On 6/24/2018 7:38 PM, 苗海泉 wrote:
Hello, everyone, we encountered two solr problems and hoped to get help. Our data volume is very large, 24.5TB a day, and the number of records is 110 billion. We originally used 49 solr nodes. Because of insufficient storage, we expanded to 100. For a solr cluster composed of multiple machines, we found that the performance of 60 solrclouds and the overall performance of 49 solr clusters are the same. How do we optimize it? Now the cluster speed is 1.5 million on average per second. Why is that?
I can't really tell what your question is. You've asked how to optimize something, but it's not clear exactly what you want to optimize. You also asked about a cluster speed of 1.5 million per second, but you haven't indicated what is happening at that rate. 1.5 million *what* per second? If you're talking about queries per second or documents indexed per second, you're already getting better performance than I would have expected.
We'll need a lot more detail about exactly what kind of problems you've encountered and what you think *should* be happening that isn't happening.
The second problem solrhome can only specify a solrhome, but now the disk is divided into two directories, another solr can be stored using hdfs, but the overall indexing performance is not up to standard, how to do, thank you for your attention.
I would use symlinks to point some of the index cores to the second directory. It is possible to reduce this to one symlink rather than one for each core. Moving things to the second location will likely be a manual process.
If you're on Windows, things are a little bit different, but NTFS does have a feature that offers very similar functionality to symlinks:
https://en.wikipedia.org/wiki/NTFS_junction_point Thanks, Shawn
