On Wed, 16 Jul 2025, Maciej W. Rozycki wrote: > I made a test once and left the system up for half a year or so. The > LBMS bit was set once, a couple of days after system reset. I cleared it > by hand and it never retriggered for the rest of the experiment, so this > single occasion must have been a glitch and not a link quality issue. I guess you also did not observe unusual number of correctable errors? I wonder if AER was under OS control & the relevant errors were unmasked (RxErr, BadTLP, BadDLLP, Replay Rollover, Replay Timeout). If the link transitions from L0 to Recovery state due to excessive LCRC failures I have seen it return at the same speed many times. I won't be able to say what the LBMS behavior is in that case for some time unless I get lucky & find one in our internal test pool.
