[MAPREDUCE-7100] Provide options to skip adding resource request for data-local and rack-local respectively

• Type: Improvement
• Status: Patch Available
• Priority: Critical
• Resolution: Unresolved
• Component/s: applicationmaster
• Assignee: Zhaohui Xin
• Reporter: Xiang Li
• Created: 31/May/18 13:11
• Updated: 27/Feb/19 05:40

Description

We are using hadoop 2.7.3 and the computing layer is running out of the storage cluster (that is, node managers are running on a different set of nodes from data nodes). The problem we meet is that the container allocation is quite slow for some jobs.
After some debugging, we found that in org.apache.hadoop.mapreduce.v2.app.rm.RMContainerRequestor#addContainerReq() (the following code is from trunk, not 2.7.3)

protected void addContainerReq(ContainerRequest req) {
    // Create resource requests
    for (String host : req.hosts) {
      // Data-local
      if (!isNodeBlacklisted(host)) {
        addResourceRequest(req.priority, host, req.capability,
            null);
      }
    }

    // Nothing Rack-local for now
    for (String rack : req.racks) {
      addResourceRequest(req.priority, rack, req.capability,
          null);
    }

    // Off-switch
    addResourceRequest(req.priority, ResourceRequest.ANY, req.capability,
        req.nodeLabelExpression);
  }

It seem that the request of data-local and rack-local could be skipped when computing layer is not the same as the storage cluster.
If I get it correctly, req.hosts and req.racks are provided by InputFormat. If the mapper is to read HDFS, req.hosts is the corresponding data node and req.racks is its rack. The debug log of AM is like:

org.apache.hadoop.mapreduce.v2.app.rm.RMContainerRequestor: addResourceRequest: applicationId=1 priority=20 resourceName=<data-node> numContainers=1 #asks=1
org.apache.hadoop.mapreduce.v2.app.rm.RMContainerRequestor: addResourceRequest: applicationId=1 priority=20 resourceName=<its rack> numContainers=1 #asks=2
org.apache.hadoop.mapreduce.v2.app.rm.RMContainerRequestor: addResourceRequest: applicationId=1 priority=20 resourceName=* numContainers=1 #asks=3

Although eventually, the resource request with resourceName=<data-node> will not be satisfied (because the data node is not node manager) in RM, it could be better if AM does not request data-local or rack-local at the very beginning, when we already know that computer layer runs out of the storage cluster.

Issue Links

• relates to: YARN-9276 Filter non-existent resource requests actively