hadoop/hadoop-tools
Steve Loughran aeb2a2f860
HADOOP-17833. Improve Magic Committer performance (#3289) (#4470)
Speed up the magic committer with key changes being

* Writes under __magic always retain directory markers

* File creation under __magic skips all overwrite checks,
  including the LIST call intended to stop files being
        created over dirs.
* mkdirs under __magic probes the path for existence
  but does not look any further.

Extra parallelism in task and job commit directory scanning
Use of createFile and openFile with parameters which all for
HEAD checks to be skipped.

The committer can write the summary _SUCCESS file to the path
`fs.s3a.committer.summary.report.directory`, which can be in a
different file system/bucket if desired, using the job id as
the filename.

Also: HADOOP-15460. S3A FS to add `fs.s3a.create.performance`

Application code can set the createFile() option
fs.s3a.create.performance to true to disable the same
safety checks when writing under magic directories.
Use with care.

The createFile option prefix `fs.s3a.create.header.`
can be used to add custom headers to S3 objects when
created.

Contributed by Steve Loughran.
2022-06-21 10:49:37 +01:00
..
hadoop-aliyun
hadoop-archive-logs
hadoop-archives
hadoop-aws HADOOP-17833. Improve Magic Committer performance (#3289) (#4470) 2022-06-21 10:49:37 +01:00
hadoop-azure HADOOP-16202. Enhanced openFile(): hadoop-azure changes. (#2584/4) 2022-04-27 19:24:33 +01:00
hadoop-azure-datalake HDFS-16453. Upgrade okhttp from 2.7.5 to 4.9.3 (#4229) 2022-05-21 03:17:15 +09:00
hadoop-datajoin
hadoop-distcp HADOOP-18269. Misleading method name in DistCpOptions.(#4216) 2022-05-30 14:04:33 +01:00
hadoop-dynamometer
hadoop-extras
hadoop-fs2img
hadoop-gridmix
hadoop-kafka
hadoop-openstack
hadoop-pipes
hadoop-resourceestimator
hadoop-rumen
hadoop-sls
hadoop-streaming
hadoop-tools-dist
pom.xml