When doing a read in HAService mode, the program would go over the list of NameNodes to look for an ObserverNode to handle it. However, it does so even when there is no ObserverNode at all, and each StandbyNode would throw an exception (when using delegation token). Therefore, we fix it by setting up a period, which means that we only iterate over the list of NameNodes every couple of minutes instead of for any read requests.

We will only change the total number of NameNodes and see that we actually go over the for loop for each read request.

20 2 - 1 May. 16, 2024, 8:57 PM


Launch on Chameleon

Launching this artifact will open it within Chameleon’s shared Jupyter experiment environment, which is accessible to all Chameleon users with an active allocation.

Download Archive

Download an archive containing the files of this artifact.

Download with git

Clone the git repository for this artifact, and checkout the version's commit

git clone https://github.com/FarFlyField/hadoop-HDFS-15118.git
# cd into the created directory
git checkout f8dce6c501a804a32f629f2effbf5416df007634

Submit feedback through GitHub issues

Version Stats

6 2 -