From: Alexander Atanasov <alexander.atana...@virtuozzo.com> nr_bat_entries are updated while resizing, some places read it without holding the bat_lock, to ensure a good value is read use READ_ONCE and WRITE_ONCE when updating. During grow/resize and shrink pios are suspended and code waits for all active inflight pios to complete.
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 | 13 +++++++++---- drivers/md/dm-ploop-map.c | 12 ++++++------ 2 files changed, 15 insertions(+), 10 deletions(-) diff --git a/drivers/md/dm-ploop-cmd.c b/drivers/md/dm-ploop-cmd.c index 50a23212270d..011d37f8fe3e 100644 --- a/drivers/md/dm-ploop-cmd.c +++ b/drivers/md/dm-ploop-cmd.c @@ -465,10 +465,14 @@ static int ploop_process_resize_cmd(struct ploop *ploop, struct ploop_cmd *cmd) ploop_hole_set_bit(dst_clu, ploop); dst_clu--; } - swap(ploop->hb_nr, cmd->resize.hb_nr); + WRITE_ONCE(ploop->hb_nr, cmd->resize.hb_nr); } else { ploop_add_md_pages(ploop, &cmd->resize.md_pages_root); - swap(ploop->nr_bat_entries, cmd->resize.nr_bat_entries); + /* + * In some places code reads nr_bat_entries without lock + * it is ok for grow but if we do shrink this may be a problem. + */ + WRITE_ONCE(ploop->nr_bat_entries, cmd->resize.nr_bat_entries); } spin_unlock_irq(&ploop->bat_lock); @@ -638,7 +642,7 @@ static int ploop_process_merge_latest_snapshot(struct ploop *ploop) int ret = 0; u32 clu; - for (clu = 0; clu < ploop->nr_bat_entries; clu++) { + for (clu = 0; clu < READ_ONCE(ploop->nr_bat_entries); clu++) { if (fatal_signal_pending(current)) { ret = -EINTR; break; @@ -974,7 +978,8 @@ static int process_flip_upper_deltas(struct ploop *ploop) struct md_page *md; u64 size; - size = (PLOOP_MAP_OFFSET + ploop->nr_bat_entries) * sizeof(map_index_t); + size = (PLOOP_MAP_OFFSET + READ_ONCE(ploop->nr_bat_entries)) + * sizeof(map_index_t); bat_clusters = DIV_ROUND_UP(size, CLU_SIZE(ploop)); hb_nr = ploop->hb_nr; diff --git a/drivers/md/dm-ploop-map.c b/drivers/md/dm-ploop-map.c index ccbc824f8371..d2d919b6c544 100644 --- a/drivers/md/dm-ploop-map.c +++ b/drivers/md/dm-ploop-map.c @@ -106,14 +106,14 @@ static int ploop_rq_valid(struct ploop *ploop, struct request *rq) end_byte = to_bytes(sector) + blk_rq_bytes(rq) - 1; end_clu = POS_TO_CLU(ploop, end_byte); - if (unlikely(end_clu >= ploop->nr_bat_entries)) { + if (unlikely(end_clu >= READ_ONCE(ploop->nr_bat_entries))) { /* * This mustn't happen, since we set max_io_len * via dm_set_target_max_io_len(). */ WARN_ONCE(1, "sec=%llu, size=%u, end_clu=%u, nr=%u\n", sector, blk_rq_bytes(rq), - end_clu, ploop->nr_bat_entries); + end_clu, READ_ONCE(ploop->nr_bat_entries)); return -EINVAL; } @@ -824,8 +824,9 @@ static void ploop_advance_local_after_bat_wb(struct ploop *ploop, off = piwb->page_id * PAGE_SIZE / sizeof(map_index_t); off -= PLOOP_MAP_OFFSET; + spin_lock_irqsave(&ploop->bat_lock, flags); /* Last and first index in copied page */ - last = ploop->nr_bat_entries - off; + last = READ_ONCE(ploop->nr_bat_entries) - off; if (last > PAGE_SIZE / sizeof(map_index_t)) last = PAGE_SIZE / sizeof(map_index_t); i = 0; @@ -835,7 +836,6 @@ static void ploop_advance_local_after_bat_wb(struct ploop *ploop, dst_clu = kmap_local_page(piwb->bat_page); /* 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) @@ -1023,7 +1023,7 @@ static int ploop_prepare_bat_update(struct ploop *ploop, struct md_page *md, off -= PLOOP_MAP_OFFSET; /* Last and first index in copied page */ - last = ploop->nr_bat_entries - off; + last = READ_ONCE(ploop->nr_bat_entries) - off; if (last > PAGE_SIZE / sizeof(map_index_t)) { last = PAGE_SIZE / sizeof(map_index_t); is_last_page = false; @@ -2426,7 +2426,7 @@ loff_t ploop_llseek_hole(struct dm_target *ti, loff_t offset, int whence) clu = SEC_TO_CLU(ploop, to_sector(offset) + ploop->skip_off); id = U32_MAX; - while (clu < ploop->nr_bat_entries) { + while (clu < READ_ONCE(ploop->nr_bat_entries)) { if (id != ploop_bat_clu_to_page_nr(clu)) { id = ploop_bat_clu_to_page_nr(clu); md = ploop_md_page_find(ploop, id); -- 2.43.5 _______________________________________________ Devel mailing list Devel@openvz.org https://lists.openvz.org/mailman/listinfo/devel
