mikerhodes commented on PR #5625: URL: https://github.com/apache/couchdb/pull/5625#issuecomment-3200592575
> ...the performance gain is quite modest (except for changes) to warrant the extra complexity and failure modes (on the flipside it does validate our deliberate reliance on the OS page cache for this so far). I find the 33% improvement in single doc reads is significant. It's definitely in line with, if not slightly greater than, what I'd expect for this kind of change. It's also where I'd expect to see the greatest benefit of this change --- like you @rnewson I'm somewhat surprised by the `_changes` seeing an 80% increase in reads per sec (I also wonder why `_all_docs` is so much higher). One other interesting thing in general with these numbers is how many more docs we read per second with the `_all_docs` call --- 49k/s vs 4k/s. Presumably the random reads are going through an `r=2` read, whereas `_all_docs` include_docs reads are going to the local shard that was chosen for `_all_docs` using an implicit `r=1`? Feels like there's something important in that disparity. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: notifications-unsubscr...@couchdb.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
