From: Chao Yu <chao@kernel.org> To: jaegeuk@kernel.org Cc: linux-f2fs-devel@lists.sourceforge.net, linux-kernel@vger.kernel.org, Chao Yu <chao@kernel.org> Subject: [PATCH] f2fs: sysfs: support discard_io_aware Date: Wed, 22 Nov 2023 22:47:15 +0800 [thread overview] Message-ID: <20231122144715.518256-1-chao@kernel.org> (raw) It gives a way to enable/disable IO aware feature for background discard, so that we can tune background discard more precisely based on undiscard condition. e.g. force to disable IO aware if there are large number of discard extents, and discard IO may always be interrupted by frequent common IO. Signed-off-by: Chao Yu <chao@kernel.org> --- Documentation/ABI/testing/sysfs-fs-f2fs | 6 ++++++ fs/f2fs/f2fs.h | 7 +++++++ fs/f2fs/segment.c | 6 +++++- fs/f2fs/sysfs.c | 9 +++++++++ 4 files changed, 27 insertions(+), 1 deletion(-) diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs index 36c3cb547901..4f1d4e636d67 100644 --- a/Documentation/ABI/testing/sysfs-fs-f2fs +++ b/Documentation/ABI/testing/sysfs-fs-f2fs @@ -740,3 +740,9 @@ Description: When compress cache is on, it controls cached page If cached page percent exceed threshold, then deny caching compress page. The value should be in range of (0, 100], by default it was initialized as 20(%). + +What: /sys/fs/f2fs/<disk>/discard_io_aware +Date: November 2023 +Contact: "Chao Yu" <chao@kernel.org> +Description: It controls to enable/disable IO aware feature for background discard. + By default, the value is 1 which indicates IO aware is on. diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 9043cedfa12b..86a145be4e53 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -374,6 +374,12 @@ enum { MAX_DPOLICY, }; +enum { + DPOLICY_IO_AWARE_DISABLE, /* force to not be aware of IO */ + DPOLICY_IO_AWARE_ENABLE, /* force to be aware of IO */ + DPOLICY_IO_AWARE_MAX, +}; + struct discard_policy { int type; /* type of discard */ unsigned int min_interval; /* used for candidates exist */ @@ -406,6 +412,7 @@ struct discard_cmd_control { unsigned int discard_urgent_util; /* utilization which issue discard proactively */ unsigned int discard_granularity; /* discard granularity */ unsigned int max_ordered_discard; /* maximum discard granularity issued by lba order */ + unsigned int discard_io_aware; /* io_aware policy */ unsigned int undiscard_blks; /* # of undiscard blocks */ unsigned int next_pos; /* next discard position */ atomic_t issued_discard; /* # of issued discard */ diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index f4ffd64b44b2..08e2f44a1264 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1172,7 +1172,10 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi, dpolicy->min_interval = dcc->min_discard_issue_time; dpolicy->mid_interval = dcc->mid_discard_issue_time; dpolicy->max_interval = dcc->max_discard_issue_time; - dpolicy->io_aware = true; + if (dcc->discard_io_aware == DPOLICY_IO_AWARE_ENABLE) + dpolicy->io_aware = true; + else if (dcc->discard_io_aware == DPOLICY_IO_AWARE_DISABLE) + dpolicy->io_aware = false; dpolicy->sync = false; dpolicy->ordered = true; if (utilization(sbi) > dcc->discard_urgent_util) { @@ -2275,6 +2278,7 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi) dcc->discard_io_aware_gran = MAX_PLIST_NUM; dcc->discard_granularity = DEFAULT_DISCARD_GRANULARITY; dcc->max_ordered_discard = DEFAULT_MAX_ORDERED_DISCARD_GRANULARITY; + dcc->discard_io_aware = DPOLICY_IO_AWARE_ENABLE; if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SEGMENT) dcc->discard_granularity = sbi->blocks_per_seg; else if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SECTION) diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 417fae96890f..7099ffa57299 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -516,6 +516,13 @@ static ssize_t __sbi_store(struct f2fs_attr *a, return count; } + if (!strcmp(a->attr.name, "discard_io_aware")) { + if (t >= DPOLICY_IO_AWARE_MAX) + return -EINVAL; + *ui = t; + return count; + } + if (!strcmp(a->attr.name, "migration_granularity")) { if (t == 0 || t > sbi->segs_per_sec) return -EINVAL; @@ -926,6 +933,7 @@ DCC_INFO_GENERAL_RW_ATTR(discard_io_aware_gran); DCC_INFO_GENERAL_RW_ATTR(discard_urgent_util); DCC_INFO_GENERAL_RW_ATTR(discard_granularity); DCC_INFO_GENERAL_RW_ATTR(max_ordered_discard); +DCC_INFO_GENERAL_RW_ATTR(discard_io_aware); /* NM_INFO ATTR */ NM_INFO_RW_ATTR(max_roll_forward_node_blocks, max_rf_node_blocks); @@ -1074,6 +1082,7 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(discard_urgent_util), ATTR_LIST(discard_granularity), ATTR_LIST(max_ordered_discard), + ATTR_LIST(discard_io_aware), ATTR_LIST(pending_discard), ATTR_LIST(gc_mode), ATTR_LIST(ipu_policy), -- 2.40.1
WARNING: multiple messages have this Message-ID (diff)
From: Chao Yu <chao@kernel.org> To: jaegeuk@kernel.org Cc: linux-kernel@vger.kernel.org, linux-f2fs-devel@lists.sourceforge.net Subject: [f2fs-dev] [PATCH] f2fs: sysfs: support discard_io_aware Date: Wed, 22 Nov 2023 22:47:15 +0800 [thread overview] Message-ID: <20231122144715.518256-1-chao@kernel.org> (raw) It gives a way to enable/disable IO aware feature for background discard, so that we can tune background discard more precisely based on undiscard condition. e.g. force to disable IO aware if there are large number of discard extents, and discard IO may always be interrupted by frequent common IO. Signed-off-by: Chao Yu <chao@kernel.org> --- Documentation/ABI/testing/sysfs-fs-f2fs | 6 ++++++ fs/f2fs/f2fs.h | 7 +++++++ fs/f2fs/segment.c | 6 +++++- fs/f2fs/sysfs.c | 9 +++++++++ 4 files changed, 27 insertions(+), 1 deletion(-) diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs index 36c3cb547901..4f1d4e636d67 100644 --- a/Documentation/ABI/testing/sysfs-fs-f2fs +++ b/Documentation/ABI/testing/sysfs-fs-f2fs @@ -740,3 +740,9 @@ Description: When compress cache is on, it controls cached page If cached page percent exceed threshold, then deny caching compress page. The value should be in range of (0, 100], by default it was initialized as 20(%). + +What: /sys/fs/f2fs/<disk>/discard_io_aware +Date: November 2023 +Contact: "Chao Yu" <chao@kernel.org> +Description: It controls to enable/disable IO aware feature for background discard. + By default, the value is 1 which indicates IO aware is on. diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 9043cedfa12b..86a145be4e53 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -374,6 +374,12 @@ enum { MAX_DPOLICY, }; +enum { + DPOLICY_IO_AWARE_DISABLE, /* force to not be aware of IO */ + DPOLICY_IO_AWARE_ENABLE, /* force to be aware of IO */ + DPOLICY_IO_AWARE_MAX, +}; + struct discard_policy { int type; /* type of discard */ unsigned int min_interval; /* used for candidates exist */ @@ -406,6 +412,7 @@ struct discard_cmd_control { unsigned int discard_urgent_util; /* utilization which issue discard proactively */ unsigned int discard_granularity; /* discard granularity */ unsigned int max_ordered_discard; /* maximum discard granularity issued by lba order */ + unsigned int discard_io_aware; /* io_aware policy */ unsigned int undiscard_blks; /* # of undiscard blocks */ unsigned int next_pos; /* next discard position */ atomic_t issued_discard; /* # of issued discard */ diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index f4ffd64b44b2..08e2f44a1264 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1172,7 +1172,10 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi, dpolicy->min_interval = dcc->min_discard_issue_time; dpolicy->mid_interval = dcc->mid_discard_issue_time; dpolicy->max_interval = dcc->max_discard_issue_time; - dpolicy->io_aware = true; + if (dcc->discard_io_aware == DPOLICY_IO_AWARE_ENABLE) + dpolicy->io_aware = true; + else if (dcc->discard_io_aware == DPOLICY_IO_AWARE_DISABLE) + dpolicy->io_aware = false; dpolicy->sync = false; dpolicy->ordered = true; if (utilization(sbi) > dcc->discard_urgent_util) { @@ -2275,6 +2278,7 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi) dcc->discard_io_aware_gran = MAX_PLIST_NUM; dcc->discard_granularity = DEFAULT_DISCARD_GRANULARITY; dcc->max_ordered_discard = DEFAULT_MAX_ORDERED_DISCARD_GRANULARITY; + dcc->discard_io_aware = DPOLICY_IO_AWARE_ENABLE; if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SEGMENT) dcc->discard_granularity = sbi->blocks_per_seg; else if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SECTION) diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 417fae96890f..7099ffa57299 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -516,6 +516,13 @@ static ssize_t __sbi_store(struct f2fs_attr *a, return count; } + if (!strcmp(a->attr.name, "discard_io_aware")) { + if (t >= DPOLICY_IO_AWARE_MAX) + return -EINVAL; + *ui = t; + return count; + } + if (!strcmp(a->attr.name, "migration_granularity")) { if (t == 0 || t > sbi->segs_per_sec) return -EINVAL; @@ -926,6 +933,7 @@ DCC_INFO_GENERAL_RW_ATTR(discard_io_aware_gran); DCC_INFO_GENERAL_RW_ATTR(discard_urgent_util); DCC_INFO_GENERAL_RW_ATTR(discard_granularity); DCC_INFO_GENERAL_RW_ATTR(max_ordered_discard); +DCC_INFO_GENERAL_RW_ATTR(discard_io_aware); /* NM_INFO ATTR */ NM_INFO_RW_ATTR(max_roll_forward_node_blocks, max_rf_node_blocks); @@ -1074,6 +1082,7 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(discard_urgent_util), ATTR_LIST(discard_granularity), ATTR_LIST(max_ordered_discard), + ATTR_LIST(discard_io_aware), ATTR_LIST(pending_discard), ATTR_LIST(gc_mode), ATTR_LIST(ipu_policy), -- 2.40.1 _______________________________________________ Linux-f2fs-devel mailing list Linux-f2fs-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
next reply other threads:[~2023-11-22 14:47 UTC|newest] Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top 2023-11-22 14:47 Chao Yu [this message] 2023-11-22 14:47 ` [f2fs-dev] [PATCH] f2fs: sysfs: support discard_io_aware Chao Yu 2023-11-30 18:30 ` patchwork-bot+f2fs 2023-11-30 18:30 ` patchwork-bot+f2fs
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=20231122144715.518256-1-chao@kernel.org \ --to=chao@kernel.org \ --cc=jaegeuk@kernel.org \ --cc=linux-f2fs-devel@lists.sourceforge.net \ --cc=linux-kernel@vger.kernel.org \ /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: linkBe 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.