You are viewing a plain text version of this content. The canonical link for it is here.
Posted to hdfs-dev@hadoop.apache.org by GitBox <gi...@apache.org> on 2019/10/18 12:52:35 UTC
[GitHub] [hadoop-ozone] elek opened a new pull request #59: HDDS-2327.
Provide new Freon test to test Ratis pipeline with pure XceiverClientRatis
elek opened a new pull request #59: HDDS-2327. Provide new Freon test to test Ratis pipeline with pure XceiverClientRatis
URL: https://github.com/apache/hadoop-ozone/pull/59
## What changes were proposed in this pull request?
Xiaoyu Yao suggested during an offline talk to implement one additional Freon test to test the ratis part only.
It can use XceiverClientManager which creates a pure XceiverClientRatis. The client can be used to generate chunks as the datanode accepts any container id / block id.
With this approach we can stress-test one selected ratis pipeline without having full end2end overhead of the key creation (OM, SCM, etc.)
## What is the link to the Apache JIRA
https://issues.apache.org/jira/browse/HDDS-2327
## How was this patch tested?
```
cd hadoop-ozone/dist/target/ozone-*/compose/ozone
docker-compose up -d --scale datanode=3
#wait
docker-compose exec scm ozone freon dcg -n1000
```
Execution should be fine. Eg:
```
10/18/19, 12:50:28 PM ==========================================================
-- Timers ----------------------------------------------------------------------
file-create
count = 1000
mean rate = 142.16 calls/second
1-minute rate = 140.00 calls/second
5-minute rate = 140.00 calls/second
15-minute rate = 140.00 calls/second
min = 0.09 milliseconds
max = 689.10 milliseconds
mean = 63.18 milliseconds
stddev = 63.59 milliseconds
median = 58.54 milliseconds
75% <= 77.92 milliseconds
95% <= 110.45 milliseconds
98% <= 133.97 milliseconds
99% <= 175.51 milliseconds
99.9% <= 675.39 milliseconds
Total execution time (sec): 7
Failures: 0
Successful executions: 1000
```
Check the number of chunk files on the system:
```
for i in `seq 1 3`; do docker exec ozone_datanode_1 find /data/ -type f; done | grep chunk | wc
3000
```
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-dev-unsubscribe@hadoop.apache.org
For additional commands, e-mail: hdfs-dev-help@hadoop.apache.org