[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12780197#action_12780197
]
Allen Wittenauer commented on HDFS-779:
---
N% actually gets tricky when total grid size i
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12780198#action_12780198
]
Owen O'Malley commented on HDFS-779:
Other points:
1. Decommissioned nodes clearly shou
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12780215#action_12780215
]
Kan Zhang commented on HDFS-779:
Just a comment on the case of connection failures due to una
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12780226#action_12780226
]
Owen O'Malley commented on HDFS-779:
I'd also point out that with the default of 8 hours
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12780228#action_12780228
]
Owen O'Malley commented on HDFS-779:
To address Allen's concern about small clusters, I'd
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12780232#action_12780232
]
Todd Lipcon commented on HDFS-779:
--
This is similar to HDFS-528, though that patch only does
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12780404#action_12780404
]
Hong Tang commented on HDFS-779:
+1 on the direction. I my previous job, we also have a simil
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14078296#comment-14078296
]
Allen Wittenauer commented on HDFS-779:
---
bq. I don't want to ever have to explain to
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14080148#comment-14080148
]
Robert Chansler commented on HDFS-779:
--
It's a lot of fun revisiting the past while All
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12891874#action_12891874
]
Konstantin Shvachko commented on HDFS-779:
--
I think we should rather target directly
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12893255#action_12893255
]
Suresh Srinivas commented on HDFS-779:
--
During startup, the ratio of *blocks with safe r
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12893850#action_12893850
]
Konstantin Shvachko commented on HDFS-779:
--
You are right the safe mode conditions a
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12902289#action_12902289
]
Robert Chansler commented on HDFS-779:
--
I, too, think it should all about the number of
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12905624#action_12905624
]
Robert Chansler commented on HDFS-779:
--
An observation from Milind: If the system retrea
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12908629#action_12908629
]
dhruba borthakur commented on HDFS-779:
---
I would like to work on this one. A similar is
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12908630#action_12908630
]
dhruba borthakur commented on HDFS-779:
---
I forgot to mention the basic premise for *del
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12908651#action_12908651
]
Joydeep Sen Sarma commented on HDFS-779:
@Dhruba - i think the real problem is why da
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12909598#action_12909598
]
dhruba borthakur commented on HDFS-779:
---
@Joy: I agree that not losing heartbeats is th
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12909844#action_12909844
]
Robert Chansler commented on HDFS-779:
--
I think Dhruba's comment #2 from the 13th suppor
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12910403#action_12910403
]
Konstantin Shvachko commented on HDFS-779:
--
Some high level thoughts on the issue.
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12910422#action_12910422
]
dhruba borthakur commented on HDFS-779:
---
> shifting priorities to processing the heartb
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12913294#action_12913294
]
Konstantin Shvachko commented on HDFS-779:
--
> I agree with you on this one. Heartbea
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12913394#action_12913394
]
dhruba borthakur commented on HDFS-779:
---
> insulate the system from the catastrophe typ
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12914199#action_12914199
]
Konstantin Shvachko commented on HDFS-779:
--
This is what I was saying in my previous
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12914213#action_12914213
]
dhruba borthakur commented on HDFS-779:
---
> 1. the load-induced-catastrophe can be solve
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12914307#action_12914307
]
Robert Chansler commented on HDFS-779:
--
(Priority for heartbeats makes sense, and is not
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12914325#action_12914325
]
dhruba borthakur commented on HDFS-779:
---
Thanks Robert for asking these questions. Thes
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12914375#action_12914375
]
Eli Collins commented on HDFS-779:
--
IIUC the use case for "catastrophic mode" is that in the
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12914511#action_12914511
]
Allen Wittenauer commented on HDFS-779:
---
> most clusters have dependencies between jobs
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12914547#action_12914547
]
dhruba borthakur commented on HDFS-779:
---
I think all three of us: Eli, Rob and I are sa
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12914640#action_12914640
]
Konstantin Shvachko commented on HDFS-779:
--
I think we have made several important s
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12914690#action_12914690
]
Joydeep Sen Sarma commented on HDFS-779:
i talked offline with Dhruba a couple of wee
[
https://issues.apache.org/jira/browse/HDFS-779?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12914698#action_12914698
]
Robert Chansler commented on HDFS-779:
--
Dhruba's suggests creating a new operation mode
33 matches
Mail list logo
