From aec3b907de48be54106600a1ecb69d1231f4801d Mon Sep 17 00:00:00 2001 From: Mateusz Kusiak Date: Thu, 18 Jan 2024 11:30:15 +0100 Subject: [PATCH 01/41] Remove hardcoded checkpoint interval checking Mdmon assumes that kernel marks checkpoint every 1/16 of the volume size and that the checkpoints are equal in size. This is not true, kernel may mark checkpoints more frequently depending on several factors, including sync speed. This results in checkpoints reported by mdadm --examine falling behind the one reported by kernel. Remove hardcoded checkpoint interval checking. Signed-off-by: Mateusz Kusiak Signed-off-by: Mariusz Tkaczyk --- monitor.c | 22 ++++++---------------- 1 file changed, 6 insertions(+), 16 deletions(-) diff --git a/monitor.c b/monitor.c index 4acec678..b8d9e881 100644 --- a/monitor.c +++ b/monitor.c @@ -564,22 +564,10 @@ static int read_and_act(struct active_array *a, fd_set *fds) } } - /* Check for recovery checkpoint notifications. We need to be a - * minimum distance away from the last checkpoint to prevent - * over checkpointing. Note reshape checkpointing is handled - * in the second branch. + /* Handle reshape checkpointing */ - if (sync_completed > a->last_checkpoint && - sync_completed - a->last_checkpoint > a->info.component_size >> 4 && - a->curr_action > reshape) { - /* A (non-reshape) sync_action has reached a checkpoint. - * Record the updated position in the metadata - */ - a->last_checkpoint = sync_completed; - a->container->ss->set_array_state(a, a->curr_state <= clean); - } else if ((a->curr_action == idle && a->prev_action == reshape) || - (a->curr_action == reshape && - sync_completed > a->last_checkpoint)) { + if ((a->curr_action == idle && a->prev_action == reshape) || + (a->curr_action == reshape && sync_completed > a->last_checkpoint)) { /* Reshape has progressed or completed so we need to * update the array state - and possibly the array size */ @@ -607,8 +595,10 @@ static int read_and_act(struct active_array *a, fd_set *fds) a->last_checkpoint = sync_completed; } - if (sync_completed > a->last_checkpoint) + if (sync_completed > a->last_checkpoint) { a->last_checkpoint = sync_completed; + a->container->ss->set_array_state(a, a->curr_state <= clean); + } if (sync_completed >= a->info.component_size) a->last_checkpoint = 0; -- 2.40.1