GitHub user charlesccychen opened a pull request:
https://github.com/apache/incubator-beam/pull/1379
Speed up GcsIO throughput by 10x
This change increases the read buffer used from 1M to 16M. Previously,
the speed of reading an incompressible file were: (50 MB: 3.17 MB/s,
100 MB: 3.79 MB/s, 200 MB: 4.13 MB/s, 400 MB: 4.24 MB/s).
The speed is now improved to: (50 MB: 24.21 MB/s, 100 MB: 42.70 MB/s,
200 MB: 42.89 MB/s, 400 MB: 46.92 MB/s).
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/charlesccychen/incubator-beam
gcsio-speed-improvement
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/incubator-beam/pull/1379.patch
To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:
This closes #1379
----
----
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
