Index: launch.scm ================================================================== --- launch.scm +++ launch.scm @@ -205,11 +205,11 @@ ) )))))) (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"))) + (let* ((update-period (string->number (or (configf:lookup *configdat* "setup" "test-stats-update-period") "60"))) (start-seconds (current-seconds)) (calc-minutes (lambda () (inexact->exact (round (- @@ -259,11 +259,12 @@ (rmt:set-state-status-and-roll-up-items run-id test-id 'foo "RUNNING" "n/a" "was marked dead; really still running.") ;;(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)") ;; MARK RUNNING (set! kill-job? #f))) (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) + (if (common:low-noise-print 600 "run zombie") ;; every five minutes is plenty + (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))))) ;; (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)