From 8f1a849968242aa3c53a05fbf1b0647a905e9cdd Mon Sep 17 00:00:00 2001
From: Atin Mukherjee <amukherj@redhat.com>
Date: Thu, 23 Aug 2018 12:12:36 +0530
Subject: [PATCH 358/359] glusterd: glusterd_brick_start shouldn't try to bring
up brick if only_connect is true
With the latest refactoring in glusterd_brick_start () function in case
we run into a situation where is_gf_service_running () return a valid
pid which is running but doesn't belong to a gluster process, even in
case of only_connect flag passed as gf_true we'd end up trying to start
a brick which would cause a deadlock in brick multiplexing as both
glusterd_restart_bricks () and glusterd_do_volume_quorum_action () would
cause context switching with each other for the same brick. The
following bt shows the same:
(gdb) t a a bt
Thread 8 (Thread 0x7fcced48a700 (LWP 11959)):
srch_vol=srch_vol@entry=0xbe0410, comp_vol=comp_vol@entry=0xc03680,
brickinfo=brickinfo@entry=0xc14ef0) at glusterd-utils.c:5834
brickinfo=0xc14ef0, volinfo=0xc03680, conf=<optimized out>)
at glusterd-utils.c:5902
brickinfo=brickinfo@entry=0xc14ef0, wait=wait@entry=_gf_false,
only_connect=only_connect@entry=_gf_true) at glusterd-utils.c:6251
volinfo=0xc03680, meets_quorum=_gf_true) at glusterd-server-quorum.c:402
at glusterd-server-quorum.c:443
iov=iov@entry=0x7fcce0004040, count=count@entry=1,
myframe=myframe@entry=0x7fcce00023a0) at glusterd-rpc-ops.c:542
iov=0x7fcce0004040, count=1, myframe=0x7fcce00023a0,
fn=0x7fccf12403d0 <__glusterd_friend_add_cbk>) at glusterd-rpc-ops.c:223
---Type <return> to continue, or q <return> to quit---
at rpc-transport.c:538
Thread 7 (Thread 0x7fccedc8b700 (LWP 11958)):
Thread 6 (Thread 0x7fccf1d67700 (LWP 11877)):
brickinfo=brickinfo@entry=0xc14ef0) at glusterd-utils.c:5834
at glusterd-utils.c:6251
Thread 5 (Thread 0x7fccf2568700 (LWP 11876)):
Thread 4 (Thread 0x7fccf2d69700 (LWP 11875)):
Thread 3 (Thread 0x7fccf356a700 (LWP 11874)):
Thread 2 (Thread 0x7fccf3d6b700 (LWP 11873)):
---Type <return> to continue, or q <return> to quit---
Thread 1 (Thread 0x7fccf68a8780 (LWP 11872)):
Fix:
The solution is to ensure we don't restart bricks if only_connect is
true and just ensure that the brick is attempted to be connected.
Test:
Simulated a code change to ensure gf_is_service_running () always return
to true to hit the scenario.
>upstream patch : https://review.gluster.org/#/c/glusterfs/+/20935
>Change-Id: Iec184e6c9e8aabef931d310f931f4d7a580f0f48
>Fixes: bz#1620544
>Signed-off-by: Atin Mukherjee <amukherj@redhat.com>
Change-Id: Iec184e6c9e8aabef931d310f931f4d7a580f0f48
BUG: 1620469
Signed-off-by: Atin Mukherjee <amukherj@redhat.com>
Reviewed-on: https://code.engineering.redhat.com/gerrit/147888
Tested-by: RHGS Build Bot <nigelb@redhat.com>
Reviewed-by: Sunil Kumar Heggodu Gopala Acharya <sheggodu@redhat.com>
---
xlators/mgmt/glusterd/src/glusterd-utils.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/xlators/mgmt/glusterd/src/glusterd-utils.c b/xlators/mgmt/glusterd/src/glusterd-utils.c
index 136a032..b9e8d8d 100644
--- a/xlators/mgmt/glusterd/src/glusterd-utils.c
+++ b/xlators/mgmt/glusterd/src/glusterd-utils.c
@@ -6173,6 +6173,8 @@ glusterd_brick_start (glusterd_volinfo_t *volinfo,
if (sys_access (pidfile , R_OK) == 0) {
sys_unlink (pidfile);
}
+ if (only_connect)
+ return 0;
goto run;
}
GF_FREE (brickpath);
@@ -6187,6 +6189,8 @@ glusterd_brick_start (glusterd_volinfo_t *volinfo,
if (sys_access (pidfile , R_OK) == 0) {
sys_unlink (pidfile);
}
+ if (only_connect)
+ return 0;
goto run;
}
}
--
1.8.3.1