Details
-
Improvement
-
Status: Open
-
Minor
-
Resolution: Unresolved
-
None
-
None
Description
The retry policy in DFSInputStream#refetchLocations was first written many years ago. It allows configuration of the base time window, but subsequent retries double in an un-configurable way. This retry strategy makes sense in some clusters as it's very conservative and will avoid DDOSing the namenode in certain systemic failure modes – for example, if a file is being read by a large hadoop job and the underlying blocks are moved by the balancer. In this case, enough datanodes would be added to the deadNodes list and all hadoop tasks would simultaneously try to refetch the blocks. The 3s doubling with random factor helps break up that stampeding herd.
However, not all cluster use-cases are created equal, so there are other cases where a more aggressive initial backoff is preferred. For example in a low-latency single reader scenario. In this case, if the balancer moves enough blocks, the reader hits this 3s backoff which is way too long for a low latency use-case.
One could configure the the window very low (10ms), but then you can hit other systemic failure modes which would result in readers DDOSing the namenode again. For example, if blocks went missing due to truly dead datanodes. In this case, many readers might be refetching locations for different files with retry backoffs like 10ms, 20ms, 40ms, etc. It takes a while to backoff enough to avoid impacting the namenode with that strategy.
I suggest adding a configurable multiplier to the backoff strategy so that operators can tune this as they see fit for their use-case. In the above low latency case, one could set the base very low (say 2ms) and the multiplier very high (say 50). This gives an aggressive first retry that very quickly backs off.
Attachments
Issue Links
- relates to
-
HBASE-26250 Automatic and near real-time healing of locality
-
- Open
-
- links to
