Message-ID: <54E5E13E.9040502@citrix.com>
Date:	Thu, 19 Feb 2015 14:12:30 +0100
From:	Roger Pau Monné <roger.pau@...rix.com>
To:	Felipe Franciosi <felipe.franciosi@...rix.com>,
	David Vrabel <david.vrabel@...rix.com>,
	Bob Liu <bob.liu@...cle.com>
CC:	'Konrad Rzeszutek Wilk' <konrad.wilk@...cle.com>,
	"xen-devel@...ts.xen.org" <xen-devel@...ts.xen.org>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	"axboe@...com" <axboe@...com>,
	"hch@...radead.org" <hch@...radead.org>,
	"avanzini.arianna@...il.com" <avanzini.arianna@...il.com>
Subject: Re: [PATCH 04/10] xen/blkfront: separate ring information to an new
 struct

El 19/02/15 a les 13.06, Felipe Franciosi ha escrit:
> 
> 
>> -----Original Message-----
>> From: David Vrabel
>> Sent: 19 February 2015 11:15
>> To: Roger Pau Monne; Bob Liu; Felipe Franciosi
>> Cc: 'Konrad Rzeszutek Wilk'; xen-devel@...ts.xen.org; linux-
>> kernel@...r.kernel.org; axboe@...com; hch@...radead.org;
>> avanzini.arianna@...il.com
>> Subject: Re: [PATCH 04/10] xen/blkfront: separate ring information to an new
>> struct
>>
>> On 19/02/15 11:08, Roger Pau Monné wrote:
>>> El 19/02/15 a les 3.05, Bob Liu ha escrit:
>>>>
>>>>
>>>> On 02/19/2015 02:08 AM, Felipe Franciosi wrote:
>>>>>> -----Original Message-----
>>>>>> From: Konrad Rzeszutek Wilk [mailto:konrad.wilk@...cle.com]
>>>>>> Sent: 18 February 2015 17:38
>>>>>> To: Roger Pau Monne
>>>>>> Cc: Bob Liu; xen-devel@...ts.xen.org; David Vrabel; linux-
>>>>>> kernel@...r.kernel.org; Felipe Franciosi; axboe@...com;
>>>>>> hch@...radead.org; avanzini.arianna@...il.com
>>>>>> Subject: Re: [PATCH 04/10] xen/blkfront: separate ring information
>>>>>> to an new struct
>>>>>>
>>>>>> On Wed, Feb 18, 2015 at 06:28:49PM +0100, Roger Pau Monné wrote:
>>>>>>> El 15/02/15 a les 9.18, Bob Liu ha escrit:
>>>>>>> AFAICT you seem to have a list of persistent grants, indirect
>>>>>>> pages and a grant table callback for each ring, isn't this
>>>>>>> supposed to be shared between all rings?
>>>>>>>
>>>>>>> I don't think we should be going down that route, or else we can
>>>>>>> hoard a large amount of memory and grants.
>>>>>>
>>>>>> It does remove the lock that would have to be accessed by each ring
>>>>>> thread to access those. Those values (grants) can be limited to be
>>>>>> a smaller value such that the overall number is the same as it was with
>> the previous version. As in:
>>>>>> each ring has = MAX_GRANTS / nr_online_cpus().
>>>>>>>
>>>>>
>>>>> We should definitely be concerned with the amount of memory consumed
>> on the backend for each plugged virtual disk. We have faced several problems
>> in XenServer around this area before; it drastically affects VBD scalability per
>> host.
>>>>>
>>>>
>>>> Right, so we have to keep both the lock and the amount of memory
>>>> consumed in mind.
>>>>
>>>>> This makes me think that all the persistent grants work was done as a
>> workaround while we were facing several performance problems around
>> concurrent grant un/mapping operations. Given all the recent submissions
>> made around this (grant ops) area, is this something we should perhaps revisit
>> and discuss whether we want to continue offering persistent grants as a feature?
>>>>>
>>>>
>>>> Agree, Life would be easier if we can remove the persistent feature.
>>>
>>> I was thinking about this yesterday, and IMHO I think we should remove
>>> persistent grants now while it's not too entangled, leaving it for
>>> later will just make our life more miserable.
>>>
>>> While it's true that persistent grants provide a throughput increase
>>> by preventing grant table operations and TLB flushes, it has several
>>> problems that cannot by avoided:
>>>
>>>  - Memory/grants hoarding, we need to reserve the same amount of
>>> memory as the amount of data that we want to have in-flight. While
>>> this is not so critical for memory, it is for grants, since using too
>>> many grants can basically deadlock other PV interfaces. There's no way
>>> to avoid this since it's the design behind persistent grants.
>>>
>>>  - Memcopy: guest needs to perform a memcopy of all data that goes
>>> through blkfront. While not so critical, Felipe found systems were
>>> memcopy was more expensive than grant map/unmap in the backend (IIRC
>>> those were AMD systems).
>>>
>>>  - Complexity/interactions: when persistent grants was designed number
>>> of requests was limited to 32 and each request could only contain 11
>>> pages. This means we had to use 352 pages/grants which was fine. Now
>>> that we have indirect IO and multiqueue in the horizon this number has
>>> gone up by orders of magnitude, I don't think this is viable/useful
>>> any more.
>>>
>>> If Konrad/Bob agree I would like to send a patch to remove persistent
>>> grants and then have the multiqueue series rebased on top of that.
>>
>> I agree with this.
>>
>> I think we can get better  performance/scalability gains of with improvements
>> to grant table locking and TLB flush avoidance.
>>
>> David
> 
> It doesn't change the fact that persistent grants (as well as the grant copy implementation we did for tapdisk3) were alternatives that allowed aggregate storage performance to increase drastically. Before committing to removing something that allow Xen users to scale their deployments, I think we need to revisit whether the recent improvements to the whole grant mechanisms (grant table locking, TLB flushing, batched calls, etc) are performing as we would (now) expect.

The fact that this extension improved performance doesn't mean it's
right or desirable. So IMHO we should just remove it and take the
performance hit. Then we can figure ways to deal with the limitations
properly instead of doing this kind of hacks because they prevent us
from moving forward.

Roger.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists