91 lines
3.4 KiB
Diff
91 lines
3.4 KiB
Diff
|
From 13ada1be201eb14ff8295a17194de8db5cdccd7f Mon Sep 17 00:00:00 2001
|
||
|
|
From: Lars Ellenberg <lars.ellenberg@linbit.com>
|
||
|
|
Date: Wed, 2 Oct 2024 14:34:02 +0200
|
||
|
|
Subject: [PATCH 32/32] drbd: open: do not delay open() if already Primary
|
||
|
|
|
||
|
|
Since 48376549f (drbd: When a remote state change is active to not touch the open_counts, 2017-10-30)
|
||
|
|
if a remote state change is pending when someone tries to open() a DRBD volume,
|
||
|
|
we wait, interruptible, for "auto-promote-timeout",
|
||
|
|
until that state change is finalized (committed or aborted),
|
||
|
|
or give up with EAGAIN if the auto-promote timeout is reached.
|
||
|
|
|
||
|
|
auto-promote-timeout by default is much smaller than twopc-timeout,
|
||
|
|
so we may get spurious open() failures.
|
||
|
|
|
||
|
|
This could be mitigated with auto-promote-timeout > twopc-timeout.
|
||
|
|
|
||
|
|
But we can just ignore the pending state change,
|
||
|
|
if changing the open_cnt won't make a difference:
|
||
|
|
if we are already Primary, or we already have openers anyways.
|
||
|
|
|
||
|
|
If
|
||
|
|
- we have some remote state change pending,
|
||
|
|
- and we are not Primary already,
|
||
|
|
- and we do not have any openers, or this is an open with write intent,
|
||
|
|
we reject NDELAY openers immediately.
|
||
|
|
Normal openers wait for the state change to be finalized
|
||
|
|
(or give up after auto-promote-timeout).
|
||
|
|
|
||
|
|
We do not need to wait if:
|
||
|
|
- there is no remote state change pending,
|
||
|
|
- or we are already Primary anyways,
|
||
|
|
- or we are Secondary, this is a read-only open, and we have openers already.
|
||
|
|
|
||
|
|
Note: we may still want to immediately reject NDELAY open if
|
||
|
|
there is a remote state change pending, even if we have an
|
||
|
|
open count != 0. These are typically short lived openers
|
||
|
|
triggered via udev. If they overlap (new open comes in
|
||
|
|
before previous close), these may still accumulate enough
|
||
|
|
time to mess with state changes.
|
||
|
|
For now, I decide to allow them.
|
||
|
|
---
|
||
|
|
drbd/drbd_main.c | 22 ++++++++++++++++++++--
|
||
|
|
1 file changed, 20 insertions(+), 2 deletions(-)
|
||
|
|
|
||
|
|
diff --git a/drbd/drbd_main.c b/drbd/drbd_main.c
|
||
|
|
index a216b725e66c..258be3b9c10d 100644
|
||
|
|
--- a/drbd/drbd_main.c
|
||
|
|
+++ b/drbd/drbd_main.c
|
||
|
|
@@ -2583,10 +2583,21 @@ enum ioc_rv {
|
||
|
|
IOC_ABORT = 2,
|
||
|
|
};
|
||
|
|
|
||
|
|
+/* If we are in the middle of a cluster wide state change, we don't want
|
||
|
|
+ * to change (open_cnt == 0), as that then could cause a failure to commit
|
||
|
|
+ * some already promised peer auto-promote locally.
|
||
|
|
+ * So we wait until the pending remote_state_change is finalized,
|
||
|
|
+ * or give up when the timeout is reached.
|
||
|
|
+ *
|
||
|
|
+ * But we don't want to fail an open on a Primary just because it happens
|
||
|
|
+ * during some unrelated remote state change.
|
||
|
|
+ * If we are already Primary, or already have an open count != 0,
|
||
|
|
+ * we don't need to wait, it won't change anything.
|
||
|
|
+ */
|
||
|
|
static enum ioc_rv inc_open_count(struct drbd_device *device, blk_mode_t mode)
|
||
|
|
{
|
||
|
|
struct drbd_resource *resource = device->resource;
|
||
|
|
- enum ioc_rv r = mode & BLK_OPEN_NDELAY ? IOC_ABORT : IOC_SLEEP;
|
||
|
|
+ enum ioc_rv r;
|
||
|
|
|
||
|
|
if (test_bit(DOWN_IN_PROGRESS, &resource->flags))
|
||
|
|
return IOC_ABORT;
|
||
|
|
@@ -2594,7 +2605,14 @@ static enum ioc_rv inc_open_count(struct drbd_device *device, blk_mode_t mode)
|
||
|
|
read_lock_irq(&resource->state_rwlock);
|
||
|
|
if (test_bit(UNREGISTERED, &device->flags))
|
||
|
|
r = IOC_ABORT;
|
||
|
|
- else if (!resource->remote_state_change) {
|
||
|
|
+ else if (resource->remote_state_change &&
|
||
|
|
+ resource->role[NOW] != R_PRIMARY &&
|
||
|
|
+ (device->open_cnt == 0 || mode & BLK_OPEN_WRITE)) {
|
||
|
|
+ if (mode & BLK_OPEN_NDELAY)
|
||
|
|
+ r = IOC_ABORT;
|
||
|
|
+ else
|
||
|
|
+ r = IOC_SLEEP;
|
||
|
|
+ } else {
|
||
|
|
r = IOC_OK;
|
||
|
|
device->open_cnt++;
|
||
|
|
if (mode & BLK_OPEN_WRITE)
|
||
|
|
--
|
||
|
|
2.35.3
|
||
|
|
|