Prometheus
Project website: http://prometheus.io/ GitHub: https://github.com/prometheus
Memory-mapping of head chunks from disk
This brought down the memory usage of Promtheus by upto 50%. This was achieved with the combination of PR#6830 and PR#6679. You can read more about it in this blog post.
'@' modifier in PromQL
Based on this design doc, the @ modifier for PromQL was added in PR#8121. Learn more in this blog post.
Subquery support in PromQL
With PR#4831, subqueries of the form
<instant_query> '[' <range> ':' [ <resolution> ] ']' [ offset <duration> ]
was introduced in Prometheus. You can read more about it in this blog post.
Vertical compaction and queries in TSDB
With PR#370, Prometheus was able to handle time-overlapping blocks of data. This enabled backfilling of old data into Prometheus.
Persist for state of alerts across restarts
GSoC 2018 work. Read more about it in my blog post.
Unit tests of rules in promtool
GSoC 2018 work. Read more about it in my blog post.
Performance and memory optimizations
It's more about the investigation than the final fix.
Noticeable reduction in memmory allocations by re-using the chunk iterators https://github.com/prometheus-junkyard/tsdb/pull/642
Efficient iteration during hashing. Go language specific optimization. https://github.com/prometheus/prometheus/pull/5707
Series of memory allocation optimizations for compaction. Original PR: https://github.com/prometheus-junkyard/tsdb/pull/627, which was broken down into PR#643 PR#644 PR#645 PR#653 PR#654.