You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by StefanRRichter <gi...@git.apache.org> on 2017/05/29 15:28:12 UTC
[GitHub] flink pull request #4011: [FLINK-6766] Update documentation about async back...
GitHub user StefanRRichter opened a pull request:
https://github.com/apache/flink/pull/4011
[FLINK-6766] Update documentation about async backends and incrementa…
…l checkpoints
This PR introduces some documentation about async heap backends and incremental snapshots with RocksDB.
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/StefanRRichter/flink backend-docu-update
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/flink/pull/4011.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 #4011
----
commit 9f26592529eec20a164e5bb8d08cc85a074c0c3b
Author: Stefan Richter <s....@data-artisans.com>
Date: 2017-05-29T15:18:19Z
[FLINK-6766] Update documentation about async backends and incremental checkpoints
----
---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
[GitHub] flink pull request #4011: [FLINK-6766] Update documentation about async back...
Posted by alpinegizmo <gi...@git.apache.org>.
Github user alpinegizmo commented on a diff in the pull request:
https://github.com/apache/flink/pull/4011#discussion_r119344251
--- Diff: docs/monitoring/large_state_tuning.md ---
@@ -138,6 +138,22 @@ Unfortunately, RocksDB's performance can vary with configuration, and there is l
RocksDB properly. For example, the default configuration is tailored towards SSDs and performs suboptimal
on spinning disks.
+**Incremental Checkpoints**
+
+Incremental checkpoints can dramatically reduce the checkpointing time in comparison to full checkpoints, at the cost of a (potentially) longer
+recovery time. The core idea is that incremental checkpoints only record all changes to the previous completed checkpoint, instead of
+producing a full, self-contained backups of the backend. Like this, incremental checkpoints build upon previous checkpoints. Flink leverages
--- End diff --
a full, self-contained backup of the state backend
---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
[GitHub] flink pull request #4011: [FLINK-6766] Update documentation about async back...
Posted by alpinegizmo <gi...@git.apache.org>.
Github user alpinegizmo commented on a diff in the pull request:
https://github.com/apache/flink/pull/4011#discussion_r119344563
--- Diff: docs/ops/state_backends.md ---
@@ -88,6 +102,13 @@ that is (per default) stored in the TaskManager data directories. Upon checkpoin
RocksDB data base will be checkpointed into the configured file system and directory. Minimal
metadata is stored in the JobManager's memory (or, in high-availability mode, in the metadata checkpoint).
+The RocksDBStateBackend always performs asynchronous snapshots.
+
+Limitations of the RocksDBStateBackend:
+
+ - As RocksDB's JNI bridge API is based on byte[], the maximum supported size per key and per value is 2^31 bytes each.
+ IMPORTANT: states that use merge operations in RocksDB (e.g. ListState) can silently accumulate value sizes > 2^31 bytes and will then fail on their next retrival. This is currently a limitation of RocksDB JNI.
+
--- End diff --
retrieval
---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
[GitHub] flink pull request #4011: [FLINK-6766] Update documentation about async back...
Posted by alpinegizmo <gi...@git.apache.org>.
Github user alpinegizmo commented on a diff in the pull request:
https://github.com/apache/flink/pull/4011#discussion_r119344615
--- Diff: docs/ops/state_backends.md ---
@@ -88,6 +102,13 @@ that is (per default) stored in the TaskManager data directories. Upon checkpoin
RocksDB data base will be checkpointed into the configured file system and directory. Minimal
metadata is stored in the JobManager's memory (or, in high-availability mode, in the metadata checkpoint).
+The RocksDBStateBackend always performs asynchronous snapshots.
+
+Limitations of the RocksDBStateBackend:
+
+ - As RocksDB's JNI bridge API is based on byte[], the maximum supported size per key and per value is 2^31 bytes each.
+ IMPORTANT: states that use merge operations in RocksDB (e.g. ListState) can silently accumulate value sizes > 2^31 bytes and will then fail on their next retrival. This is currently a limitation of RocksDB JNI.
--- End diff --
retrieval
---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
[GitHub] flink pull request #4011: [FLINK-6766] Update documentation about async back...
Posted by asfgit <gi...@git.apache.org>.
Github user asfgit closed the pull request at:
https://github.com/apache/flink/pull/4011
---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
[GitHub] flink issue #4011: [FLINK-6766] Update documentation about async backends an...
Posted by rmetzger <gi...@git.apache.org>.
Github user rmetzger commented on the issue:
https://github.com/apache/flink/pull/4011
I'll merge the change.
---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
[GitHub] flink issue #4011: [FLINK-6766] Update documentation about async backends an...
Posted by StefanRRichter <gi...@git.apache.org>.
Github user StefanRRichter commented on the issue:
https://github.com/apache/flink/pull/4011
Thanks for the input @alpinegizmo ! I updated the text accordingly.
---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
[GitHub] flink issue #4011: [FLINK-6766] Update documentation about async backends an...
Posted by StefanRRichter <gi...@git.apache.org>.
Github user StefanRRichter commented on the issue:
https://github.com/apache/flink/pull/4011
CC @rmetzger
---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---