[tarantool-patches] [PATCH v2 2/2] swim: be suspicious when add new member
Vladislav Shpilevoy
v.shpilevoy at tarantool.org
Sun Jun 30 23:01:56 MSK 2019
The previous commit solves one important problem with too long
event dissemination. Events could for too long time occupy the
whole UDP packet. Now they live log() time, but 'dead' and 'left'
members were bound to TTD. Such members were deleted after TTD
is 0.
Now they are deleted to early. Cluster nodes too early forget
about dead ones, and nodes not aware of death of the latters, can
accidentally resurrect them via anti-entropy. Cluster nodes need
to be suspicious when someone tells them to add a new not dead
member.
This patch makes SWIM add a new member in two cases only: manually
and if an ACK was received from it. A new member can't be added
indirectly via events and anti-entropy anymore. Instead, a ping is
sent to the members who are said to be new and alive. If ACK is
received directly from them, then they are added.
The patch does not affect updates. They are still indirect,
because if something has updated in an existing member, then it
is definitely alive.
Part of #4253
---
src/lib/swim/swim.c | 29 ++++++++++++++++++++++++++---
test/unit/swim.c | 11 ++++-------
test/unit/swim.result | 17 +++++++++++------
3 files changed, 41 insertions(+), 16 deletions(-)
diff --git a/src/lib/swim/swim.c b/src/lib/swim/swim.c
index 9647094f5..6fbac00ec 100644
--- a/src/lib/swim/swim.c
+++ b/src/lib/swim/swim.c
@@ -1510,6 +1510,10 @@ swim_update_member(struct swim *swim, const struct swim_member_def *def,
* @param swim SWIM instance to upsert into.
* @param def Member definition to build a new member or update an
* existing one.
+ * @param is_direct True, if the member definition was received
+ * directly from that member. Via ping or ack from him.
+ * Otherwise the definition can't be trusted, if it states,
+ * that a new member should be added.
* @param[out] result A result member: a new, or an updated, or
* NULL in case of nothing has changed. For example, @a def
* was too old.
@@ -1520,7 +1524,7 @@ swim_update_member(struct swim *swim, const struct swim_member_def *def,
*/
static int
swim_upsert_member(struct swim *swim, const struct swim_member_def *def,
- struct swim_member **result)
+ bool is_direct, struct swim_member **result)
{
struct swim_member *member = swim_find_member(swim, &def->uuid);
if (member == NULL) {
@@ -1538,6 +1542,25 @@ swim_upsert_member(struct swim *swim, const struct swim_member_def *def,
* forever.
*/
goto skip;
+ } else if (def->status < MEMBER_DEAD && ! is_direct) {
+ /*
+ * If a member is not dead, then it can't
+ * be added as simple as that. In fact it
+ * can be already dead, but sender of that
+ * definition didn't know that. The only
+ * way to be sure - send him a ping. And
+ * one exception - if the sender of the
+ * definition is exactly that member, then
+ * it can be trusted of course.
+ */
+ struct swim_task *t = swim_task_new(swim_task_delete_cb,
+ swim_task_delete_cb,
+ "probe ping");
+ if (t == NULL)
+ return -1;
+ swim_send_ping(swim, t, &def->addr);
+ *result = NULL;
+ return 0;
}
*result = swim_new_member(swim, &def->addr, &def->uuid,
def->status, &def->incarnation,
@@ -1597,7 +1620,7 @@ swim_process_members(struct swim *swim, const char *prefix,
struct swim_member *member;
if (swim_member_def_decode(&def, pos, end, prefix) != 0)
return -1;
- if (swim_upsert_member(swim, &def, &member) != 0) {
+ if (swim_upsert_member(swim, &def, false, &member) != 0) {
/*
* Not a critical error. Other members
* still can be updated.
@@ -1639,7 +1662,7 @@ swim_process_failure_detection(struct swim *swim, const char **pos,
mdef.incarnation = def.incarnation;
mdef.uuid = *uuid;
struct swim_member *member;
- if (swim_upsert_member(swim, &mdef, &member) != 0)
+ if (swim_upsert_member(swim, &mdef, true, &member) != 0)
return -1;
/*
* It can be NULL, for example, in case of too old
diff --git a/test/unit/swim.c b/test/unit/swim.c
index d776a8231..db9441157 100644
--- a/test/unit/swim.c
+++ b/test/unit/swim.c
@@ -254,7 +254,7 @@ swim_test_add_remove(void)
static void
swim_test_basic_failure_detection(void)
{
- swim_start_test(9);
+ swim_start_test(8);
struct swim_cluster *cluster = swim_cluster_new(2);
swim_cluster_set_ack_timeout(cluster, 0.5);
@@ -275,11 +275,8 @@ swim_test_basic_failure_detection(void)
"but it is dead after one more");
swim_run_for(1);
- is(swim_cluster_member_status(cluster, 0, 1), MEMBER_DEAD, "after 2 "\
- "more unacks the member still is not deleted - dissemination TTD "\
- "keeps it");
is(swim_cluster_wait_status(cluster, 0, 1, swim_member_status_MAX, 2),
- 0, "but it is dropped after 2 rounds when TTD gets 0");
+ 0, "it is dropped after one more round when TTD gets 0");
/*
* After IO unblock pending messages will be processed all
@@ -584,12 +581,12 @@ swim_test_quit(void)
swim_cluster_interconnect(cluster, 1, 2);
swim_cluster_quit_node(cluster, 0);
- swim_run_for(2);
+ swim_run_for(1);
is(swim_cluster_member_status(cluster, 2, 0), MEMBER_LEFT,
"S3 sees S1 as left");
is(swim_cluster_member_status(cluster, 1, 0), swim_member_status_MAX,
"S2 does not see S1 at all");
- swim_run_for(2);
+ swim_run_for(1);
is(swim_cluster_member_status(cluster, 2, 0), swim_member_status_MAX,
"after more time S1 is dropped from S3");
is(swim_cluster_member_status(cluster, 1, 0), swim_member_status_MAX,
diff --git a/test/unit/swim.result b/test/unit/swim.result
index 04a2778e6..1fde80132 100644
--- a/test/unit/swim.result
+++ b/test/unit/swim.result
@@ -1,5 +1,5 @@
*** main_f ***
-1..22
+1..23
*** swim_test_one_link ***
1..6
ok 1 - no rounds - no fullmesh
@@ -65,16 +65,15 @@ ok 4 - subtests
ok 5 - subtests
*** swim_test_add_remove: done ***
*** swim_test_basic_failure_detection ***
- 1..9
+ 1..8
ok 1 - node is added as alive
ok 2 - member still is not suspected after 1 noack
ok 3 - but it is suspected after one more
ok 4 - it is not dead after 2 more noacks
ok 5 - but it is dead after one more
- ok 6 - after 2 more unacks the member still is not deleted - dissemination TTD keeps it
- ok 7 - but it is dropped after 2 rounds when TTD gets 0
- ok 8 - fullmesh is restored
- ok 9 - a member is added back on an ACK
+ ok 6 - it is dropped after one more round when TTD gets 0
+ ok 7 - fullmesh is restored
+ ok 8 - a member is added back on an ACK
ok 6 - subtests
*** swim_test_basic_failure_detection: done ***
*** swim_test_probe ***
@@ -237,4 +236,10 @@ ok 21 - subtests
ok 3 - S2 sees new generation of S1
ok 22 - subtests
*** swim_test_generation: done ***
+ *** swim_test_dissemination_speed ***
+ 1..2
+ ok 1 - dissemination work in log time even at the very start of a cluster
+ ok 2 - dissemination can withstand an event storm
+ok 23 - subtests
+ *** swim_test_dissemination_speed: done ***
*** main_f: done ***
--
2.20.1 (Apple Git-117)
More information about the Tarantool-patches
mailing list