From 9529f8aa40922f817b8868a3f21d498ec110ef9c Mon Sep 17 00:00:00 2001 From: Vytautas Jankauskas Date: Fri, 7 Jun 2019 14:31:53 +0200 Subject: [PATCH] Adding a configurable number of retries default configuration. More information on T0 twiki cookbook. --- bin/00_deploy_prod.sh | 8 ++++++++ bin/00_deploy_replay.sh | 9 +++++++++ 2 files changed, 17 insertions(+) diff --git a/bin/00_deploy_prod.sh b/bin/00_deploy_prod.sh index ef2af730..e79b1d6e 100755 --- a/bin/00_deploy_prod.sh +++ b/bin/00_deploy_prod.sh @@ -256,3 +256,11 @@ echo "config.AgentStatusWatcher.pendingSlotsSitePercent = 40" >> ./config/tier0/ echo "config.AgentStatusWatcher.runningExpressPercent = 25" >> ./config/tier0/config.py echo "config.AgentStatusWatcher.runningRepackPercent = 10" >> ./config/tier0/config.py +#Configurable retry number for failing jobs before they go to paused +echo "config.RetryManager.PauseAlgo.section_('Express')" >> ./config/tier0/config.py +echo "config.RetryManager.PauseAlgo.Express.retryErrorCodes = { 8001: 0, 70: 0, 50513: 0, 50660: 0, 50661: 0, 71304: 0, 99109: 0, 99303: 0, 99400: 0, 8001: 0, 50115: 0 }" >> ./config/tier0/config.py +echo "config.RetryManager.PauseAlgo.section_('Processing')" >> ./config/tier0/config.py +echo "config.RetryManager.PauseAlgo.Processing.retryErrorCodes = { 8001: 0, 70: 0, 50513: 0, 50660: 0, 50661: 0, 71304: 0, 99109: 0, 99303: 0, 99400: 0, 8001: 0, 50115: 0 }" >> ./config/tier0/config.py +echo "config.RetryManager.PauseAlgo.section_('Repack')" >> ./config/tier0/config.py +echo "config.RetryManager.PauseAlgo.Repack.retryErrorCodes = { 8001: 0, 70: 0, 50513: 0, 50660: 0, 50661: 0, 71304: 0, 99109: 0, 99303: 0, 99400: 0, 8001: 0, 50115: 0 }" >> ./config/tier0/config.py + diff --git a/bin/00_deploy_replay.sh b/bin/00_deploy_replay.sh index 8f629691..2391f1cf 100755 --- a/bin/00_deploy_replay.sh +++ b/bin/00_deploy_replay.sh @@ -226,3 +226,12 @@ echo "config.AgentStatusWatcher.pendingSlotsSitePercent = 40" >> ./config/tier0/ echo "config.AgentStatusWatcher.runningExpressPercent = 25" >> ./config/tier0/config.py echo "config.AgentStatusWatcher.runningRepackPercent = 10" >> ./config/tier0/config.py + +#Configurable retry number for failing jobs before they go to paused +echo "config.RetryManager.PauseAlgo.section_('Express')" >> ./config/tier0/config.py +echo "config.RetryManager.PauseAlgo.Express.retryErrorCodes = { 8001: 0, 70: 0, 50513: 0, 50660: 0, 50661: 0, 71304: 0, 99109: 0, 99303: 0, 99400: 0, 8001: 0, 50115: 0 }" >> ./config/tier0/config.py +echo "config.RetryManager.PauseAlgo.section_('Processing')" >> ./config/tier0/config.py +echo "config.RetryManager.PauseAlgo.Processing.retryErrorCodes = { 8001: 0, 70: 0, 50513: 0, 50660: 0, 50661: 0, 71304: 0, 99109: 0, 99303: 0, 99400: 0, 8001: 0, 50115: 0 }" >> ./config/tier0/config.py +echo "config.RetryManager.PauseAlgo.section_('Repack')" >> ./config/tier0/config.py +echo "config.RetryManager.PauseAlgo.Repack.retryErrorCodes = { 8001: 0, 70: 0, 50513: 0, 50660: 0, 50661: 0, 71304: 0, 99109: 0, 99303: 0, 99400: 0, 8001: 0, 50115: 0 }" >> ./config/tier0/config.py +