* stashing changes
* split filesystem collector into fio and legacy functions
* read fio results into analyzer
* remove test script
* update go.mod
* remove old notes
* go mod tidy
* fix up go.mod
* fix up go.mod
* refactor tests for fio
* make schemas
* remove local scripts
* local watch script for building troubleshoot
* document watch script
* fix var names
* handle errors if run as non-root
* go mod tidy
* use String interface
* collector happy path test
* invalid filesize
* invalid filesize
* tests
* remove old code
* remove old init function
* let actions tests run this
* clean up tests
* go mod tidy
* remove duplicated type declaration
* remove old file create code
Add a background IOPS feature to the filesystem performance collector
that specifies separate read and write background IOPS to perform while
measuring latency. This allows for better assessment of whether etcd
will be stable when running alongside other workloads on the same
cluster.
Also add templating to the outcome message of the filesystem performance
analyzers to allow printing individual latency percentiles or the entire
table.
Remove the random IOPS benchmark since it was attempting to perform
unaligned direct I/O.