Mosharaf Chowdhury
92d2a9a13a
Removed unncessary stuff from HttpParallelLocalFileShuffle
2010-12-22 11:28:50 -08:00
Mosharaf Chowdhury
4ab268ee36
HttpParallelLocalFileShuffle also has a consuming thread. It works on EC2.
2010-12-21 23:50:02 -08:00
Mosharaf Chowdhury
5f7bfbc70e
HttpBlockedLocalFileShuffle has also been converted to have per-reducer consumption thread. Works in local mesos, but NOT on EC2 :|
2010-12-21 23:05:32 -08:00
Mosharaf Chowdhury
5f0cdabd40
Added a separate thread to deserialize (1 thread per reducer) in CustomParallelLocalFileShuffle
...
Upside: No synchronized blocking on "combiners" variable. 3x faster :)
Downside: Inefficient implementation. Requiring too much temporary data. Approx. 2x increase in memory requirement :( Should be fixed at some point.
2010-12-21 21:52:37 -08:00
Mosharaf Chowdhury
f4d0e917a2
Added all the options to the java-opts file. Tired of writing them for separate runs :|
2010-12-21 18:59:51 -08:00
Mosharaf Chowdhury
6ef17e918b
Fixed logging. Again.
2010-12-21 18:49:35 -08:00
Mosharaf Chowdhury
f47fb44479
- Divided maxConnections to max[Rx|Tx]Connections.
...
- Fixed config param loading bug in CustomParallelLFS
2010-12-21 17:34:51 -08:00
Mosharaf Chowdhury
d92b067350
Fixed log message in CustomParallelLocalFileShuffle that was giving some problem in log processing.
2010-12-21 13:12:15 -08:00
Mosharaf Chowdhury
3b21a5fb26
Code formatting...
2010-12-19 18:03:20 -08:00
Mosharaf Chowdhury
81f78282e1
All shuffle implementations are now in the same place. Time to work on new things.
2010-12-19 14:32:40 -08:00
Mosharaf Chowdhury
272c72b405
Merge branch 'mos-shuffle' into mos-shuffle-parallel
...
Conflicts:
conf/java-opts
src/scala/spark/BasicLocalFileShuffle.scala
2010-12-19 14:25:13 -08:00
Mosharaf Chowdhury
ca37e7b33d
Renamed CustomParallelLocalFileShuffle
2010-12-19 14:22:05 -08:00
Mosharaf Chowdhury
864d202cda
Merge branch 'mos-shuffle-parallel-http' into mos-shuffle
...
Conflicts:
conf/java-opts
src/scala/spark/BlockedLocalFileShuffle.scala
src/scala/spark/CustomBlockedLocalFileShuffle.scala
src/scala/spark/HttpBlockedLocalFileShuffle.scala
2010-12-19 14:08:39 -08:00
Mosharaf Chowdhury
89172fcd69
Renamed this version of BlockedLocalFileShuffle to CustomBlockedLocalFileShuffle.
2010-12-19 14:05:35 -08:00
Mosharaf Chowdhury
a83a722256
Renamed BlockedLocalFileShuffle to HttpBlockedLocalFileShuffle for merging with the mos-shuffle branch.
2010-12-19 14:02:19 -08:00
Mosharaf Chowdhury
62d61ed928
- Reimplemented BlockedLocalFileShuffle without creating too many files.
...
- Clients now request for byte ranges to the server using an INDEX file.
2010-12-18 14:03:49 -08:00
Mosharaf Chowdhury
e30fdeb025
Updated GroupByKey example.
2010-12-16 20:30:18 -08:00
Mosharaf Chowdhury
a40cbc1904
Code formatting.
2010-12-16 16:54:02 -08:00
Mosharaf Chowdhury
ce96d8a7d3
First version of BlockedLocalFileShuffle is in. It works!
2010-12-16 15:15:51 -08:00
Mosharaf Chowdhury
fddcdf87c9
Added a small description of how ParallelLFS works.
2010-12-16 11:58:00 -08:00
Mosharaf Chowdhury
77a4017585
Fixed config param naming in ParallelLocalFileShuffle
2010-12-16 11:42:37 -08:00
Mosharaf Chowdhury
c5483e39f9
- ParallelLocalFileShuffle does NOT use HttpPipelining at all.
...
- Config option related to pipelining has been removed.
- Summary: Basic -> Pipelining / Parallel -> NO pipelining
2010-12-15 22:08:34 -08:00
Mosharaf Chowdhury
56d8a2afa1
- Updated java-opts file of this branch.
...
- Renamed some ParallelLocalFileShuffle config options for clarity.
2010-12-15 20:56:22 -08:00
Mosharaf Chowdhury
25fb3c4cf6
- Brought back Matei's LocalFileShuffle implementation as BasicLocalFileShuffle
...
- Renamed parallel-pull version to ParallelLocalFileShuffle
- Note that setting max-concurrent connections to 1 in ParallelLocalFileShuffle should essentially be the same as BasicLocalFileShuffle
2010-12-15 20:33:28 -08:00
Mosharaf Chowdhury
f82cc17bc5
UseHttpPipelining option is brought back in. It works!
2010-12-07 10:07:30 -08:00
Mosharaf Chowdhury
7e2d72c328
Multiple connections created at a time. No upper limit on the server side though.
2010-12-04 18:55:55 -08:00
Mosharaf Chowdhury
c6df327dd7
Updated logging format.
2010-12-04 16:41:13 -08:00
Mosharaf Chowdhury
7df20d681a
Combined MaxRxPeers and MaxTxPeers to a single config parameter MaxConnections
2010-12-04 14:37:16 -08:00
Mosharaf Chowdhury
b1745b3103
Removed an unnecessary byte array in the middle. Probabaly will have to bring it back if we do block level data movement.
2010-12-04 13:55:25 -08:00
Mosharaf Chowdhury
3a671ce989
Config parameters are in place. Good to go (I think)
2010-12-04 10:59:06 -08:00
Mosharaf Chowdhury
476a216d9d
Parallel is working. Need to fix/finalize some config parameters.
2010-12-04 02:05:41 -08:00
Mosharaf Chowdhury
c546c299bc
combining is happening inside the thread. Its still synchronized though.
2010-12-04 00:59:25 -08:00
Mosharaf Chowdhury
0d7ca7751e
Bug fixes. Not yet parallel.
2010-12-04 00:06:47 -08:00
Mosharaf Chowdhury
52086cef32
Building blocks are in place. Still not pulling parallely though.
2010-12-03 20:29:39 -08:00
Mosharaf Chowdhury
540a41163f
UseHttpPipelining is 'true' by default.
2010-12-02 19:56:17 -08:00
Mosharaf Chowdhury
0de859fbe2
Enabling/disabling HTTP pipelining is a config option now. Performance tradeoffs are not obvious yet.
2010-12-02 02:32:44 -08:00
Mosharaf Chowdhury
8494b3a4f9
- Added log messages for benchmarking.
...
- Added GroupByTest.scala for benchmarking.
2010-11-27 23:51:43 -08:00
Matei Zaharia
f8ea98d989
Remove -unchecked compiler parameter
2010-11-13 18:39:07 -08:00
Matei Zaharia
f8966ffc11
Added a shuffle test with negative hash codes for some keys (this was a bug earlier)
2010-11-12 16:18:45 -08:00
Matei Zaharia
d0a9966555
Unit tests for shuffle operations. Fixes #33 .
2010-11-12 16:12:14 -08:00
Matei Zaharia
7b25ab87af
Added options for using an external HTTP server with LocalFileShuffle
2010-11-09 13:46:30 -08:00
Matei Zaharia
504f839c65
Removed unnecessary collectAsMap
2010-11-08 08:49:42 -08:00
Matei Zaharia
9d3f05a990
Made shuffle algorithm pluggable and added LocalFileShuffle.
2010-11-08 00:46:12 -08:00
Matei Zaharia
d9ea6d69a5
Create output files one by one instead of at the same time in the map
...
phase of DfsShuffle.
2010-11-06 10:53:57 -07:00
Matei Zaharia
16ff4dc0be
Merge branch 'matei-shuffle' of github.com:mesos/spark into matei-shuffle
2010-11-04 14:40:36 -07:00
Matei Zaharia
d984b8ab23
Properly set the number of output splits in DFS shuffle
2010-11-04 14:39:55 -07:00
root
4cc0984b43
Fixed a small bug in DFS shuffle -- the number of reduce tasks was not being set based on numOutputSplits
2010-11-04 21:34:55 +00:00
Matei Zaharia
96f0be935a
Added groupBy function in RDD
2010-11-03 23:58:53 -07:00
Matei Zaharia
72ec298cd4
Added reduceByKey, groupByKey and join operations based on combine, as
...
well as versions of the shuffle operations that set the number of splits
automatically.
2010-11-03 23:51:11 -07:00
Matei Zaharia
d947cb9778
Fixed a bug with negative hashcodes
2010-11-03 22:52:41 -07:00