 0 *default-log-port* "test names:        " (string-intersperse (sort test-names string<) " "))
    (debug:print-info 0 *default-log-port* "required tests:    " (string-intersperse (sort required-tests string<) " "))

    ;; on the first pass or call to run-tests set FAILS to NOT_STARTED if
    ;; -keepgoing is specified
    (if (eq? *passnum* 0)
	(begin







|







623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
    ;; (set! required-tests     (lset-intersection equal? test-names all-test-names))
    
    ;; look up all tests matching the comma separated list of globs in
    ;; test-patts (using % as wildcard)

    ;; (set! test-names (delete-duplicates (tests:get-valid-tests *toppath* test-patts)))
    (debug:print-info 0 *default-log-port* "tests search path: " (string-intersperse (tests:get-tests-search-path *configdat*) " "))
    (debug:print-info 2 *default-log-port* "all tests:         " (string-intersperse (sort all-test-names string<) " "))
    (debug:print-info 0 *default-log-port* "test names:        " (string-intersperse (sort test-names string<) " "))
    (debug:print-info 0 *default-log-port* "required tests:    " (string-intersperse (sort required-tests string<) " "))

    ;; on the first pass or call to run-tests set FAILS to NOT_STARTED if
    ;; -keepgoing is specified
    (if (eq? *passnum* 0)
	(begin
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
                          (waiton-record   (hash-table-ref/default test-records waiton #f))
			  (waiton-tconfig  (if waiton-record (vector-ref waiton-record 1) #f))
			  (waiton-itemized (and waiton-tconfig
						(or (hash-table-ref/default waiton-tconfig "items" #f)
						    (hash-table-ref/default waiton-tconfig "itemstable" #f))))
			  (itemmaps        (tests:get-itemmaps config))  ;; (configf:lookup config "requirements" "itemmap"))
			  (new-test-patts  (tests:extend-test-patts test-patts hed waiton itemmaps hed-itemized-waiton))) 
		     (debug:print-info 0 *default-log-port* "Test " waiton " has " (if waiton-record "a" "no") " waiton-record and" (if waiton-itemized " " " no ") "items")
		     ;; need to account for test-patt here, if I am test "a", selected with a test-patt of "hed/b%"
		     ;; and we are waiting on "waiton" we need to add "waiton/,waiton/b%" to test-patt
		     ;; is this satisfied by merely appending "/" to the waiton name added to the list?
		     ;;
		     ;; This approach causes all of the items in an upstream test to be run 
		     ;; if we have this waiton already processed once we can analzye it for extending
		     ;; tests to be run, since we can't properly process waitons unless they have been







|







737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
                          (waiton-record   (hash-table-ref/default test-records waiton #f))
			  (waiton-tconfig  (if waiton-record (vector-ref waiton-record 1) #f))
			  (waiton-itemized (and waiton-tconfig
						(or (hash-table-ref/default waiton-tconfig "items" #f)
						    (hash-table-ref/default waiton-tconfig "itemstable" #f))))
			  (itemmaps        (tests:get-itemmaps config))  ;; (configf:lookup config "requirements" "itemmap"))
			  (new-test-patts  (tests:extend-test-patts test-patts hed waiton itemmaps hed-itemized-waiton))) 
		     (debug:print-info 2 *default-log-port* "Test " waiton " has " (if waiton-record "a" "no") " waiton-record and" (if waiton-itemized " " " no ") "items")
		     ;; need to account for test-patt here, if I am test "a", selected with a test-patt of "hed/b%"
		     ;; and we are waiting on "waiton" we need to add "waiton/,waiton/b%" to test-patt
		     ;; is this satisfied by merely appending "/" to the waiton name added to the list?
		     ;;
		     ;; This approach causes all of the items in an upstream test to be run 
		     ;; if we have this waiton already processed once we can analzye it for extending
		     ;; tests to be run, since we can't properly process waitons unless they have been
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
                                   (set! test-names (cons waiton test-names)) ;; need to process this one, only add once the waiton tconfig read
                                   (set! required-tests (cons (conc waiton "/") required-tests))
                                   (set! test-patts new-test-patts))
                                 (begin
                                   (debug:print-info 0 *default-log-port* "Waitor(s) not yet on testpatt for " waiton ", setting up to re-process it")
                                   (set! tal (append (cons waiton tal)(list hed)))))
                             (begin
                               (debug:print-info 0 *default-log-port* "Adding non-itemized test " waiton " to required-tests")
                               (set! required-tests (cons waiton required-tests))
                               (set! test-patts new-test-patts)))
			 (begin
			   (debug:print-info 0 *default-log-port* "No testconfig info yet for " waiton ", setting up to re-process it")
			   (set! tal (append (cons waiton tal)(list hed))))) ;; (cons (conc waiton "/") required-tests))
		     ;; NOPE: didn't work. required needs to be plain test names. Try tacking on to test-patts
		     ;;  - doesn't work







|







759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
                                   (set! test-names (cons waiton test-names)) ;; need to process this one, only add once the waiton tconfig read
                                   (set! required-tests (cons (conc waiton "/") required-tests))
                                   (set! test-patts new-test-patts))
                                 (begin
                                   (debug:print-info 0 *default-log-port* "Waitor(s) not yet on testpatt for " waiton ", setting up to re-process it")
                                   (set! tal (append (cons waiton tal)(list hed)))))
                             (begin
                               (debug:print-info 2 *default-log-port* "Adding non-itemized test " waiton " to required-tests")
                               (set! required-tests (cons waiton required-tests))
                               (set! test-patts new-test-patts)))
			 (begin
			   (debug:print-info 0 *default-log-port* "No testconfig info yet for " waiton ", setting up to re-process it")
			   (set! tal (append (cons waiton tal)(list hed))))) ;; (cons (conc waiton "/") required-tests))
		     ;; NOPE: didn't work. required needs to be plain test names. Try tacking on to test-patts
		     ;;  - doesn't work
895
896
897
898
899
900
901

902
903
904
905
906
907
908
;; 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)







>







896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
;; 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))
         (junk (debug:print-info 4 *default-log-port* "expand-items calling rmt:get-prereqs-not-met"))
	 (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)
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
	   (list (car newtal)(append (cdr newtal) reg) '() reruns)
	  #f)) 
     ((null? runnables)
      (debug:print-info 4 *default-log-port* "cond branch - "  "ei-7")
      #f) ;; if we get here and non-completed is null then it is all over.
     (else
      (debug:print-info 4 *default-log-port* "cond branch - "  "ei-8")
      (debug:print 0 *default-log-port* "WARNING: FAILS or incomplete tests maybe preventing completion of this run. Watch for issues with test " hed ", continuing for now")
      (list (car newtal)(cdr newtal) reg reruns)))))

(define (runs:mixed-list-testname-and-testrec->list-of-strings inlst)
  (if (null? inlst)
      '()
      (map (lambda (t)
	     (cond







|







1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
	   (list (car newtal)(append (cdr newtal) reg) '() reruns)
	  #f)) 
     ((null? runnables)
      (debug:print-info 4 *default-log-port* "cond branch - "  "ei-7")
      #f) ;; if we get here and non-completed is null then it is all over.
     (else
      (debug:print-info 4 *default-log-port* "cond branch - "  "ei-8")
      (debug:print 2 *default-log-port* "WARNING: FAILS or incomplete tests maybe preventing completion of this run. Watch for issues with test " hed ", continuing for now")
      (list (car newtal)(cdr newtal) reg reruns)))))

(define (runs:mixed-list-testname-and-testrec->list-of-strings inlst)
  (if (null? inlst)
      '()
      (map (lambda (t)
	     (cond
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
		  (debug:print-info 0 *default-log-port* "Skipping test " tfullname " as it has been marked do not run due to being completed or not runnable"))
	      (if (or (not (null? tal))(not (null? reg)))
		  (loop (runs:queue-next-hed tal reg reglen regfull)
			(runs:queue-next-tal tal reg reglen regfull)
			(runs:queue-next-reg tal reg reglen regfull)
			reruns))))
        ;; (loop (car tal)(cdr tal) reg reruns))))

	(runs:incremental-print-results run-id)
	(debug:print 4 *default-log-port* "TOP OF LOOP => "
		     "test-name: " test-name
		     "\n  hed:         " hed
		     "\n  tal:         " (runs:pretty-long-list tal)
		     "\n  reg:         " reg
                     "\n  test-record  " test-record







<







1667
1668
1669
1670
1671
1672
1673

1674
1675
1676
1677
1678
1679
1680
		  (debug:print-info 0 *default-log-port* "Skipping test " tfullname " as it has been marked do not run due to being completed or not runnable"))
	      (if (or (not (null? tal))(not (null? reg)))
		  (loop (runs:queue-next-hed tal reg reglen regfull)
			(runs:queue-next-tal tal reg reglen regfull)
			(runs:queue-next-reg tal reg reglen regfull)
			reruns))))
        ;; (loop (car tal)(cdr tal) reg reruns))))

	(runs:incremental-print-results run-id)
	(debug:print 4 *default-log-port* "TOP OF LOOP => "
		     "test-name: " test-name
		     "\n  hed:         " hed
		     "\n  tal:         " (runs:pretty-long-list tal)
		     "\n  reg:         " reg
                     "\n  test-record  " test-record
1849
1850
1851
1852
1853
1854
1855
1856

1857
1858
1859
1860
1861

1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873

1874
1875
1876
1877
1878
1879
1880
		  (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))))
         

	 ;; this case should not happen, added to help catch any bugs
	 ((and (list? items) itemdat)
          (debug:print-info 4 *default-log-port* "cond branch - "  "rtq-5")
	  (debug:print-error 0 *default-log-port* "Should not have a list of items in a test and the itemspath set - please report this")
	  (exit 1))

	 ((not (null? reruns))
          (debug:print-info 4 *default-log-port* "cond branch - "  "rtq-6")
	  (let* ((newlst (tests:filter-non-runnable run-id tal test-records)) ;; i.e. not FAIL, WAIVED, INCOMPLETE, PASS, KILLED,
		 (junked (lset-difference equal? tal newlst)))
	    (debug:print-info 4 *default-log-port* "full drop through, if reruns is less than 100 we will force retry them, reruns=" reruns ", tal=" tal)
	    (if (< num-retries max-retries)
		(set! newlst (append reruns newlst)))
	    (set! num-retries (+ num-retries 1))
	    ;; (thread-sleep! (+ 1 *global-delta*))
	    (if (not (null? newlst))
		;; since reruns have been tacked on to newlst create new reruns from junked
		(loop (car newlst)(cdr newlst) reg (delete-duplicates junked)))))

	 ((not (null? tal))
          (debug:print-info 4 *default-log-port* "cond branch - "  "rtq-7")
	  (debug:print-info 4 *default-log-port* "I'm pretty sure I shouldn't get here."))
	 ((not (null? reg)) ;; could we get here with leftovers?
          (debug:print-info 4 *default-log-port* "cond branch - "  "rtq-8")
	  (debug:print-info 0 *default-log-port* "Have leftovers!")
	  (loop (car reg)(cdr reg) '() reruns))







|
>





>












>







1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
		  (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))))
        

	 ;; this case should not happen, added to help catch any bugs
	 ((and (list? items) itemdat)
          (debug:print-info 4 *default-log-port* "cond branch - "  "rtq-5")
	  (debug:print-error 0 *default-log-port* "Should not have a list of items in a test and the itemspath set - please report this")
	  (exit 1))

	 ((not (null? reruns))
          (debug:print-info 4 *default-log-port* "cond branch - "  "rtq-6")
	  (let* ((newlst (tests:filter-non-runnable run-id tal test-records)) ;; i.e. not FAIL, WAIVED, INCOMPLETE, PASS, KILLED,
		 (junked (lset-difference equal? tal newlst)))
	    (debug:print-info 4 *default-log-port* "full drop through, if reruns is less than 100 we will force retry them, reruns=" reruns ", tal=" tal)
	    (if (< num-retries max-retries)
		(set! newlst (append reruns newlst)))
	    (set! num-retries (+ num-retries 1))
	    ;; (thread-sleep! (+ 1 *global-delta*))
	    (if (not (null? newlst))
		;; since reruns have been tacked on to newlst create new reruns from junked
		(loop (car newlst)(cdr newlst) reg (delete-duplicates junked)))))

	 ((not (null? tal))
          (debug:print-info 4 *default-log-port* "cond branch - "  "rtq-7")
	  (debug:print-info 4 *default-log-port* "I'm pretty sure I shouldn't get here."))
	 ((not (null? reg)) ;; could we get here with leftovers?
          (debug:print-info 4 *default-log-port* "cond branch - "  "rtq-8")
	  (debug:print-info 0 *default-log-port* "Have leftovers!")
	  (loop (car reg)(cdr reg) '() reruns))
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
	     (set! runflag #t))

	    (else (set! runflag #f)))
	   (debug:print 4 *default-log-port* "RUNNING => runflag: " runflag " STATE: " (test:get-state testdat) " STATUS: " (test:get-status testdat))
	   (if (not runflag)
	       (if (not parent-test)
		   (if (runs:lownoise (conc "not starting test" full-test-name) 60)
		       (debug:print 1 *default-log-port* "NOTE: Not starting test " full-test-name " as it is state \"" (test:get-state testdat) 
				    "\" and status \"" (test:get-status testdat) "\", use -rerun \"" (test:get-status testdat)
				    "\" or -force to override")))
	       ;; NOTE: No longer be checking prerequisites here! Will never get here unless prereqs are
	       ;;       already met.
	       ;; This would be a great place to do the process-fork
	       ;; 
	       (let ((skip-test   #f)







|







2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
	     (set! runflag #t))

	    (else (set! runflag #f)))
	   (debug:print 4 *default-log-port* "RUNNING => runflag: " runflag " STATE: " (test:get-state testdat) " STATUS: " (test:get-status testdat))
	   (if (not runflag)
	       (if (not parent-test)
		   (if (runs:lownoise (conc "not starting test" full-test-name) 60)
		       (debug:print 3 *default-log-port* "NOTE: Not starting test " full-test-name " as it is state \"" (test:get-state testdat) 
				    "\" and status \"" (test:get-status testdat) "\", use -rerun \"" (test:get-status testdat)
				    "\" or -force to override")))
	       ;; NOTE: No longer be checking prerequisites here! Will never get here unless prereqs are
	       ;;       already met.
	       ;; This would be a great place to do the process-fork
	       ;; 
	       (let ((skip-test   #f)
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
		    ;; seek and kill in flight -runtests with % as testpatt here
		    ;; (if (equal? testpatt "%")
		    (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))
		    (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)
		    (debug:print 1 *default-log-port* "Waiting for run " runkey ", run=" runnamepatt " to complete"))
		   ((archive)
		    (debug:print 1 *default-log-port* "Archiving/restoring (" (args:get-arg "-archive") ") data for run: " runkey " " (db:get-value-by-header run header "runname"))







|







2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
		    ;; seek and kill in flight -runtests with % as testpatt here
		    ;; (if (equal? testpatt "%")
		    (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))
		    (debug:print 2 *default-log-port* "Modifying state and status 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)
		    (debug:print 1 *default-log-port* "Waiting for run " runkey ", run=" runnamepatt " to complete"))
		   ((archive)
		    (debug:print 1 *default-log-port* "Archiving/restoring (" (args:get-arg "-archive") ") data for run: " runkey " " (db:get-value-by-header run header "runname"))
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
				       )
				      ) ; end case rem-status
                                    ) ; end let
                                  ); end cond has-subrun

                                 (else
                                  ;; BB - TODO - consider backgrounding to threads to delete tests (work below) 
                                  (debug:print-info 0 *default-log-port* "test: " test-name " itest-state: " test-state)
                                  (if (member test-state (list "RUNNING" "LAUNCHED" "REMOTEHOSTSTART" "KILLREQ"))
                                      (begin
                                        (if (not (hash-table-ref/default test-retry-time test-fulln #f))
                                            (begin
                                              ;; want to set to REMOVING BUT CANNOT do it here?
                                              (hash-table-set! test-retry-time test-fulln (current-seconds))))
                                        (if (> (- (current-seconds)(hash-table-ref test-retry-time test-fulln)) allow-run-time)







|







2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
				       )
				      ) ; end case rem-status
                                    ) ; end let
                                  ); end cond has-subrun

                                 (else
                                  ;; BB - TODO - consider backgrounding to threads to delete tests (work below) 
                                  (debug:print-info 2 *default-log-port* "test: " test-name " itest-state: " test-state)
                                  (if (member test-state (list "RUNNING" "LAUNCHED" "REMOTEHOSTSTART" "KILLREQ"))
                                      (begin
                                        (if (not (hash-table-ref/default test-retry-time test-fulln #f))
                                            (begin
                                              ;; want to set to REMOVING BUT CANNOT do it here?
                                              (hash-table-set! test-retry-time test-fulln (current-seconds))))
                                        (if (> (- (current-seconds)(hash-table-ref test-retry-time test-fulln)) allow-run-time)
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
	;; 			      (thread-sleep! 1)
	 ;; 			      (loop (rmt:no-sync-get-lock lock-key) expire-time)))))))
	 )
    (case clean-mode
      ((remove-data-only)(mt:test-set-state-status-by-id (db:test-get-run_id test)(db:test-get-id test) "CLEANING" "LOCKED" #f))
      ((remove-all)      (mt:test-set-state-status-by-id (db:test-get-run_id test)(db:test-get-id test) "REMOVING" "LOCKED" #f))
      ((archive-remove)  (mt:test-set-state-status-by-id (db:test-get-run_id test)(db:test-get-id test) "ARCHIVE_REMOVING" #f #f)))
    (debug:print-info 1 *default-log-port* "Attempting to remove " (if real-dir (conc " dir " real-dir " and ") "") " link " run-dir)
    (if (and real-dir 
	     (> (string-length real-dir) 5)
	     (common:file-exists? real-dir)) ;; bad heuristic but should prevent /tmp /home etc.
	(let* ((realpath (resolve-pathname run-dir)))
	  (debug:print-info 1 *default-log-port* "Recursively removing " realpath)
	  (if (common:file-exists? realpath)
	      (runs:safe-delete-test-dir realpath)







|







2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
	;; 			      (thread-sleep! 1)
	 ;; 			      (loop (rmt:no-sync-get-lock lock-key) expire-time)))))))
	 )
    (case clean-mode
      ((remove-data-only)(mt:test-set-state-status-by-id (db:test-get-run_id test)(db:test-get-id test) "CLEANING" "LOCKED" #f))
      ((remove-all)      (mt:test-set-state-status-by-id (db:test-get-run_id test)(db:test-get-id test) "REMOVING" "LOCKED" #f))
      ((archive-remove)  (mt:test-set-state-status-by-id (db:test-get-run_id test)(db:test-get-id test) "ARCHIVE_REMOVING" #f #f)))
    (debug:print-info 2 *default-log-port* "Attempting to remove " (if real-dir (conc " dir " real-dir " and ") "") " link " run-dir)
    (if (and real-dir 
	     (> (string-length real-dir) 5)
	     (common:file-exists? real-dir)) ;; bad heuristic but should prevent /tmp /home etc.
	(let* ((realpath (resolve-pathname run-dir)))
	  (debug:print-info 1 *default-log-port* "Recursively removing " realpath)
	  (if (common:file-exists? realpath)
	      (runs:safe-delete-test-dir realpath)
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
	  (let* ((linktree (common:get-linktree)) ;; (if toppath (configf:lookup *configdat* "setup" "linktree")))
		 (runtop   (conc linktree "/" target "/" runname))
		 (files    (if (common:file-exists? runtop)
			       (append (glob (conc runtop "/.megatest*"))
				       (glob (conc runtop "/.runconfig*")))
			       '())))
	    (if (null? files)
		(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
			 exn
			 (debug:print 0 *default-log-port* "WARNING: Failed to remove file " f ", exn=" exn)
		       (delete-file f)))
		   files))))
	  (debug:print-error 0 *default-log-port* "-clean-cache requires -runname."))
      (debug:print-error 0 *default-log-port* "-clean-cache requires -target or -reqtarg")))







|

|









3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
	  (let* ((linktree (common:get-linktree)) ;; (if toppath (configf:lookup *configdat* "setup" "linktree")))
		 (runtop   (conc linktree "/" target "/" runname))
		 (files    (if (common:file-exists? runtop)
			       (append (glob (conc runtop "/.megatest*"))
				       (glob (conc runtop "/.runconfig*")))
			       '())))
	    (if (null? files)
		(debug:print-info 2 *default-log-port* "No cached megatest or runconfigs files found. None removed.")
		(begin
		  (debug:print-info 2 *default-log-port* "Removing cached files:\n    " (string-intersperse files "\n    "))
		  (for-each 
		   (lambda (f)
		     (handle-exceptions
			 exn
			 (debug:print 0 *default-log-port* "WARNING: Failed to remove file " f ", exn=" exn)
		       (delete-file f)))
		   files))))
	  (debug:print-error 0 *default-log-port* "-clean-cache requires -runname."))
      (debug:print-error 0 *default-log-port* "-clean-cache requires -target or -reqtarg")))

Modified server.scm from [6d2db21290] to [99d72bd3eb].

109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
    ((rpc)  (db:obj->string (vector success/fail query-sig result)))
    ((http) (db:obj->string (vector success/fail query-sig result)))
    ((fs)   result)
    (else 
     (debug:print-error 0 *default-log-port* "unrecognised transport type: " *transport-type*)
     result)))

;; Given a run id start a server process    ### NOTE ### > file 2>&1 
;; if the run-id is zero and the target-host is set 
;; try running on that host
;;   incidental: rotate logs in logs/ dir.
;;
(define  (server:run areapath) ;; areapath is *toppath* for a given testsuite area
  (let* ((curr-host   (get-host-name))
         ;; (attempt-in-progress (server:start-attempted? areapath))
         ;; (dot-server-url (server:check-if-running areapath))







|
|







109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
    ((rpc)  (db:obj->string (vector success/fail query-sig result)))
    ((http) (db:obj->string (vector success/fail query-sig result)))
    ((fs)   result)
    (else 
     (debug:print-error 0 *default-log-port* "unrecognised transport type: " *transport-type*)
     result)))

;; Given an area path,  start a server process    ### NOTE ### > file 2>&1 
;; if the target-host is set 
;; try running on that host
;;   incidental: rotate logs in logs/ dir.
;;
(define  (server:run areapath) ;; areapath is *toppath* for a given testsuite area
  (let* ((curr-host   (get-host-name))
         ;; (attempt-in-progress (server:start-attempted? areapath))
         ;; (dot-server-url (server:check-if-running areapath))
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169


170
171
172
173
174
175
176
	     (not (string-match (conc "("curr-host "|" curr-host"\\..*)") target-host))
	     (not (equal? curr-ip target-host)))
	(begin
	  (debug:print-info 0 *default-log-port* "Starting server on " target-host ", logfile is " logfile)
	  (setenv "TARGETHOST" target-host)))
      
    (setenv "TARGETHOST_LOGF" logfile)
    (thread-sleep! (/ (random 5000) 1000)) ;; add about a random (up to 5 seconds) initial delay. It seems pretty common that many running tests request a server at the same time
    ;; (common:wait-for-normalized-load load-limit " delaying server start due to load" target-host) ;; do not try starting servers on an already overloaded machine, just wait forever
    #;(common:wait-for-homehost-load load-limit (conc " delaying server start due to load on homehost. limit is " load-limit))
    (system (conc "nbfake " cmdln))
    (unsetenv "TARGETHOST_LOGF")
    (if (get-environment-variable "TARGETHOST")(unsetenv "TARGETHOST"))
    (thread-join! log-rotate)
    (pop-directory)))

;; given a path to a server log return: host port startseconds
;; any changes to number of elements returned by this fuction will dirctly affect server:record->url,server:record->id,server:kill,server:get-num-alive which uses match let 



(define (server:logf-get-start-info logf)
  (let ((server-rx (regexp "^SERVER STARTED: (\\S+):(\\d+) AT ([\\d\\.]+) server-id: (\\S+)")) ;; SERVER STARTED: host:port AT timesecs server id
        (dbprep-rx (regexp "^SERVER: dbprep"))
        (dbprep-found 0)) 
    (handle-exceptions
	exn







|
|
<






|
|
>
>







152
153
154
155
156
157
158
159
160

161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
	     (not (string-match (conc "("curr-host "|" curr-host"\\..*)") target-host))
	     (not (equal? curr-ip target-host)))
	(begin
	  (debug:print-info 0 *default-log-port* "Starting server on " target-host ", logfile is " logfile)
	  (setenv "TARGETHOST" target-host)))
      
    (setenv "TARGETHOST_LOGF" logfile)
    (thread-sleep! (/ (random 3000) 1000)) ;; add a random initial delay. It seems pretty common that many running tests request a server at the same time
    (debug:print 0 *default-log-port* "INFO: starting server at " (common:human-time))

    (system (conc "nbfake " cmdln))
    (unsetenv "TARGETHOST_LOGF")
    (if (get-environment-variable "TARGETHOST")(unsetenv "TARGETHOST"))
    (thread-join! log-rotate)
    (pop-directory)))

;; given a path to a server log return: host port startseconds server-id
;; any changes to number of elements returned by this fuction will dirctly affect server:record->url,server:record->id,server:kill,server:get-num-alive which use match let 
;; example of what it's looking for in the log file:
;;     SERVER STARTED: 10.38.175.67:50216 AT 1616502350.0 server-id: 4907e90fc55c7a09694e3f658c639cf4 

(define (server:logf-get-start-info logf)
  (let ((server-rx (regexp "^SERVER STARTED: (\\S+):(\\d+) AT ([\\d\\.]+) server-id: (\\S+)")) ;; SERVER STARTED: host:port AT timesecs server id
        (dbprep-rx (regexp "^SERVER: dbprep"))
        (dbprep-found 0)) 
    (handle-exceptions
	exn
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233



234
235
236
237
238
239
240
241
242
243
244
245
246
			(list (car dat) ;; host
			      (string->number (cadr dat)) ;; port
			      (string->number (caddr dat))
                              (cadr (cddr dat))))))
                (begin 
                   (if dbprep-found
                      (begin
                         (debug:print-info 0 *default-log-port* "Server is in dbprep at " (current-seconds))
                         (thread-sleep! 25)
                      )
                      (debug:print-info 0 *default-log-port* "Unable to get server info from " logf " at " (current-seconds))
                   )
		    (list #f #f #f #f)))))))))

;; get a list of servers with all relevant data
;; ( mod-time host port start-time pid )
;;
(define (server:get-list areapath #!key (limit #f))
  (let ((fname-rx    (regexp "^(|.*/)server-(\\d+)-(\\S+).log$"))
	(day-seconds (* 24 60 60)))
    ;; if the directory exists continue to get the list
    ;; otherwise attempt to create the logs dir and then
    ;; continue
    (if (if (directory-exists? (conc areapath "/logs"))
	    '()
	    (if (file-write-access? areapath)
		(begin
		  (condition-case
		   (create-directory (conc areapath "/logs") #t)
		   (exn (i/o file)(debug:print 0 *default-log-port* "ERROR: Cannot create directory at " (conc areapath "/logs")))
		   (exn ()(debug:print 0 *default-log-port* "ERROR: Unknown error attemtping to get server list. exn=" exn)))
		  (directory-exists? (conc areapath "/logs")))
		'()))

        ;; Get the list of server logs that do not contain "exiting". Ignore logs for servers that have exited.



	(let* ((server-logs-cmd  (conc "grep -iL exiting " areapath "/logs/server-*-*.log"))
               (server-logs   (string-split (string-chomp (call-with-input-pipe server-logs-cmd read-all))))
	       (num-serv-logs (length server-logs)))
	  (if (or (null? server-logs) (= num-serv-logs 0))
              (let ()
                 (debug:print 1  *default-log-port* "There are no servers running")
	         '()
              )
	      (let loop ((hed  (string-chomp (car server-logs)))
			 (tal  (cdr server-logs))
			 (res '()))
		(let* ((mod-time  (handle-exceptions
				   exn







|
|

|



|



















|
>
>
>
|
<



|







200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238

239
240
241
242
243
244
245
246
247
248
249
			(list (car dat) ;; host
			      (string->number (cadr dat)) ;; port
			      (string->number (caddr dat))
                              (cadr (cddr dat))))))
                (begin 
                   (if dbprep-found
                      (begin
                         (debug:print-info 2 *default-log-port* "Server is in dbprep at " (common:human-time))
                         (thread-sleep! 0.5) ;; was 25 sec but that blocked things from starting?
                      )
                      (debug:print-info 0 *default-log-port* "Unable to get server info from " logf " at " (seconds->time-string (current-seconds)))
                   )
		    (list #f #f #f #f)))))))))

;; get a list of servers from the log files, with all relevant data
;; ( mod-time host port start-time pid )
;;
(define (server:get-list areapath #!key (limit #f))
  (let ((fname-rx    (regexp "^(|.*/)server-(\\d+)-(\\S+).log$"))
	(day-seconds (* 24 60 60)))
    ;; if the directory exists continue to get the list
    ;; otherwise attempt to create the logs dir and then
    ;; continue
    (if (if (directory-exists? (conc areapath "/logs"))
	    '()
	    (if (file-write-access? areapath)
		(begin
		  (condition-case
		   (create-directory (conc areapath "/logs") #t)
		   (exn (i/o file)(debug:print 0 *default-log-port* "ERROR: Cannot create directory at " (conc areapath "/logs")))
		   (exn ()(debug:print 0 *default-log-port* "ERROR: Unknown error attemtping to get server list. exn=" exn)))
		  (directory-exists? (conc areapath "/logs")))
		'()))

        ;; Get the list of server logs. First remove logs for servers that have exited.
	(let* (
               ;; For some reason, when I uncomment the below line, ext-tests sometimes starts 1000's of servers.
               ;; (exiting-servers (system (conc "bash -c 'rm -f `grep -il exiting " areapath "/logs/server-*-*.log 2> /dev/null`'")))
               (server-logs   (glob (conc areapath "/logs/server-*-*.log")))

	       (num-serv-logs (length server-logs)))
	  (if (or (null? server-logs) (= num-serv-logs 0))
              (let ()
                 (debug:print 2  *default-log-port* "There are no servers running at " (common:human-time))
	         '()
              )
	      (let loop ((hed  (string-chomp (car server-logs)))
			 (tal  (cdr server-logs))
			 (res '()))
		(let* ((mod-time  (handle-exceptions
				   exn
363
364
365
366
367
368
369
370



371
372
373
374
375
376
377
378
379
380





381
382
383
384
385
386
387
388
389
390
391


392

393
394

395
396
397
398


399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425



426
427
428
429
430
431
432

(define (server:get-client-signature) ;; BB> why is this proc named "get-"?  it returns nothing -- set! has not return value.
  (if *my-client-signature* *my-client-signature*
      (let ((sig (server:mk-signature)))
        (set! *my-client-signature* sig)
        *my-client-signature*)))

;; wait for server=start-last to be three seconds old



;;
(define (server:wait-for-server-start-last-flag areapath)
  (let* ((start-flag (conc areapath "/logs/server-start-last"))
	 ;;; THIS INTERACTS WITH [server] timeout. Suggest using 0.1 or above for timeout (6 seconds)
	 (reftime    (configf:lookup-number *configdat* "server" "idletime" default: 4))
	 (server-key (conc (get-host-name) "-" (current-process-id))))
    (if (file-exists? start-flag)
	(let* ((fmodtime (file-modification-time start-flag))
	       (delta    (- (current-seconds) fmodtime))
	       (all-go   (> delta reftime)))





	  (if (and all-go
		   (begin
                     (debug:print-info 0 *default-log-port* "Writing " start-flag)
		     (with-output-to-file start-flag
		       (lambda ()
			 (print server-key)))
		     (thread-sleep! 0.25)
		     (let ((res (with-input-from-file start-flag
				  (lambda ()
				    (read-line)))))
		       (equal? server-key res))))


	      #t ;; (system (conc "touch " start-flag)) ;; lazy but safe

	      (begin
		(debug:print-info 0 *default-log-port* "Gating server start, last start: "

				  fmodtime ", delta: " delta ", reftime: " reftime ", all-go=" all-go)
		(thread-sleep! reftime)
		(server:wait-for-server-start-last-flag areapath)))))))



;; kind start up of servers, wait 40 seconds before allowing another server for a given
;; run-id to be launched
;;
(define (server:kind-run areapath)
  ;; look for $MT_RUN_AREA_HOME/logs/server-start-last
  ;; and wait for it to be at least 3 seconds old
  (server:wait-for-server-start-last-flag areapath)
  (if (not (server:check-if-running areapath)) ;; why try if there is already a server running?
      (let* ((last-run-dat (hash-table-ref/default *server-kind-run* areapath '(0 0))) ;; callnum, whenrun
	     (call-num     (car last-run-dat))
	     (when-run     (cadr last-run-dat))
	     (run-delay    (+ (case call-num
				((0)    0)
				((1)   20)
				((2)  300)
				(else 600))
			      (random 5)))   ;; add a small random number just in case a lot of jobs hit the work hosts simultaneously
	     (lock-file    (conc areapath "/logs/server-start.lock")))
	(if	(> (- (current-seconds) when-run) run-delay)
		(let* ((start-flag (conc areapath "/logs/server-start-last")))
		  (common:simple-file-lock-and-wait lock-file expire-time: 15)
                  (debug:print-info  0 *default-log-port* "server:kind-run: touching " start-flag)
		  (system (conc "touch " start-flag)) ;; lazy but safe
		  (server:run areapath)
		  (thread-sleep! 2) ;; don't release the lock for at least a few seconds
		  (common:simple-file-release-lock lock-file)))
	(hash-table-set! *server-kind-run* areapath (list (+ call-num 1)(current-seconds))))))




;; this one seems to be the general entry point
;;
(define (server:start-and-wait areapath #!key (timeout 60))
  (let ((give-up-time (+ (current-seconds) timeout)))
    (let loop ((server-info (server:check-if-running areapath))
	       (try-num    0))







|
>
>
>




|




|
>
>
>
>
>
|

|
|
<
<

|
<
<
|
>
>
|
>


>
|
|


>
>
|
|



|


|
<
<
<
<
<
<
<
<

<
|
|
|
|
|
|
|
|
>
>
>







366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395


396
397


398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420








421

422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439

(define (server:get-client-signature) ;; BB> why is this proc named "get-"?  it returns nothing -- set! has not return value.
  (if *my-client-signature* *my-client-signature*
      (let ((sig (server:mk-signature)))
        (set! *my-client-signature* sig)
        *my-client-signature*)))


;; if server-start-last exists, and wasn't old enough, wait <idle time> + 1, then call this function recursively until it is old enough.
;; if it is old enough, overwrite it and wait 0.25 seconds.
;; if it then has the wrong server key, wait <idle time> + 1 and call this function recursively.
;;
(define (server:wait-for-server-start-last-flag areapath)
  (let* ((start-flag (conc areapath "/logs/server-start-last"))
	 ;;; THIS INTERACTS WITH [server] timeout. Suggest using 0.1 or above for timeout (6 seconds)
	 (idletime    (configf:lookup-number *configdat* "server" "idletime" default: 4))
	 (server-key (conc (get-host-name) "-" (current-process-id))))
    (if (file-exists? start-flag)
	(let* ((fmodtime (file-modification-time start-flag))
	       (delta    (- (current-seconds) fmodtime))
	       (old-enough   (> delta idletime))
               (new-server-key "")
              )

          ;; write start-flag file, wait 0.25s, then if previously the start-flag file was older than <idletime> seconds, and the new file still has the same server key as you just wrote, return #t.
	  ;; the intention is to make sure nfs can read the file we just wrote, and make sure it was written by us, and not another process.
           (if (and old-enough
		   (begin
                     (debug:print-info 2 *default-log-port* "Writing " start-flag)
		     (with-output-to-file start-flag (lambda () (print server-key)))


		     (thread-sleep! 0.25)
		     (set! new-server-key (with-input-from-file start-flag (lambda () (read-line))))


		     (equal? server-key new-server-key))
                )
	      #t

           ;; If either of the above conditions is not true, print a "Gating server start" message, wait <idle-time> + 1, then call this function recursively. 
	      (begin
		(debug:print-info 0 *default-log-port* "Gating server start, last start: "
				  (seconds->time-string fmodtime) ", time since last start: " delta ", required idletime: " idletime ", gating reason:" (if old-enough "another job started a server" "too soon to start another server"))

		(thread-sleep! ( + 1 idletime))
		(server:wait-for-server-start-last-flag areapath)))))))


        
;; kind start up of server, wait before allowing another server for a given
;; area to be launched
;;
(define (server:kind-run areapath)
  ;; look for $MT_RUN_AREA_HOME/logs/server-start-last
  ;; and wait for it to be at least <server idletime> seconds old
  (server:wait-for-server-start-last-flag areapath)
  (if (not (server:check-if-running areapath)) ;; why try if there is already a server running?
      (let* (








	     (lock-file    (conc areapath "/logs/server-start.lock")))

	(let* ((start-flag (conc areapath "/logs/server-start-last")))
	  (common:simple-file-lock-and-wait lock-file expire-time: 25)
	  (debug:print-info  2 *default-log-port* "server:kind-run: touching " start-flag)
	  (system (conc "touch " start-flag)) ;; lazy but safe
	  (server:run areapath)
	  (thread-sleep! 20) ;; don't release the lock for at least a few seconds. And allow time for the server startup to get to "SERVER STARTED".
	  (common:simple-file-release-lock lock-file)))

      (debug:print-info 0 *default-log-port* "Found server already running. NOT trying to start another.")
   )
)

;; this one seems to be the general entry point
;;
(define (server:start-and-wait areapath #!key (timeout 60))
  (let ((give-up-time (+ (current-seconds) timeout)))
    (let loop ((server-info (server:check-if-running areapath))
	       (try-num    0))
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
  (let ((ns (string->number
	     (or (configf:lookup *configdat* "server" "numservers") "notanumber"))))
    (or ns numservers)))

;; no longer care if multiple servers are started by accident. older servers will drop off in time.
;;
(define (server:check-if-running areapath) ;;  #!key (numservers "2"))
  (let* ((ns            (server:get-num-servers))
	 (servers       (server:get-best (server:get-list areapath))))
    (if (or (and servers
		 (null? servers))
	    (not servers)
	    (and (list? servers)
		 (< (length servers) (random ns)))) ;; somewhere between 0 and numservers
        #f
        (let loop ((hed (car servers))
                   (tal (cdr servers)))
          (let ((res (server:check-server hed)))
            (if res
                hed
                (if (null? tal)







|





|







454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
  (let ((ns (string->number
	     (or (configf:lookup *configdat* "server" "numservers") "notanumber"))))
    (or ns numservers)))

;; no longer care if multiple servers are started by accident. older servers will drop off in time.
;;
(define (server:check-if-running areapath) ;;  #!key (numservers "2"))
  (let* ((ns            (server:get-num-servers)) ;; get the setting the for maximum number of servers allowed
	 (servers       (server:get-best (server:get-list areapath))))
    (if (or (and servers
		 (null? servers))
	    (not servers)
	    (and (list? servers)
		 (< (length servers) (+ 1 (random ns))))) ;; somewhere between 1 and numservers
        #f
        (let loop ((hed (car servers))
                   (tal (cdr servers)))
          (let ((res (server:check-server hed)))
            (if res
                hed
                (if (null? tal)

Modified subrun.scm from [bd1952a98c] to [85650ceb7f].

126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
      (let* ((action-switches-str
              (conc "-kill-runs" ))
             (kill-result
              (subrun:exec-sub-megatest test-run-dir action-switches-str "kill")))
        kill-result)
      #t))

(define (subrun:launch-cmd test-run-dir #!optional (sub-cmd "-run")) ;; BUG: "-run" should be changed to "-rerun-clean" but current doesn't work
  (if (subrun:subrun-removed? test-run-dir)
      (subrun:unset-subrun-removed test-run-dir))      

  (let* ((log-prefix "run")
         (switches (subrun:selector+log-switches test-run-dir log-prefix))
         (run-wait #t)
         (cmd      (conc "megatest " sub-cmd " " switches" "
                         (if run-wait "-run-wait " ""))))
    cmd))


(define (subrun:sanitize-path inpath)
  (let* ((insane-pattern (irregex "[^[a-zA-Z0-9_\\-]")))







|





|







126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
      (let* ((action-switches-str
              (conc "-kill-runs" ))
             (kill-result
              (subrun:exec-sub-megatest test-run-dir action-switches-str "kill")))
        kill-result)
      #t))

(define (subrun:launch-cmd test-run-dir run-mode #!optional (sub-cmd "-run")) ;; BUG: "-run" should be changed to "-rerun-clean" but current doesn't work
  (if (subrun:subrun-removed? test-run-dir)
      (subrun:unset-subrun-removed test-run-dir))      

  (let* ((log-prefix "run")
         (switches (subrun:selector+log-switches test-run-dir log-prefix))
         (run-wait (equal? run-mode "yes"))
         (cmd      (conc "megatest " sub-cmd " " switches" "
                         (if run-wait "-run-wait " ""))))
    cmd))


(define (subrun:sanitize-path inpath)
  (let* ((insane-pattern (irregex "[^[a-zA-Z0-9_\\-]")))

Modified tests.scm from [58a365a2ab] to [58cccc5f49].

51
52
53
54
55
56
57

58
59
60
61
62
63
64

;; Call this one to do all the work and get a standardized list of tests
;;   gets paths from configs and finds valid tests 
;;   returns hash of testname --> fullpath
;;
(define (tests:get-all)
  (let* ((test-search-path   (tests:get-tests-search-path *configdat*)))

    (tests:get-valid-tests (make-hash-table) test-search-path)))

(define (tests:get-tests-search-path cfgdat)
  (let ((paths (let ((section (if cfgdat
				  (configf:get-section cfgdat "tests-paths")
				  #f)))
		 (if section







>







51
52
53
54
55
56
57
58
59
60
61
62
63
64
65

;; Call this one to do all the work and get a standardized list of tests
;;   gets paths from configs and finds valid tests 
;;   returns hash of testname --> fullpath
;;
(define (tests:get-all)
  (let* ((test-search-path   (tests:get-tests-search-path *configdat*)))
    (debug:print 8 *default-log-port* "test-search-path: " test-search-path)
    (tests:get-valid-tests (make-hash-table) test-search-path)))

(define (tests:get-tests-search-path cfgdat)
  (let ((paths (let ((section (if cfgdat
				  (configf:get-section cfgdat "tests-paths")
				  #f)))
		 (if section
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
	       (tests:dashboard-body page pg-size keys numkeys total-runs linktree area-name get-prev-links get-next-links #f run-patt target-patt)) ;; update this function
	      (close-output-port oup)
					; (set! page (+ 1 page))
	      (if (> total-runs (* (+ 1 page) pg-size))
		  (loop (+ 1  page)))))
	  (common:simple-file-release-lock lockfile))
	(begin
	  (debug-print 0 *default-log-port* "Failed to get lock on file outf, lockfile: " lockfile) #f))))


(define (tests:readlines filename)
  (call-with-input-file filename
    (lambda (p)
      (let loop ((line (read-line p))
                 (result '()))







|







908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
	       (tests:dashboard-body page pg-size keys numkeys total-runs linktree area-name get-prev-links get-next-links #f run-patt target-patt)) ;; update this function
	      (close-output-port oup)
					; (set! page (+ 1 page))
	      (if (> total-runs (* (+ 1 page) pg-size))
		  (loop (+ 1  page)))))
	  (common:simple-file-release-lock lockfile))
	(begin
	  (debug:print 0 *default-log-port* "Failed to get lock on file outf, lockfile: " lockfile) #f))))


(define (tests:readlines filename)
  (call-with-input-file filename
    (lambda (p)
      (let loop ((line (read-line p))
                 (result '()))
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
                                       #f)
                                      (
                                       (and wait-a-minute (> tries-left 0))
                                       (thread-sleep! 10)
                                       (debug:print 0 *default-log-port* "WARNING: testconfig file does not exist: "test-configf" will retry in 10 seconds.  Tries left: "tries-left) ;; BB: this fires
                                       (loopa (sub1 tries-left)))
                                      (else
                                       (debug:print 0 *default-log-port* "WARNING: testconfig file does not exist: "test-configf) ;; BB: this fires
                                       #f))))
		     (tcfg         (if testexists
				       (read-config test-configf #f system-allowed
						    environ-patt: (if system-allowed
								      "pre-launch-env-vars"
								      #f))
				       #f)))







|







1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
                                       #f)
                                      (
                                       (and wait-a-minute (> tries-left 0))
                                       (thread-sleep! 10)
                                       (debug:print 0 *default-log-port* "WARNING: testconfig file does not exist: "test-configf" will retry in 10 seconds.  Tries left: "tries-left) ;; BB: this fires
                                       (loopa (sub1 tries-left)))
                                      (else
                                       (debug:print 2 *default-log-port* "WARNING: testconfig file does not exist: "test-configf) ;; BB: this fires
                                       #f))))
		     (tcfg         (if testexists
				       (read-config test-configf #f system-allowed
						    environ-patt: (if system-allowed
								      "pre-launch-env-vars"
								      #f))
				       #f)))
1840
1841
1842
1843
1844
1845
1846

1847
1848
1849
1850
1851
1852
1853
1854
1855
1856












1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873

;;======================================================================
;; refactoring this block into tests:get-full-data from line 263 of runs.scm
;;======================================================================
;; hed is the test name
;; test-records is a hash of test-name => test record
(define (tests:get-full-data test-names test-records required-tests all-tests-registry)

  (if (not (null? test-names))
      (let loop ((hed (car test-names))
		 (tal (cdr test-names)))         ;; 'return-procs tells the config reader to prep running system but return a proc
	(debug:print-info 4 *default-log-port* "hed=" hed " at top of loop")
        ;; don't know item-path at this time, let the testconfig get the top level testconfig
	(let* ((config  (tests:get-testconfig hed #f all-tests-registry 'return-procs))
	       (waitons (let ((instr (if config 
					 (configf:lookup config "requirements" "waiton")
					 (begin ;; No config means this is a non-existant test
					   (debug:print-error 0 *default-log-port* "non-existent required test \"" hed "\", grep through your testconfigs to find and remove or create the test. Discarding and continuing.")












					     ""))))
			  (debug:print-info 8 *default-log-port* "waitons string is " instr)
			  (string-split (cond
					 ((procedure? instr)
					  (let ((res (instr)))
					    (debug:print-info 8 *default-log-port* "waiton procedure results in string " res " for test " hed)
					    res))
					 ((string? instr)     instr)
					 (else 
					  ;; NOTE: This is actually the case of *no* waitons! ;; (debug:print-error 0 *default-log-port* "something went wrong in processing waitons for test " hed)
					  ""))))))
	  (if (not config) ;; this is a non-existant test called in a waiton. 
	      (if (null? tal)
		  test-records
		  (loop (car tal)(cdr tal)))
	      (begin
		(debug:print-info 8 *default-log-port* "waitons: " waitons)







>
|







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








|







1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887

;;======================================================================
;; refactoring this block into tests:get-full-data from line 263 of runs.scm
;;======================================================================
;; hed is the test name
;; test-records is a hash of test-name => test record
(define (tests:get-full-data test-names test-records required-tests all-tests-registry)
  (let ((missing-waitons (make-hash-table)))
    (if (not (null? test-names))
      (let loop ((hed (car test-names))
		 (tal (cdr test-names)))         ;; 'return-procs tells the config reader to prep running system but return a proc
	(debug:print-info 4 *default-log-port* "hed=" hed " at top of loop")
        ;; don't know item-path at this time, let the testconfig get the top level testconfig
	(let* ((config  (tests:get-testconfig hed #f all-tests-registry 'return-procs))
	       (waitons (let ((instr (if config 
					 (configf:lookup config "requirements" "waiton")
					 (begin ;; No config means this is a non-existent test
                                           (let ((waiters '()))
                                             ;; find the waiter(s) for this waiton.
                                             (for-each 
                                               (lambda(waiter)
                                                 ;; (print "test-record = " (hash-table-ref test-records waiter))
                                                 ;; (print "waitons = " (vector-ref (hash-table-ref test-records waiter) 2))
                                                 (if (member hed (vector-ref (hash-table-ref test-records waiter) 2))
                                                    (set! waiters (cons waiter waiters))
                                                 )
                                               )
                                             (hash-table-keys test-records))
                                             (hash-table-set! missing-waitons hed waiters)
                                           )
					   ""))))
			  (debug:print-info 8 *default-log-port* "waitons string is " instr)
			  (string-split (cond
					 ((procedure? instr)
					  (let ((res (instr)))
					    (debug:print-info 8 *default-log-port* "waiton procedure results in string " res " for test " hed)
					    res))
					 ((string? instr)     instr)
					 (else 
					  ;; NOTE: This is actually the case of *no* waitons! ;; 
					  ""))))))
	  (if (not config) ;; this is a non-existant test called in a waiton. 
	      (if (null? tal)
		  test-records
		  (loop (car tal)(cdr tal)))
	      (begin
		(debug:print-info 8 *default-log-port* "waitons: " waitons)
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925







1926
1927
1928
1929
1930
1931
1932
						     (debug:print-info 4 *default-log-port* "items and itemstable are lists, calc now\n"
								       "    items: " items " itemstable: " itemstable)
						     (items:get-items-from-config config))
						    (else #f)))                           ;; not iterated
						 #f      ;; itemsdat 5
						 #f      ;; spare - used for item-path
						 )))
		(for-each 
		 (lambda (waiton)
		   (if (and waiton (not (member waiton test-names)))
		       (begin
			 (set! required-tests (cons waiton required-tests))
			 (set! test-names (cons waiton test-names))))) ;; was an append, now a cons
		 waitons)
		(let ((remtests (delete-duplicates (append waitons tal))))
		  (if (not (null? remtests))
		      (loop (car remtests)(cdr remtests))
		      test-records))))))))








;;======================================================================
;; test steps
;;======================================================================

;; teststep-set-status! used to be here








|

|







|
>
>
>
>
>
>
>







1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
						     (debug:print-info 4 *default-log-port* "items and itemstable are lists, calc now\n"
								       "    items: " items " itemstable: " itemstable)
						     (items:get-items-from-config config))
						    (else #f)))                           ;; not iterated
						 #f      ;; itemsdat 5
						 #f      ;; spare - used for item-path
						 )))
                (for-each 
		 (lambda (waiton)
		   (if (and waiton (not (string= "#f" waiton)) (not (member waiton test-names)))
		       (begin
			 (set! required-tests (cons waiton required-tests))
			 (set! test-names (cons waiton test-names))))) ;; was an append, now a cons
		 waitons)
		(let ((remtests (delete-duplicates (append waitons tal))))
		  (if (not (null? remtests))
		      (loop (car remtests)(cdr remtests))
		      test-records)))))))
      (for-each
         (lambda (missing-waiton)
            (debug:print-error 0 *default-log-port* "non-existent test \"" missing-waiton "\" is a waiton for tests " (hash-table-ref missing-waitons missing-waiton))
         )
         (hash-table-keys missing-waitons)
      )
))

;;======================================================================
;; test steps
;;======================================================================

;; teststep-set-status! used to be here

Modified tests/mintest/megatest.config from [bfa94e44af] to [444a72500f].

17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34

[fields]
X TEXT

[setup]
max_concurrent_jobs 50
linktree #{getenv MT_RUN_AREA_HOME}/linktree
transport http

[server]
port 8090

[jobtools]
useshell yes
launcher nbfind

[disks]
disk0 #{getenv PWD}/runs







<






|



17
18
19
20
21
22
23

24
25
26
27
28
29
30
31
32
33

[fields]
X TEXT

[setup]
max_concurrent_jobs 50
linktree #{getenv MT_RUN_AREA_HOME}/linktree


[server]
port 8090

[jobtools]
useshell yes
launcher nbfake

[disks]
disk0 #{getenv PWD}/runs

Modified tests/mintest/tests/a/testconfig from [7f9803b9fe] to [61be51e47c].

14
15
16
17
18
19
20







21
22
23
# 
#     You should have received a copy of the GNU General Public License
#     along with Megatest.  If not, see <http://www.gnu.org/licenses/>.

# Add steps here. Format is "stepname script"
[ezsteps]
step1 echo SUCCESS








[requirements]
waiton b







>
>
>
>
>
>
>



14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
# 
#     You should have received a copy of the GNU General Public License
#     along with Megatest.  If not, see <http://www.gnu.org/licenses/>.

# Add steps here. Format is "stepname script"
[ezsteps]
step1 echo SUCCESS
# step1 ((xterm&);echo SUCCESS)
# step2 xterm_and_success

[scripts]
xterm_and_success #!/bin/bash
  xterm -T step2 &
  echo SUCCESS

[requirements]
waiton b

Modified utils/mk_wrapper from [713ec8f660] to [4fc79e58e7].

42
43
44
45
46
47
48









49
50
51
52
53
54
55
if [ "\$LD_LIBRARY_PATH" != "" ];then
  export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:\$LD_LIBRARY_PATH:$libdir
else
  export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$libdir
fi

export MT_SQLITE3_EXE=$sqlite3_exe









__EOF
) > $cfgfile
  echo 
else
  echo "INFO: LD_LIBRARY_PATH not set" >&2
fi








>
>
>
>
>
>
>
>
>







42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
if [ "\$LD_LIBRARY_PATH" != "" ];then
  export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:\$LD_LIBRARY_PATH:$libdir
else
  export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$libdir
fi

export MT_SQLITE3_EXE=$sqlite3_exe

http_vars="http_proxy https_proxy HTTP_PROXY HTTPS_PROXY"
for i in \$http_vars
do
j=\${!i}
if [ "\$j" != "" ]; then
   unset \$i
fi
done
__EOF
) > $cfgfile
  echo 
else
  echo "INFO: LD_LIBRARY_PATH not set" >&2
fi

91
92
93
94
95
96
97
98
99
100
101
102
103
if [[ \$(ulimit -a | grep 'open files' | awk '{print \$4}') -gt 10000 ]];then ulimit -n 10000;fi
EOF

# echo "#!/bin/bash" > $target
# echo "exec $prefix/bin/.\$(lsb_release -sr)/$cmd \"\$@\"" >> $target

echo "lsbr=\$(lsb_release -sr)" >> $target
if [ "$LD_LIBRARY_PATH" != "" ];then
  echo "source $prefix/bin/.\$lsbr/cfg.sh" >> $target
fi

# echo "if [[ -e \$lsbr ]];then source \$lsbr;fi" >> $target
echo "exec $prefix/bin/.\$lsbr/$cmd \"\$@\"" >> $target







<
|
<



100
101
102
103
104
105
106

107

108
109
110
if [[ \$(ulimit -a | grep 'open files' | awk '{print \$4}') -gt 10000 ]];then ulimit -n 10000;fi
EOF

# echo "#!/bin/bash" > $target
# echo "exec $prefix/bin/.\$(lsb_release -sr)/$cmd \"\$@\"" >> $target

echo "lsbr=\$(lsb_release -sr)" >> $target

echo "source $prefix/bin/.\$lsbr/cfg.sh" >> $target


# echo "if [[ -e \$lsbr ]];then source \$lsbr;fi" >> $target
echo "exec $prefix/bin/.\$lsbr/$cmd \"\$@\"" >> $target