mirrors/scoutfs
1
0
Fork 0
mirror of https://github.com/versity/scoutfs.git synced 2026-07-29 03:23:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update quorum status files more frequently

Browse Source 
We were seeing rare test failures where it looked like is_leader wasn't
set for any of the mounts.   The test that couldn't find a set is_leader
file had just perfomed some mounts so we know that a server was up and
processing requests.

The quorum task wasn't updating the status that's shown in sysfs and
debugfs until after the server started up.  This opened the race where
the server was able to serve mount requests and have the test run to
find no is_leader file set before the quorum task was able to update the
stats and make its election visible.

This updates the quorum task to make its status visible more often,
typically before it does something that will take a while.  The
is_leader will now be visible before the server is started so the test
will always see the file after server starts up and lets mounts finish.

Signed-off-by: Zach Brown <zab@versity.com>
This commit is contained in:
Zach Brown
2022-03-15 15:07:57 -07:00
parent 57a1d75e52
commit 38e5aa77c4
1 changed files with 22 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
kmod/src/quorum.c
+22 -4
View File
@@ -609,6 +609,21 @@ out:
return ret;
}
/*
* The main quorum task maintains its private status. It seemed cleaner
* to occasionally copy the status for showing in sysfs/debugfs files
* than to have the two lock access to shared status. The show copy is
* updated after being modified before the quorum task sleeps for a
* significant amount of time, either waiting on timeouts or interacting
* with the server.
*/
static void update_show_status(struct quorum_info *qinf, struct quorum_status *qst)
{
spin_lock(&qinf->show_lock);
qinf->show_status = *qst;
spin_unlock(&qinf->show_lock);
}
/*
* The quorum work always runs in the background of quorum member
* mounts. It's responsible for starting and stopping the server if
@@ -651,6 +666,8 @@ static void scoutfs_quorum_worker(struct work_struct *work)
while (!(qinf->shutdown || scoutfs_forcing_unmount(sb))) {
update_show_status(qinf, &qst);
ret = recv_msg(sb, &msg, qst.timeout);
if (ret < 0) {
if (ret != -ETIMEDOUT && ret != -EAGAIN) {
@@ -681,10 +698,6 @@ static void scoutfs_quorum_worker(struct work_struct *work)
scoutfs_inc_counter(sb, quorum_send_resignation);
}
spin_lock(&qinf->show_lock);
qinf->show_status = qst;
spin_unlock(&qinf->show_lock);
trace_scoutfs_quorum_loop(sb, qst.role, qst.term, qst.vote_for,
qst.vote_bits,
ktime_to_timespec64(qst.timeout));
@@ -695,6 +708,7 @@ static void scoutfs_quorum_worker(struct work_struct *work)
if (qst.role == LEADER) {
scoutfs_warn(sb, "saw msg type %u from %u for term %llu while leader in term %llu, shutting down server.",
msg.type, msg.from, msg.term, qst.term);
update_show_status(qinf, &qst);
scoutfs_server_stop(sb);
}
qst.role = FOLLOWER;
@@ -758,6 +772,8 @@ static void scoutfs_quorum_worker(struct work_struct *work)
qst.term);
qst.timeout = heartbeat_interval();
update_show_status(qinf, &qst);
/* record that we've been elected before starting up server */
ret = update_quorum_block(sb, SCOUTFS_QUORUM_EVENT_ELECT, qst.term, true);
if (ret < 0)
@@ -817,6 +833,8 @@ static void scoutfs_quorum_worker(struct work_struct *work)
}
}
update_show_status(qinf, &qst);
/* always try to stop a running server as we stop */
if (test_bit(QINF_FLAG_SERVER, &qinf->flags)) {
scoutfs_server_stop(sb);