We have observed one interesting issue with checkpointing. We are using 64G
RAM 12 CPU with 3K iops/128mbps SSDs. Our application fills up the WAL
directory really fast and hence the RAM. We made the following observations
0. Not so bad news first, it resumes processing after getting stuck for
Ok, Raymond i understand. But seems no one have good answer here, it depends on
appropriate fs and near (probably cloud) layer implementation.
If you not observe «throttling» messages (described in prev link) seems it`s
all ok, but of course you can benchmark your io by yourself with 3-rd party