Skip to content

Commit b38ab0a

Browse files
authored
docs: update sample config and blog url (#31)
* docs: update sample config and blog url
1 parent 6790ea1 commit b38ab0a

File tree

2 files changed

+7
-10
lines changed

2 files changed

+7
-10
lines changed

README.md

Lines changed: 4 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@ Pafka: Persistent Memory (PMem) Accelerated Kafka
1515

1616
Pafka is an evolved version of Apache Kafka developed by [MemArk](https://memark.io/en). Kafka is an open-source distributed event streaming/message queue system for handling real-time data feeds efficiently and reliably. However, its performance (e.g., throughput and latency) is constrained by slow external storage. Pafka enhances Kafka based on tiered storage architecture, which is usually equipped with high-performance SSD or Intel® Optane™ Persistent Memory (PMem). With the careful design of data migration algorithms, it improves overall persistence performance with low cost. For example, it can well support the scenario that high data production rate is repeated after an interval of time (e.g., special discount is released every one hour from a shopping website); it is also capable of improving the overall performance when high throughput is required over a long period.
1717

18-
Please refer to our latest blog for Pafka benchmark and use cases :point_right: [English](https://memark.medium.com/pafka-0-2-0-optimized-kafka-based-on-tiered-storage-architecture-1261078ef46b) ([中文](https://memark.io/index.php/2021/09/24/pafka_020/))
18+
Please refer to our latest blog for Pafka benchmark and use cases :point_right: [English](https://memark.medium.com/pafka-0-3-0-release-low-cost-solution-to-peak-traffic-scenario-in-kafka-6eb073de7798) ([中文](https://memark.io/index.php/2021/12/29/pafka-0-3-0/))
1919

2020
## 2. Architecture
2121

@@ -36,8 +36,6 @@ The easiest way to try Pafka is to use the docker image: https://hub.docker.com/
3636
docker run -it 4pdopensource/pafka-dev bash
3737
```
3838

39-
where $YOUR_PMEM_PATH is the mount point of PMem (DAX file system) in the host system.
40-
4139
If you use the docker image, you can skip the following `Compile` step.
4240

4341
### 3.2. Compile
@@ -99,11 +97,11 @@ Sample config in config/server.properties is as follows:
9997

10098
# log file channel type; Options: "file", "pmem", "tiered".
10199
# if "file": use normal file as vanilla Kafka does. Following configs are not applicable.
102-
log.channel.type=file
100+
log.channel.type=tiered
103101
# the storage types for each layers (separated by ,)
104-
storage.tiers.types=PMEM,HDD
102+
storage.tiers.types=NVME,HDD
105103
# first-layer storage paths (separated by ,)
106-
storage.tiers.first.paths=/pmem
104+
storage.tiers.first.paths=/nvme
107105
# first-layer storage capacities in bytes (separated by ,); -1 means use all the space
108106
storage.tiers.first.sizes=-1
109107
# second-layer storage paths (separated by ,)

docker/Dockerfile

Lines changed: 3 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -16,7 +16,7 @@
1616
FROM centos:7.3.1611
1717

1818
LABEL maintainer="zhanghao@4paradigm.com"
19-
VOLUME ["/mnt/mem", "/mnt/hdd", "/pmem"]
19+
VOLUME ["/hdd", "/pmem", "/nvme", "/ssd"]
2020

2121
# Set the timezone.
2222
ENV TZ="/usr/share/zoneinfo/Asia/Singapore"
@@ -37,7 +37,7 @@ RUN yum install -y libpmem librpmem libpmemblk libpmemlog libpmemobj libpmempool
3737
RUN pip3 install setuptools==46.4.0 && pip3 install jupyterlab tabulate
3838

3939
# or clone directly
40-
# git clone --branch feat/notebook git@gitlab.4pd.io:hpc_sg/kafka.git /opt/pafka-dev
40+
# git clone https://github.com/4paradigm/pafka.git /opt/pafka-dev
4141
COPY ./ /opt/pafka-dev
4242

4343
# set workdir
@@ -47,7 +47,6 @@ WORKDIR /opt/pafka-dev
4747
RUN ./gradlew jar
4848

4949
# set workdir to notebook
50-
WORKDIR /opt/pafka-dev/notebook
50+
WORKDIR /opt/pafka-dev
5151

52-
ENTRYPOINT ["/opt/pafka-dev/docker/entrypoint.sh"]
5352
CMD ["bash"]

0 commit comments

Comments
 (0)