[
https://issues.apache.org/jira/browse/HADOOP-6105?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12723993#action_12723993
]
Arun C Murthy commented on HADOOP-6105:
---
+1 for this direction.
> Provide a
[
https://issues.apache.org/jira/browse/HADOOP-5985?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12722454#action_12722454
]
Arun C Murthy commented on HADOOP-5985:
---
Sorry for jumping in late, I som
[
https://issues.apache.org/jira/browse/HADOOP-5985?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5985:
--
Component/s: mapred
> A single slow (but not dead) map TaskTracker impedes MapReduce progr
[
https://issues.apache.org/jira/browse/HADOOP-5964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12721676#action_12721676
]
Arun C Murthy commented on HADOOP-5964:
---
Forgot to add that I've m
[
https://issues.apache.org/jira/browse/HADOOP-5964?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5964:
--
Attachment: HADOOP-5964_8_20090618.patch
Thanks for the review Hemanth - as you pointed out
Issue Type: Bug
Components: benchmarks
Affects Versions: 0.21.0
Reporter: Arun C Murthy
Fix For: 0.21.0
GridMix data generation scripts need to use the newer mapreduce api.
--
This message is automatically generated by JIRA.
-
You can reply to this
[
https://issues.apache.org/jira/browse/HADOOP-5964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12721114#action_12721114
]
Arun C Murthy commented on HADOOP-5964:
---
Some notes about this patch:
#
[
https://issues.apache.org/jira/browse/HADOOP-5964?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5964:
--
Attachment: HADOOP-5964_7_20090618.patch
Some bug fixes and added counters to track how long
[
https://issues.apache.org/jira/browse/HADOOP-5964?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5964:
--
Attachment: HADOOP-5964_6_20090617.patch
Reasonably well tested patch, appreciate any
[
https://issues.apache.org/jira/browse/HADOOP-5795?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12720459#action_12720459
]
Arun C Murthy commented on HADOOP-5795:
---
Quick note: making the length manda
[
https://issues.apache.org/jira/browse/HADOOP-5964?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5964:
--
Attachment: HADOOP-5964_4_20090615.patch
After much consideration I decided to revert back to
Components: mapred
Affects Versions: 0.20.0
Reporter: Arun C Murthy
Fix For: 0.21.0
HADOOP-4305 added a global black-list of tasktrackers.
We saw a scenario on one of our clusters where a few jobs caused a lot of
tasktrackers to immediately be blacklisted. This was caused
[
https://issues.apache.org/jira/browse/HADOOP-5964?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5964:
--
Attachment: HADOOP-5964_2_20090609.patch
Updated patch.
> Fix the 'cluster drain
[
https://issues.apache.org/jira/browse/HADOOP-5964?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5964:
--
Attachment: HADOOP-5964_1_20090608.patch
Reasonably well tested patch for review... this
[
https://issues.apache.org/jira/browse/HADOOP-5090?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12716723#action_12716723
]
Arun C Murthy commented on HADOOP-5090:
---
Also, I *really* don't think
[
https://issues.apache.org/jira/browse/HADOOP-5964?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy reassigned HADOOP-5964:
-
Assignee: Arun C Murthy
> Fix the 'cluster drain' problem in the Capacity
[
https://issues.apache.org/jira/browse/HADOOP-5090?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12716526#action_12716526
]
Arun C Murthy commented on HADOOP-5090:
---
I'd strongly urge *against*
[
https://issues.apache.org/jira/browse/HADOOP-5884?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12715857#action_12715857
]
Arun C Murthy commented on HADOOP-5884:
---
I'm just proposing we add #slo
[
https://issues.apache.org/jira/browse/HADOOP-5964?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5964:
--
Attachment: HADOOP-5964_0_20090602.patch
Very early patch.
I haven't introdu
[
https://issues.apache.org/jira/browse/HADOOP-5964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12715768#action_12715768
]
Arun C Murthy commented on HADOOP-5964:
---
A _much_ better model is for the sched
adoop Core
Issue Type: Bug
Components: contrib/capacity-sched
Affects Versions: 0.20.0
Reporter: Arun C Murthy
Fix For: 0.21.0
When a HighRAMJob turns up at the head of the queue, the current implementation
of support for HighRAMJobs in the Capacity Sch
[
https://issues.apache.org/jira/browse/HADOOP-5884?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12715281#action_12715281
]
Arun C Murthy commented on HADOOP-5884:
---
Long term - we really should
[
https://issues.apache.org/jira/browse/HADOOP-5884?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12715275#action_12715275
]
Arun C Murthy commented on HADOOP-5884:
---
Can we also add the number of slots to
[
https://issues.apache.org/jira/browse/HADOOP-5664?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12714243#action_12714243
]
Arun C Murthy commented on HADOOP-5664:
---
+1
> Use of ReentrantLock.lo
[
https://issues.apache.org/jira/browse/HADOOP-5885?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy resolved HADOOP-5885.
---
Resolution: Invalid
> Error occurred during initialization of
[
https://issues.apache.org/jira/browse/HADOOP-5885?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12713644#action_12713644
]
Arun C Murthy commented on HADOOP-5885:
---
This looks like a bad misconfigura
On May 26, 2009, at 5:11 PM, Owen O'Malley wrote:
I'd like to propose a code freeze and branch date of 7/31. One major
exception is for HDFS file append, which I think we need in 0.21 and
will take longer than that.
+1
Arun
[
https://issues.apache.org/jira/browse/HADOOP-5876?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12711277#action_12711277
]
Arun C Murthy commented on HADOOP-5876:
---
What kind of shuffle information are
: mapred
Reporter: Arun C Murthy
The motivation is similar to HADOOP-5831...
Currently we collect map-outputs in the sort buffer (io.sort.mb) which we
eventually sort and spill to disk. For latency-sensitive applications with
sufficient memory, e.g. terasort, we could do better by
[
https://issues.apache.org/jira/browse/HADOOP-5846?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12709765#action_12709765
]
Arun C Murthy commented on HADOOP-5846:
---
Haven't we had problems with jo
[
https://issues.apache.org/jira/browse/HADOOP-5846?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12709761#action_12709761
]
Arun C Murthy commented on HADOOP-5846:
---
Is the proposal to add another
Reporter: Arun C Murthy
Assignee: Arun C Murthy
Fix For: 0.21.0
HADOOP-3446 fixed the reduce to not flush the in-memory shuffled map-outputs
before feeding to the reduce. However for latency-sensitive applications with
lots of memory like the terasort this
Components: mapred
Reporter: Arun C Murthy
We have evidence that cutting the shuffle-crossbar between maps and reduces (m
* r) leads to perfomant applications since:
# It cuts down the number of connections necessary to shuffle and hence reduces
load on the serving-side
[
https://issues.apache.org/jira/browse/HADOOP-5737?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12708336#action_12708336
]
Arun C Murthy commented on HADOOP-5737:
---
+1
> UGI checks in testcases are
[
https://issues.apache.org/jira/browse/HADOOP-5795?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12708132#action_12708132
]
Arun C Murthy commented on HADOOP-5795:
---
Dhruba, I was thinking it was implic
[
https://issues.apache.org/jira/browse/HADOOP-4874?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12707564#action_12707564
]
Arun C Murthy commented on HADOOP-4874:
---
Tatu - please open a new jira for fa
[
https://issues.apache.org/jira/browse/HADOOP-5795?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12707446#action_12707446
]
Arun C Murthy commented on HADOOP-5795:
---
bq. Map listBlockLocations(Path[]);
[
https://issues.apache.org/jira/browse/HADOOP-5790?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy resolved HADOOP-5790.
---
Resolution: Duplicate
Assignee: (was: Arun C Murthy)
Duplicate of HADOOP-5791
Affects Versions: 0.20.0
Reporter: Arun C Murthy
Fix For: 0.21.0
Currently map-reduce applications (specifically file-based input-formats) use
FileSystem.getFileBlockLocations to compute splits. However they are forced to
call it once per file.
The downsides are multiple
Components: mapred
Affects Versions: 0.20.0
Reporter: Arun C Murthy
Assignee: Arun C Murthy
Fix For: 0.21.0
It would be good for latency-sensitive applications to tune the shuffle
read/connection timeouts...
--
This message is automatically
Components: mapred
Affects Versions: 0.20.0
Reporter: Arun C Murthy
Assignee: Arun C Murthy
Fix For: 0.21.0
It would be good for latency-sensitive applications to tune the shuffle
read/connection timeouts... in fact this made a huge difference
: mapred
Affects Versions: 0.20.0
Reporter: Arun C Murthy
Assignee: Arun C Murthy
Fix For: 0.21.0
We could improve the RPC between the Child and TaskTracker:
* Set ping interval lower by default to 5s
* Disable nagle's algorithm (tcp no-delay)
--
: Improvement
Reporter: Arun C Murthy
Assignee: Arun C Murthy
Currently it's set in bin/hadoop-daemon.sh... we should allow it to be
specified in conf/hadoop-env.sh
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the
[
https://issues.apache.org/jira/browse/HADOOP-5787?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5787:
--
Component/s: scripts
Affects Version/s: 0.20.0
Fix Version/s: 0.21.0
[
https://issues.apache.org/jira/browse/HADOOP-5737?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12707126#action_12707126
]
Arun C Murthy commented on HADOOP-5737:
---
bq. For case #1, JobTracker.getFileSy
[
https://issues.apache.org/jira/browse/HADOOP-5737?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12706516#action_12706516
]
Arun C Murthy commented on HADOOP-5737:
---
The patch looks fine. I'd rath
[
https://issues.apache.org/jira/browse/HADOOP-5670?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12706194#action_12706194
]
Arun C Murthy edited comment on HADOOP-5670 at 5/5/09 2:0
[
https://issues.apache.org/jira/browse/HADOOP-5772?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12706195#action_12706195
]
Arun C Murthy commented on HADOOP-5772:
---
Sure, alternatively we could use this
[
https://issues.apache.org/jira/browse/HADOOP-5670?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12706194#action_12706194
]
Arun C Murthy commented on HADOOP-5670:
---
One important and related feature are
[
https://issues.apache.org/jira/browse/HADOOP-5643?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12706135#action_12706135
]
Arun C Murthy commented on HADOOP-5643:
---
bq.I think we are going throug
adoop Core
Issue Type: New Feature
Components: conf
Reporter: Arun C Murthy
We have various bits and pieces of code to refresh certain configuration files,
various components to restrict access to who can actually refresh the configs
etc.
I propose we start thin
[
https://issues.apache.org/jira/browse/HADOOP-5768?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12705663#action_12705663
]
Arun C Murthy commented on HADOOP-5768:
---
+1
We should also expand the suppo
On Apr 22, 2009, at 7:17 PM, Samprita Hegde wrote:
Hi,
I am trying see the feasibility of using shared spaces for the
communication of the Task Completion Events in Hadoop. For this I am
trying
to replace the InterTracker Protocol with a co-ordination space so
that one
thread in a Task Tr
[
https://issues.apache.org/jira/browse/HADOOP-5737?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12702309#action_12702309
]
Arun C Murthy commented on HADOOP-5737:
---
Also, another thing to check is whethe
[
https://issues.apache.org/jira/browse/HADOOP-5737?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12702306#action_12702306
]
Arun C Murthy commented on HADOOP-5737:
---
Does this anomaly happen in all test-c
[
https://issues.apache.org/jira/browse/HADOOP-5726?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12702304#action_12702304
]
Arun C Murthy commented on HADOOP-5726:
---
+1 for the direction.
I'd propos
[
https://issues.apache.org/jira/browse/HADOOP-5725?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12702254#action_12702254
]
Arun C Murthy commented on HADOOP-5725:
---
bq. I had jobs with tasks expected to
[
https://issues.apache.org/jira/browse/HADOOP-5632?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12702039#action_12702039
]
Arun C Murthy commented on HADOOP-5632:
---
Well, we need to consider the 'p
[
https://issues.apache.org/jira/browse/HADOOP-5632?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12701550#action_12701550
]
Arun C Murthy commented on HADOOP-5632:
---
bq. If running tasks status updates ca
[
https://issues.apache.org/jira/browse/HADOOP-5632?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12701543#action_12701543
]
Arun C Murthy commented on HADOOP-5632:
---
bq. ?? The sequence number seems str
[
https://issues.apache.org/jira/browse/HADOOP-5684?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5684:
--
Attachment: HADOOP-5684_0_20090420.patch
I've been running for a while with this
[
https://issues.apache.org/jira/browse/HADOOP-5684?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy reassigned HADOOP-5684:
-
Assignee: Arun C Murthy
> separate jvm param for mapper and redu
[
https://issues.apache.org/jira/browse/HADOOP-5639?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy resolved HADOOP-5639.
---
Resolution: Duplicate
Duplicate of HADOOP-869.
> Remove cyclic calls between JobTrac
[
https://issues.apache.org/jira/browse/HADOOP-5572?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12689125#action_12689125
]
Arun C Murthy commented on HADOOP-5572:
---
+1
> The map progress value should
[
https://issues.apache.org/jira/browse/HADOOP-5531?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12683513#action_12683513
]
Arun C Murthy commented on HADOOP-5531:
---
+1
> Disable Chukwa unit tests on
[
https://issues.apache.org/jira/browse/HADOOP-5514?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12682882#action_12682882
]
Arun C Murthy commented on HADOOP-5514:
---
+1.
Eventually we should rep
[
https://issues.apache.org/jira/browse/HADOOP-5382?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12682852#action_12682852
]
Arun C Murthy commented on HADOOP-5382:
---
+1
> The new map/reduce api
[
https://issues.apache.org/jira/browse/HADOOP-5281?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12682745#action_12682745
]
Arun C Murthy commented on HADOOP-5281:
---
+1
> GzipCodec fails second tim
[
https://issues.apache.org/jira/browse/HADOOP-5442?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy resolved HADOOP-5442.
---
Resolution: Fixed
Fix Version/s: 0.21.0
I just committed this. Thanks, Amar!
>
[
https://issues.apache.org/jira/browse/HADOOP-5459?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12681948#action_12681948
]
Arun C Murthy commented on HADOOP-5459:
---
+1
> CRC errors not detected
[
https://issues.apache.org/jira/browse/HADOOP-4996?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12677598#action_12677598
]
Arun C Murthy commented on HADOOP-4996:
---
Amareshwari, if I remember right -
[
https://issues.apache.org/jira/browse/HADOOP-4744?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12675763#action_12675763
]
Arun C Murthy commented on HADOOP-4744:
---
+1
> Wrong resolution of hostn
[
https://issues.apache.org/jira/browse/HADOOP-5299?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12675440#action_12675440
]
Arun C Murthy commented on HADOOP-5299:
---
Caveat emptor:
# Typical mid-to-l
On Feb 19, 2009, at 4:28 PM, Nigel Daley wrote:
I have created a candidate build for Hadoop 0.19.1.
This release fixes some data loss issues in 0.19.0 and introduces an
incompatible change by disabling the file append API (HADOOP-5224).
As you can see in Jira, there are still a couple mapr
On Feb 18, 2009, at 10:37 AM, Amin Astaneh wrote:
Lukáš-
Well, we have a graduate student that is using our facilities for a
Masters' thesis in Map/Reduce. You guys are generating topics in
computer science research.
What do we need to do in order to get our documentation on the
Hadoop
[
https://issues.apache.org/jira/browse/HADOOP-4490?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12674504#action_12674504
]
Arun C Murthy commented on HADOOP-4490:
---
bq. If it is felt that this should be
[
https://issues.apache.org/jira/browse/HADOOP-4490?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-4490:
--
Status: Open (was: Patch Available)
Some comments after a discussion with Hemanth:
# We
[
https://issues.apache.org/jira/browse/HADOOP-5244?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy resolved HADOOP-5244.
---
Resolution: Duplicate
Duplicate of HADOOP-4780.
> Distributed cache spends a lot of t
[
https://issues.apache.org/jira/browse/HADOOP-5223?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12672923#action_12672923
]
Arun C Murthy commented on HADOOP-5223:
---
Forgot to add that we felt it's
[
https://issues.apache.org/jira/browse/HADOOP-5223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5223:
--
Attachment: HADOOP-5233_part0.patch
Another puzzle piece, includes a completed Fetcher
[
https://issues.apache.org/jira/browse/HADOOP-5223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5223:
--
Attachment: HADOOP-5233_api.patch
Here is a the rough draft of the api we've been worki
[
https://issues.apache.org/jira/browse/HADOOP-5160?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12671343#action_12671343
]
Arun C Murthy commented on HADOOP-5160:
---
Were other jobs 'alive' in t
[
https://issues.apache.org/jira/browse/HADOOP-5160?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12671054#action_12671054
]
Arun C Murthy commented on HADOOP-5160:
---
As of hadoop-0.18 the Map-Reduce sched
On Feb 5, 2009, at 1:13 AM, zhangwei wrote:
Hi，all
I run a job with lzop enabled (mapred.output.compress=true and
mapred
.output.compression.codec=org.apache.hadoop.io.compress.LzopCodec),
but it always fails with these logs,seems it can’t load native-lzo
library, but I don’t know how to set
[
https://issues.apache.org/jira/browse/HADOOP-5138?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5138:
--
Resolution: Fixed
Fix Version/s: 0.21.0
Status: Resolved (was: Patch
[
https://issues.apache.org/jira/browse/HADOOP-4033?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12668964#action_12668964
]
Arun C Murthy commented on HADOOP-4033:
---
bq. Actually, I'd propose that we
: 0.20.0
Reporter: Arun C Murthy
Priority: Blocker
Fix For: 0.20.0
For some reason the LocalDirAllocator.getLocaPathToRead doesn't find files
which are present, extra logging shows:
{noformat}
2009-01-30 06:43:32,312
[
https://issues.apache.org/jira/browse/HADOOP-5131?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12668387#action_12668387
]
Arun C Murthy commented on HADOOP-5131:
---
Good catch Devaraj! I actually saw the
On Jan 22, 2009, at 10:46 PM, Nigel Daley wrote:
I have created a candidate build for Hadoop 0.18.3. This fixes 51
issues in 0.18.2, including several problems that may lead to data
loss from the file system.
*** Please download and test it before the
*** vote closes on Tuesday, January 2
[
https://issues.apache.org/jira/browse/HADOOP-5131?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5131:
--
Attachment: HADOOP-5131_0_20090127.patch
Preliminary patch while I continue testing
[
https://issues.apache.org/jira/browse/HADOOP-5130?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12667631#action_12667631
]
Arun C Murthy commented on HADOOP-5130:
---
To clarify - the task did eventu
[
https://issues.apache.org/jira/browse/HADOOP-5130?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5130:
--
Priority: Blocker (was: Critical)
Fix Version/s: 0.20.0
Promoting this to a blocker
Versions: 0.20.0
Reporter: Arun C Murthy
Fix For: 0.21.0
Currently DataXcieverServer.java hardcodes MAX_XCEIVER_COUNT to 256.
I ran a randomwriter with 4k maps and output replication set to 40 - all write
pipelines failed since each DataNode hit the above limit and refused
: mapred
Affects Versions: 0.20.0
Reporter: Arun C Murthy
Assignee: Arun C Murthy
Currently the ReduceCopier.run has a hard-coded 5s sleep which hurts jobs where
latency is important, we really should have a mechanism where the thread
fetching task-completion events
Project: Hadoop Core
Issue Type: Bug
Components: mapred
Affects Versions: 0.20.0
Reporter: Arun C Murthy
Priority: Critical
I saw atleast a couple of instances where the task assigned to the TaskTracker
is launched several minutes after the receipt of
[
https://issues.apache.org/jira/browse/HADOOP-5128?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5128:
--
Summary: JobQueueTaskScheduler could assign multiple reduces per heartbeat
(was
Project: Hadoop Core
Issue Type: Improvement
Components: mapred
Affects Versions: 0.20.0
Reporter: Arun C Murthy
Assignee: Arun C Murthy
Currently the TaskTracker strictly respects the heartbeat interval, this causes
utilization issues when all
[
https://issues.apache.org/jira/browse/HADOOP-5128?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arun C Murthy updated HADOOP-5128:
--
Component/s: mapred
Assignee: Arun C Murthy
> JobQueueTaskScheduler should Ass
: Improvement
Affects Versions: 0.21.0
Reporter: Arun C Murthy
Currently the JobQueueTaskScheduler assigns only 1 reduce per heartbeat, for
applications where latency is important we could assign more reduces (upto
available slots).
--
This message is automatically generated by
[
https://issues.apache.org/jira/browse/HADOOP-4667?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12666446#action_12666446
]
Arun C Murthy commented on HADOOP-4667:
---
bq. The JobInProgress class shoul
1 - 100 of 851 matches
Mail list logo
