Milimetric has uploaded a new change for review. ( https://gerrit.wikimedia.org/r/370322 )
Change subject: [WIP] Don't merge this ...................................................................... [WIP] Don't merge this This change that allows us to run one-off _private snapshots more easily. I'm not sure whether you can set private_suffix to an empty string, and I haven't tested that yet. I'm just going to use this change to run the 2017-07_private snapshot, and we can decide what to do when Joseph's back. Change-Id: Ib63f27430c15872de1966fa51728211dfe6b3486 --- M oozie/mediawiki/history/datasets.xml M oozie/mediawiki/history/datasets_raw.xml M oozie/mediawiki/history/denormalize/coordinator.properties M oozie/mediawiki/history/denormalize/coordinator.xml 4 files changed, 18 insertions(+), 16 deletions(-) git pull ssh://gerrit.wikimedia.org:29418/analytics/refinery refs/changes/22/370322/1 diff --git a/oozie/mediawiki/history/datasets.xml b/oozie/mediawiki/history/datasets.xml index c2232d8..08bab57 100644 --- a/oozie/mediawiki/history/datasets.xml +++ b/oozie/mediawiki/history/datasets.xml @@ -22,7 +22,7 @@ frequency="${coord:months(1)}" initial-instance="${start_time}" timezone="Universal"> - <uri-template>${mw_directory}/user_history/snapshot=${YEAR}-${MONTH}</uri-template> + <uri-template>${mw_directory}/user_history/snapshot=${YEAR}-${MONTH}${private_suffix}</uri-template> <done-flag>_SUCCESS</done-flag> </dataset> @@ -30,7 +30,7 @@ frequency="${coord:months(1)}" initial-instance="${start_time}" timezone="Universal"> - <uri-template>${mw_directory}/page_history/snapshot=${YEAR}-${MONTH}</uri-template> + <uri-template>${mw_directory}/page_history/snapshot=${YEAR}-${MONTH}${private_suffix}</uri-template> <done-flag>_SUCCESS</done-flag> </dataset> @@ -38,7 +38,7 @@ frequency="${coord:months(1)}" initial-instance="${start_time}" timezone="Universal"> - <uri-template>${mw_directory}/history/snapshot=${YEAR}-${MONTH}</uri-template> + <uri-template>${mw_directory}/history/snapshot=${YEAR}-${MONTH}${private_suffix}</uri-template> <done-flag>_SUCCESS</done-flag> </dataset> @@ -48,7 +48,7 @@ frequency="${coord:months(1)}" initial-instance="${start_time}" timezone="Universal"> - <uri-template>${mw_directory}/user_history/snapshot=${YEAR}-${MONTH}</uri-template> + <uri-template>${mw_directory}/user_history/snapshot=${YEAR}-${MONTH}${private_suffix}</uri-template> <done-flag>_PARTITIONED</done-flag> </dataset> @@ -56,7 +56,7 @@ frequency="${coord:months(1)}" initial-instance="${start_time}" timezone="Universal"> - <uri-template>${mw_directory}/page_history/snapshot=${YEAR}-${MONTH}</uri-template> + <uri-template>${mw_directory}/page_history/snapshot=${YEAR}-${MONTH}${private_suffix}</uri-template> <done-flag>_PARTITIONED</done-flag> </dataset> @@ -64,7 +64,7 @@ frequency="${coord:months(1)}" initial-instance="${start_time}" timezone="Universal"> - <uri-template>${mw_directory}/history/snapshot=${YEAR}-${MONTH}</uri-template> + <uri-template>${mw_directory}/history/snapshot=${YEAR}-${MONTH}${private_suffix}</uri-template> <done-flag>_PARTITIONED</done-flag> </dataset> @@ -73,7 +73,7 @@ frequency="${coord:months(1)}" initial-instance="${start_time}" timezone="Universal"> - <uri-template>${mw_directory}/metrics/snapshot=${YEAR}-${MONTH}</uri-template> + <uri-template>${mw_directory}/metrics/snapshot=${YEAR}-${MONTH}${private_suffix}</uri-template> <done-flag>_SUCCESS</done-flag> </dataset> </datasets> diff --git a/oozie/mediawiki/history/datasets_raw.xml b/oozie/mediawiki/history/datasets_raw.xml index a672a0e..931d5e3 100644 --- a/oozie/mediawiki/history/datasets_raw.xml +++ b/oozie/mediawiki/history/datasets_raw.xml @@ -25,7 +25,7 @@ frequency="${coord:months(1)}" initial-instance="${start_time}" timezone="Universal"> - <uri-template>${mw_raw_directory}/tables/archive/snapshot=${YEAR}-${MONTH}</uri-template> + <uri-template>${mw_raw_directory}/tables/archive/snapshot=${YEAR}-${MONTH}${private_suffix}</uri-template> <done-flag>_SUCCESS</done-flag> </dataset> @@ -33,7 +33,7 @@ frequency="${coord:months(1)}" initial-instance="${start_time}" timezone="Universal"> - <uri-template>${mw_raw_directory}/tables/logging/snapshot=${YEAR}-${MONTH}</uri-template> + <uri-template>${mw_raw_directory}/tables/logging/snapshot=${YEAR}-${MONTH}${private_suffix}</uri-template> <done-flag>_SUCCESS</done-flag> </dataset> @@ -41,7 +41,7 @@ frequency="${coord:months(1)}" initial-instance="${start_time}" timezone="Universal"> - <uri-template>${mw_raw_directory}/tables/page/snapshot=${YEAR}-${MONTH}</uri-template> + <uri-template>${mw_raw_directory}/tables/page/snapshot=${YEAR}-${MONTH}${private_suffix}</uri-template> <done-flag>_SUCCESS</done-flag> </dataset> @@ -49,7 +49,7 @@ frequency="${coord:months(1)}" initial-instance="${start_time}" timezone="Universal"> - <uri-template>${mw_raw_directory}/tables/revision/snapshot=${YEAR}-${MONTH}</uri-template> + <uri-template>${mw_raw_directory}/tables/revision/snapshot=${YEAR}-${MONTH}${private_suffix}</uri-template> <done-flag>_SUCCESS</done-flag> </dataset> @@ -57,7 +57,7 @@ frequency="${coord:months(1)}" initial-instance="${start_time}" timezone="Universal"> - <uri-template>${mw_raw_directory}/tables/user/snapshot=${YEAR}-${MONTH}</uri-template> + <uri-template>${mw_raw_directory}/tables/user/snapshot=${YEAR}-${MONTH}${private_suffix}</uri-template> <done-flag>_SUCCESS</done-flag> </dataset> @@ -65,7 +65,7 @@ frequency="${coord:months(1)}" initial-instance="${start_time}" timezone="Universal"> - <uri-template>${mw_raw_directory}/tables/user_groups/snapshot=${YEAR}-${MONTH}</uri-template> + <uri-template>${mw_raw_directory}/tables/user_groups/snapshot=${YEAR}-${MONTH}${private_suffix}</uri-template> <done-flag>_SUCCESS</done-flag> </dataset> </datasets> diff --git a/oozie/mediawiki/history/denormalize/coordinator.properties b/oozie/mediawiki/history/denormalize/coordinator.properties index 8ed1900..21ad83e 100644 --- a/oozie/mediawiki/history/denormalize/coordinator.properties +++ b/oozie/mediawiki/history/denormalize/coordinator.properties @@ -42,6 +42,8 @@ # HDFS path to mediawiki history datasets definitions datasets_file = ${oozie_directory}/mediawiki/history/datasets.xml mw_directory = ${name_node}/wmf/data/wmf/mediawiki +# If running a manual _private snapshot, set this to _private, otherwise leave empty +private_suffix = '' # mw tables mw_project_namespace_map_table = wmf_raw.mediawiki_project_namespace_map @@ -94,4 +96,4 @@ # Coordinator to start. oozie.coord.application.path = ${coordinator_file} oozie.use.system.libpath = true -oozie.action.external.stats.write = true \ No newline at end of file +oozie.action.external.stats.write = true diff --git a/oozie/mediawiki/history/denormalize/coordinator.xml b/oozie/mediawiki/history/denormalize/coordinator.xml index 4a7144f..741a436 100644 --- a/oozie/mediawiki/history/denormalize/coordinator.xml +++ b/oozie/mediawiki/history/denormalize/coordinator.xml @@ -125,7 +125,7 @@ <configuration> <property> <name>snapshot</name> - <value>${coord:formatTime(coord:nominalTime(), "yyyy")}-${coord:formatTime(coord:nominalTime(), "MM")}</value> + <value>${coord:formatTime(coord:nominalTime(), "yyyy")}-${coord:formatTime(coord:nominalTime(), "MM")}${private_suffix}</value> </property> <property> <name>user_history_location</name> @@ -157,4 +157,4 @@ </sla:info> </action> -</coordinator-app> \ No newline at end of file +</coordinator-app> -- To view, visit https://gerrit.wikimedia.org/r/370322 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: newchange Gerrit-Change-Id: Ib63f27430c15872de1966fa51728211dfe6b3486 Gerrit-PatchSet: 1 Gerrit-Project: analytics/refinery Gerrit-Branch: master Gerrit-Owner: Milimetric <dandree...@wikimedia.org> _______________________________________________ MediaWiki-commits mailing list MediaWiki-commits@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits