[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16437381#comment-16437381 ] Apache Spark commented on SPARK-16630: -- User 'attilapiros' has created a pull request for this issue: https://github.com/apache/spark/pull/21068 > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves >Priority: Major > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other hardware issue or > hadoop configuration issue. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[
https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16432495#comment-16432495
]
Attila Zsolt Piros commented on SPARK-16630:
Let me illustrate my problem with an example:
- the limit for blacklisted nodes is configured to 2
- we have one node blacklisted close to the yarn allocator ("host1" ->
expiryTime1), this is the new code I am working on
- scheduler requests a new executors along with blacklisted nodes (task-level):
"host2", "host3"
(org.apache.spark.deploy.yarn.YarnAllocator#requestTotalExecutorsWithPreferredLocalities)
So I have to choose 2 nodes to communicate towards YARN. My idea to pass
expiryTime2 and expiryTime3 to the YarnAllocator to choose the most relevant 2
nodes (the one which expires latter are the more relevant).
For this in the case class RequestExecutors the nodeBlacklist field type is
changed to Map[String, Long] from Set[String].
> Blacklist a node if executors won't launch on it.
> -
>
> Key: SPARK-16630
> URL: https://issues.apache.org/jira/browse/SPARK-16630
> Project: Spark
> Issue Type: Improvement
> Components: YARN
>Affects Versions: 1.6.2
>Reporter: Thomas Graves
>Priority: Major
>
> On YARN, its possible that a node is messed or misconfigured such that a
> container won't launch on it. For instance if the Spark external shuffle
> handler didn't get loaded on it , maybe its just some other hardware issue or
> hadoop configuration issue.
> It would be nice we could recognize this happening and stop trying to launch
> executors on it since that could end up causing us to hit our max number of
> executor failures and then kill the job.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16432467#comment-16432467 ] Thomas Graves commented on SPARK-16630: --- sorry I don't follow, the list we get from the blacklist tracker is all nodes that are blacklisted currently that haven't met the expiry to unblacklist them. You just union them with the yarn allocator list. There is obviously some race condition there if one of the nodes it just about to be unblacklisted but I don't see that as a major issue, the next allocation will not have it. Is there something I'm missing? > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves >Priority: Major > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other hardware issue or > hadoop configuration issue. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16432415#comment-16432415 ] Attila Zsolt Piros commented on SPARK-16630: I would need the expiry times to choose the most relevant (most fresh) subset of nodes to backlist when the limit is less then the union of all blacklist-able nodes. So it is only used for sorting. > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves >Priority: Major > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other hardware issue or > hadoop configuration issue. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16432244#comment-16432244 ] Thomas Graves commented on SPARK-16630: --- yes I think it would make sense as the union of all blacklisted nodes. I'm not sure what you mean by your last question. The expiry currently is all handled in the BlacklistTracker, I wouldn't want to move that out into the yarn allocator. Just use the information passed to it unless there is a case it doesn't cover? > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves >Priority: Major > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other hardware issue or > hadoop configuration issue. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16432165#comment-16432165 ] Attila Zsolt Piros commented on SPARK-16630: I have question regarding limiting the number of blacklisted nodes according to the cluster size. With this change there will be two sources of nodes to be backlisted: - one list is coming from the scheduler (existing node level backlisting) - the other is computed here close to the YARN (stored along with the expiry times) I think it makes sense to have the limit for the complete list (union) of blacklisted nodes, am I right? If this limit is for the complete list then regarding the subset I think the newly blacklisted nodes are more up-to-date to be used then the earlier backlisted ones. So I would pass the expiry times from the scheduler to the YARN allocator to make the subset of backlisted nodes to be communicated to YARN. What is your opinion? > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves >Priority: Major > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other hardware issue or > hadoop configuration issue. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16428721#comment-16428721 ] Attila Zsolt Piros commented on SPARK-16630: Yes you are right more executors can be allocated on the same host. I have checked and using getNumClusterNodes is not as hard so I will do that. > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves >Priority: Major > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other hardware issue or > hadoop configuration issue. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16427377#comment-16427377 ] Thomas Graves commented on SPARK-16630: --- the problem is that spark.executor.instances (or dynamic allocation) doesn't necessarily represent the # of nodes in the cluster, especially if you look at dynamic allocation. Depending on the size of your nodes you can have a lot more executors then nodes, thus it could easily end up blacklisting the entire cluster. I would rather look at the actual # of nodes in the cluster. Is that turning out to be hard? > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves >Priority: Major > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other hardware issue or > hadoop configuration issue. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16427181#comment-16427181 ] Attila Zsolt Piros commented on SPARK-16630: [~tgraves] what about stopping YARN backlisting when a configured limit with the default of "spark.executor.instances" * "spark.yarn.backlisting.default.executor.instances.size.weight" (a better name for the weight is welcomed) limit is reached (including all the blacklisted nodes even stage and task level blacklisted nodes) and in case of dynamic allocation the default is Int.MaxValue so there is no limit at all? This idea comes from the calculation of the default for maxNumExecutorFailures. > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves >Priority: Major > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other hardware issue or > hadoop configuration issue. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16427123#comment-16427123 ] Attila Zsolt Piros commented on SPARK-16630: [~irashid] I would reuse spark.blacklist.application.maxFailedExecutorsPerNode which has already a default = 2. I think it makes sense to use the same limit for per node failures before adding the node to the backlist. But in this case I cannot consider spark.yarn.max.executor.failures into the default. > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves >Priority: Major > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other hardware issue or > hadoop configuration issue. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16424906#comment-16424906 ] Imran Rashid commented on SPARK-16630: -- Be sure to look at the discussion on this PR about the same thing on mesos: https://github.com/apache/spark/pull/20640 Even if a lot of the details are tied into the cluster manager, I hope that we can make the general configuration (how many failures, what the timeouts are) etc. common to all cluster managers and can put it in a common spot. > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves >Priority: Major > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other hardware issue or > hadoop configuration issue. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16391649#comment-16391649 ] Attila Zsolt Piros commented on SPARK-16630: I am working on this issue. > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves >Priority: Major > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other hardware issue or > hadoop configuration issue. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16390232#comment-16390232 ] Thomas Graves commented on SPARK-16630: --- yes yarn tells you the # of nodemanagers. allocateResponse -> getNumClusterNodes > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves >Priority: Major > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other hardware issue or > hadoop configuration issue. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[
https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16390159#comment-16390159
]
Imran Rashid commented on SPARK-16630:
--
I'd also take {{spark.yarn.max.executor.failures}} into account for figuring
out a default. In particular we'd want the default to be below that, so one
bad node wouldn't kill the app.
Does it makes sense for this to be tied into the generic BlacklistTracker? I
guess all the interesting logic will be cluster specific so maybe not.
{quote}
We also want to take into account small clusters and perhaps stop blacklisting
if a certain percent of the cluster is already blacklisted.
{quote}
I don't think that is possible -- is the size of the cluster exposed at all?
you raise a good point though, we'd need to have some way to detect this, to
avoid the app just sitting idle indefinitely.
> Blacklist a node if executors won't launch on it.
> -
>
> Key: SPARK-16630
> URL: https://issues.apache.org/jira/browse/SPARK-16630
> Project: Spark
> Issue Type: Improvement
> Components: YARN
>Affects Versions: 1.6.2
>Reporter: Thomas Graves
>Priority: Major
>
> On YARN, its possible that a node is messed or misconfigured such that a
> container won't launch on it. For instance if the Spark external shuffle
> handler didn't get loaded on it , maybe its just some other hardware issue or
> hadoop configuration issue.
> It would be nice we could recognize this happening and stop trying to launch
> executors on it since that could end up causing us to hit our max number of
> executor failures and then kill the job.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16387846#comment-16387846 ] Thomas Graves commented on SPARK-16630: --- yes something along these lines is what I was thinking. we would want a configurable number of failures (perhaps we can reuse one of the existing settings, but woudl need to think about more) at which point we would blacklist the node due to executor launch failures and we could have a timeout at which point we could retry. We also want to take into account small clusters and perhaps stop blacklisting if a certain percent of the cluster is already blacklisted. > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves >Priority: Major > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other hardware issue or > hadoop configuration issue. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16387071#comment-16387071 ] Attila Zsolt Piros commented on SPARK-16630: Of course we can consider "spark.yarn.executor.failuresValidityInterval" for "yarn-level" backlisting too. > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves >Priority: Major > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other hardware issue or > hadoop configuration issue. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16386789#comment-16386789 ] Attila Zsolt Piros commented on SPARK-16630: I have checked the existing sources and I would like to open a discussion about the possible solution. As I have seen YarnAllocator#processCompletedContainers could be extended to track the number of failures by host. Also YarnAllocator is responsible to update the task-level backlisted nodes with YARN (calling AMRMClient#updateBlacklist). So a relatively easy solution would be to have a separate counter here (which is independent from task level failures) with its own configured limit and updating YARN with the union of task-level backlisted nodes and "allocator-level" backlisted nodes. What is your opinion? > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves >Priority: Major > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other hardware issue or > hadoop configuration issue. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-16630) Blacklist a node if executors won't launch on it.
[ https://issues.apache.org/jira/browse/SPARK-16630?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15384744#comment-15384744 ] Thomas Graves commented on SPARK-16630: --- Note this is more at the resource manager level where in like the ApplicationMaster/YarnAllocator we would look at the failure reason since the Spark scheduler itself wouldn't even know about this attempt to launch the executor. > Blacklist a node if executors won't launch on it. > - > > Key: SPARK-16630 > URL: https://issues.apache.org/jira/browse/SPARK-16630 > Project: Spark > Issue Type: Improvement > Components: YARN >Affects Versions: 1.6.2 >Reporter: Thomas Graves > > On YARN, its possible that a node is messed or misconfigured such that a > container won't launch on it. For instance if the Spark external shuffle > handler didn't get loaded on it , maybe its just some other transient error. > It would be nice we could recognize this happening and stop trying to launch > executors on it since that could end up causing us to hit our max number of > executor failures and then kill the job. -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
