[Devel] [PATCH vz9 v2 07/65] dm-ploop: convert wait_list and wb_batch_llist to use lockless lists

Konstantin Khorenko khorenko at virtuozzo.com
Wed Feb 12 12:33:00 MSK 2025


From: Alexander Atanasov <alexander.atanasov at virtuozzo.com>

Convert to lockless lists - intermix with regular list due to
that next pointer in both list_head and llist_head is the first
field, and prev is not used. Do this so we can make babysteps
forward.

https://virtuozzo.atlassian.net/browse/VSTOR-91820
Signed-off-by: Alexander Atanasov <alexander.atanasov at virtuozzo.com>

======
Patchset description:
ploop: optimistations and scalling

Ploop processes requsts in a different threads in parallel
where possible which results in significant improvement in
performance and makes further optimistations possible.

Known bugs:
  - delayed metadata writeback is not working and is missing error handling
     - patch to disable it until fixed
  - fast path is not working - causes rcu lockups - patch to disable it

Further improvements:
  - optimize md pages lookups

Alexander Atanasov (50):
  dm-ploop: md_pages map all pages at creation time
  dm-ploop: Use READ_ONCE/WRITE_ONCE to access md page data
  dm-ploop: fsync after all pios are sent
  dm-ploop: move md status to use proper bitops
  dm-ploop: convert wait_list and wb_batch_llist to use lockless lists
  dm-ploop: convert enospc handling to use lockless lists
  dm-ploop: convert suspended_pios list to use lockless list
  dm-ploop: convert the rest of the lists to use llist variant
  dm-ploop: combine processing of pios thru prepare list and remove
    fsync worker
  dm-ploop: move from wq to kthread
  dm-ploop: move preparations of pios into the caller from worker
  dm-ploop: fast path execution for reads
  dm-ploop: do not use a wrapper for set_bit to make a page writeback
  dm-ploop: BAT use only one list for writeback
  dm-ploop: make md writeback timeout to be per page
  dm-ploop: add interface to disable bat writeback delay
  dm-ploop: convert wb_batch_list to lockless variant
  dm-ploop: convert high_prio to status
  dm-ploop: split cow processing into two functions
  dm-ploop: convert md page rw lock to spin lock
  dm-ploop: convert bat_rwlock to bat_lock spinlock
  dm-ploop: prepare bat updates under bat_lock
  dm-ploop: make ploop_bat_write_complete ready for parallel pio
    completion
  dm-ploop: make ploop_submit_metadata_writeback return number of
    requests sent
  dm-ploop: introduce pio runner threads
  dm-ploop: add pio list ids to be used when passing pios to runners
  dm-ploop: process pios via runners
  dm-ploop: disable metadata writeback delay
  dm-ploop: disable fast path
  dm-ploop: use lockless lists for chained cow updates list
  dm-ploop: use lockless lists for data ready pios
  dm-ploop: give runner threads better name
  dm-ploop: resize operation - add holes bitmap locking
  dm-ploop: remove unnecessary operations
  dm-ploop: use filp per thread
  dm-ploop: catch if we try to advance pio past bio end
  dm-ploop: support REQ_FUA for data pios
  dm-ploop: proplerly access nr_bat_entries
  dm-ploop: fix locking and improve error handling when submitting pios
  dm-ploop: fix how ENOTBLK is handled
  dm-ploop: sync when suspended or stopping
  dm-ploop: rework bat completion logic
  dm-ploop: rework logic in pio processing
  dm-ploop: end fsync pios in parallel
  dm-ploop: make filespace preallocations async
  dm-ploop: resubmit enospc pios from dispatcher thread
  dm-ploop: dm-ploop: simplify discard completion
  dm-ploop: use GFP_ATOMIC instead of GFP_NOIO
  dm-ploop: fix locks used in mixed context
  dm-ploop: fix how current flags are managed inside threads

Andrey Zhadchenko (13):
  dm-ploop: do not flush after metadata writes
  dm-ploop: set IOCB_DSYNC on all FUA requests
  dm-ploop: remove extra ploop_cluster_is_in_top_delta()
  dm-ploop: introduce per-md page locking
  dm-ploop: reduce BAT accesses on discard completion
  dm-ploop: simplify llseek
  dm-ploop: speed up ploop_prepare_bat_update()
  dm-ploop: make new allocations immediately visible in BAT
  dm-ploop: drop ploop_cluster_is_in_top_delta()
  dm-ploop: do not wait for BAT update for non-FUA requests
  dm-ploop: add delay for metadata writeback
  dm-ploop: submit all postponed metadata on REQ_OP_FLUSH
  dm-ploop: handle REQ_PREFLUSH

Feature: dm-ploop: ploop target driver
Signed-off-by: Konstantin Khorenko <khorenko at virtuozzo.com>
---
 drivers/md/dm-ploop-bat.c    |  2 +-
 drivers/md/dm-ploop-map.c    | 50 +++++++++++++++++++-----------------
 drivers/md/dm-ploop-target.c |  2 +-
 drivers/md/dm-ploop.h        |  6 ++---
 4 files changed, 32 insertions(+), 28 deletions(-)

diff --git a/drivers/md/dm-ploop-bat.c b/drivers/md/dm-ploop-bat.c
index 02e4ddf950e3..655d0e4c91ab 100644
--- a/drivers/md/dm-ploop-bat.c
+++ b/drivers/md/dm-ploop-bat.c
@@ -80,7 +80,7 @@ static struct md_page *ploop_alloc_md_page(u32 id)
 	page = alloc_page(GFP_KERNEL);
 	if (!page)
 		goto err_page;
-	INIT_LIST_HEAD(&md->wait_list);
+	init_llist_head(&md->wait_llist);
 
 	md->status = 0;
 	md->bat_levels = levels;
diff --git a/drivers/md/dm-ploop-map.c b/drivers/md/dm-ploop-map.c
index fc07d24c34a0..fa8cb0c44f8c 100644
--- a/drivers/md/dm-ploop-map.c
+++ b/drivers/md/dm-ploop-map.c
@@ -381,13 +381,14 @@ static bool ploop_delay_if_md_busy(struct ploop *ploop, struct md_page *md,
 
 	WARN_ON_ONCE(!list_empty(&pio->list));
 
-	write_lock_irqsave(&ploop->bat_rwlock, flags);
+	/* lock protects piwb */
+	read_lock_irqsave(&ploop->bat_rwlock, flags);
 	piwb = md->piwb;
 	if (piwb && (piwb->type != type || test_bit(MD_WRITEBACK, &md->status))) {
-		list_add_tail(&pio->list, &md->wait_list);
+		llist_add(&pio->llist, &md->wait_llist);
 		busy = true;
 	}
-	write_unlock_irqrestore(&ploop->bat_rwlock, flags);
+	read_unlock_irqrestore(&ploop->bat_rwlock, flags);
 
 	return busy;
 }
@@ -546,16 +547,13 @@ static void ploop_unlink_completed_pio(struct ploop *ploop, struct pio *pio)
 
 static bool ploop_md_make_dirty(struct ploop *ploop, struct md_page *md)
 {
-	unsigned long flags;
 	bool new = false;
 
-	write_lock_irqsave(&ploop->bat_rwlock, flags);
 	WARN_ON_ONCE(test_bit(MD_WRITEBACK, &md->status));
 	if (!test_and_set_bit(MD_DIRTY, &md->status)) {
-		list_add_tail(&md->wb_link, &ploop->wb_batch_list);
+		llist_add(&md->wb_llink, &ploop->wb_batch_llist);
 		new = true;
 	}
-	write_unlock_irqrestore(&ploop->bat_rwlock, flags);
 
 	return new;
 }
@@ -757,7 +755,9 @@ static void ploop_advance_local_after_bat_wb(struct ploop *ploop,
 	map_index_t *dst_clu, off;
 	unsigned long flags;
 	LIST_HEAD(list);
-
+	struct llist_node *wait_llist_pending;
+	struct pio *pio;
+	struct llist_node *pos, *t;
 	BUG_ON(!md);
 	bat_entries = md->kmpage;
 
@@ -774,8 +774,6 @@ static void ploop_advance_local_after_bat_wb(struct ploop *ploop,
 		i = PLOOP_MAP_OFFSET;
 
 	dst_clu = kmap_local_page(piwb->bat_page);
-	write_lock_irqsave(&ploop->bat_rwlock, flags);
-
 	for (; i < last; i++) {
 		if (piwb->type == PIWB_TYPE_DISCARD) {
 			ploop_piwb_discard_completed(ploop, success, i + off, dst_clu[i]);
@@ -801,11 +799,21 @@ static void ploop_advance_local_after_bat_wb(struct ploop *ploop,
 
 	WARN_ON_ONCE(!test_bit(MD_WRITEBACK, &md->status));
 	clear_bit(MD_WRITEBACK, &md->status);
+	/* protect piwb */
+	write_lock_irqsave(&ploop->bat_rwlock, flags);
 	md->piwb = NULL;
-	list_splice_tail_init(&md->wait_list, &list);
 	write_unlock_irqrestore(&ploop->bat_rwlock, flags);
 	kunmap_local(dst_clu);
 
+	wait_llist_pending = llist_del_all(&md->wait_llist);
+	if (wait_llist_pending) {
+		wait_llist_pending = llist_reverse_order(wait_llist_pending);
+		llist_for_each_safe(pos, t, wait_llist_pending) {
+			pio = llist_entry(pos, typeof(*pio), llist);
+			list_add(&pio->list, &list);
+		}
+	}
+
 	if (!list_empty(&list))
 		ploop_dispatch_pios(ploop, NULL, &list);
 }
@@ -1764,22 +1772,18 @@ static void ploop_process_resubmit_pios(struct ploop *ploop,
 static void ploop_submit_metadata_writeback(struct ploop *ploop)
 {
 	struct md_page *md;
-	while (1) {
-		write_lock_irq(&ploop->bat_rwlock);
-		md = list_first_entry_or_null(&ploop->wb_batch_list,
-				struct md_page, wb_link);
-		if (!md) {
-			write_unlock_irq(&ploop->bat_rwlock);
-			break;
-		}
-		list_del_init(&md->wb_link);
-		/* L1L2 mustn't be redirtyed, when wb in-flight! */
+	struct md_page *t;
+	struct llist_node *wbl;
+
+	wbl = llist_del_all(&ploop->wb_batch_llist);
+	if (!wbl)
+		return;
+	wbl = llist_reverse_order(wbl);
+	llist_for_each_entry_safe(md, t, wbl, wb_llink) {
 		WARN_ON_ONCE(!test_bit(MD_DIRTY, &md->status));
 		WARN_ON_ONCE(test_bit(MD_WRITEBACK, &md->status));
 		set_bit(MD_WRITEBACK, &md->status);
 		clear_bit(MD_DIRTY, &md->status);
-		write_unlock_irq(&ploop->bat_rwlock);
-
 		ploop_index_wb_submit(ploop, md->piwb);
 	}
 }
diff --git a/drivers/md/dm-ploop-target.c b/drivers/md/dm-ploop-target.c
index 8b3b840dea66..b66ae3a9a4b0 100644
--- a/drivers/md/dm-ploop-target.c
+++ b/drivers/md/dm-ploop-target.c
@@ -378,7 +378,7 @@ static int ploop_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	INIT_LIST_HEAD(&ploop->resubmit_pios);
 	INIT_LIST_HEAD(&ploop->enospc_pios);
 	INIT_LIST_HEAD(&ploop->cluster_lk_list);
-	INIT_LIST_HEAD(&ploop->wb_batch_list);
+	init_llist_head(&ploop->wb_batch_llist);
 	ploop->bat_entries = RB_ROOT;
 	timer_setup(&ploop->enospc_timer, ploop_enospc_timer, 0);
 
diff --git a/drivers/md/dm-ploop.h b/drivers/md/dm-ploop.h
index 72adeec17ed7..d459a02ded5d 100644
--- a/drivers/md/dm-ploop.h
+++ b/drivers/md/dm-ploop.h
@@ -120,9 +120,9 @@ struct md_page {
 	struct page *page;
 	void *kmpage;
 	u8 *bat_levels;
-	struct list_head wait_list;
+	struct llist_head wait_llist;
 
-	struct list_head wb_link;
+	struct llist_node wb_llink;
 	struct ploop_index_wb *piwb;
 };
 
@@ -165,7 +165,7 @@ struct ploop {
 	u32 hb_nr; /* holes_bitmap size in bits */
 	rwlock_t bat_rwlock;
 
-	struct list_head wb_batch_list;
+	struct llist_head wb_batch_llist;
 
 	/*
 	 * Hash table to link non-exclusive submitted bios.
-- 
2.43.5



More information about the Devel mailing list