From: Vlastimil Babka <vbabka@suse.cz>
To: Vitaly Wool <vitalywool@gmail.com>
Cc: "Minchan Kim" <minchan@kernel.org>,
"Sergey Senozhatsky" <sergey.senozhatsky@gmail.com>,
"Dan Streetman" <ddstreet@ieee.org>,
LKML <linux-kernel@vger.kernel.org>,
Linux-MM <linux-mm@kvack.org>, 김준수 <iamjoonsoo.kim@lge.com>,
"Gioh Kim" <gioh.kim@lge.com>
Subject: Re: [PATCH 0/3] allow zram to use zbud as underlying allocator
Date: Thu, 1 Oct 2015 09:52:16 +0200 [thread overview]
Message-ID: <560CE630.6060207@suse.cz> (raw)
In-Reply-To: <CAMJBoFNpqrr_5iuQ68TrRPP=Uv0SYPra6XH27NAcG+Apq=CoSg@mail.gmail.com>
On 09/30/2015 05:46 PM, Vitaly Wool wrote:
> On Wed, Sep 30, 2015 at 5:37 PM, Vlastimil Babka <vbabka@suse.cz> wrote:
>> On 09/25/2015 11:54 AM, Vitaly Wool wrote:
>>>
>>> Hello Minchan,
>>>
>>> the main use case where I see unacceptably long stalls in UI with
>>> zsmalloc is switching between users in Android.
>>> There is a way to automate user creation and switching between them so
>>> the test I run both to get vmstat statistics and to profile stalls is
>>> to create a user, switch to it and switch back. Each test cycle does
>>> that 10 times, and all the results presented below are averages for 20
>>> runs.
>>>
>>> Kernel configurations used for testing:
>>>
>>> (1): vanilla
>>> (2): (1) plus "make SLUB atomic" patch [1]
>>> (3): (1) with zbud instead of zsmalloc
>>> (4): (2) with compaction defer logic mostly disabled
>>
>>
>> Disabling compaction deferring leads to less compaction stalls? That indeed
>> looks very weird and counter-intuitive. Also what's "mostly" disabled mean?
>
> Not that I'm not surprised myself. However, this is how it goes.
> Namely, I reverted the following patches:
> - mm, compaction: defer each zone individually instead of preferred zone
Oh, I see. Then you didn't disable compaction defer logic, but made it
coarse again instead of per-zone. Which means that an allocation that
can be satisfied from Normal zone will use the Normal zone's deferred
state to decide whether to compact also DMA and DMA32 zones *within the
same allocation attempt*. So by reverting the patch you might indeed get
less compact_stall (and success+failure) counts, but each stall will try
to compact all three zones. With individual defer, some stall might be
just for DMA32, some just for Normal, and the total number might be
higher, but the compaction overhead should be better distributed among
all the attempts. Looking at your latencies, looks like that's working fine:
>
> The UI is blocked after user switching for, average:
> (1) 1.84 seconds
> (2) 0.89 seconds
> (3) 1.32 seconds
> (4) 0.87 seconds
Average for (2) vs (4) is roughly the same, I would guess within noise.
> The UI us blocked after user switching for, worst-case:
> (1) 2.91
> (2) 1.12
> (3) 1.79
> (4) 1.34
The worst case is actually worse without individual defer, because you
end up compacting all zones in each single stall. With individual defer,
there's a low probability of that happening.
> - mm, compaction: embed migration mode in compact_control
This probably affects just THPs.
> - mm, compaction: add per-zone migration pfn cache for async compaction
Hard to say what's the effect of this.
> - mm: compaction: encapsulate defer reset logic
This is just code consolidation.
> ~vitaly
>
WARNING: multiple messages have this Message-ID (diff)
From: Vlastimil Babka <vbabka@suse.cz>
To: Vitaly Wool <vitalywool@gmail.com>
Cc: "Minchan Kim" <minchan@kernel.org>,
"Sergey Senozhatsky" <sergey.senozhatsky@gmail.com>,
"Dan Streetman" <ddstreet@ieee.org>,
LKML <linux-kernel@vger.kernel.org>,
Linux-MM <linux-mm@kvack.org>, 김준수 <iamjoonsoo.kim@lge.com>,
"Gioh Kim" <gioh.kim@lge.com>
Subject: Re: [PATCH 0/3] allow zram to use zbud as underlying allocator
Date: Thu, 1 Oct 2015 09:52:16 +0200 [thread overview]
Message-ID: <560CE630.6060207@suse.cz> (raw)
In-Reply-To: <CAMJBoFNpqrr_5iuQ68TrRPP=Uv0SYPra6XH27NAcG+Apq=CoSg@mail.gmail.com>
On 09/30/2015 05:46 PM, Vitaly Wool wrote:
> On Wed, Sep 30, 2015 at 5:37 PM, Vlastimil Babka <vbabka@suse.cz> wrote:
>> On 09/25/2015 11:54 AM, Vitaly Wool wrote:
>>>
>>> Hello Minchan,
>>>
>>> the main use case where I see unacceptably long stalls in UI with
>>> zsmalloc is switching between users in Android.
>>> There is a way to automate user creation and switching between them so
>>> the test I run both to get vmstat statistics and to profile stalls is
>>> to create a user, switch to it and switch back. Each test cycle does
>>> that 10 times, and all the results presented below are averages for 20
>>> runs.
>>>
>>> Kernel configurations used for testing:
>>>
>>> (1): vanilla
>>> (2): (1) plus "make SLUB atomic" patch [1]
>>> (3): (1) with zbud instead of zsmalloc
>>> (4): (2) with compaction defer logic mostly disabled
>>
>>
>> Disabling compaction deferring leads to less compaction stalls? That indeed
>> looks very weird and counter-intuitive. Also what's "mostly" disabled mean?
>
> Not that I'm not surprised myself. However, this is how it goes.
> Namely, I reverted the following patches:
> - mm, compaction: defer each zone individually instead of preferred zone
Oh, I see. Then you didn't disable compaction defer logic, but made it
coarse again instead of per-zone. Which means that an allocation that
can be satisfied from Normal zone will use the Normal zone's deferred
state to decide whether to compact also DMA and DMA32 zones *within the
same allocation attempt*. So by reverting the patch you might indeed get
less compact_stall (and success+failure) counts, but each stall will try
to compact all three zones. With individual defer, some stall might be
just for DMA32, some just for Normal, and the total number might be
higher, but the compaction overhead should be better distributed among
all the attempts. Looking at your latencies, looks like that's working fine:
>
> The UI is blocked after user switching for, average:
> (1) 1.84 seconds
> (2) 0.89 seconds
> (3) 1.32 seconds
> (4) 0.87 seconds
Average for (2) vs (4) is roughly the same, I would guess within noise.
> The UI us blocked after user switching for, worst-case:
> (1) 2.91
> (2) 1.12
> (3) 1.79
> (4) 1.34
The worst case is actually worse without individual defer, because you
end up compacting all zones in each single stall. With individual defer,
there's a low probability of that happening.
> - mm, compaction: embed migration mode in compact_control
This probably affects just THPs.
> - mm, compaction: add per-zone migration pfn cache for async compaction
Hard to say what's the effect of this.
> - i? 1/4 mm: compaction: encapsulate defer reset logic
This is just code consolidation.
> ~vitaly
>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2015-10-01 7:52 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-09-14 13:49 [PATCH 0/3] allow zram to use zbud as underlying allocator Vitaly Wool
2015-09-14 13:49 ` Vitaly Wool
2015-09-14 13:50 ` [PATCH 1/3] zram: make max_zpage_size configurable Vitaly Wool
2015-09-14 13:50 ` Vitaly Wool
2015-09-15 1:00 ` Sergey Senozhatsky
2015-09-15 1:00 ` Sergey Senozhatsky
2015-09-15 7:18 ` Vitaly Wool
2015-09-15 7:38 ` Sergey Senozhatsky
2015-09-15 7:38 ` Sergey Senozhatsky
2015-09-15 5:42 ` Dan Streetman
2015-09-15 5:42 ` Dan Streetman
2015-09-15 6:08 ` Sergey Senozhatsky
2015-09-15 6:08 ` Sergey Senozhatsky
2015-09-14 13:51 ` [PATCH 2/3] zpool/zsmalloc/zbud: align on interfaces Vitaly Wool
2015-09-14 13:51 ` Vitaly Wool
2015-09-15 1:06 ` Sergey Senozhatsky
2015-09-15 1:06 ` Sergey Senozhatsky
2015-09-15 5:09 ` Dan Streetman
2015-09-15 5:09 ` Dan Streetman
2015-09-14 13:55 ` [PATCH 3/3] zram: use common zpool interface Vitaly Wool
2015-09-14 13:55 ` Vitaly Wool
2015-09-15 1:12 ` Sergey Senozhatsky
2015-09-15 1:12 ` Sergey Senozhatsky
2015-09-15 6:03 ` Dan Streetman
2015-09-15 6:03 ` Dan Streetman
2015-09-14 14:01 ` [PATCH 0/3] allow zram to use zbud as underlying allocator Vlastimil Babka
2015-09-14 14:01 ` Vlastimil Babka
2015-09-14 14:12 ` Vitaly Wool
2015-09-14 14:12 ` Vitaly Wool
2015-09-14 14:14 ` Vlastimil Babka
2015-09-14 14:14 ` Vlastimil Babka
2015-09-15 4:08 ` Dan Streetman
2015-09-15 4:08 ` Dan Streetman
2015-09-15 4:22 ` Sergey Senozhatsky
2015-09-15 4:22 ` Sergey Senozhatsky
2015-09-17 6:21 ` Vlastimil Babka
2015-09-17 6:21 ` Vlastimil Babka
2015-09-17 9:19 ` Sergey Senozhatsky
2015-09-17 9:19 ` Sergey Senozhatsky
2015-09-15 0:49 ` Sergey Senozhatsky
2015-09-15 0:49 ` Sergey Senozhatsky
2015-09-15 6:13 ` Minchan Kim
2015-09-15 6:13 ` Minchan Kim
2015-09-25 9:54 ` Vitaly Wool
2015-09-25 9:54 ` Vitaly Wool
2015-09-30 7:52 ` Minchan Kim
2015-09-30 7:52 ` Minchan Kim
2015-09-30 8:01 ` Vitaly Wool
2015-09-30 8:01 ` Vitaly Wool
2015-09-30 8:13 ` Minchan Kim
2015-09-30 8:13 ` Minchan Kim
2015-09-30 8:18 ` Vitaly Wool
2015-09-30 8:18 ` Vitaly Wool
2015-09-30 15:37 ` Vlastimil Babka
2015-09-30 15:37 ` Vlastimil Babka
2015-09-30 15:46 ` Vitaly Wool
2015-09-30 15:46 ` Vitaly Wool
2015-10-01 7:52 ` Vlastimil Babka [this message]
2015-10-01 7:52 ` Vlastimil Babka
2015-10-10 9:33 ` Vitaly Wool
2015-10-10 9:33 ` Vitaly Wool
2015-10-14 13:28 ` Vlastimil Babka
2015-10-14 13:28 ` Vlastimil Babka
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=560CE630.6060207@suse.cz \
--to=vbabka@suse.cz \
--cc=ddstreet@ieee.org \
--cc=gioh.kim@lge.com \
--cc=iamjoonsoo.kim@lge.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=minchan@kernel.org \
--cc=sergey.senozhatsky@gmail.com \
--cc=vitalywool@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.