Megatest

Check-in [93a64cc658]
Login
☰Home Timeline Files Branches Tags Tickets Wiki Login
Overview
Comment:cleaned up debug messages
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | v1.65-telemetry
Files: files | file ages | folders
SHA1: 93a64cc658c724fcd79a05faa637853c868665bb
User & Date: bjbarcla on 2019-02-27 17:14:25
Other Links: branch diff | manifest | tags
Context
2019-02-27
17:16
capture telemetry todo check-in: 44acc1ef5a user: bjbarcla tags: v1.65-telemetry
17:14
cleaned up debug messages check-in: 93a64cc658 user: bjbarcla tags: v1.65-telemetry
2019-02-26
17:01
corrected rmt:general-call call check-in: 9d5c51a64f user: bjbarcla tags: v1.65-telemetry
Changes
Hide Diffs Side-by-Side Diffs Ignore Whitespace Patch

Modified db.scm from [47c4f51cd1] to [cffb18caf7].

︙
1674
1675
1676
1677
1678
1679
1680
1681

1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696

1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712

1713
1714
1715
1716
1717
1718
1719

1674
1675
1676
1677
1678
1679
1680

1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695

1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711

1712
1713
1714
1715
1716
1717
1718
1719








-
+














-
+















-
+








                   (equal? item-path "")) ;; this is a toplevel test
              ;; what to do with toplevel? call rollup?
              (begin
                (set! toplevels   (cons (list test-id run-dir uname testname item-path run-id) toplevels))
                (debug:print-info 0 *default-log-port* "Found old toplevel test in RUNNING state, test-id=" test-id))
              (begin
                (set! incompleted (cons (list test-id run-dir uname testname item-path run-id) incompleted))
                (debug:print-info 0 *default-log-port* "BB> Found old test in RUNNING state, test-id=" test-id" exceeded running-deadtime "running-deadtime" now="(current-seconds)" event-time="event-time" run-duration="run-duration))))
                (debug:print-info 0 *default-log-port* "Found old test in RUNNING state, test-id=" test-id" exceeded running-deadtime "running-deadtime" now="(current-seconds)" event-time="event-time" run-duration="run-duration))))
        db
        "SELECT id,rundir,uname,testname,item_path,event_time,run_duration FROM tests WHERE run_id=? AND (strftime('%s','now') - event_time) > (run_duration + ?) AND state IN ('RUNNING');"
        run-id running-deadtime)

       
       (sqlite3:for-each-row 
        (lambda (test-id run-dir uname testname item-path event-time run-duration)
          (if (and (equal? uname "n/a")
                   (equal? item-path "")) ;; this is a toplevel test
              ;; what to do with toplevel? call rollup?
              (begin
                (set! toplevels   (cons (list test-id run-dir uname testname item-path run-id) toplevels))
                (debug:print-info 0 *default-log-port* "Found old toplevel test in RUNNING state, test-id=" test-id))
              (begin
                (debug:print-info 0 *default-log-port* "BB> Found old test in REMOTEHOSTSTART state, test-id=" test-id" exceeded running-deadtime "running-deadtime" now="(current-seconds)" event-time="event-time" run-duration="run-duration)
                (debug:print-info 0 *default-log-port* "Found old test in REMOTEHOSTSTART state, test-id=" test-id" exceeded running-deadtime "running-deadtime" now="(current-seconds)" event-time="event-time" run-duration="run-duration)
                (set! incompleted (cons (list test-id run-dir uname testname item-path run-id) incompleted)))))
        db
        "SELECT id,rundir,uname,testname,item_path,event_time,run_duration FROM tests WHERE run_id=? AND (strftime('%s','now') - event_time) > (run_duration + ?) AND state IN ('REMOTEHOSTSTART');"
        run-id remotehoststart-deadtime)

       ;; in LAUNCHED for more than one day. Could be long due to job queues TODO/BUG: Need override for this in config
       ;;
       ;; (db:delay-if-busy dbdat)
       (sqlite3:for-each-row
        (lambda (test-id run-dir uname testname item-path)
          (if (and (equal? uname "n/a")
                   (equal? item-path "")) ;; this is a toplevel test
              ;; what to do with toplevel? call rollup?
              (set! toplevels   (cons (list test-id run-dir uname testname item-path run-id) toplevels))
              (begin
                (debug:print-info 0 *default-log-port* "BB> Found old test in REMOTEHOSTSTART state, test-id=" test-id" exceeded remotehoststart-deadtime "remotehoststart-deadtime)
                (debug:print-info 0 *default-log-port* "Found old test in LAUNCHED state, test-id=" test-id" 1 day since event_time marked")
                (set! oldlaunched (cons (list test-id run-dir uname testname item-path run-id) oldlaunched)))))
        db
        "SELECT id,rundir,uname,testname,item_path FROM tests WHERE run_id=? AND (strftime('%s','now') - event_time) > 86400 AND state IN ('LAUNCHED');"
        run-id)
       
       (debug:print-info 18 *default-log-port* "Found " (length oldlaunched) " old LAUNCHED items, " (length toplevels) " old LAUNCHED toplevel tests and " (length incompleted) " tests marked RUNNING but apparently dead.")
︙

Modified docs/manual/megatest_manual.html from [453b3aeb82] to [eadc4c2938].

︙
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970

898
899
900
901
902
903
904



























































905
906
907
908
909
910
911








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








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.</p></div>
</div>
</div>
</div>
<div class="sect1">
<h2 id="_overview">Overview</h2>
<div class="sectionbody">
<div class="sect2">
<h3 id="_stand_alone_megatest_area">Stand-alone Megatest Area</h3>
<div class="paragraph"><p>A single, stand-alone, Megatest based testsuite or "area" is
sufficient for most validation, automation and build problems.</p></div>
<div class="imageblock">
<div class="content">
<img src="megatest-stand-alone-area.png" alt="Static">
</div>
</div>
<div class="paragraph"><p>Megatest is designed as a distributed or decoupled system. This means
you can run the areas stand-alone with no additional
infrastructure. I.e. there are no databases, web servers or other
centralized resources needed. However as your needs grow you can
integrate multiple areas into a bigger system.</p></div>
<div class="sect3">
<h4 id="_component_descriptions">Component Descriptions</h4>
<div class="olist arabic"><ol class="arabic">
<li>
<p>
Multi-area dashboard and xterm. A gui (the dashboard) is usually the
  best option for controlling and launching runs but all operations
  can also be done from the commandline. Note: The not yet released
  multi-area dashboard replaces the old dashboard for browsing and
  controlling runs but for managing a single area the old dashboard
  works very well.
</p>
</li>
<li>
<p>
Area/testsuite. This is your testsuite or automation definition and
  consists of the information in megatest.config, runconfigs.config
  and your testconfigs along with any custom scripting that can&#8217;t be
  done with the native Megatest features.
</p>
</li>
<li>
<p>
If your testsuite or build automation is too large to run on a
  single instance you can distribute your jobs into a compute server
  pool. The only current requirements are password-less ssh access and
  a network filesystem.
</p>
</li>
</ol></div>
</div>
</div>
<div class="sect2">
<h3 id="_full_system_architecture">Full System Architecture</h3>
<div class="imageblock">
<div class="content">
<img src="megatest-system-architecture.png" alt="Static">
</div>
</div>
</div>
</div>
</div>
<div class="sect1">
<h2 id="_installation">Installation</h2>
<div class="sectionbody">
<div class="sect2">
<h3 id="_dependencies">Dependencies</h3>
<div class="paragraph"><p>Chicken scheme and a number of "eggs" are required for building
︙
3031
3032
3033
3034
3035
3036
3037
3038

3039
3040
3041
3042

2972
2973
2974
2975
2976
2977
2978

2979
2980
2981
2982
2983








-
+





</div>
</div>
</div>
<div id="footnotes"><hr></div>
<div id="footer">
<div id="footer-text">
Version 1.0<br>
Last updated 2018-11-29 09:32:52 PST
Last updated 2019-02-19 11:13:54 PST
</div>
</div>
</body>
</html>

Modified launch.scm from [7d23ee6c29] to [510de63cde].

︙
380
381
382
383
384
385
386
387

388
389
390
391
392
393
394

380
381
382
383
384
385
386

387
388
389
390
391
392
393
394








-
+








    ;; (tests:set-full-meta-info test-id run-id (calc-minutes) work-area)
    (tests:set-full-meta-info #f test-id run-id (calc-minutes) work-area 10)

    (let loop ((minutes   (calc-minutes))
	       (cpu-load  (alist-ref 'adj-core-load (common:get-normalized-cpu-load #f)))
	       (disk-free (get-df (current-directory)))
               (last-sync (current-seconds)))
      (BB> "launch:monitor-job - top of loop encountered at "(current-seconds)" with last-sync="last-sync)
      (common:telemetry-log "zombie" (conc "launch:monitor-job - top of loop encountered at "(current-seconds)" with last-sync="last-sync))
      (let* ((over-time     (> (current-seconds) (+ last-sync update-period)))
             (new-cpu-load  (let* ((load  (alist-ref 'adj-core-load (common:get-normalized-cpu-load #f)))
                                   (delta (abs (- load cpu-load))))
                              (if (> delta 0.1) ;; don't bother updating with small changes
                                  load
                                  #f)))
             (new-disk-free (let* ((df    (if over-time ;; only get df every 30 seconds
︙
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

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








-
+
















-
+

-
+








             (do-sync       (or new-cpu-load new-disk-free over-time))

             (test-info   (rmt:get-test-info-by-id run-id test-id))
             (state       (db:test-get-state test-info))
             (status      (db:test-get-status test-info))
             (kill-reason  "no kill reason specified")
             (kill-job?    #f))
        (BB> "launch:monitor-job - decision time encountered at "(current-seconds)" with last-sync="last-sync" do-sync="do-sync" over-time="over-time" update-period="update-period)
        (common:telemetry-log "zombie" (conc "launch:monitor-job - decision time encountered at "(current-seconds)" with last-sync="last-sync" do-sync="do-sync" over-time="over-time" update-period="update-period))
        (cond
         ((test-get-kill-request run-id test-id)
          (set! kill-reason "KILLING TEST since received kill request (KILLREQ)")
          (set! kill-job? #t))
         ((and runtlim (> (- (current-seconds) start-seconds) runtlim))
          (set! kill-reason (conc "KILLING TEST DUE TO TIME LIMIT EXCEEDED! Runtime=" run-seconds " seconds, limit=" runtlim))
          (set! kill-job? #t))
         ((equal? status "DEAD")
          (set! kill-reason "KILLING TEST because it was marked as DEAD by launch:handle-zombie-tests (might indicate really overloaded server or else overzealous setup.deadtime)")
          (set! kill-job? #t)))

        (debug:print 4 *default-log-port* "cpu: " new-cpu-load " disk: " new-disk-free " last-sync: " last-sync " do-sync: " do-sync)
        (launch:handle-zombie-tests run-id)
        (when do-sync
          ;;(with-output-to-file (conc (getenv "MT_TEST_RUN_DIR") "/last-loadinfo.log" #:append)
          ;;  (lambda () (pp (list (current-seconds) new-cpu-load new-disk-free (calc-minutes)))))
          (BB> "launch:monitor-job - dosync started at "(current-seconds))
          (common:telemetry-log "zombie" (conc  "launch:monitor-job - dosync started at "(current-seconds)))
          (tests:update-central-meta-info run-id test-id new-cpu-load new-disk-free (calc-minutes) #f #f)
          (BB> "launch:monitor-job - dosync finished at "(current-seconds)))
          (common:telemetry-log "zombie" (conc "launch:monitor-job - dosync finished at "(current-seconds)))
        
	(if kill-job? 
	    (begin
              (debug:print-info 0 *default-log-port* "proceeding to kill test: "kill-reason)
	      (mutex-lock! m)
	      ;; NOTE: The pid can change as different steps are run. Do we need handshaking between this
	      ;;       section and the runit section? Or add a loop that tries three times with a 1/4 second
︙

This page was generated in about 0.14s by Fossil 2.24 [452f8e1ffc] 2024-03-26 15:36:00