Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: Re: [f2fs-dev] [PATCH 1/2] f2fs: run discard jobs when put_super
To:     Jaegeuk Kim <jaegeuk@kernel.org>
CC:     <linux-kernel@vger.kernel.org>,
        <linux-f2fs-devel@lists.sourceforge.net>
References: <20190123000229.45236-1-jaegeuk@kernel.org>
 <2afde906-0bbc-7464-104b-237343ed218b@huawei.com>
 <20190125005615.GB2196@jaegeuk-macbookpro.roam.corp.google.com>
From:   Chao Yu <yuchao0@huawei.com>
Message-ID: <9521d2d2-c3c9-f193-ffe7-29bb70e90c89@huawei.com>
Date:   Fri, 25 Jan 2019 09:26:03 +0800
User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:52.0) Gecko/20100101
 Thunderbird/52.9.1
MIME-Version: 1.0
In-Reply-To: <20190125005615.GB2196@jaegeuk-macbookpro.roam.corp.google.com>
Content-Type: text/plain; charset="windows-1252"
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 2019/1/25 8:56, Jaegeuk Kim wrote:
> On 01/23, Chao Yu wrote:
>> On 2019/1/23 8:02, Jaegeuk Kim wrote:
>>> When we umount f2fs, we need to avoid long delay due to discard commands, which
>>> is actually taking tens of seconds, if storage is very slow on UNMAP. So, this
>>> patch introduces timeout-based work on it.
>>>
>>> By default, let me give 5 seconds for discard.
>>>
>>> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
>>> ---
>>>  Documentation/ABI/testing/sysfs-fs-f2fs |  7 +++++++
>>>  fs/f2fs/f2fs.h                          |  5 ++++-
>>>  fs/f2fs/segment.c                       | 11 ++++++++++-
>>>  fs/f2fs/super.c                         | 17 ++++++++---------
>>>  fs/f2fs/sysfs.c                         |  3 +++
>>>  5 files changed, 32 insertions(+), 11 deletions(-)
>>>
>>> diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
>>> index a7ce33199457..91822ce25831 100644
>>> --- a/Documentation/ABI/testing/sysfs-fs-f2fs
>>> +++ b/Documentation/ABI/testing/sysfs-fs-f2fs
>>> @@ -86,6 +86,13 @@ Description:
>>>  		The unit size is one block, now only support configuring in range
>>>  		of [1, 512].
>>>  
>>> +What:          /sys/fs/f2fs/<disk>/umount_discard_timeout
>>> +Date:          January 2019
>>> +Contact:       "Jaegeuk Kim" <jaegeuk@kernel.org>
>>> +Description:
>>> +		Set timeout to issue discard commands during umount.
>>> +		Default: 5 secs
>>> +
>>>  What:		/sys/fs/f2fs/<disk>/max_victim_search
>>>  Date:		January 2014
>>>  Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>
>>> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
>>> index 0f564883e078..6b6ec5600089 100644
>>> --- a/fs/f2fs/f2fs.h
>>> +++ b/fs/f2fs/f2fs.h
>>> @@ -191,6 +191,7 @@ enum {
>>>  #define DEF_CP_INTERVAL			60	/* 60 secs */
>>>  #define DEF_IDLE_INTERVAL		5	/* 5 secs */
>>>  #define DEF_DISABLE_INTERVAL		5	/* 5 secs */
>>> +#define DEF_UMOUNT_DISCARD_TIMEOUT	5	/* 5 secs */
>>>  
>>>  struct cp_control {
>>>  	int reason;
>>> @@ -310,6 +311,7 @@ struct discard_policy {
>>>  	bool sync;			/* submit discard with REQ_SYNC flag */
>>>  	bool ordered;			/* issue discard by lba order */
>>>  	unsigned int granularity;	/* discard granularity */
>>> +	int timeout;			/* discard timeout for put_super */
>>>  };
>>>  
>>>  struct discard_cmd_control {
>>> @@ -1110,6 +1112,7 @@ enum {
>>>  	DISCARD_TIME,
>>>  	GC_TIME,
>>>  	DISABLE_TIME,
>>> +	UMOUNT_DISCARD_TIMEOUT,
>>>  	MAX_TIME,
>>
>> After the patch, MAX_TIME will be 6, so if we set @timeout to 6 via sysfs,
>> the configuration will not be enabled due to below condition, right?
> 
> Yup.
> 
>>
>> +	if (dpolicy->timeout != MAX_TIME)
>> +		f2fs_update_time(sbi, dpolicy->timeout);
>>
>>>  };
>>>  
>>> @@ -3006,7 +3009,7 @@ void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
>>>  bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
>>>  void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi);
>>>  void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi);
>>> -bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi);
>>> +bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi);
>>>  void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
>>>  					struct cp_control *cpc);
>>>  void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi);
>>> diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
>>> index 9b79056d705d..97e0faf09ebf 100644
>>> --- a/fs/f2fs/segment.c
>>> +++ b/fs/f2fs/segment.c
>>> @@ -1037,6 +1037,7 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi,
>>>  
>>>  	dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
>>>  	dpolicy->io_aware_gran = MAX_PLIST_NUM;
>>> +	dpolicy->timeout = MAX_TIME;
>>>  
>>>  	if (discard_type == DPOLICY_BG) {
>>>  		dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
>>> @@ -1424,7 +1425,14 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
>>>  	int i, issued = 0;
>>>  	bool io_interrupted = false;
>>>  
>>> +	if (dpolicy->timeout != MAX_TIME)
>>> +		f2fs_update_time(sbi, dpolicy->timeout);
>>> +
>>>  	for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
>>> +		if (dpolicy->timeout != MAX_TIME &&
>>> +				f2fs_time_over(sbi, dpolicy->timeout))
>>> +			break;
>>> +
>>>  		if (i + 1 < dpolicy->granularity)
>>>  			break;
>>>  
>>> @@ -1611,7 +1619,7 @@ void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi)
>>>  }
>>>  
>>>  /* This comes from f2fs_put_super */
>>> -bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi)
>>> +bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi)
>>>  {
>>>  	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
>>>  	struct discard_policy dpolicy;
>>> @@ -1619,6 +1627,7 @@ bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi)
>>>  
>>>  	__init_discard_policy(sbi, &dpolicy, DPOLICY_UMOUNT,
>>>  					dcc->discard_granularity);
>>> +	dpolicy.timeout = UMOUNT_DISCARD_TIMEOUT;
>>>  	__issue_discard_cmd(sbi, &dpolicy);
>>>  	dropped = __drop_discard_cmd(sbi);
>>>  
>>> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
>>> index ea514acede36..7998ff5418f2 100644
>>> --- a/fs/f2fs/super.c
>>> +++ b/fs/f2fs/super.c
>>> @@ -1029,6 +1029,9 @@ static void f2fs_put_super(struct super_block *sb)
>>>  	int i;
>>>  	bool dropped;
>>>  
>>> +	/* be sure to wait for any on-going discard commands */
>>> +	dropped = f2fs_issue_discard_timeout(sbi);
>>> +
>>>  	f2fs_quota_off_umount(sb);
>>>  
>>>  	/* prevent remaining shrinker jobs */
>>> @@ -1044,17 +1047,12 @@ static void f2fs_put_super(struct super_block *sb)
>>>  		struct cp_control cpc = {
>>>  			.reason = CP_UMOUNT,
>>>  		};
>>> -		f2fs_write_checkpoint(sbi, &cpc);
>>> -	}
>>>  
>>> -	/* be sure to wait for any on-going discard commands */
>>> -	dropped = f2fs_wait_discard_bios(sbi);
>>> +		if ((f2fs_hw_support_discard(sbi) ||
>>> +				f2fs_hw_should_discard(sbi)) &&
>>> +				!sbi->discard_blks && !dropped)
>>> +			cpc.reason |= CP_TRIMMED;
>>>  
>>> -	if ((f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) &&
>>> -					!sbi->discard_blks && !dropped) {
>>> -		struct cp_control cpc = {
>>> -			.reason = CP_UMOUNT | CP_TRIMMED,
>>> -		};
>>>  		f2fs_write_checkpoint(sbi, &cpc);
>>
>> Still, there will be problematic as I commented in last patch, could you
>> check that?

Ping,

If this checkpoint generate discard entry, tagged CP_TRIMMED flag should be
wrong, so the right order should be?

write_checkpoint(CP_UMOUNT)

dropped = f2fs_wait_discard_bios()

if (... && no_drop && no_remain_discard)
	f2fs_write_checkpoint(sbi, CP_UMOUNT | CP_TRIMMED);

Am I missing something?

Thanks,

>>
>> Thanks,
>>
>>>  	}
>>>  
>>> @@ -2706,6 +2704,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
>>>  	sbi->interval_time[DISCARD_TIME] = DEF_IDLE_INTERVAL;
>>>  	sbi->interval_time[GC_TIME] = DEF_IDLE_INTERVAL;
>>>  	sbi->interval_time[DISABLE_TIME] = DEF_DISABLE_INTERVAL;
>>> +	sbi->interval_time[UMOUNT_DISCARD_TIMEOUT] = DEF_UMOUNT_DISCARD_TIMEOUT;
>>>  	clear_sbi_flag(sbi, SBI_NEED_FSCK);
>>>  
>>>  	for (i = 0; i < NR_COUNT_TYPE; i++)
>>> diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
>>> index 5b83e1d66cb3..18c627e8fc90 100644
>>> --- a/fs/f2fs/sysfs.c
>>> +++ b/fs/f2fs/sysfs.c
>>> @@ -426,6 +426,8 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
>>>  F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, discard_idle_interval,
>>>  					interval_time[DISCARD_TIME]);
>>>  F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle_interval, interval_time[GC_TIME]);
>>> +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info,
>>> +		umount_discard_timeout, interval_time[UMOUNT_DISCARD_TIMEOUT]);
>>>  F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable);
>>>  F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, readdir_ra, readdir_ra);
>>>  F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_pin_file_thresh, gc_pin_file_threshold);
>>> @@ -483,6 +485,7 @@ static struct attribute *f2fs_attrs[] = {
>>>  	ATTR_LIST(idle_interval),
>>>  	ATTR_LIST(discard_idle_interval),
>>>  	ATTR_LIST(gc_idle_interval),
>>> +	ATTR_LIST(umount_discard_timeout),
>>>  	ATTR_LIST(iostat_enable),
>>>  	ATTR_LIST(readdir_ra),
>>>  	ATTR_LIST(gc_pin_file_thresh),
>>>
> 
> .
>