[
https://issues.apache.org/jira/browse/YARN-4665?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Daniel Templeton updated YARN-4665:
---
Priority: Major (was: Critical)
Description:
The change introduced in YARN-514 opens up a hole into which applications can
fall and be lost. Prior to YARN-514, the {{submitApplication()}} call did not
complete until the application state was persisted to the state store. After
YARN-514, the {{submitApplication()}} call is asynchronous, with the
application state being saved later.
If the state store is slow or unresponsive, it may be that an application's
state may not be persisted for quite a while. During that time, if the RM
fails (over), all applications that have not yet been persisted to the state
store will be lost. If the active RM loses ZK connectivity, a significant
number of job submissions can pile up before the ZK connection times out,
resulting in a large pile of client failures when it finally does.
This issue is inherent in the design of YARN-514. I see three solutions:
1. Add a WAL to the state store. HBase does it, so we know how to do it. It
seems like a heavy solution to the original problem, however. It's certainly
not a trivial change.
2. Revert YARN-514 and update the RPC layer to allow a connection to be parked
if it's doing something that may take a while. This is a generally useful
feature but could be a deep rabbit hole.
3. Revert YARN-514 and add back-pressure to the job submission. For example, we
set a maximum number of threads that can simultaneously be assigned to handle
job submissions. When that threshold is reached, new job submissions get a
try-again-later response. This is also a generally useful feature and should be
a fairly constrained set of changes.
I think the third option is the most approachable. It's the smallest change,
and it adds useful behavior beyond solving the original issue.
was:
The change introduced in YARN-514 opens up a hole into which applications can
fall and be lost. Prior to YARN-514, the {{submitApplication()}} call did not
complete until the application state was persisted to the state store. After
YARN-514, the {{submitApplication()}} call is asynchronous, with the
application state being saved later.
If the state store is slow or unresponsive, it may be that an application's
state may not be persisted for quite a while. During that time, if the RM
fails (over), all applications that have not yet been persisted to the state
store will be lost without the client being aware.
This issue is inherent in the design of YARN-514. I see three solutions:
1. Add a WAL to the state store. HBase does it, so we know how to do it. It
seems like a heavy solution to the original problem, however. It's certainly
not a trivial change.
2. Revert YARN-514 and update the RPC layer to allow a connection to be parked
if it's doing something that may take a while. This is a generally useful
feature but could be a deep rabbit hole.
3. Revert YARN-514 and add back-pressure to the job submission. For example, we
set a maximum number of threads that can simultaneously be assigned to handle
job submissions. When that threshold is reached, new job submissions get a
try-again-later response. This is also a generally useful feature and should be
a fairly constrained set of changes. The downside is that it impacts the API.
I think the third option is the most approachable. It's the smallest change,
and it adds useful behavior beyond solving the original issue. And I don't
think the API impact is significant.
[~rohithsharma], I've updated the description to be more specific about the
issue. Yes, the client will keep polling, and it fails cleanly when the RM
fails, but the RM failure is not always clean, leaving the potential for huge
numbers of client failures.
> Asynch submit can lose application submissions
> --
>
> Key: YARN-4665
> URL: https://issues.apache.org/jira/browse/YARN-4665
> Project: Hadoop YARN
> Issue Type: Bug
>Affects Versions: 2.1.0-beta
>Reporter: Daniel Templeton
>Assignee: Daniel Templeton
>
> The change introduced in YARN-514 opens up a hole into which applications can
> fall and be lost. Prior to YARN-514, the {{submitApplication()}} call did
> not complete until the application state was persisted to the state store.
> After YARN-514, the {{submitApplication()}} call is asynchronous, with the
> application state being saved later.
> If the state store is slow or unresponsive, it may be that an application's
> state may not be persisted for quite a while. During that time, if the RM
> fails (over), all applications that have not yet been persisted to the state
> store will be lost. If the active RM loses ZK connectivity, a significant
>