[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14937889#comment-14937889
]
Hudson commented on HDFS-9040:
--
FAILURE: Integrated in Hadoop-Yarn-trunk-Java8 #473 (See
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14938109#comment-14938109
]
Hudson commented on HDFS-9040:
--
FAILURE: Integrated in Hadoop-Hdfs-trunk-Java8 #439 (See
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14938678#comment-14938678
]
Hudson commented on HDFS-9040:
--
FAILURE: Integrated in Hadoop-Mapreduce-trunk-Java8 #465 (See
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14938486#comment-14938486
]
Hudson commented on HDFS-9040:
--
FAILURE: Integrated in Hadoop-Mapreduce-trunk #2408 (See
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14937635#comment-14937635
]
Hudson commented on HDFS-9040:
--
FAILURE: Integrated in Hadoop-Yarn-trunk #1203 (See
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14937386#comment-14937386
]
Hudson commented on HDFS-9040:
--
FAILURE: Integrated in Hadoop-trunk-Commit #8548 (See
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14937189#comment-14937189
]
Hudson commented on HDFS-9040:
--
FAILURE: Integrated in Hadoop-Hdfs-trunk #2379 (See
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14933706#comment-14933706
]
Zhe Zhang commented on HDFS-9040:
-
I'm finishing up my review, will post soon.
> Erasure coding: Refactor
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14933703#comment-14933703
]
Jing Zhao commented on HDFS-9040:
-
[~walter.k.su] and [~zhz], any further comments on the patch?
> Erasure
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14934036#comment-14934036
]
Jing Zhao commented on HDFS-9040:
-
Thanks for the review, Zhe! For {{getFollowingBlock}}, currently we
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14934073#comment-14934073
]
Zhe Zhang commented on HDFS-9040:
-
Thanks Jing for the updated patch.
bq. The data streamer does not call
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14934142#comment-14934142
]
Hadoop QA commented on HDFS-9040:
-
\\
\\
| (x) *{color:red}-1 overall{color}* |
\\
\\
|| Vote || Subsystem
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14933899#comment-14933899
]
Zhe Zhang commented on HDFS-9040:
-
I think the latest patch looks pretty good -- thanks Jing for the great
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14905924#comment-14905924
]
Hadoop QA commented on HDFS-9040:
-
\\
\\
| (x) *{color:red}-1 overall{color}* |
\\
\\
|| Vote || Subsystem
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14907075#comment-14907075
]
Hadoop QA commented on HDFS-9040:
-
\\
\\
| (x) *{color:red}-1 overall{color}* |
\\
\\
|| Vote || Subsystem
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14905302#comment-14905302
]
Jing Zhao commented on HDFS-9040:
-
Thanks for the review, [~walter.k.su]!
bq. It's not good enough
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14905438#comment-14905438
]
Hadoop QA commented on HDFS-9040:
-
\\
\\
| (x) *{color:red}-1 overall{color}* |
\\
\\
|| Vote || Subsystem
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14905642#comment-14905642
]
Hadoop QA commented on HDFS-9040:
-
\\
\\
| (x) *{color:red}-1 overall{color}* |
\\
\\
|| Vote || Subsystem
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14905659#comment-14905659
]
Walter Su commented on HDFS-9040:
-
bq. The socket timeout is 60s by default.
Yeah. It turns out it's in the
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14903889#comment-14903889
]
Walter Su commented on HDFS-9040:
-
bq. 1. Flush out all the enqueued data to DataNodes before handling
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14903906#comment-14903906
]
Hadoop QA commented on HDFS-9040:
-
\\
\\
| (x) *{color:red}-1 overall{color}* |
\\
\\
|| Vote || Subsystem
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14902207#comment-14902207
]
Li Bo commented on HDFS-9040:
-
I have just done a test with and without HDFS-9040-HDFS-7285.003.patch. The
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14901080#comment-14901080
]
Zhe Zhang commented on HDFS-9040:
-
bq. but we dont know if idx 6~8 are permanent lost or delayed.
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14900536#comment-14900536
]
Walter Su commented on HDFS-9040:
-
bq. 5. Another issue is, when NN restarts and receives block reports
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14900554#comment-14900554
]
Walter Su commented on HDFS-9040:
-
If it's a "append()" recovery, of course we should NOT truncate any
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14901197#comment-14901197
]
Jing Zhao commented on HDFS-9040:
-
bq. In short, bumpGS is useful for choosing working set(healthy
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14877451#comment-14877451
]
Zhe Zhang commented on HDFS-9040:
-
Thanks for the comment Jing. The discussion is getting more and more
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14805096#comment-14805096
]
Zhe Zhang commented on HDFS-9040:
-
In the read-being-written scenario, file size itself is calculated from
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14805110#comment-14805110
]
Zhe Zhang commented on HDFS-9040:
-
I agree with Walter's analysis. Bumping GS in write pipeline is useful
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14876807#comment-14876807
]
Jing Zhao commented on HDFS-9040:
-
Good point about the GS bump! Some thinking along the line:
# First
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14805089#comment-14805089
]
Walter Su commented on HDFS-9040:
-
bq. For the last block group, we can calculate the length of each block
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14875837#comment-14875837
]
Walter Su commented on HDFS-9040:
-
bq. I think the key point here is to bump the GS, which is necessary to
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14791655#comment-14791655
]
Zhe Zhang commented on HDFS-9040:
-
Thanks Jing for the new patch! The structure looks much cleaner now.
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14791739#comment-14791739
]
Walter Su commented on HDFS-9040:
-
bq. should we just do updatePipeline when completing the block? 1. In
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14803316#comment-14803316
]
Zhe Zhang commented on HDFS-9040:
-
bq. 3. We might want to add the logic to replace a failed
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14803339#comment-14803339
]
Jing Zhao commented on HDFS-9040:
-
I think the key point here is to bump the GS, which is necessary to
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14805014#comment-14805014
]
Li Bo commented on HDFS-9040:
-
Thanks for the deep discussion here. One point confused me:
bq. Only based on
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14746493#comment-14746493
]
Zhe Zhang commented on HDFS-9040:
-
bq. Maybe we can do the refactoring after merging EC feature into trunk?
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14746779#comment-14746779
]
Hadoop QA commented on HDFS-9040:
-
\\
\\
| (x) *{color:red}-1 overall{color}* |
\\
\\
|| Vote || Subsystem
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14746443#comment-14746443
]
Jing Zhao commented on HDFS-9040:
-
Thanks for the great review, Walter and Zhe!
bq. Speaking blockToken,
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14746541#comment-14746541
]
Jing Zhao commented on HDFS-9040:
-
I agree. Let's see if we can be confident about this fix before the
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14745021#comment-14745021
]
Walter Su commented on HDFS-9040:
-
Oh, I see you flush all before call checkStreamerFailures. Please ignore
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14745016#comment-14745016
]
Walter Su commented on HDFS-9040:
-
1. toClose is not safe. If we write a small file and close quickly, we
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14745093#comment-14745093
]
Walter Su commented on HDFS-9040:
-
2. If a streamer fails immediately after you add it to healthySet. Is
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14746077#comment-14746077
]
Zhe Zhang commented on HDFS-9040:
-
Since we have agreed to move the {{locateFollowingBlock}} logic to
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14745527#comment-14745527
]
Walter Su commented on HDFS-9040:
-
Speaking blockToken, it reminds me another severe issue. Assume user's
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14744281#comment-14744281
]
Jing Zhao commented on HDFS-9040:
-
Thanks for the comments, Zhe, Walter and Bo!
bq. With
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14744316#comment-14744316
]
Zhe Zhang commented on HDFS-9040:
-
bq. With BlockGroupDataStreamer I can make 9 internal streamers to wait
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=1473#comment-1473
]
Zhe Zhang commented on HDFS-9040:
-
bq. The reason I prefer not to do locateFollowingBlock in
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14744298#comment-14744298
]
Zhe Zhang commented on HDFS-9040:
-
I just created HDFS-9079 to explore preallocating GS. Refreshing token
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14744645#comment-14744645
]
Walter Su commented on HDFS-9040:
-
bq. Yeah, I can understand your concern. In the replication mechanism,
[
https://issues.apache.org/jira/browse/HDFS-9040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14744854#comment-14744854
]
Hadoop QA commented on HDFS-9040:
-
\\
\\
| (x) *{color:red}-1 overall{color}* |
\\
\\
|| Vote || Subsystem
52 matches
Mail list logo