Re: CEPH dmclock per-client QoS control

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



There's an initial implementation sitting around in a branch
(https://github.com/athanatos/ceph/tree/sjust/wip-dmclock-librados-rebase),
but it still needs a lot of work.  In short, it's not ready in current
master.
-Sam

On Thu, Jul 30, 2020 at 2:45 PM Eric Ivancich <ivancich@xxxxxxxxxx> wrote:
>
> > On Jun 19, 2020, at 12:59 AM, qjpqzb@xxxxxxxxx wrote:
> >
> > Hi,
> >
> > I am trying to use CEPH dmclock to see how it works for QoS control. Especially, I want to set “osd_op_queue” as “mclock_client” to config different [r, w, l] for each client. The CEPH version I use is nautilus 14.2.9.
>
> That feature was never fully realized and did not support setting reservation, weight, and limit for each client. At best it simply kept a separate queue for each client so each client’s tags would increment independently thereby promoting some “fairness" between clients.
>
> And as I look at master, it appears that the mclock scheduler was re-worked by Sam Just and that feature is no longer there.
>
> > I noticed that in "OSD CONFIG REFERENCE" section of CEPH documentation, it states that "the mClock based ClientQueue (mclock_client) also incorporates the client identifier in order to promote fairness between clients.", so I believe librados can support per-client configurations right now. I wonder how I can set up the CEPH configuration to config different (r, w, l) for different clients using such “client identifier"? Thanks.
>
> I’d started an effort to allow client configuration via librados but needed to move onto other rgw-centered tasks. Sam was looking at that code but I don’t know where he went with it.
>
> Best,
>
> Eric
> _______________________________________________
> Dev mailing list -- dev@xxxxxxx
> To unsubscribe send an email to dev-leave@xxxxxxx
_______________________________________________
Dev mailing list -- dev@xxxxxxx
To unsubscribe send an email to dev-leave@xxxxxxx




[Index of Archives]     [CEPH Users]     [Ceph Devel]     [Ceph Large]     [Information on CEPH]     [Linux BTRFS]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux