Skip to content

Commit

Permalink
Resolving parquet-tools memory error
Browse files Browse the repository at this point in the history
  • Loading branch information
chandrashekar-s committed May 9, 2024
1 parent 1dea2be commit 4ac7275
Showing 1 changed file with 12 additions and 6 deletions.
18 changes: 12 additions & 6 deletions e2e-tests/pipeline_validation.sh
Original file line number Diff line number Diff line change
Expand Up @@ -195,17 +195,23 @@ function fhir_source_query() {
# OPENMRS
#################################################
function test_parquet_sink() {

print_message "java heap"
print_message "$(java -XX:+PrintFlagsFinal -version | grep HeapSize)"

print_message "Counting number of patients, encounters and obs sinked to parquet files"
local total_patients_streamed=$(java -jar ./controller-spark/parquet-tools-1.11.1.jar rowcount \
"${HOME_PATH}/${PARQUET_SUBDIR}/Patient/" | awk '{print $3}')
local total_patients_streamed=$(java -Xms16g -Xmx16g -jar
./controller-spark/parquet-tools-1.11.1.jar rowcount "${HOME_PATH}/${PARQUET_SUBDIR}/Patient/" | \
awk '{print $3}')
print_message "Total patients synced to parquet ---> ${total_patients_streamed}"

local total_encounters_streamed=$(java -jar ./controller-spark/parquet-tools-1.11.1.jar rowcount \
"${HOME_PATH}/${PARQUET_SUBDIR}/Encounter/" | awk '{print $3}')
local total_encounters_streamed=$(java -Xms16g -Xmx16g -jar
./controller-spark/parquet-tools-1.11.1.jar rowcount "${HOME_PATH}/${PARQUET_SUBDIR}/Encounter/" \
| awk '{print $3}')
print_message "Total encounters synced to parquet ---> ${total_encounters_streamed}"

local total_obs_streamed=$(java -jar ./controller-spark/parquet-tools-1.11.1.jar rowcount \
"${HOME_PATH}/${PARQUET_SUBDIR}/Observation/" | awk '{print $3}')
local total_obs_streamed=$(java -Xms16g -Xmx16g -jar ./controller-spark/parquet-tools-1.11.1.jar \
rowcount "${HOME_PATH}/${PARQUET_SUBDIR}/Observation/" | awk '{print $3}')
print_message "Total obs synced to parquet ---> ${total_obs_streamed}"

if [[ "${total_patients_streamed}" == "${TOTAL_TEST_PATIENTS}" && "${total_encounters_streamed}" \
Expand Down

0 comments on commit 4ac7275

Please sign in to comment.