From a822c83e47d97cdef38c4352e1ef62d9f46cfe98 Mon Sep 17 00:00:00 2001 From: Joe Thornber Date: Fri, 3 Jul 2015 10:22:42 +0100 Subject: dm thin: allocate the cell_sort_array dynamically Given the pool's cell_sort_array holds 8192 pointers it triggers an order 5 allocation via kmalloc. This order 5 allocation is prone to failure as system memory gets more fragmented over time. Fix this by allocating the cell_sort_array using vmalloc. Signed-off-by: Joe Thornber Signed-off-by: Mike Snitzer Cc: stable@vger.kernel.org --- drivers/md/dm-thin.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'drivers/md/dm-thin.c') diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index c33f61a4cc28..8f015d924a24 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -268,7 +269,7 @@ struct pool { process_mapping_fn process_prepared_mapping; process_mapping_fn process_prepared_discard; - struct dm_bio_prison_cell *cell_sort_array[CELL_SORT_ARRAY_SIZE]; + struct dm_bio_prison_cell **cell_sort_array; }; static enum pool_mode get_pool_mode(struct pool *pool); @@ -2777,6 +2778,7 @@ static void __pool_destroy(struct pool *pool) { __pool_table_remove(pool); + vfree(pool->cell_sort_array); if (dm_pool_metadata_close(pool->pmd) < 0) DMWARN("%s: dm_pool_metadata_close() failed.", __func__); @@ -2889,6 +2891,13 @@ static struct pool *pool_create(struct mapped_device *pool_md, goto bad_mapping_pool; } + pool->cell_sort_array = vmalloc(sizeof(*pool->cell_sort_array) * CELL_SORT_ARRAY_SIZE); + if (!pool->cell_sort_array) { + *error = "Error allocating cell sort array"; + err_p = ERR_PTR(-ENOMEM); + goto bad_sort_array; + } + pool->ref_count = 1; pool->last_commit_jiffies = jiffies; pool->pool_md = pool_md; @@ -2897,6 +2906,8 @@ static struct pool *pool_create(struct mapped_device *pool_md, return pool; +bad_sort_array: + mempool_destroy(pool->mapping_pool); bad_mapping_pool: dm_deferred_set_destroy(pool->all_io_ds); bad_all_io_ds: -- cgit v1.2.3 From bcc696fac11fe13e59dda5aaec6322a25b7c9a3a Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 15 Jul 2015 16:52:04 -0400 Subject: dm thin: stay in out-of-data-space mode once no_space_timeout expires This fixes an issue where running out of data space would cause the thin-pool's metadata to become read-only. There was no reason to make metadata read-only -- calling set_pool_mode() with PM_READ_ONLY was a misguided way to error all queued and future write IOs. We can accomplish the same by degrading from PM_OUT_OF_DATA_SPACE to PM_OUT_OF_DATA_SPACE with error_if_no_space enabled. Otherwise, the use of PM_READ_ONLY could cause a race where commit() was started before the PM_READ_ONLY transition but dm_pool_commit_metadata() would go on to fail because the block manager had transitioned to read-only. The return of -EPERM from dm_pool_commit_metadata(), due to attempting to commit while in read-only mode, caused the thin-pool to set 'needs_check' because a metadata_operation_failed(). This needless cascade of failures makes life for users more difficult than needed. Reported-by: Vivek Goyal Signed-off-by: Mike Snitzer --- drivers/md/dm-thin.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'drivers/md/dm-thin.c') diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 8f015d924a24..34e79531ea3f 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2282,18 +2282,23 @@ static void do_waker(struct work_struct *ws) queue_delayed_work(pool->wq, &pool->waker, COMMIT_PERIOD); } +static void notify_of_pool_mode_change_to_oods(struct pool *pool); + /* * We're holding onto IO to allow userland time to react. After the * timeout either the pool will have been resized (and thus back in - * PM_WRITE mode), or we degrade to PM_READ_ONLY and start erroring IO. + * PM_WRITE mode), or we degrade to PM_OUT_OF_DATA_SPACE w/ error_if_no_space. */ static void do_no_space_timeout(struct work_struct *ws) { struct pool *pool = container_of(to_delayed_work(ws), struct pool, no_space_timeout); - if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) - set_pool_mode(pool, PM_READ_ONLY); + if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) { + pool->pf.error_if_no_space = true; + notify_of_pool_mode_change_to_oods(pool); + error_retry_list(pool); + } } /*----------------------------------------------------------------*/ @@ -2371,6 +2376,14 @@ static void notify_of_pool_mode_change(struct pool *pool, const char *new_mode) dm_device_name(pool->pool_md), new_mode); } +static void notify_of_pool_mode_change_to_oods(struct pool *pool) +{ + if (!pool->pf.error_if_no_space) + notify_of_pool_mode_change(pool, "out-of-data-space (queue IO)"); + else + notify_of_pool_mode_change(pool, "out-of-data-space (error IO)"); +} + static bool passdown_enabled(struct pool_c *pt) { return pt->adjusted_pf.discard_passdown; @@ -2455,7 +2468,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) * frequently seeing this mode. */ if (old_mode != new_mode) - notify_of_pool_mode_change(pool, "out-of-data-space"); + notify_of_pool_mode_change_to_oods(pool); pool->process_bio = process_bio_read_only; pool->process_discard = process_discard_bio; pool->process_cell = process_cell_read_only; -- cgit v1.2.3 From e4c78e210daea17f82f12037005df225e22189b9 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 15 Jul 2015 11:40:24 -0400 Subject: dm thin: display 'needs_check' in status if it is set There is currently no way to see that the needs_check flag has been set in the metadata. Display 'needs_check' in the thin-pool status if it is set in the thinp metadata. Also, update thinp documentation. Signed-off-by: Mike Snitzer --- Documentation/device-mapper/thin-provisioning.txt | 9 ++++++++- drivers/md/dm-thin.c | 10 ++++++++-- 2 files changed, 16 insertions(+), 3 deletions(-) (limited to 'drivers/md/dm-thin.c') diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt index 4f67578b2954..1699a55b7b70 100644 --- a/Documentation/device-mapper/thin-provisioning.txt +++ b/Documentation/device-mapper/thin-provisioning.txt @@ -296,7 +296,7 @@ ii) Status underlying device. When this is enabled when loading the table, it can get disabled if the underlying device doesn't support it. - ro|rw + ro|rw|out_of_data_space If the pool encounters certain types of device failures it will drop into a read-only metadata mode in which no changes to the pool metadata (like allocating new blocks) are permitted. @@ -314,6 +314,13 @@ ii) Status module parameter can be used to change this timeout -- it defaults to 60 seconds but may be disabled using a value of 0. + needs_check + A metadata operation has failed, resulting in the needs_check + flag being set in the metadata's superblock. The metadata + device must be deactivated and checked/repaired before the + thin-pool can be made fully operational again. '-' indicates + needs_check is not set. + iii) Messages create_thin diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 34e79531ea3f..1c50c580215c 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -3738,6 +3738,7 @@ static void emit_flags(struct pool_features *pf, char *result, * Status line is: * / * / + * */ static void pool_status(struct dm_target *ti, status_type_t type, unsigned status_flags, char *result, unsigned maxlen) @@ -3839,6 +3840,11 @@ static void pool_status(struct dm_target *ti, status_type_t type, else DMEMIT("queue_if_no_space "); + if (dm_pool_metadata_needs_check(pool->pmd)) + DMEMIT("needs_check "); + else + DMEMIT("- "); + break; case STATUSTYPE_TABLE: @@ -3942,7 +3948,7 @@ static struct target_type pool_target = { .name = "thin-pool", .features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE | DM_TARGET_IMMUTABLE, - .version = {1, 15, 0}, + .version = {1, 16, 0}, .module = THIS_MODULE, .ctr = pool_ctr, .dtr = pool_dtr, @@ -4329,7 +4335,7 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits) static struct target_type thin_target = { .name = "thin", - .version = {1, 15, 0}, + .version = {1, 16, 0}, .module = THIS_MODULE, .ctr = thin_ctr, .dtr = thin_dtr, -- cgit v1.2.3