Given how fundamental disk space is to operational competence, it's hard to imagine anyone actually parsing this output instead of using at least something like the machine readable option. The switch is rather simple if they need to make it, and they will be better for it, so I support tidying up this output so new users have a better experience.
Kind Regards, Brandon On Mon, Dec 4, 2023 at 8:44 AM Brad <bscho...@gmail.com> wrote: > > Tablestats currently reports output in a mixed format which is neither ideal > for human readability nor machine readability. Spaces are also > inconsistently used and 13 digit numbers w/out commas or larger units are > complicated to read. > > For example, 'Bytes repaired / un-repaired / pending' uses KiB, MiB units, > but 'Space used live / total' uses bytes. > > Space used (live): 1463210998523 > Space used (total): 1463210998523 > > Bytes repaired: 0.000KiB > Bytes unrepaired: 4315.386GiB > Bytes pending repair: 0.000KiB > > Given tablestats supports a machine readable formatting with the -f format > option for json or yaml output, this Jira proposes: > > standardizing the output to be human readable (-H) as default and > eliminating the current mixed mode of formatting. > > The above example would become: > > Space used (live): 1463.210 GiB > Space used (total): 1463.210 GiB > > Bytes repaired: 0.000 KiB > Bytes unrepaired: 4315.386 GiB > Bytes pending repair: 0.000 KiB > > Existing machine readable formatting (with -f) will be unchanged. More > detailed examples can be found in the Jira CASSANDRA-19104 and associated > google spreadsheet detailing the existing and proposed output: > https://tinyurl.com/38edebjd > > We welcome feedback and thoughts on this. >
