| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 26 Mar 2020 17:00:18 +0800
From: Chao Yu <yuchao0@...wei.com>
To: Sahitya Tummala <stummala@...eaurora.org>,
Jaegeuk Kim <jaegeuk@...nel.org>,
<linux-f2fs-devel@...ts.sourceforge.net>
CC: <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] f2fs: fix long latency due to discard during umount
Hi Sahitya,
On 2020/3/18 12:44, Sahitya Tummala wrote:
> F2FS already has a default timeout of 5 secs for discards that
> can be issued during umount, but it can take more than the 5 sec
> timeout if the underlying UFS device queue is already full and there
> are no more available free tags to be used. In that case, submit_bio()
> will wait for the already queued discard requests to complete to get
> a free tag, which can potentially take way more than 5 sec.
>
> Fix this by submitting the discard requests with REQ_NOWAIT
> flags during umount. This will return -EAGAIN for UFS queue/tag full
> scenario without waiting in the context of submit_bio(). The FS can
> then handle these requests by retrying again within the stipulated
> discard timeout period to avoid long latencies.
>
> Signed-off-by: Sahitya Tummala <stummala@...eaurora.org>
> ---
> v2:
> - Handle the case where a dc can have multiple bios associated with it
>
> fs/f2fs/f2fs.h | 1 +
> fs/f2fs/segment.c | 83 ++++++++++++++++++++++++++++++++++++++++++++++++-------
> 2 files changed, 74 insertions(+), 10 deletions(-)
>
> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> index 12a197e..67b8dcc 100644
> --- a/fs/f2fs/f2fs.h
> +++ b/fs/f2fs/f2fs.h
> @@ -340,6 +340,7 @@ struct discard_cmd_control {
> struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */
> struct list_head wait_list; /* store on-flushing entries */
> struct list_head fstrim_list; /* in-flight discard from fstrim */
> + struct list_head retry_list; /* list of cmds to retry */
> wait_queue_head_t discard_wait_queue; /* waiting queue for wake-up */
> unsigned int discard_wake; /* to wake up discard thread */
> struct mutex cmd_lock;
> diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
> index fb3e531..4162c76 100644
> --- a/fs/f2fs/segment.c
> +++ b/fs/f2fs/segment.c
> @@ -1029,13 +1029,16 @@ static void f2fs_submit_discard_endio(struct bio *bio)
> struct discard_cmd *dc = (struct discard_cmd *)bio->bi_private;
> unsigned long flags;
>
> - dc->error = blk_status_to_errno(bio->bi_status);
> -
> spin_lock_irqsave(&dc->lock, flags);
> + if (!dc->error)
> + dc->error = blk_status_to_errno(bio->bi_status);
> +
> dc->bio_ref--;
> - if (!dc->bio_ref && dc->state == D_SUBMIT) {
> - dc->state = D_DONE;
> - complete_all(&dc->wait);
> + if (!dc->bio_ref) {
> + if (dc->error || dc->state == D_SUBMIT) {
> + dc->state = D_DONE;
> + complete_all(&dc->wait);
> + }
> }
> spin_unlock_irqrestore(&dc->lock, flags);
> bio_put(bio);
> @@ -1124,10 +1127,13 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
> struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
> struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ?
> &(dcc->fstrim_list) : &(dcc->wait_list);
> - int flag = dpolicy->sync ? REQ_SYNC : 0;
> - block_t lstart, start, len, total_len;
> + int flag;
> + block_t lstart, start, len, total_len, orig_len;
> int err = 0;
>
> + flag = dpolicy->sync ? REQ_SYNC : 0;
> + flag |= dpolicy->type == DPOLICY_UMOUNT ? REQ_NOWAIT : 0;
> +
> if (dc->state != D_PREP)
> return 0;
>
> @@ -1139,7 +1145,7 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
> lstart = dc->lstart;
> start = dc->start;
> len = dc->len;
> - total_len = len;
> + orig_len = total_len = len;
>
> dc->len = 0;
>
> @@ -1203,6 +1209,14 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
> bio->bi_end_io = f2fs_submit_discard_endio;
> bio->bi_opf |= flag;
> submit_bio(bio);
> + if (flag & REQ_NOWAIT) {
> + if (dc->error == -EAGAIN) {
> + dc->len = orig_len;
> + list_move(&dc->list, &dcc->retry_list);
> + err = dc->error;
I encounter lots of dmesg, which should be printed by __remove_discard_cmd()
F2FS-fs (dm-0): Issue discard(23552, 23552, 2) failed, ret: -11
This should happen only if we didn't handle all discard in 5 seconds during
umount.
So I doubt we failed to move dc to retry_list, because after submit_bio(),
end_io() is not called synchronously as the bio was just pluged?
Thanks,
> + break;
> + }
> + }
>
> atomic_inc(&dcc->issued_discard);
>
> @@ -1463,6 +1477,40 @@ static unsigned int __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi,
> return issued;
> }
>
> +static bool __should_discard_retry(struct f2fs_sb_info *sbi,
> + struct discard_policy *dpolicy)
> +{
> + struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
> + struct discard_cmd *dc, *tmp;
> + bool retry = false;
> + unsigned long flags;
> +
> + if (dpolicy->type != DPOLICY_UMOUNT)
> + f2fs_bug_on(sbi, 1);
> +
> + mutex_lock(&dcc->cmd_lock);
> + list_for_each_entry_safe(dc, tmp, &(dcc->retry_list), list) {
> + if (dpolicy->timeout != 0 &&
> + f2fs_time_over(sbi, dpolicy->timeout)) {
> + retry = false;
> + break;
> + }
> +
> + spin_lock_irqsave(&dc->lock, flags);
> + if (!dc->bio_ref) {
> + dc->state = D_PREP;
> + dc->error = 0;
> + reinit_completion(&dc->wait);
> + __relocate_discard_cmd(dcc, dc);
> + retry = true;
> + }
> + spin_unlock_irqrestore(&dc->lock, flags);
> + }
> + mutex_unlock(&dcc->cmd_lock);
> +
> + return retry;
> +}
> +
> static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
> struct discard_policy *dpolicy)
> {
> @@ -1470,12 +1518,13 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
> struct list_head *pend_list;
> struct discard_cmd *dc, *tmp;
> struct blk_plug plug;
> - int i, issued = 0;
> + int i, err, issued = 0;
> bool io_interrupted = false;
>
> if (dpolicy->timeout != 0)
> f2fs_update_time(sbi, dpolicy->timeout);
>
> +retry:
> for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
> if (dpolicy->timeout != 0 &&
> f2fs_time_over(sbi, dpolicy->timeout))
> @@ -1509,7 +1558,10 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
> break;
> }
>
> - __submit_discard_cmd(sbi, dpolicy, dc, &issued);
> + err = __submit_discard_cmd(sbi, dpolicy, dc, &issued);
> + if (err == -EAGAIN)
> + congestion_wait(BLK_RW_ASYNC,
> + DEFAULT_IO_TIMEOUT);
>
> if (issued >= dpolicy->max_requests)
> break;
> @@ -1522,6 +1574,10 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
> break;
> }
>
> + if (!list_empty(&dcc->retry_list) &&
> + __should_discard_retry(sbi, dpolicy))
> + goto retry;
> +
> if (!issued && io_interrupted)
> issued = -1;
>
> @@ -1613,6 +1669,12 @@ static unsigned int __wait_discard_cmd_range(struct f2fs_sb_info *sbi,
> goto next;
> }
>
> + if (dpolicy->type == DPOLICY_UMOUNT &&
> + !list_empty(&dcc->retry_list)) {
> + wait_list = &dcc->retry_list;
> + goto next;
> + }
> +
> return trimmed;
> }
>
> @@ -2051,6 +2113,7 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
> for (i = 0; i < MAX_PLIST_NUM; i++)
> INIT_LIST_HEAD(&dcc->pend_list[i]);
> INIT_LIST_HEAD(&dcc->wait_list);
> + INIT_LIST_HEAD(&dcc->retry_list);
> INIT_LIST_HEAD(&dcc->fstrim_list);
> mutex_init(&dcc->cmd_lock);
> atomic_set(&dcc->issued_discard, 0);
>
Powered by blists - more mailing lists