FYI, I just created FLINK-19568 for tracking this issue.
Thank you~ Xintong Song [1] https://issues.apache.org/jira/browse/FLINK-19568 On Mon, Oct 12, 2020 at 2:18 PM Xintong Song <tonysong...@gmail.com> wrote: > Hi Paul, > > Thanks for reporting this. > > Indeed, Flink's RM currently performs several HDFS operations in the rpc > main thread when preparing the TM context, which may block the main thread > when HDFS is slow. > > Unfortunately, I don't see any out-of-box approach that fixes the problem > at the moment, except for increasing the heartbeat timeout. > > As for the long run solution, I think there's an easier approach. We can > move creating of the TM contexts away from the rpc main thread. Ideally, we > should try to avoid performing any heavy operations which do not modify the > RM's internal states in the rpc main thread. With FLINK-19241, this can be > achieved easily by delegating the work to the io executor. > > Thank you~ > > Xintong Song > > > > On Mon, Oct 12, 2020 at 12:44 PM Paul Lam <paullin3...@gmail.com> wrote: > >> Hi, >> >> After FLINK-13184 is implemented (even with Flink 1.11), occasionally >> there would still be jobs >> with high parallelism getting TM-RM heartbeat timeouts when RM is busy >> creating TM contexts >> on cluster initialization and HDFS is slow at that moment. >> >> Apart from increasing the TM heartbeat timeout, is there any recommended >> out of the box >> approach that can reduce the chance of getting the timeouts? >> >> In the long run, is it possible to limit the number of taskmanager >> contexts that RM creates at >> a time, so that the heartbeat triggers can chime in? >> >> Thanks! >> >> Best, >> Paul Lam >> >