The commit is pushed to "branch-rh9-5.14.0-427.44.1.vz9.80.x-ovz" and will
appear at g...@bitbucket.org:openvz/vzkernel.git
after rh9-5.14.0-427.44.1.vz9.80.6
------>
commit e039c9267ba62f2db1f77febb90b0c46a3ac7871
Author: Andrey Zhadchenko <andrey.zhadche...@virtuozzo.com>
Date: Fri Jan 24 17:35:58 2025 +0200
dm-ploop: submit all postponed metadata on REQ_OP_FLUSH
On every flush request we should submit all accumulated metadata
changes, wait for their completion and only then do the flush.
https://virtuozzo.atlassian.net/browse/VSTOR-91817
Signed-off-by: Andrey Zhadchenko <andrey.zhadche...@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 | 42 ++++++++++++++++++++++++++++++++++++++++++
drivers/md/dm-ploop.h | 3 +++
2 files changed, 45 insertions(+)
diff --git a/drivers/md/dm-ploop-map.c b/drivers/md/dm-ploop-map.c
index 92844d032810..fdbf20145223 100644
--- a/drivers/md/dm-ploop-map.c
+++ b/drivers/md/dm-ploop-map.c
@@ -67,6 +67,7 @@ void ploop_index_wb_init(struct ploop_index_wb *piwb, struct
ploop *ploop)
piwb->completed = false;
piwb->page_id = PAGE_NR_NONE;
piwb->type = PIWB_TYPE_ALLOC;
+ piwb->flush_pio = NULL;
}
void ploop_init_pio(struct ploop *ploop, unsigned int bi_op, struct pio *pio)
@@ -873,6 +874,7 @@ static void ploop_bat_write_complete(struct pio *pio, void
*piwb_ptr,
blk_status_t bi_status)
{
struct ploop_index_wb *piwb = piwb_ptr;
+ struct pio *flush_pio = piwb->flush_pio;
struct ploop *ploop = piwb->ploop;
struct pio *aux_pio;
struct ploop_cow *cow;
@@ -911,6 +913,12 @@ static void ploop_bat_write_complete(struct pio *pio, void
*piwb_ptr,
ploop_complete_cow(cow, bi_status);
}
+ if (flush_pio) {
+ if (atomic_dec_and_test(&flush_pio->md_inflight))
+ ploop_dispatch_pios(ploop, flush_pio, NULL);
+ piwb->flush_pio = NULL;
+ }
+
/*
* In case of update BAT is failed, dst_clusters will be
* set back to holes_bitmap on last put_piwb().
@@ -1972,6 +1980,35 @@ int ploop_worker(void *data)
return 0;
}
+static void ploop_prepare_flush(struct ploop *ploop, struct pio *pio)
+{
+ struct md_page *md, *n;
+ int md_inflight = 0;
+
+ write_lock_irq(&ploop->bat_rwlock);
+
+ list_for_each_entry(md, &ploop->wb_batch_list_prio, wb_link) {
+ md_inflight++;
+ md->piwb->flush_pio = pio;
+ }
+
+ list_for_each_entry_safe(md, n, &ploop->wb_batch_list, wb_link) {
+ md_inflight++;
+ md->piwb->flush_pio = pio;
+ list_del(&md->wb_link);
+ list_add_tail(&md->wb_link, &ploop->wb_batch_list_prio);
+ }
+
+ atomic_set(&pio->md_inflight, md_inflight);
+
+ write_unlock_irq(&ploop->bat_rwlock);
+
+ if (md_inflight)
+ ploop_schedule_work(ploop);
+ else
+ ploop_dispatch_pios(ploop, pio, NULL);
+}
+
static void ploop_submit_embedded_pio(struct ploop *ploop, struct pio *pio)
{
struct ploop_rq *prq = pio->endio_cb_data;
@@ -1994,6 +2031,11 @@ static void ploop_submit_embedded_pio(struct ploop
*ploop, struct pio *pio)
ploop_inc_nr_inflight(ploop, pio);
+ if ((pio->bi_op & REQ_OP_MASK) == REQ_OP_FLUSH) {
+ ploop_prepare_flush(ploop, pio);
+ return;
+ }
+
if (pio->queue_list_id == PLOOP_LIST_FLUSH) {
/* Let the FLUSH go last from the queue , do not run here to
preserve ordering */
llist_add((struct llist_node *)(&pio->list),
&ploop->pios[PLOOP_LIST_PREPARE]);
diff --git a/drivers/md/dm-ploop.h b/drivers/md/dm-ploop.h
index 8bfc5e87a24e..c08acb1a3cc9 100644
--- a/drivers/md/dm-ploop.h
+++ b/drivers/md/dm-ploop.h
@@ -108,6 +108,7 @@ struct ploop_index_wb {
blk_status_t bi_status;
u32 page_id;
struct bio_vec aux_bvec;
+ struct pio *flush_pio;
};
/* Metadata page */
@@ -300,6 +301,8 @@ struct pio {
int ret; /* iocb result */
void (*complete)(struct pio *me);
void *data;
+
+ atomic_t md_inflight;
};
/* Delta COW private */
_______________________________________________
Devel mailing list
Devel@openvz.org
https://lists.openvz.org/mailman/listinfo/devel
