From: Philipp Reisner <philipp.reisner@linbit.com>
To: linux-kernel@vger.kernel.org, Jens Axboe <axboe@kernel.dk>
Cc: drbd-dev@lists.linbit.com
Subject: [Drbd-dev] [PATCH 16/19] drbd: separate out __al_write_transaction helper function
Date: Tue, 4 Aug 2015 14:56:40 +0200 [thread overview]
Message-ID: <1438693003-17554-17-git-send-email-philipp.reisner@linbit.com> (raw)
In-Reply-To: <1438693003-17554-1-git-send-email-philipp.reisner@linbit.com>
From: Lars Ellenberg <lars.ellenberg@linbit.com>
To be able to "force out" an activity log transaction,
even if there are no pending updates.
This will be used to relocate the on-disk activity log,
if the on-disk offsets have to be changed,
without the need to empty the activity log first.
While at it, move the definition,
so we can drop the forward declaration of a static helper.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
drivers/block/drbd/drbd_actlog.c | 304 ++++++++++++++++++++-------------------
1 file changed, 156 insertions(+), 148 deletions(-)
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 1318e32..f83dcca 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -288,7 +288,162 @@ bool drbd_al_begin_io_prepare(struct drbd_device *device, struct drbd_interval *
return need_transaction;
}
-static int al_write_transaction(struct drbd_device *device);
+#if (PAGE_SHIFT + 3) < (AL_EXTENT_SHIFT - BM_BLOCK_SHIFT)
+/* Currently BM_BLOCK_SHIFT, BM_EXT_SHIFT and AL_EXTENT_SHIFT
+ * are still coupled, or assume too much about their relation.
+ * Code below will not work if this is violated.
+ * Will be cleaned up with some followup patch.
+ */
+# error FIXME
+#endif
+
+static unsigned int al_extent_to_bm_page(unsigned int al_enr)
+{
+ return al_enr >>
+ /* bit to page */
+ ((PAGE_SHIFT + 3) -
+ /* al extent number to bit */
+ (AL_EXTENT_SHIFT - BM_BLOCK_SHIFT));
+}
+
+static sector_t al_tr_number_to_on_disk_sector(struct drbd_device *device)
+{
+ const unsigned int stripes = device->ldev->md.al_stripes;
+ const unsigned int stripe_size_4kB = device->ldev->md.al_stripe_size_4k;
+
+ /* transaction number, modulo on-disk ring buffer wrap around */
+ unsigned int t = device->al_tr_number % (device->ldev->md.al_size_4k);
+
+ /* ... to aligned 4k on disk block */
+ t = ((t % stripes) * stripe_size_4kB) + t/stripes;
+
+ /* ... to 512 byte sector in activity log */
+ t *= 8;
+
+ /* ... plus offset to the on disk position */
+ return device->ldev->md.md_offset + device->ldev->md.al_offset + t;
+}
+
+static int __al_write_transaction(struct drbd_device *device, struct al_transaction_on_disk *buffer)
+{
+ struct lc_element *e;
+ sector_t sector;
+ int i, mx;
+ unsigned extent_nr;
+ unsigned crc = 0;
+ int err = 0;
+
+ memset(buffer, 0, sizeof(*buffer));
+ buffer->magic = cpu_to_be32(DRBD_AL_MAGIC);
+ buffer->tr_number = cpu_to_be32(device->al_tr_number);
+
+ i = 0;
+
+ /* Even though no one can start to change this list
+ * once we set the LC_LOCKED -- from drbd_al_begin_io(),
+ * lc_try_lock_for_transaction() --, someone may still
+ * be in the process of changing it. */
+ spin_lock_irq(&device->al_lock);
+ list_for_each_entry(e, &device->act_log->to_be_changed, list) {
+ if (i == AL_UPDATES_PER_TRANSACTION) {
+ i++;
+ break;
+ }
+ buffer->update_slot_nr[i] = cpu_to_be16(e->lc_index);
+ buffer->update_extent_nr[i] = cpu_to_be32(e->lc_new_number);
+ if (e->lc_number != LC_FREE)
+ drbd_bm_mark_for_writeout(device,
+ al_extent_to_bm_page(e->lc_number));
+ i++;
+ }
+ spin_unlock_irq(&device->al_lock);
+ BUG_ON(i > AL_UPDATES_PER_TRANSACTION);
+
+ buffer->n_updates = cpu_to_be16(i);
+ for ( ; i < AL_UPDATES_PER_TRANSACTION; i++) {
+ buffer->update_slot_nr[i] = cpu_to_be16(-1);
+ buffer->update_extent_nr[i] = cpu_to_be32(LC_FREE);
+ }
+
+ buffer->context_size = cpu_to_be16(device->act_log->nr_elements);
+ buffer->context_start_slot_nr = cpu_to_be16(device->al_tr_cycle);
+
+ mx = min_t(int, AL_CONTEXT_PER_TRANSACTION,
+ device->act_log->nr_elements - device->al_tr_cycle);
+ for (i = 0; i < mx; i++) {
+ unsigned idx = device->al_tr_cycle + i;
+ extent_nr = lc_element_by_index(device->act_log, idx)->lc_number;
+ buffer->context[i] = cpu_to_be32(extent_nr);
+ }
+ for (; i < AL_CONTEXT_PER_TRANSACTION; i++)
+ buffer->context[i] = cpu_to_be32(LC_FREE);
+
+ device->al_tr_cycle += AL_CONTEXT_PER_TRANSACTION;
+ if (device->al_tr_cycle >= device->act_log->nr_elements)
+ device->al_tr_cycle = 0;
+
+ sector = al_tr_number_to_on_disk_sector(device);
+
+ crc = crc32c(0, buffer, 4096);
+ buffer->crc32c = cpu_to_be32(crc);
+
+ if (drbd_bm_write_hinted(device))
+ err = -EIO;
+ else {
+ bool write_al_updates;
+ rcu_read_lock();
+ write_al_updates = rcu_dereference(device->ldev->disk_conf)->al_updates;
+ rcu_read_unlock();
+ if (write_al_updates) {
+ if (drbd_md_sync_page_io(device, device->ldev, sector, WRITE)) {
+ err = -EIO;
+ drbd_chk_io_error(device, 1, DRBD_META_IO_ERROR);
+ } else {
+ device->al_tr_number++;
+ device->al_writ_cnt++;
+ }
+ }
+ }
+
+ return err;
+}
+
+static int al_write_transaction(struct drbd_device *device)
+{
+ struct al_transaction_on_disk *buffer;
+ int err;
+
+ if (!get_ldev(device)) {
+ drbd_err(device, "disk is %s, cannot start al transaction\n",
+ drbd_disk_str(device->state.disk));
+ return -EIO;
+ }
+
+ /* The bitmap write may have failed, causing a state change. */
+ if (device->state.disk < D_INCONSISTENT) {
+ drbd_err(device,
+ "disk is %s, cannot write al transaction\n",
+ drbd_disk_str(device->state.disk));
+ put_ldev(device);
+ return -EIO;
+ }
+
+ /* protects md_io_buffer, al_tr_cycle, ... */
+ buffer = drbd_md_get_buffer(device, __func__);
+ if (!buffer) {
+ drbd_err(device, "disk failed while waiting for md_io buffer\n");
+ put_ldev(device);
+ return -ENODEV;
+ }
+
+ err = __al_write_transaction(device, buffer);
+
+ drbd_md_put_buffer(device);
+ put_ldev(device);
+
+ return err;
+}
+
void drbd_al_begin_io_commit(struct drbd_device *device)
{
@@ -420,153 +575,6 @@ void drbd_al_complete_io(struct drbd_device *device, struct drbd_interval *i)
wake_up(&device->al_wait);
}
-#if (PAGE_SHIFT + 3) < (AL_EXTENT_SHIFT - BM_BLOCK_SHIFT)
-/* Currently BM_BLOCK_SHIFT, BM_EXT_SHIFT and AL_EXTENT_SHIFT
- * are still coupled, or assume too much about their relation.
- * Code below will not work if this is violated.
- * Will be cleaned up with some followup patch.
- */
-# error FIXME
-#endif
-
-static unsigned int al_extent_to_bm_page(unsigned int al_enr)
-{
- return al_enr >>
- /* bit to page */
- ((PAGE_SHIFT + 3) -
- /* al extent number to bit */
- (AL_EXTENT_SHIFT - BM_BLOCK_SHIFT));
-}
-
-static sector_t al_tr_number_to_on_disk_sector(struct drbd_device *device)
-{
- const unsigned int stripes = device->ldev->md.al_stripes;
- const unsigned int stripe_size_4kB = device->ldev->md.al_stripe_size_4k;
-
- /* transaction number, modulo on-disk ring buffer wrap around */
- unsigned int t = device->al_tr_number % (device->ldev->md.al_size_4k);
-
- /* ... to aligned 4k on disk block */
- t = ((t % stripes) * stripe_size_4kB) + t/stripes;
-
- /* ... to 512 byte sector in activity log */
- t *= 8;
-
- /* ... plus offset to the on disk position */
- return device->ldev->md.md_offset + device->ldev->md.al_offset + t;
-}
-
-int al_write_transaction(struct drbd_device *device)
-{
- struct al_transaction_on_disk *buffer;
- struct lc_element *e;
- sector_t sector;
- int i, mx;
- unsigned extent_nr;
- unsigned crc = 0;
- int err = 0;
-
- if (!get_ldev(device)) {
- drbd_err(device, "disk is %s, cannot start al transaction\n",
- drbd_disk_str(device->state.disk));
- return -EIO;
- }
-
- /* The bitmap write may have failed, causing a state change. */
- if (device->state.disk < D_INCONSISTENT) {
- drbd_err(device,
- "disk is %s, cannot write al transaction\n",
- drbd_disk_str(device->state.disk));
- put_ldev(device);
- return -EIO;
- }
-
- /* protects md_io_buffer, al_tr_cycle, ... */
- buffer = drbd_md_get_buffer(device, __func__);
- if (!buffer) {
- drbd_err(device, "disk failed while waiting for md_io buffer\n");
- put_ldev(device);
- return -ENODEV;
- }
-
- memset(buffer, 0, sizeof(*buffer));
- buffer->magic = cpu_to_be32(DRBD_AL_MAGIC);
- buffer->tr_number = cpu_to_be32(device->al_tr_number);
-
- i = 0;
-
- /* Even though no one can start to change this list
- * once we set the LC_LOCKED -- from drbd_al_begin_io(),
- * lc_try_lock_for_transaction() --, someone may still
- * be in the process of changing it. */
- spin_lock_irq(&device->al_lock);
- list_for_each_entry(e, &device->act_log->to_be_changed, list) {
- if (i == AL_UPDATES_PER_TRANSACTION) {
- i++;
- break;
- }
- buffer->update_slot_nr[i] = cpu_to_be16(e->lc_index);
- buffer->update_extent_nr[i] = cpu_to_be32(e->lc_new_number);
- if (e->lc_number != LC_FREE)
- drbd_bm_mark_for_writeout(device,
- al_extent_to_bm_page(e->lc_number));
- i++;
- }
- spin_unlock_irq(&device->al_lock);
- BUG_ON(i > AL_UPDATES_PER_TRANSACTION);
-
- buffer->n_updates = cpu_to_be16(i);
- for ( ; i < AL_UPDATES_PER_TRANSACTION; i++) {
- buffer->update_slot_nr[i] = cpu_to_be16(-1);
- buffer->update_extent_nr[i] = cpu_to_be32(LC_FREE);
- }
-
- buffer->context_size = cpu_to_be16(device->act_log->nr_elements);
- buffer->context_start_slot_nr = cpu_to_be16(device->al_tr_cycle);
-
- mx = min_t(int, AL_CONTEXT_PER_TRANSACTION,
- device->act_log->nr_elements - device->al_tr_cycle);
- for (i = 0; i < mx; i++) {
- unsigned idx = device->al_tr_cycle + i;
- extent_nr = lc_element_by_index(device->act_log, idx)->lc_number;
- buffer->context[i] = cpu_to_be32(extent_nr);
- }
- for (; i < AL_CONTEXT_PER_TRANSACTION; i++)
- buffer->context[i] = cpu_to_be32(LC_FREE);
-
- device->al_tr_cycle += AL_CONTEXT_PER_TRANSACTION;
- if (device->al_tr_cycle >= device->act_log->nr_elements)
- device->al_tr_cycle = 0;
-
- sector = al_tr_number_to_on_disk_sector(device);
-
- crc = crc32c(0, buffer, 4096);
- buffer->crc32c = cpu_to_be32(crc);
-
- if (drbd_bm_write_hinted(device))
- err = -EIO;
- else {
- bool write_al_updates;
- rcu_read_lock();
- write_al_updates = rcu_dereference(device->ldev->disk_conf)->al_updates;
- rcu_read_unlock();
- if (write_al_updates) {
- if (drbd_md_sync_page_io(device, device->ldev, sector, WRITE)) {
- err = -EIO;
- drbd_chk_io_error(device, 1, DRBD_META_IO_ERROR);
- } else {
- device->al_tr_number++;
- device->al_writ_cnt++;
- }
- }
- }
-
- drbd_md_put_buffer(device);
- put_ldev(device);
-
- return err;
-}
-
static int _try_lc_del(struct drbd_device *device, struct lc_element *al_ext)
{
int rv;
--
1.9.1
next prev parent reply other threads:[~2015-08-04 12:57 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-08-04 12:56 [Drbd-dev] [PATCH 00/19] RFC DRBD updates for the 4.3 merge window (part II) Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 01/19] drbd: Rename asender to ack_receiver Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 02/19] drbd: Create a dedicated workqueue for sending acks on the control connection Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 03/19] drbd: prevent NULL pointer deref when resuming diskless primary Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 04/19] drbd: debugfs: expose ed_data_gen_id Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 05/19] drbd: use resource name in workqueue Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 06/19] drbd: avoid redefinition of BITS_PER_PAGE Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 07/19] drbd: use bitmap_weight() helper, don't open code Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 08/19] drbd: fix spurious alert level printk Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 09/19] drbd: fix queue limit setup for discard Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 10/19] drbd: make drbd known to lsblk: use bd_link_disk_holder Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 11/19] lru_cache: Converted lc_seq_printf_status to return void Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 12/19] drbd: don't block forever in disconnect during resync if fencing=r-a-stonith Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 13/19] drbd: fix memory leak in drbd_adm_resize Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 14/19] drbd: fix "endless" transfer log walk in protocol A Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 15/19] drbd: make suspend_io() / resume_io() must be thread and recursion safe Philipp Reisner
2015-08-04 12:56 ` Philipp Reisner [this message]
2015-08-04 12:56 ` [Drbd-dev] [PATCH 17/19] drbd: avoid potential deadlock during handshake Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 18/19] drbd: fix error path during resize Philipp Reisner
2015-08-04 12:56 ` [Drbd-dev] [PATCH 19/19] MAINTAINERS: Updated information for DRBD DRIVER Philipp Reisner
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1438693003-17554-17-git-send-email-philipp.reisner@linbit.com \
--to=philipp.reisner@linbit.com \
--cc=axboe@kernel.dk \
--cc=drbd-dev@lists.linbit.com \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox