[ https://issues.apache.org/jira/browse/HADOOP-1245?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12533868 ]
Michael Bieniosek commented on HADOOP-1245: ------------------------------------------- It might be enough to use the value at the jobtracker as a default, and override with the tasktracker value if it's present (along with the compatibility note). If a tasktracker is configured differently than the jobtracker, it's more likely the configurer intended the tasktracker's value to be used, as opposed to the configurer expecting the tasktracker value to be ignored. So I doubt using the jobtracker as an overridable default will break anybody. > value for mapred.tasktracker.tasks.maximum taken from jobtracker, not > tasktracker > --------------------------------------------------------------------------------- > > Key: HADOOP-1245 > URL: https://issues.apache.org/jira/browse/HADOOP-1245 > Project: Hadoop > Issue Type: Bug > Components: mapred > Affects Versions: 0.12.3 > Reporter: Michael Bieniosek > Assignee: Michael Bieniosek > Attachments: tasktracker-max-tasks-1245.patch > > > I want to create a cluster with machines with different numbers of CPUs. > Consequently, each machine should have a different value for > mapred.tasktracker.tasks.maximum, since my map tasks are CPU bound. > When a new job starts up, the jobtracker uses its (single) value for > mapred.tasktracker.tasks.maximum to assign tasks. This means that each > tasktracker gets the same number of tasks, regardless of how I configured > that particular machine. > The jobtracker should not consult its config for the value of > mapred.tasktracker.tasks.maximum. It should assign tasks (or allow > tasktrackers to request tasks) according to each tasktracker's value of > mapred.tasktracker.tasks.maximum. > Originally, I thought the behavior was slightly different, so this issue > contained this text: > After the first task finishes on each tasktracker, the tasktracker will > request new tasks from the jobtracker according to the tasktracker's value > for mapred.tasktracker.tasks.maximum. So after the first round of map tasks > is done, the cluster reverts to a mode that works well for heterogeneous > clusters. -- This message is automatically generated by JIRA. - You can reply to this email to add a comment to the issue online.