Messages in this thread | | | Subject | Re: stalling IO regression since linux 5.12, through 5.18 | From | Holger Hoffstätte <> | Date | Wed, 17 Aug 2022 20:21:39 +0200 |
| |
On 2022-08-17 20:15, Jan Kara wrote: > On Wed 17-08-22 13:57:00, Chris Murphy wrote: >> On Wed, Aug 17, 2022, at 12:47 PM, Chris Murphy wrote: >> Can you boot with >>>> "megaraid_sas.host_tagset_enable = 0" kernel option and see whether the >>>> issue reproduces? >> >> This has been running an hour without symptoms. It's strongly suggestive, >> but needs to run overnight to be sure. Anecdotally, the max write IO is >> less than what I'm used to seeing. > > OK, if this indeed passes then b6e68ee82585 ("blk-mq: Improve performance > of non-mq IO schedulers with multiple HW queues") might be what's causing > issues (although I don't know how yet...). > > Honza
Certainly explains why BFQ turned up as a suspect, considering it's still single-queue (fair MQ scheduling is .. complicated).
-h
| |