Overview
| Comment: | speculative fixes for lockdb issues and dead server connections (bug d33ba94) |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | v1.60 | v1.6005_ww45.2 |
| Files: | files | file ages | folders |
| SHA1: |
85565c63a070d7ea7f3a639e1efdffb9 |
| User & Date: | matt on 2014-11-05 03:18:40 |
| Other Links: | branch diff | manifest | tags |
Context
|
2014-11-05
| ||
| 11:05 | Added exception handler to lock-queue call. Added transaction to create db in tdb check-in: 343a1c8579 user: mrwellan tags: v1.60 | |
| 03:18 | speculative fixes for lockdb issues and dead server connections (bug d33ba94) check-in: 85565c63a0 user: matt tags: v1.60, v1.6005_ww45.2 | |
|
2014-11-04
| ||
| 22:44 | Improvements to sharing access to lock db in lock-queue check-in: 96e9934cfa user: matt tags: v1.60 | |
Changes
Modified lock-queue.scm from [9d2a7c3661] to [f53d3994cd].
| ︙ | ︙ | |||
141 142 143 144 145 146 147 |
(define (lock-queue:release-lock fname test-id #!key (count 10))
(let* ((dbdat (lock-queue:open-db fname)))
(handle-exceptions
exn
(begin
(debug:print 0 "WARNING: Failed to release queue lock. Will try again in few seconds")
(debug:print 0 " message: " ((condition-property-accessor 'exn 'message) exn))
| | > > > > > > > > | | 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 |
(define (lock-queue:release-lock fname test-id #!key (count 10))
(let* ((dbdat (lock-queue:open-db fname)))
(handle-exceptions
exn
(begin
(debug:print 0 "WARNING: Failed to release queue lock. Will try again in few seconds")
(debug:print 0 " message: " ((condition-property-accessor 'exn 'message) exn))
(thread-sleep! (/ count 10))
(if (> count 0)
(begin
(sqlite3:finalize! (lock-queue:db-dat-get-db dbdat))
(lock-queue:release-lock fname test-id count: (- count 1)))
(let ((journal (conc fname "-journal")))
;; If we've tried ten times and failed there is a serious problem
;; try to remove the lock db and allow it to be recreated
(handle-exceptions
exn
#f
(if (file-exists? journal)(delete-file journal))
(if (file-exists? fname) (delete-file fname))
#f))))
(sqlite3:execute (lock-queue:db-dat-get-db dbdat) "DELETE FROM runlocks WHERE test_id=?;" test-id)
(sqlite3:finalize! (lock-queue:db-dat-get-db dbdat)))))
(define (lock-queue:steal-lock dbdat test-id #!key (count 10))
(debug:print-info 0 "Attempting to steal lock at " (lock-queue:db-dat-get-path dbdat))
(tasks:wait-on-journal (lock-queue:db-dat-get-path dbdat) 1200 "lock-queue:steal-lock; waiting on journal")
(handle-exceptions
|
| ︙ | ︙ |
Modified rmt.scm from [ef41e52830] to [f191ba6eba].
| ︙ | ︙ | |||
88 89 90 91 92 93 94 95 96 97 98 99 100 101 |
(if connection-info
(let ((res (http-transport:client-api-send-receive run-id connection-info cmd jparams)))
(http-transport:server-dat-update-last-access connection-info)
(if res
(db:string->obj res)
(let ((new-connection-info (client:setup run-id)))
(debug:print 0 "WARNING: Communication failed, trying call to http-transport:client-api-send-receive again.")
(rmt:send-receive cmd run-id params))))
(let ((max-avg-qry (string->number (or (configf:lookup *configdat* "server" "server-query-threshold") "-1"))))
(debug:print-info 4 "no server and read-only query, bypassing normal channel")
;; (if (rmt:write-frequency-over-limit? cmd run-id)(server:kind-run run-id))
(let ((curr-max (rmt:get-max-query-average)))
(if (> (cdr curr-max) max-avg-qry)
(begin
| > | 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 |
(if connection-info
(let ((res (http-transport:client-api-send-receive run-id connection-info cmd jparams)))
(http-transport:server-dat-update-last-access connection-info)
(if res
(db:string->obj res)
(let ((new-connection-info (client:setup run-id)))
(debug:print 0 "WARNING: Communication failed, trying call to http-transport:client-api-send-receive again.")
(hash-table-delete! *runremote* run-id)
(rmt:send-receive cmd run-id params))))
(let ((max-avg-qry (string->number (or (configf:lookup *configdat* "server" "server-query-threshold") "-1"))))
(debug:print-info 4 "no server and read-only query, bypassing normal channel")
;; (if (rmt:write-frequency-over-limit? cmd run-id)(server:kind-run run-id))
(let ((curr-max (rmt:get-max-query-average)))
(if (> (cdr curr-max) max-avg-qry)
(begin
|
| ︙ | ︙ |