lkml.org 
[lkml]   [2020]   [May]   [21]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: io_uring vs CPU hotplug, was Re: [PATCH 5/9] blk-mq: don't set data->ctx and data->hctx in blk_mq_alloc_request_hctx
Date
Jens Axboe <axboe@kernel.dk> writes:
> Again, this is mixing up io_uring and blk-mq. Maybe it's the fact that
> both use 'ctx' that makes this confusing. On the blk-mq side, the 'ctx'
> is the per-cpu queue context, for io_uring it's the io_uring instance.

Yes, that got me horribly confused. :)

> io_sq_thread() doesn't care about any sort of percpu mappings, it's
> happy as long as it'll keep running regardless of whether or not the
> optional pinned CPU is selected and then offlined.

Fair enough.

So aside of the potential spin forever if the uring thread is lifted to
an RT scheduling class, this looks all good.

Though I assume that if that thread is pinned and an admin pushs it into
RT scheduling the spinning live lock can happen independent of cpu
hotplug.

Thanks,

tglx

\
 
 \ /
  Last update: 2020-05-21 22:01    [W:0.070 / U:0.068 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site