New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
hugegraph服务挂了 #2484
Comments
嗨,@2867021781!很高兴再次看到你在这里提问。希望一切都好! 根据您提供的信息,我有以下几个建议来帮助您排查HugeGraph服务频繁崩溃的问题:
通过遵循这些排查步骤,您应该能够找出并解决导致HugeGraph服务频繁崩溃的问题。 参考资料:
Sources
|
@dosu-bot 整体回复得不错, 不过注意一下 其中有些配置项是只有最新代码里才有的, 以后可以确认改进一下, 另外之后回复类似的问题, 也可以参考下面的回复 (提醒用户升级版本, 去系统日志里查询 kill 原因等)
@2867021781 单机 rocksdb 建议升级一下到社区的最新版本 (至少是 PS: Better use English to describe your problems in Apache Community instead (Thanks~) |
@2867021781 你好! 感谢您的反馈和耐心等待。根据 imbajin 的建议,我想提醒您升级HugeGraph到最新版本(至少是 此外,如果您的单机使用RocksDB,建议您检查是否发生了OOM(Out of Memory)错误,可能是因为RocksDB使用了过多内存而导致系统进行了OOM-kill,这可能会导致没有异常信息。您可以去系统日志里查看确认是否发生了这样的情况。 希望这些建议能帮助您解决HugeGraph服务频繁崩溃的问题。如果您有任何其他疑问或需要进一步帮助,请随时告诉我。 祝您好运!
|
|
非常感谢,我排查下看看 |
Based on the information you provided, it seems like the HugeGraph service might be crashing due to insufficient memory resources. The To dynamically configure the # Before setting JAVA_OPTIONS
if [ -n "$HUGEGRAPH_MAX_MEM" ]; then
XMX=$HUGEGRAPH_MAX_MEM
else
XMX=$(calc_xmx $MIN_MEM $MAX_MEM)
if [ $? -ne 0 ]; then
echo "Failed to start HugeGraphServer, requires at least ${MIN_MEM}MB free memory" >> "${OUTPUT}"
exit 1
fi
fi
JAVA_OPTIONS="-Xms${MIN_MEM}m -Xmx${XMX}m -XX:+HeapDumpOnOutOfMemoryError -XX:HeapDumpPath=${LOGS} ${USER_OPTION}" With this modification, you can dynamically set the export HUGEGRAPH_MAX_MEM=6254
./hugegraph-server.sh <GREMLIN_SERVER_CONF> <REST_SERVER_CONF> <OPEN_SECURITY_CHECK> This approach allows you to adjust the maximum heap size based on your requirements without modifying the script each time. You can find the script here. As for the recommended memory settings for HugeGraph version 0.12.0 when running on a machine with 32GB of memory, the script sets the maximum heap memory ( If the service is still crashing without any error messages, it could be due to a variety of reasons such as insufficient system resources, configuration issues, port conflicts, file permissions, daemon mode failures, external dependencies, script errors, or logging configuration. You can review the startup script and configuration files, check system resources and file permissions, and ensure the log file is accessible and monitored to diagnose and fix such issues. Unfortunately, I couldn't find specific system requirements for running HugeGraph version 0.12.0 with RocksDB as the backend on a CentOS 3.10.0-957.el7.x86_64 server in the repository. However, ensuring that your system has sufficient resources (CPU, memory, disk space) and that HugeGraph and RocksDB are correctly configured should help in running the service smoothly. I hope this helps! If you have any more questions or need further clarification, feel free to ask. Sources
|
Bug Type (问题类型)
None
Before submit
Environment (环境信息)
Expected & Actual behavior (期望与实际表现)
单机服务,用的0.12.0版本,常会发生 hugegraph服务挂了,但没有任何错误信息,,,该怎么去排查呢
Vertex/Edge example (问题点 / 边数据举例)
No response
Schema [VertexLabel, EdgeLabel, IndexLabel] (元数据结构)
No response
The text was updated successfully, but these errors were encountered: