Comments (4)
In our production environment, the size of shuffle is usually hundreds of GBs. For very small shuffles, Firestorm will be slower than native shuffles. But there seems to be room for optimization.
from firestorm.
@packageman with firestorm, there are some RPC calls to send data, as you mentioned, requirePreallocation etc. Your case is the same as we expected, with small shuffle data, Firestorm will be a little slower than origin shuffle.
For reference, Firestorm is target to :
- Support Spark on K8s things
- Improve job's performance/stability with heavy shuffle workload, eg, shuffle data = TB, partition num = 50000+
from firestorm.
Support Spark on K8s things
Currently, we are running Spark on k8s.
with small shuffle data, Firestorm will be a little slower than origin shuffle
It looks not only a little slower but also a lot slower(2mins vs 5.6mins), nearly 2 times. I understand that grpc call will take some extra time, but the total time is more than double that of the native shuffle when working with small shuffle data, which is not consistent with your description.
with native shuffle:
with Firestorm:
from firestorm.
@packageman with your case, 1W+task total, the delay should be depend on task number of parallels, if every task is slower about 0.5s with Firstorm, then
- 1W parallels task should be slower 0.5s total
- 1000 parallels task should be slower 5s total
- 100 parallels task should be slower 50s total
It's the behave we known, Firstorm is not target to improve performance with any situation. Platform can decide if use Firestorm with all Spark job, or with specific job.
From your case, input data for every task is less than 1MB, shuffle write data is less than 1kb. Optimize job to have more data for every task will be better.
from firestorm.
Related Issues (20)
- Whether multiple disks are supported for local storage? HOT 4
- duplicate servlets map in Coordinator Server
- 使用firestorm-0.4.0 运行spark3.1.1官方的JavaWordCount报如下错误,并且在yarn-client模式下driver端进程一直不退出 HOT 10
- What‘s the difference between `spark.rss.storage.type` and `rss.storage.type`? HOT 18
- yarn-client模式下driver端进程一直不退出 HOT 9
- In local mode, why directory should be deleted first? HOT 1
- [QUESTION] 依赖Hadoop环境? HOT 3
- [QUESTION] Executor在shuffle write/read 过程中是否落本地盘? HOT 2
- [Feature Request]Add a web UI in Coordinated Server to show the detailed server/job/metrics information HOT 1
- hardcoded relative paths HOT 6
- Whether local multiple replicas are supported? HOT 2
- Compared to the native spark, the shuffle write data of firestorm is always smaller HOT 2
- Unexpected crc value for blockId[474989042101783], expected:1518107711, actual:3331113690 HOT 5
- Shuffle read does not read all data completely? HOT 31
- Support shuffle data replica? HOT 5
- Coordinator HA problem HOT 6
- fault tolerance HOT 4
- Clear buffered data when acquiring memory failed and then retry
- To support more tasks with Firestorm
- how to enter into uniffle wechat or dingtalk?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from firestorm.