Bukhtawar Khan
Bukhtawar Khan
Thanks @backslasht here I intend to keep the data stored at rest in a format that makes it easier for diverse query engines to be plugged in and helps data...
> > As far as I remember, the `source` field could be disabled (and often is), so it looks to me the proposal is more about having a side store...
We have a benchmarks directory for JMH benchmarks, might be a good starting place for such optimisations
Just a quick note, please also benchmark/profile for CPU and JVM overhead reduction with the change during ser/de.
Failed due to https://github.com/opensearch-project/OpenSearch/issues/4881
> Hi, as primary shard may write index data/translog to remote store. If there is a brain split, old primary still accepts bulk requests from client. Files on remote storage...
I concur the thought of having a separate API to revisit our freshness and durability semantics and pack optimizations as needed. I guess the network infrastructure/firewall would potentially limit how...
Yes I believe this should be reproducible on a multi-node setup, hosting shards of few 100MBs, where we exclude IP of one node and trigger a relocation process of shards...
Adding @sachinpkale for his thoughts as well. Will take a look shortly
Thanks Gaurav, Ideally cluster state applier thread blocks or should block any blocking or networking operation on that thread. But given the flow with remote store we might need a...