Updated docker container to only be used for the sparql server and up…

…dates every 30 minutes

Dockerfile

@@ -1,3 +1,14 @@
-# This docker file is used for populating and pushing the container for the official HRA KG with all data within
-FROM ghcr.io/hubmapconsortium/hra-do-server:main
-COPY dist /dist
+FROM phenoscape/blazegraph:latest
+
+# The URL of the blazegraph journal to use
+ENV DB_URL=http://cdn-humanatlas-io.s3-website.us-east-2.amazonaws.com/digital-objects/blazegraph.jnl
+
+RUN apt-get update && apt-get -y install cron
+
+COPY ./context/blazegraph.properties .
+COPY ./context/sync.cron /etc/cron.d/sync.cron
+RUN crontab /etc/cron.d/sync.cron
+
+COPY ./context/startup.sh ./context/sync.sh /
+
+ENTRYPOINT [ "/startup.sh" ]

context/blazegraph.properties

@@ -0,0 +1,50 @@
+#
+# Note: These options are applied when the journal and the triple store are
+# first created.
+
+##
+## Journal options.
+##
+
+# The backing file. This contains all your data.  You want to put this someplace
+# safe.  The default locator will wind up in the directory from which you start
+# your servlet container.
+com.bigdata.journal.AbstractJournal.file=blazegraph.jnl
+
+# The persistence engine.  Use 'Disk' for the WORM or 'DiskRW' for the RWStore.
+com.bigdata.journal.AbstractJournal.bufferMode=DiskRW
+
+# Setup for the RWStore recycler rather than session protection.
+com.bigdata.service.AbstractTransactionService.minReleaseAge=1
+
+# Enable group commit. See http://wiki.blazegraph.com/wiki/index.php/GroupCommit
+# Note: Group commit is a beta feature in BlazeGraph release 1.5.1.
+#com.bigdata.journal.Journal.groupCommit=true
+
+com.bigdata.btree.writeRetentionQueue.capacity=4000
+com.bigdata.btree.BTree.branchingFactor=128
+
+# 200M initial extent.
+com.bigdata.journal.AbstractJournal.initialExtent=209715200
+com.bigdata.journal.AbstractJournal.maximumExtent=209715200
+
+##
+## Setup for QUADS mode without the full text index.
+##
+com.bigdata.rdf.sail.truthMaintenance=false
+com.bigdata.rdf.store.AbstractTripleStore.quads=true
+com.bigdata.rdf.store.AbstractTripleStore.statementIdentifiers=false
+com.bigdata.rdf.store.AbstractTripleStore.textIndex=false
+com.bigdata.rdf.store.AbstractTripleStore.axiomsClass=com.bigdata.rdf.axioms.NoAxioms
+
+# Bump up the branching factor for the lexicon indices on the default kb.
+com.bigdata.namespace.kb.lex.com.bigdata.btree.BTree.branchingFactor=400
+
+# Bump up the branching factor for the statement indices on the default kb.
+com.bigdata.namespace.kb.spo.com.bigdata.btree.BTree.branchingFactor=1024
+
+# Uncomment to enable collection of OS level performance counters.  When
+# collected they will be self-reported through the /counters servlet and
+# the workbench "Performance" tab.
+#
+# com.bigdata.journal.Journal.collectPlatformStatistics=true

context/startup.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+echo "export DB_URL=${DB_URL}" > /sync.env
+echo "export BLAZEGRAPH_MEMORY=${BLAZEGRAPH_MEMORY}" >> /sync.env
+echo "export BLAZEGRAPH_TIMEOUT=${BLAZEGRAPH_TIMEOUT}" >> /sync.env
+echo "export BLAZEGRAPH_READONLY=${BLAZEGRAPH_READONLY}" >> /sync.env
+
+/sync.sh && cron -f

context/sync.cron

@@ -0,0 +1 @@
+*/30 * * * * /sync.sh > /proc/1/fd/1 2>/proc/1/fd/2

context/sync.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+source /sync.env
+PATH=$PATH:/usr/local/openjdk-8/bin
+
+LOCAL_DB=/data/blazegraph.jnl
+ETAG_FILE=${LOCAL_DB}.etag
+
+REMOTE_ETAG=$(curl -sIX GET $DB_URL | grep -i etag | cut -d\" -f 2)
+LOCAL_ETAG=$(touch $ETAG_FILE && cat $ETAG_FILE)
+
+if [ "$REMOTE_ETAG" != "$LOCAL_ETAG" ]; then
+  echo "Syncing DB with" $REMOTE_ETAG
+
+  curl --compressed -H 'Accept-encoding: gzip' -so $LOCAL_DB $DB_URL
+  echo $REMOTE_ETAG > $ETAG_FILE
+
+  killall -q java
+  cd /data
+  /blazegraph/entrypoint.sh &
+fi