Antony Mayi created SPARK-12617:
---
Summary: socket descriptor leak killing streaming app
Key: SPARK-12617
URL: https://issues.apache.org/jira/browse/SPARK-12617
Project: Spark
Issue Type: Bug
[
https://issues.apache.org/jira/browse/SPARK-12617?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-12617:
Description:
There is a socket descriptor leakage in a pyspark streaming app when configured
with
[
https://issues.apache.org/jira/browse/SPARK-12617?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-12617:
Attachment: bug.py
> socket descriptor leak killing streaming app
>
[
https://issues.apache.org/jira/browse/SPARK-12617?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-12617:
Description:
There is a socket descriptor leakage in a pyspark streaming app when configured
with
[
https://issues.apache.org/jira/browse/SPARK-12617?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-12617:
Description:
There is a socket descriptor leakage in a pyspark streaming app when configured
with
[
https://issues.apache.org/jira/browse/SPARK-12511?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15073816#comment-15073816
]
Antony Mayi commented on SPARK-12511:
-
just found SPARK-11711 which looks to be the same issue
>
[
https://issues.apache.org/jira/browse/SPARK-12511?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-12511:
Description:
Spark streaming application when configured with checkpointing is filling
driver's
[
https://issues.apache.org/jira/browse/SPARK-12511?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-12511:
Description:
Spark streaming application when configured with checkpointing is filling
driver's
Antony Mayi created SPARK-12511:
---
Summary: streaming driver with checkpointing unable to finalize
leading to OOM
Key: SPARK-12511
URL: https://issues.apache.org/jira/browse/SPARK-12511
Project: Spark
[
https://issues.apache.org/jira/browse/SPARK-12511?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-12511:
Description:
Spark streaming application when configured with checkpointing is filling
driver's
[
https://issues.apache.org/jira/browse/SPARK-12511?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-12511:
Attachment: bug.py
> streaming driver with checkpointing unable to finalize leading to OOM
>
[
https://issues.apache.org/jira/browse/SPARK-12511?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-12511:
Attachment: finalizer-spark_assembly.png
finalizer-pending.png
[
https://issues.apache.org/jira/browse/SPARK-12511?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-12511:
Description:
Spark streaming application when configured with checkpointing is filling
driver's
[
https://issues.apache.org/jira/browse/SPARK-6717?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15032822#comment-15032822
]
Antony Mayi commented on SPARK-6717:
this seems to be even bigger problem in 1.5 as the workaround
[
https://issues.apache.org/jira/browse/SPARK-11498?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15015060#comment-15015060
]
Antony Mayi commented on SPARK-11498:
-
can't reproduce on 1.5.2, seems to be fixed.
>
[
https://issues.apache.org/jira/browse/SPARK-11498?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-11498:
Description:
{code:title=/tmp/bug.py}
from pyspark import SparkContext
from pyspark.sql import
Antony Mayi created SPARK-11498:
---
Summary: TreeNodeException under very special condition
Key: SPARK-11498
URL: https://issues.apache.org/jira/browse/SPARK-11498
Project: Spark
Issue Type: Bug
[
https://issues.apache.org/jira/browse/SPARK-11498?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-11498:
Description:
{code}
from pyspark import SparkContext
from pyspark.sql import SQLContext, Row
sc =
[
https://issues.apache.org/jira/browse/SPARK-8708?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14611555#comment-14611555
]
Antony Mayi commented on SPARK-8708:
bq. Antony Mayi In your real case, how many
[
https://issues.apache.org/jira/browse/SPARK-8708?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14611304#comment-14611304
]
Antony Mayi commented on SPARK-8708:
I suspect this issue with all data in single
[
https://issues.apache.org/jira/browse/SPARK-8708?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14608169#comment-14608169
]
Antony Mayi commented on SPARK-8708:
The real case is about 13M of users, few hundreds
[
https://issues.apache.org/jira/browse/SPARK-8708?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14608214#comment-14608214
]
Antony Mayi commented on SPARK-8708:
ok, more detailed example showing there really
[
https://issues.apache.org/jira/browse/SPARK-8708?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14608169#comment-14608169
]
Antony Mayi edited comment on SPARK-8708 at 6/30/15 11:55 AM:
--
Antony Mayi created SPARK-8708:
--
Summary: MatrixFactorizationModel.predictAll() populates single
partition only
Key: SPARK-8708
URL: https://issues.apache.org/jira/browse/SPARK-8708
Project: Spark
[
https://issues.apache.org/jira/browse/SPARK-6334?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-6334:
---
Attachment: gc.png
spark-local dir not getting cleared during ALS
[
https://issues.apache.org/jira/browse/SPARK-6334?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14390771#comment-14390771
]
Antony Mayi commented on SPARK-6334:
bq. btw. I see based on the sourcecode
[
https://issues.apache.org/jira/browse/SPARK-6334?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi reopened SPARK-6334:
spark-local dir not getting cleared during ALS
--
[
https://issues.apache.org/jira/browse/SPARK-6334?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14371122#comment-14371122
]
Antony Mayi commented on SPARK-6334:
bq. 2. Use less number of blocks, even you have
[
https://issues.apache.org/jira/browse/SPARK-6334?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14364764#comment-14364764
]
Antony Mayi commented on SPARK-6334:
users: 12.5 millions
ratings: 3.3 billions
rank:
[
https://issues.apache.org/jira/browse/SPARK-6334?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-6334:
---
Attachment: als-diskusage.png
this is the disk usage pattern during ALS - 90% is when YARN kills the
[
https://issues.apache.org/jira/browse/SPARK-6334?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-6334:
---
Comment: was deleted
(was: this is the disk usage pattern during ALS - 90% is when YARN kills the
[
https://issues.apache.org/jira/browse/SPARK-6334?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-6334:
---
Description:
when running bigger ALS training spark spills loads of temp data into the
local-dir (in
[
https://issues.apache.org/jira/browse/SPARK-6334?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Antony Mayi updated SPARK-6334:
---
Description:
when running bigger ALS training spark spills loads of temp data into the
local-dir (in
Antony Mayi created SPARK-6334:
--
Summary: spark-local dir not getting cleared during ALS
Key: SPARK-6334
URL: https://issues.apache.org/jira/browse/SPARK-6334
Project: Spark
Issue Type: Bug
[
https://issues.apache.org/jira/browse/SPARK-6334?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14361715#comment-14361715
]
Antony Mayi edited comment on SPARK-6334 at 3/14/15 11:11 AM:
--
[
https://issues.apache.org/jira/browse/SPARK-6334?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14361715#comment-14361715
]
Antony Mayi commented on SPARK-6334:
bq. What are the files that are filling up the
[
https://issues.apache.org/jira/browse/SPARK-6334?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14361712#comment-14361712
]
Antony Mayi commented on SPARK-6334:
it is 12TB combined across all nodes available to
[
https://issues.apache.org/jira/browse/SPARK-6334?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14361947#comment-14361947
]
Antony Mayi commented on SPARK-6334:
I had to increase the partitioning up to this
[
https://issues.apache.org/jira/browse/SPARK-6334?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14361951#comment-14361951
]
Antony Mayi commented on SPARK-6334:
btw. I see based on the sourcecode checkpointing
39 matches
Mail list logo
