Hi Jeff,
How many CPU ?
What is the CPU load average (information provided by Linux top command in
the first line) ?
I don't think it is the root cause of your issue, but 1 NRT + 1 TLOG
replica per shard is not a usual practice. You have to create 2 TLOG
replicas per shard and let Solr elect the NRT one.
Regards
Dominique
Le dim. 8 août 2021 à 21:42, Jeff <mccallumj...@gmail.com> a écrit :
> Hello,
> I am currently running a 20 node Solrcloud on 7.7
>
> We have 800,000,000 documents
>
> I am experiencing CPU spikes well over 100%
> Adding more CPU did not solve the issue.
>
> searcherExecutor times are ballooning.
>
> I have 2 replicas per shard. 1 NRT and 1 TLOG.
>
> We are indexing around 200,000 per hour.
>
> I have disabled soft commit.
>
> Any help is greatly appreciated!
>
> <maxTime>${solr.autoCommit.maxTime:60000}</maxTime>
> <openSearcher>true</openSearcher>
>
