-
Notifications
You must be signed in to change notification settings - Fork 615
-
单个数据集的数据可能在几万到几十万不等,数据集的数量在一百个左右,主要考虑查询效率和内存占用的情况下,哪种方式更合适?
Beta Was this translation helpful? Give feedback.
All reactions
Replies: 1 comment
-
Hey @skysider, I'm here to assist you with any questions or issues you have. I'm a bot designed to help you with bug fixes, answering questions, and becoming a contributor. If you need any help, feel free to ask!
在考虑查询效率和内存占用的情况下,将结构相同但不存在关联关系的多个数据集集中放在一个图数据库还是各自放在不同的图数据库,性能表现会有所不同。
-
集中放在一个图数据库:
-
各自放在不同的图数据库:
- 查询效率:将数据集分开存储可以避免不相关数据集之间的干扰,可能会提高查询效率,特别是当查询主要集中在单个数据集时。
- 内存占用:分开存储可以更好地控制每个图数据库的内存使用,但需要额外的资源来管理多个图数据库实例。
根据 HugeGraph 的基准测试,单个大图数据库在批量插入和遍历操作中表现优异 [2] [3] 。然而,具体选择还需根据实际使用场景和数据集的特点进行权衡。如果查询频繁且数据集之间没有关联,分开存储可能会更合适;如果需要高效的插入和更新操作,集中存储可能更有优势。
Beta Was this translation helpful? Give feedback.
All reactions
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment