Hexiaoqiao commented on a change in pull request #1028: HDFS-14617 - Improve fsimage load time by writing sub-sections to the fsimage index URL: https://github.com/apache/hadoop/pull/1028#discussion_r301356812
########## File path: hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/DFSConfigKeys.java ########## @@ -878,6 +878,22 @@ public static final String DFS_IMAGE_TRANSFER_CHUNKSIZE_KEY = "dfs.image.transfer.chunksize"; public static final int DFS_IMAGE_TRANSFER_CHUNKSIZE_DEFAULT = 64 * 1024; + public static final String DFS_IMAGE_PARALLEL_LOAD_KEY = + "dfs.image.parallel.load"; + public static final boolean DFS_IMAGE_PARALLEL_LOAD_DEFAULT = true; + + public static final String DFS_IMAGE_PARALLEL_TARGET_SECTIONS_KEY = + "dfs.image.parallel.target.sections"; + public static final int DFS_IMAGE_PARALLEL_TARGET_SECTIONS_DEFAULT = 12; + + public static final String DFS_IMAGE_PARALLEL_INODE_THRESHOLD_KEY = + "dfs.image.parallel.inode.threshold"; + public static final int DFS_IMAGE_PARALLEL_INODE_THRESHOLD_DEFAULT = 1000000; + + public static final String DFS_IMAGE_PARALLEL_THREADS_KEY = + "dfs.image.parallel.threads"; + public static final int DFS_IMAGE_PARALLEL_THREADS_DEFAULT = 4; + Review comment: IIUC, threads size should be not greater than target sections, otherwise the remaining threads will not be used or some other issues. So is it necessary to warn this configuration limit? ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
