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: [PATCH 06/18] drbd: allow write-ordering policy to be bumped up again
Date: Mon, 30 Jun 2014 17:52:55 +0200 [thread overview]
Message-ID: <1404143587-24344-7-git-send-email-philipp.reisner@linbit.com> (raw)
In-Reply-To: <1404143587-24344-1-git-send-email-philipp.reisner@linbit.com>
From: Lars Ellenberg <lars.ellenberg@linbit.com>
Previously, once you disabled flushes as a means of enforcing
write-ordering, you'd need to detach/re-attach to enable them again.
Allow drbdsetup disk-options to re-enable previously disabled
write-ordering policy options at runtime.
While at it fix RCU in drbd_bump_write_ordering()
max_allowed_wo() uses rcu_dereference, therefore it must
be called within rcu_read_lock()/rcu_read_unlock()
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
drivers/block/drbd/drbd_nl.c | 10 +++++++++-
drivers/block/drbd/drbd_receiver.c | 6 ++++--
2 files changed, 13 insertions(+), 3 deletions(-)
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 0bf8a60..66065e6 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1294,6 +1294,13 @@ static unsigned int drbd_al_extents_max(struct drbd_backing_dev *bdev)
return (al_size_4k - 1) * AL_CONTEXT_PER_TRANSACTION;
}
+static bool write_ordering_changed(struct disk_conf *a, struct disk_conf *b)
+{
+ return a->disk_barrier != b->disk_barrier ||
+ a->disk_flushes != b->disk_flushes ||
+ a->disk_drain != b->disk_drain;
+}
+
int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
{
struct drbd_config_context adm_ctx;
@@ -1400,7 +1407,8 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
else
set_bit(MD_NO_FUA, &device->flags);
- drbd_bump_write_ordering(device->resource, NULL, WO_bdev_flush);
+ if (write_ordering_changed(old_disk_conf, new_disk_conf))
+ drbd_bump_write_ordering(device->resource, NULL, WO_bdev_flush);
drbd_md_sync(device);
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index bb1434d..8d8a6b7 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1290,7 +1290,8 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin
};
pwo = resource->write_ordering;
- wo = min(pwo, wo);
+ if (wo != WO_bdev_flush)
+ wo = min(pwo, wo);
rcu_read_lock();
idr_for_each_entry(&resource->devices, device, vnr) {
if (get_ldev(device)) {
@@ -1300,11 +1301,12 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin
put_ldev(device);
}
}
- rcu_read_unlock();
if (bdev)
wo = max_allowed_wo(bdev, wo);
+ rcu_read_unlock();
+
resource->write_ordering = wo;
if (pwo != resource->write_ordering || wo == WO_bdev_flush)
drbd_info(resource, "Method to ensure write ordering: %s\n", write_ordering_str[resource->write_ordering]);
--
1.9.1
next prev parent reply other threads:[~2014-06-30 16:01 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-06-30 15:52 [PATCH 00/18] RFC DRBD fixes Philipp Reisner
2014-06-30 15:52 ` [PATCH 01/18] drbd: Move write_ordering from connection to resource Philipp Reisner
2014-06-30 15:52 ` [PATCH 02/18] drbd: device->ldev is not guaranteed on an D_ATTACHING disk Philipp Reisner
2014-06-30 15:52 ` [PATCH 03/18] drbd: rename drbd_free_bc() to drbd_free_ldev() Philipp Reisner
2014-06-30 15:52 ` [PATCH 04/18] drbd: reduce number of spinlock drop/re-aquire cycles Philipp Reisner
2014-06-30 15:52 ` [PATCH 05/18] drbd: refactor use of first_peer_device() Philipp Reisner
2014-06-30 15:52 ` Philipp Reisner [this message]
2014-06-30 15:52 ` [PATCH 07/18] drbd: get rid of atomic update on disk bitmap works Philipp Reisner
2014-06-30 15:52 ` [PATCH 08/18] drbd: fix a race stopping the worker thread Philipp Reisner
2014-06-30 15:52 ` [PATCH 09/18] drbd: fix resync finished detection Philipp Reisner
2014-06-30 15:52 ` [PATCH 10/18] drbd: stop the meta data sync timer before open coded meta data sync Philipp Reisner
2014-06-30 15:53 ` [PATCH 11/18] drbd: re-add lost conf_mutex protection in drbd_set_role Philipp Reisner
2014-06-30 15:53 ` [PATCH 12/18] drbd: trigger tcp_push_pending_frames() for PING and PING_ACK Philipp Reisner
2014-06-30 15:53 ` [PATCH 13/18] drbd: move set_disk_ro() to after we persisted the new role Philipp Reisner
2014-06-30 15:53 ` [PATCH 14/18] drbd: explicitly submit meta data requests with REQ_NOIDLE Philipp Reisner
2014-06-30 15:53 ` [PATCH 15/18] drbd: close race when detaching from disk Philipp Reisner
2014-06-30 15:53 ` [PATCH 16/18] drbd: make sure disk cleanup happens in worker context Philipp Reisner
2014-06-30 15:53 ` [PATCH 17/18] drbd: use drbd_device_post_work() in more places Philipp Reisner
2014-06-30 15:53 ` [PATCH 18/18] drbd: get rid of drbd_queue_work_front 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=1404143587-24344-7-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
all inboxes | Powered by JetHome®