Hi Amaury, > One additional question, what is the uptime of your process which > suffers from 1 million stuck connections ? Just to know if this grows > rapidly or slowly over time.
Uptime was 54d 22h36m45s when we captured the ~1.22M figure. Growth was slow and roughly linear, not a spike: we cross-checked five sibling nodes in the same cluster (same config, same traffic mix) over that same ~55 day window and all of them climbed at close to the same rate, around 22k stuck connections/day.
