Paul Dix
Paul Dix
@hiltontj We encountered a problem with concurrency in IOx before that required moving query planning off of the IO threadpool and onto the DF threadpool. The pr is influxdata/influxdb_iox#11029 which...
It would be interesting to see this overlaid with the queries per second as well. Showing the throughput in addition to the latencies is useful.
The v2 returns a 204 because we built the InfluxDB Cloud 2 as the first v2 product, which accepts data before validating it and making it available for query. Because...
Can you get some EXPLAIN plans from some of these queries? I'm curious if deduplication is running, which should be something that we generally don't need except for stuff in...
Right now there's nothing built in. But if you copy the everything under `node_id` prefix to another directory, start up a server with that changed node_id to the directory you...
This is going to be an expensive query in v3. That's because we currently don't keep an index of the tag values. The benefit of this is that cardinality doesn't...
Is this still an issue? Is there something short and actionable for us to do here? I'm looking for a summary.