[Devel] [PATCH RHEL9 COMMIT] dm-ploop: disable metadata writeback delay

[Konstantin Khorenko]

The commit is pushed to "branch-rh9-5.14.0-427.44.1.vz9.80.x-ovz" and will appear at git at bitbucket.org:openvz/vzkernel.git
after rh9-5.14.0-427.44.1.vz9.80.6
------>
commit 079d405a56e631e9e2048a9b1b62f862bb950e8d
Author: Alexander Atanasov <alexander.atanasov at virtuozzo.com>
Date:   Fri Jan 24 17:36:15 2025 +0200

    dm-ploop: disable metadata writeback delay
    
    Delayed metadata writeback results in a hang, disable
    it until it is fixed. Pios end in the waiting list of
    md and get stuck there never to complete.
    
    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
---
 drivers/md/dm-ploop-map.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/md/dm-ploop-map.c b/drivers/md/dm-ploop-map.c
index 037d7806b179..fac338e31c80 100644
--- a/drivers/md/dm-ploop-map.c
+++ b/drivers/md/dm-ploop-map.c
@@ -818,9 +818,10 @@ static void ploop_advance_local_after_bat_wb(struct ploop *ploop,
 	/* holes bit map requires bat_lock */
 	spin_lock_irqsave(&ploop->bat_lock, flags);
 	spin_lock(&md->md_lock);
+#ifdef PLOOP_DELAYWB
 	if (piwb->type == PIWB_TYPE_ALLOC)
 		goto skip_apply;
-
+#endif
 	for (; i < last; i++) {
 		if (piwb->type == PIWB_TYPE_DISCARD) {
 			ploop_piwb_discard_completed(ploop, success, i + off, dst_clu[i]);
@@ -837,7 +838,9 @@ static void ploop_advance_local_after_bat_wb(struct ploop *ploop,
 			ploop_hole_set_bit(i + off, ploop);
 		}
 	}
+#ifdef PLOOP_DELAYWB
 skip_apply:
+#endif
 
 	WARN_ON_ONCE(!test_bit(MD_WRITEBACK, &md->status));
 	/* protect piwb */
@@ -1200,8 +1203,10 @@ static int ploop_alloc_cluster(struct ploop *ploop, struct ploop_index_wb *piwb,
 	WRITE_ONCE(piwb->md->bat_levels[clu], ploop_top_level(ploop));
 	spin_unlock_irqrestore(&piwb->md->md_lock, flags);
 	kunmap_local(to);
+#ifdef PLOOP_DELAYWB
 	to = piwb->md->kmpage;
 	WRITE_ONCE(to[clu], *dst_clu);
+#endif
 out:
 	return ret;
 }
@@ -1492,6 +1497,7 @@ static void ploop_submit_cow_index_wb(struct ploop_cow *cow)
 	WRITE_ONCE(to[clu], cow->dst_clu);
 	kunmap_local(to);
 
+#ifdef PLOOP_DELAYWB
 	spin_lock_irqsave(&md->md_lock, flags);
 	to = md->kmpage;
 	WRITE_ONCE(to[clu], cow->dst_clu);
@@ -1499,7 +1505,7 @@ static void ploop_submit_cow_index_wb(struct ploop_cow *cow)
 	spin_unlock_irqrestore(&md->md_lock, flags);
 
 	ploop_md_up_prio(ploop, md);
-
+#endif
 	/* Prevent double clearing of holes_bitmap bit on complete_cow() */
 	cow->dst_clu = BAT_ENTRY_NONE;
 	spin_lock_irq(&ploop->deferred_lock);
@@ -1593,12 +1599,19 @@ static bool ploop_locate_new_cluster_and_attach_pio(struct ploop *ploop,
 		goto error;
 	}
 
+#ifdef PLOOP_DELAYWB
 	if (pio->bi_op & REQ_FUA) {
 		piwb->pio->bi_op |= REQ_FUA;
 		ploop_attach_end_action(pio, piwb);
 		ploop_md_up_prio(ploop, md);
 	}
-
+#else
+	if (pio->bi_op & REQ_FUA) {
+		piwb->pio->bi_op |= REQ_FUA;
+		ploop_md_up_prio(ploop, md);
+	}
+	ploop_attach_end_action(pio, piwb);
+#endif
 	attached = true;
 out:
 	return attached;
@@ -1871,7 +1884,8 @@ static inline int ploop_submit_metadata_writeback(struct ploop *ploop, int force
 	 */
 	llist_for_each_safe(pos, t, ll_wb_batch) {
 		md = list_entry((struct list_head *)pos, typeof(*md), wb_link);
-		if (!llist_empty(&md->wait_llist) || force ||
+		/* XXX: fixme delay results in a hang - TBD */
+		if (1 || !llist_empty(&md->wait_llist) || force ||
 		    test_bit(MD_HIGHPRIO, &md->status) ||
 		    time_before(md->dirty_timeout, timeout) ||
 		    ploop->force_md_writeback) {