lkml.org 
[lkml]   [2021]   [Sep]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [LKP] Re: [mm] 8cc621d2f4: fio.write_iops -21.8% regression
From
Date
Hi Minchan,

    Do you have time to look at this? I re-test it in  v5.14, the
regression still existed. Thanks.

On 5/26/2021 12:57 AM, Chris Goldsworthy wrote:
> On 2021-05-25 09:39, Minchan Kim wrote:
>> On Tue, May 25, 2021 at 08:16:03AM -0700, Minchan Kim wrote:
>>
>> < snip >
>>
>>> > > On Thu, May 20, 2021 at 04:31:44PM +0800, kernel test robot wrote:
>>> > > >
>>> > > >
>>> > > > Greeting,
>>> > > >
>>> > > > FYI, we noticed a -21.8% regression of fio.write_iops due to
>>> commit:
>>> > > >
>>> > > >
>>> > > > commit: 8cc621d2f45ddd3dc664024a647ee7adf48d79a5 ("mm: fs:
>>> > > > invalidate BH LRU during page migration")
>>> > > >
>>> https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
>>> > > >
>>> > > >
>>> > > > in testcase: fio-basic
>>> > > > on test machine: 96 threads 2 sockets Intel(R) Xeon(R) Gold
>>> 6252 CPU
>>> > > > @ 2.10GHz with 256G memory
>>> > > > with following parameters:
>>> > > >
>>> > > >     disk: 2pmem
>>> > > >     fs: ext4
>>> > > >     runtime: 200s
>>> > > >     nr_task: 50%
>>> > > >     time_based: tb
>>> > > >     rw: randwrite
>>> > > >     bs: 4k
>>> > > >     ioengine: libaio
>>> > > >     test_size: 200G
>>> > > >     cpufreq_governor: performance
>>> > > >     ucode: 0x5003006
>>> > > >
>>> > > > test-description: Fio is a tool that will spawn a number of
>>> threads
>>> > > > or processes doing a particular type of I/O action as
>>> specified by
>>> > > > the user.
>>> > > > test-url: https://github.com/axboe/fio
>>> > > >
>>> > > >
>>> > > >
>>> > > > If you fix the issue, kindly add following tag
>>> > > > Reported-by: kernel test robot <oliver.sang@intel.com>
>>> > > >
>>> > > >
>>> > > > Details are as below:
>>> > > >
>>> -------------------------------------------------------------------------------------------------->
>>> > > >
>>> > > >
>>> > > > To reproduce:
>>> > > >
>>> > > >         git clone https://github.com/intel/lkp-tests.git
>>> > > >         cd lkp-tests
>>> > > >         bin/lkp install job.yaml  # job file is
>>> > > > attached in this email
>>> > > >         bin/lkp split-job --compatible job.yaml  # generate
>>> the yaml
>>> > > > file for lkp run
>>> > > >         bin/lkp run generated-yaml-file
>>> > >
>>> > > Hi,
>>> > >
>>> > > I tried to insall the lkp-test in my machine by following above
>>> guide
>>> > > but failed
>>> > > due to package problems(I guess it's my problem since I use
>>> something
>>> > > particular
>>> > > environement). However, I guess it comes from increased miss
>>> ratio of
>>> > > bh_lrus
>>> > > since the patch caused more frequent invalidation of the bh_lrus
>>> calls
>>> > > compared
>>> > > to old. For example, lru_add_drain could be called from several hot
>>> > > places(e.g.,
>>> > > unmap and pagevec_release from several path) and it could keeps
>>> > > invalidating
>>> > > bh_lrus.
>>> > >
>>> > > IMO, we should move the overhead from such hot path to cold one.
>>> How
>>> > > about this?
>>> > >
>>> > > From ebf4ede1cf32fb14d85f0015a3693cb8e1b8dbfe Mon Sep 17
>>> 00:00:00 2001
>>> > > From: Minchan Kim <minchan@kernel.org>
>>> > > Date: Thu, 20 May 2021 11:17:56 -0700
>>> > > Subject: [PATCH] invalidate bh_lrus only at lru_add_drain_all
>>> > >
>>> > > Not-Yet-Signed-off-by: Minchan Kim <minchan@kernel.org>
>>> > > ---
>>> > >  mm/swap.c | 15 +++++++++++++--
>>> > >  1 file changed, 13 insertions(+), 2 deletions(-)
>>> > >
>>> > > diff --git a/mm/swap.c b/mm/swap.c
>>> > > index dfb48cf9c2c9..d6168449e28c 100644
>>> > > --- a/mm/swap.c
>>> > > +++ b/mm/swap.c
>>> > > @@ -642,7 +642,6 @@ void lru_add_drain_cpu(int cpu)
>>> > >          pagevec_lru_move_fn(pvec, lru_lazyfree_fn);
>>> > >
>>> > >      activate_page_drain(cpu);
>>> > > -    invalidate_bh_lrus_cpu(cpu);
>>> > >  }
>>> > >
>>> > >  /**
>>> > > @@ -725,6 +724,17 @@ void lru_add_drain(void)
>>> > >      local_unlock(&lru_pvecs.lock);
>>> > >  }
>>> > >
>>> > > +void lru_and_bh_lrus_drain(void)
>>> > > +{
>>> > > +    int cpu;
>>> > > +
>>> > > +    local_lock(&lru_pvecs.lock);
>>> > > +    cpu = smp_processor_id();
>>> > > +    lru_add_drain_cpu(cpu);
>>> > > +    local_unlock(&lru_pvecs.lock);
>>> > > +    invalidate_bh_lrus_cpu(cpu);
>>> > > +}
>>> > > +
>>> >
>>> > Nit: drop int cpu?
>>>
>>> Do you mean to suggest using smp_processor_id at both places
>>> instead of local varaible? Since the invalidate_bh_lrus_cpu
>>> is called out of the lru_pvecs.lock, I wanted to express
>>> the draining happens at the same CPU via storing the CPU.
>>>
>>> >
>>> > >  void lru_add_drain_cpu_zone(struct zone *zone)
>>> > >  {
>>> > >      local_lock(&lru_pvecs.lock);
>>> > > @@ -739,7 +749,7 @@ static DEFINE_PER_CPU(struct work_struct,
>>> > > lru_add_drain_work);
>>> > >
>>> > >  static void lru_add_drain_per_cpu(struct work_struct *dummy)
>>> > >  {
>>> > > -    lru_add_drain();
>>> > > +    lru_and_bh_lrus_drain();
>>> > >  }
>>> > >
>>> > >  /*
>>> > > @@ -881,6 +891,7 @@ void lru_cache_disable(void)
>>> > >      __lru_add_drain_all(true);
>>> > >  #else
>>> > >      lru_add_drain();
>>> > > +    invalidate_bh_lrus_cpu(smp_processor_id());
>>> > >  #endif
>>> > >  }
>>> >
>>> > Can't we replace the call to lru_add_drain() and
>>> > invalidate_bh_lrus_cpu(smp_processor_id()) with a single call to
>>> > lru_and_bh_lrus_drain()?
>>>
>>> Good idea.
>>
>> From 8caadeb49d82403a08643dfbdb0b7749017c00bb Mon Sep 17 00:00:00 2001
>> From: Minchan Kim <minchan@kernel.org>
>> Date: Tue, 25 May 2021 08:19:17 -0700
>> Subject: [PATCH] mm: fs: invalidate bh_lrus for only cold path
>>
>> kernel test robot reported the regression of fio.write_iops[1]
>> with [2].
>>
>> Since lru_add_drain is called frequently, invalidate bh_lrus
>> there could increase bh_lrus cache miss ratio, which needs
>> more IO in the end.
>>
>> This patch moves the bh_lrus invalidation from the hot path(
>> e.g., zap_page_range, pagevec_release) to cold path(i.e.,
>> lru_add_drain_all, lru_cache_disable).
>>
>> [1]
>> https://lore.kernel.org/lkml/20210520083144.GD14190@xsang-OptiPlex-9020/
>> [2] 8cc621d2f45d, mm: fs: invalidate BH LRU during page migration
>> Cc: Xing, Zhengjun <zhengjun.xing@intel.com>
>> Cc: Chris Goldsworthy <cgoldswo@codeaurora.org>
>> Reported-by: kernel test robot <oliver.sang@intel.com>
>> Signed-off-by: Minchan Kim <minchan@kernel.org>
>> ---
>>  mm/swap.c | 16 +++++++++++++---
>>  1 file changed, 13 insertions(+), 3 deletions(-)
>>
>> diff --git a/mm/swap.c b/mm/swap.c
>> index 1958d5feb148..3e25d99a9dbb 100644
>> --- a/mm/swap.c
>> +++ b/mm/swap.c
>> @@ -642,7 +642,6 @@ void lru_add_drain_cpu(int cpu)
>>          pagevec_lru_move_fn(pvec, lru_lazyfree_fn);
>>
>>      activate_page_drain(cpu);
>> -    invalidate_bh_lrus_cpu(cpu);
>>  }
>>
>>  /**
>> @@ -725,6 +724,17 @@ void lru_add_drain(void)
>>      local_unlock(&lru_pvecs.lock);
>>  }
>>
>> +static void lru_add_and_bh_lrus_drain(void)
>> +{
>> +    int cpu;
>> +
>> +    local_lock(&lru_pvecs.lock);
>> +    cpu = smp_processor_id();
>> +    lru_add_drain_cpu(cpu);
>> +    local_unlock(&lru_pvecs.lock);
>> +    invalidate_bh_lrus_cpu(cpu);
>> +}
>> +
>>  void lru_add_drain_cpu_zone(struct zone *zone)
>>  {
>>      local_lock(&lru_pvecs.lock);
>> @@ -739,7 +749,7 @@ static DEFINE_PER_CPU(struct work_struct,
>> lru_add_drain_work);
>>
>>  static void lru_add_drain_per_cpu(struct work_struct *dummy)
>>  {
>> -    lru_add_drain();
>> +    lru_add_and_bh_lrus_drain();
>>  }
>>
>>  /*
>> @@ -880,7 +890,7 @@ void lru_cache_disable(void)
>>       */
>>      __lru_add_drain_all(true);
>>  #else
>> -    lru_add_drain();
>> +    lru_add_and_bh_lrus_drain();
>>  #endif
>>  }
>
> Feel free to add:
> Reviewed-by: Chris Goldsworthy <cgoldswo@codeaurora.org>
>

--
Zhengjun Xing

\
 
 \ /
  Last update: 2021-09-03 09:12    [W:0.073 / U:1.896 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site