I had already disabled prometheus plugin (again, only using for the rbd stats), but will also remove the rbd pool from the rbd_support module, as well as disable the rbd_support module. It seems slightly more stable so far, but still not rock solid as it was before. Thanks, Reed
On Aug 15, 2019, at 8:10 AM, Mykola Golub <to.my.trociny@gmail.com> wrote:
On Wed, Aug 14, 2019 at 12:12:36PM -0500, Reed Dier wrote:
My main metrics source is the influx plugin, but I enabled the prometheus plugin to get access to the per-rbd image metrics. I may disable prometheus and see if that yields better stability, until possibly the influx plugin gets updated to support those metric exports.
Before disabling the prometheus plugin, could you try just disabling per-rbd image metrics (i.e. set rbd_stats_pools param to empty)? Per-rbd images stats is a new feature and might be heavy depending on your cluster size and image count, so it would be nice to check this first.
I also see you have rbd_support module enabled. It would be good to have it temporary disabled during this experiment too.
-- Mykola Golub