[
https://issues.apache.org/jira/browse/HADOOP-11183?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Thomas Demoor updated HADOOP-11183:
-----------------------------------
Attachment: info-003.patch.md
HADOOP-11183.003.patch
003.patch:
- concurrent uploading of parallel uploads / partUploads (of the same or
different multipartUploads) in different threads
- controllable max memory footprint through threadpoolexecutor w/ blocking
queue (causes dependency on HADOOP-11463)
- More info in: info-003.patch.md
- Speedup: my 10 MB/s connection from work upload of a 128MB file is 20% faster
to AWS Ireland. Bigger files and higher throughput increase the speedup:
directly on Amplidata's object store the difference is huge.
- Documentation is being added in HADOOP-11522
Difference with 002.patch:
- HDFS-like statistics counting: I prefer this, and you? See previous comment
for more info.
Remark 2 and 3 from my comment on 001.patch are still open.
> Memory-based S3AOutputstream
> ----------------------------
>
> Key: HADOOP-11183
> URL: https://issues.apache.org/jira/browse/HADOOP-11183
> Project: Hadoop Common
> Issue Type: Improvement
> Components: fs/s3
> Affects Versions: 2.6.0
> Reporter: Thomas Demoor
> Assignee: Thomas Demoor
> Attachments: HADOOP-11183.001.patch, HADOOP-11183.002.patch,
> HADOOP-11183.003.patch, info-003.patch.md, info-S3AFastOutputStream-sync.md
>
>
> Currently s3a buffers files on disk(s) before uploading. This JIRA
> investigates adding a memory-based upload implementation.
> The motivation is evidently performance: this would be beneficial for users
> with high network bandwidth to S3 (EC2?) or users that run Hadoop directly on
> an S3-compatible object store (FYI: my contributions are made in name of
> Amplidata).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
