performance/io-threads: Modify the conditions for triggering watchdog…

[jifengzhou]

… protection

The io-threads watchdog will cause the glusterfsd to terminate when the brick load is high

Fixes: #3468 Signed-off-by: Jifeng Zhou [email protected]

[gluster-ant]

Can one of the admins verify this patch?

[gluster-ant]

Can one of the admins verify this patch?

[gluster-ant]

Can one of the admins verify this patch?

[harshita-shree]

/run regression

[gluster-ant]

1 test(s) failed ./tests/bugs/replicate/issue-1254-prioritize-enospc.t

0 test(s) generated core

6 test(s) needed retry ./tests/000-flaky/basic_afr_split-brain-favorite-child-policy.t ./tests/000-flaky/basic_mount-nfs-auth.t ./tests/000-flaky/bugs_core_multiplex-limit-issue-151.t ./tests/000-flaky/bugs_nfs_bug-1116503.t ./tests/bugs/replicate/bug-1341650.t ./tests/bugs/replicate/issue-1254-prioritize-enospc.t

2 flaky test(s) marked as success even though they failed ./tests/000-flaky/basic_mount-nfs-auth.t ./tests/000-flaky/bugs_nfs_bug-1116503.t https://build.gluster.org/job/gh_centos7-regression/2437/

[jifengzhou]

@harshita-shree It feels like this test error has nothing to do with the merge I submitted. How to fix this error next? thanks

[harshita-shree]

/run regression

[gluster-ant]

1 test(s) failed ./tests/bugs/glusterd/brick-order-check-add-brick.t

0 test(s) generated core

4 test(s) needed retry ./tests/000-flaky/basic_afr_split-brain-favorite-child-policy.t ./tests/000-flaky/basic_mount-nfs-auth.t ./tests/000-flaky/bugs_nfs_bug-1116503.t ./tests/bugs/glusterd/brick-order-check-add-brick.t

2 flaky test(s) marked as success even though they failed ./tests/000-flaky/basic_mount-nfs-auth.t ./tests/000-flaky/bugs_nfs_bug-1116503.t https://build.gluster.org/job/gh_centos7-regression/2462/

[jifengzhou]

@harshita-shree Excuse me, why does Jenkins test fail frequently? I also encountered this situation several times in the PR I submitted before. It takes several "/run regression" to pass all of them.

[gluster-ant]

CLANG-FORMAT FAILURE: Before merging the patch, this diff needs to be considered for passing clang-format

old mode 100755
new mode 100644
index 070ae3ac2..644e2e575
--- a/xlators/performance/io-threads/src/io-threads.c
+++ b/xlators/performance/io-threads/src/io-threads.c
@@ -1074,15 +1074,16 @@ iot_watchdog(void *arg)
             }
 
             high_count = 0;
-            for (j = 0; j < i; j++ ) {
+            for (j = 0; j < i; j++) {
                 high_count += fop_data->queue_sizes;
             }
-            gf_log(this->name, GF_LOG_DEBUG, "the length of the higher priority queue: %d", high_count);
+            gf_log(this->name, GF_LOG_DEBUG,
+                   "the length of the higher priority queue: %d", high_count);
 
             /*
              * When the number of running threads is greater than
              * the total number of thread queues with higher priority,
-             * we consider that the fop request of the current 
+             * we consider that the fop request of the current
              * priority queue can be executed.
              */
             if ((priv->curr_count - priv->sleep_count) > high_count) {

[stale[bot]]

Thank you for your contributions. Noticed that this issue is not having any activity in last ~6 months! We are marking this issue as stale because it has not had recent activity. It will be closed in 2 weeks if no one responds with a comment here.

[stale[bot]]

Closing this issue as there was no update since my last update on issue. If this is an issue which is still valid, feel free to open it.