Re: [PATCH 0/2] range-bw : Another I/O scheduling policy of dm-ioband (v1)
- From: Dong-Jae Kang <baramsori72@xxxxxxxxx>
- Date: Wed, 6 May 2009 10:26:39 +0900
Hi, Chris Snook
2009/5/4 Chris Snook <chris.snook@xxxxxxxxx>:
On Mon, May 4, 2009 at 6:56 AM, Dong-Jae Kang <baramsori72@xxxxxxxxx> wrote:
range-bw has two kinds of operation modes, min-max and max mode.
Min-max mode is to supports guaranteeing the minimum I/O requirement
and limitation of unnecessary I/O bandwidth at the same time. And max
mode is to support only limitation. So in case of min-max mode, you
need to configure min-bw and max-bw values and in case of max mode,
configure only max-bw.
Please forgive me if I missed a previous discussion, but how is max
mode different from min-max mode with a minimum of zero? I understand
that there may be some special-case optimizations you can do
internally, but it's unclear to me why you need two different
interfaces.
Thank you for your good comments,
As you asked,
max mode is actually same with min-max mode with a zero minimum value.
It is only to consider the aspect of user interface now.
the reason is as below
according to the usage case, some users may be interested in
guranteeing the minimum BW
and limitation of maximum BW at the same time (the basic
fuctionalilty of range-bw), but, some
users can be interested in only limitation of BW to reserve the BW for
another service.
actually, I was overlooking that users are confused with the two kinds
of interface
So, your comments will be related with my future work :)
if two kinds of mode is confused or unnecessary to people,
I will re-consider about supporting the unified interfaces as you pointed
or I try to optimize the scheduling policy for max mode.
and this work will be applied in next release of range-bw.
Thank you, Chris Snook
--
Best Regards,
Dong-Jae Kang
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
- References:
- [PATCH 0/2] range-bw : Another I/O scheduling policy of dm-ioband (v1)
- From: Dong-Jae Kang
- Re: [PATCH 0/2] range-bw : Another I/O scheduling policy of dm-ioband (v1)
- From: Chris Snook
- [PATCH 0/2] range-bw : Another I/O scheduling policy of dm-ioband (v1)
- Prev by Date: [PATCH 5/10] scsi: megaraid_sas - Fixed load/unload issue and Fire the system pd DCDB cmd to MegaRAID SAS FW to get the system PDs
- Next by Date: Re: [PATCH 1/3] ptrace: ptrace_attach: check PF_KTHREAD + exit_state instead of ->mm
- Previous by thread: Re: [PATCH 0/2] range-bw : Another I/O scheduling policy of dm-ioband (v1)
- Next by thread: [PATCH 1/2] range-bw documentation
- Index(es):
Relevant Pages
|
