This is an automated email from the ASF dual-hosted git repository. michaelsmith pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/impala.git
commit 782cda44996ac73c0c14cc0727683c9e3ef1fd1a Author: Michael Smith <[email protected]> AuthorDate: Thu Sep 21 15:17:07 2023 -0700 IMPALA-12453: Increase yarn high disk threshold Yarn will mark a node as unavailable for running jobs if it exceeds the disk threshold. We only have one node, so that means jobs hang until disk frees up. Exhaustive test runs are approaching using 300GB, which is a common size for our test environments, and we see some tests hanging on yarn jobs. Increases the disk threshold from default of 90% to 99%; in test environments the remaining 1% is ~3GB. That should still be sufficient in case yarn needs to throttle workloads to avoid using all the disk, while leaving most of the disk available. Change-Id: I06b723e4ecea94ce95fb2bd41bd356fba694e87a Reviewed-on: http://gerrit.cloudera.org:8080/20501 Reviewed-by: Impala Public Jenkins <[email protected]> Tested-by: Impala Public Jenkins <[email protected]> --- .../cluster/node_templates/common/etc/hadoop/conf/yarn-site.xml.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/testdata/cluster/node_templates/common/etc/hadoop/conf/yarn-site.xml.py b/testdata/cluster/node_templates/common/etc/hadoop/conf/yarn-site.xml.py index f9372bf5a..dbcd9f9be 100644 --- a/testdata/cluster/node_templates/common/etc/hadoop/conf/yarn-site.xml.py +++ b/testdata/cluster/node_templates/common/etc/hadoop/conf/yarn-site.xml.py @@ -71,6 +71,11 @@ CONFIG = { # to speed up data-loading. 'yarn.nodemanager.resource.memory-mb': _get_yarn_nm_ram_mb(), + # Allow YARN to run with at least 3GB disk free. Otherwise it hangs completely. + # Avoids disabling YARN disk monitoring completely because otherwise multiple jobs might + # use up all the disk in a scenario where otherwise they could complete sequentially. + 'yarn.nodemanager.disk-health-checker.max-disk-utilization-per-disk-percentage': 99, + # Increase YARN container resources to 2GB to avoid dataload failures 'yarn.app.mapreduce.am.resource.mb': 2048,
