From: Alexander Atanasov <alexander.atana...@virtuozzo.com> Prepare for threads. Convert rwlock to spin lock. This patch converts existing rwlocks only. In the next one lock is used where required.
https://virtuozzo.atlassian.net/browse/VSTOR-91821 Signed-off-by: Alexander Atanasov <alexander.atana...@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-cmd.c | 8 ++++---- drivers/md/dm-ploop-map.c | 22 ++++++++++++---------- drivers/md/dm-ploop-target.c | 2 +- drivers/md/dm-ploop.h | 2 +- 4 files changed, 18 insertions(+), 16 deletions(-) diff --git a/drivers/md/dm-ploop-cmd.c b/drivers/md/dm-ploop-cmd.c index fa9f8c9d8d40..dc0be65261f1 100644 --- a/drivers/md/dm-ploop-cmd.c +++ b/drivers/md/dm-ploop-cmd.c @@ -34,7 +34,7 @@ static void ploop_advance_holes_bitmap(struct ploop *ploop, return; cmd->resize.stage++; - write_lock_irqsave(&ploop->bat_rwlock, flags); + spin_lock_irqsave(&ploop->bat_lock, flags); /* Copy and swap holes_bitmap */ size = DIV_ROUND_UP(ploop->hb_nr, 8); memcpy(cmd->resize.holes_bitmap, ploop->holes_bitmap, size); @@ -59,7 +59,7 @@ static void ploop_advance_holes_bitmap(struct ploop *ploop, } spin_unlock(&md->md_lock); } - write_unlock_irqrestore(&ploop->bat_rwlock, flags); + spin_unlock_irqrestore(&ploop->bat_lock, flags); } static int ploop_wait_for_completion_maybe_killable(struct completion *comp, @@ -451,7 +451,7 @@ static int ploop_process_resize_cmd(struct ploop *ploop, struct ploop_cmd *cmd) /* Update header metadata */ ret = ploop_grow_update_header(ploop, cmd); out: - write_lock_irq(&ploop->bat_rwlock); + spin_lock_irq(&ploop->bat_lock); if (ret) { /* Cleanup: mark new BAT overages as free clusters */ dst_clu = cmd->resize.dst_clu - 1; @@ -465,7 +465,7 @@ static int ploop_process_resize_cmd(struct ploop *ploop, struct ploop_cmd *cmd) ploop_add_md_pages(ploop, &cmd->resize.md_pages_root); swap(ploop->nr_bat_entries, cmd->resize.nr_bat_entries); } - write_unlock_irq(&ploop->bat_rwlock); + spin_unlock_irq(&ploop->bat_lock); return ret; } diff --git a/drivers/md/dm-ploop-map.c b/drivers/md/dm-ploop-map.c index bf7a24e074d0..1032b0e74d39 100644 --- a/drivers/md/dm-ploop-map.c +++ b/drivers/md/dm-ploop-map.c @@ -557,13 +557,13 @@ 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); + spin_lock_irqsave(&ploop->bat_lock, flags); WARN_ON_ONCE(test_bit(MD_WRITEBACK, &md->status)); if (!test_and_set_bit(MD_DIRTY, &md->status)) { llist_add((struct llist_node *)&md->wb_link, &ploop->wb_batch_llist); new = true; } - write_unlock_irqrestore(&ploop->bat_rwlock, flags); + spin_unlock_irqrestore(&ploop->bat_lock, flags); md->dirty_timeout = jiffies + ploop->md_submit_delay_ms*HZ/1000; return new; @@ -573,7 +573,7 @@ static void ploop_md_up_prio(struct ploop *ploop, struct md_page *md) { unsigned long flags; - write_lock_irqsave(&ploop->bat_rwlock, flags); + spin_lock_irqsave(&ploop->bat_lock, flags); if (test_bit(MD_WRITEBACK, &md->status)) goto out; if (test_and_set_bit(MD_HIGHPRIO, &md->status)) @@ -581,7 +581,7 @@ static void ploop_md_up_prio(struct ploop *ploop, struct md_page *md) WARN_ON_ONCE(!test_bit(MD_DIRTY, &md->status)); out: - write_unlock_irqrestore(&ploop->bat_rwlock, flags); + spin_unlock_irqrestore(&ploop->bat_lock, flags); } void ploop_disable_writeback_delay(struct ploop *ploop) @@ -732,9 +732,9 @@ static void ploop_complete_cow(struct ploop_cow *cow, blk_status_t bi_status) ploop_del_cluster_lk(ploop, cow_pio); if (dst_clu != BAT_ENTRY_NONE && bi_status != BLK_STS_OK) { - read_lock_irqsave(&ploop->bat_rwlock, flags); + spin_lock_irqsave(&ploop->bat_lock, flags); ploop_hole_set_bit(dst_clu, ploop); - read_unlock_irqrestore(&ploop->bat_rwlock, flags); + spin_unlock_irqrestore(&ploop->bat_lock, flags); } ploop_queue_or_fail(ploop, blk_status_to_errno(bi_status), cow_pio); @@ -1842,6 +1842,7 @@ static void ploop_process_resubmit_pios(struct ploop *ploop, static void ploop_submit_metadata_writeback(struct ploop *ploop) { + unsigned long flags; LIST_HEAD(ll_skipped); unsigned long timeout = jiffies; struct md_page *md; @@ -1849,9 +1850,9 @@ static void ploop_submit_metadata_writeback(struct ploop *ploop) struct llist_node *ll_wb_batch; /* Lock here to protect against md_inflight counting */ - write_lock_irq(&ploop->bat_rwlock); + spin_lock_irqsave(&ploop->bat_lock, flags); ll_wb_batch = llist_del_all(&ploop->wb_batch_llist); - write_unlock_irq(&ploop->bat_rwlock); + spin_unlock_irqrestore(&ploop->bat_lock, flags); /* * Pages are set dirty so no one must touch lists * if new md entries are dirtied they are added at the start of the list @@ -2005,6 +2006,7 @@ static int ploop_prepare_flush(struct ploop *ploop, struct pio *pio) struct md_page *md; int md_inflight = 0; struct llist_node *pos, *t; + unsigned long flags; if (pio->bi_op & REQ_PREFLUSH && (pio->bi_op & REQ_OP_MASK) != REQ_OP_FLUSH) { flush_pio = ploop_alloc_pio(ploop, GFP_NOIO); @@ -2021,7 +2023,7 @@ static int ploop_prepare_flush(struct ploop *ploop, struct pio *pio) flush_pio->free_on_endio = true; } - write_lock_irq(&ploop->bat_rwlock); + spin_lock_irqsave(&ploop->bat_lock, flags); llist_for_each_safe(pos, t, ploop->wb_batch_llist.first) { md = list_entry((struct list_head *)pos, typeof(*md), wb_link); md_inflight++; @@ -2030,7 +2032,7 @@ static int ploop_prepare_flush(struct ploop *ploop, struct pio *pio) } atomic_set(&flush_pio->md_inflight, md_inflight); - write_unlock_irq(&ploop->bat_rwlock); + spin_unlock_irqrestore(&ploop->bat_lock, flags); return md_inflight; } diff --git a/drivers/md/dm-ploop-target.c b/drivers/md/dm-ploop-target.c index 9a4a4dc57bb5..dc63c18cece8 100644 --- a/drivers/md/dm-ploop-target.c +++ b/drivers/md/dm-ploop-target.c @@ -405,7 +405,7 @@ static int ploop_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto err; } - rwlock_init(&ploop->bat_rwlock); + spin_lock_init(&ploop->bat_lock); spin_lock_init(&ploop->err_status_lock); init_rwsem(&ploop->ctl_rwsem); init_waitqueue_head(&ploop->service_wq); diff --git a/drivers/md/dm-ploop.h b/drivers/md/dm-ploop.h index 3dcf37c51b2a..10c8cf2e154a 100644 --- a/drivers/md/dm-ploop.h +++ b/drivers/md/dm-ploop.h @@ -174,7 +174,7 @@ struct ploop { */ void *holes_bitmap; /* Clearing a bit occurs from kwork only */ u32 hb_nr; /* holes_bitmap size in bits */ - rwlock_t bat_rwlock; + spinlock_t bat_lock; struct llist_head wb_batch_llist; -- 2.43.5 _______________________________________________ Devel mailing list Devel@openvz.org https://lists.openvz.org/mailman/listinfo/devel
