[PATCH] box: serialize calls to box.cfg
Vladimir Davydov
vdavydov.dev at gmail.com
Tue Aug 7 12:43:26 MSK 2018
It is dangerous to call box.cfg() concurrently from different fibers.
For example, replication configuration uses static variables and yields
so calling it concurrently can result in a crash. To make sure it never
happens, let's protect box.cfg() with a lock.
Closes #3606
---
https://github.com/tarantool/tarantool/issues/3606
https://github.com/tarantool/tarantool/tree/dv/gh-3606-concurrent-replication-cfg-fix
src/box/lua/load_cfg.lua | 21 ++++++++++++++++++---
test/replication/misc.result | 24 ++++++++++++++++++++++++
test/replication/misc.test.lua | 10 ++++++++++
3 files changed, 52 insertions(+), 3 deletions(-)
diff --git a/src/box/lua/load_cfg.lua b/src/box/lua/load_cfg.lua
index 0b668cdc..4de79220 100644
--- a/src/box/lua/load_cfg.lua
+++ b/src/box/lua/load_cfg.lua
@@ -5,6 +5,21 @@ local json = require('json')
local private = require('box.internal')
local urilib = require('uri')
local math = require('math')
+local fiber = require('fiber')
+
+-- Function decorator that is used to prevent box.cfg() from
+-- being called concurrently by different fibers.
+local lock = fiber.channel(1)
+local function locked(f)
+ return function(...)
+ lock:put(true)
+ local status = pcall(f, ...)
+ lock:get()
+ if not status then
+ box.error()
+ end
+ end
+end
-- all available options
local default_cfg = {
@@ -409,7 +424,7 @@ local function load_cfg(cfg)
-- Save new box.cfg
box.cfg = cfg
if not pcall(private.cfg_check) then
- box.cfg = load_cfg -- restore original box.cfg
+ box.cfg = locked(load_cfg) -- restore original box.cfg
return box.error() -- re-throw exception from check_cfg()
end
-- Restore box members after initial configuration
@@ -423,7 +438,7 @@ local function load_cfg(cfg)
__newindex = function(table, index)
error('Attempt to modify a read-only table')
end,
- __call = reload_cfg,
+ __call = locked(reload_cfg),
})
private.cfg_load()
for key, fun in pairs(dynamic_cfg) do
@@ -439,7 +454,7 @@ local function load_cfg(cfg)
box.schema.upgrade{auto = true}
end
end
-box.cfg = load_cfg
+box.cfg = locked(load_cfg)
-- gh-810:
-- hack luajit default cpath
diff --git a/test/replication/misc.result b/test/replication/misc.result
index ff0dbf54..9d9d010c 100644
--- a/test/replication/misc.result
+++ b/test/replication/misc.result
@@ -23,6 +23,30 @@ box.cfg{replication = {'127.0.0.1:12345', box.cfg.listen}}
- error: 'Incorrect value for option ''replication'': failed to connect to one or
more replicas'
...
+-- gh-3606 - Tarantool crashes if box.cfg.replication is updated concurrently
+fiber = require('fiber')
+---
+...
+c = fiber.channel(2)
+---
+...
+f = function() fiber.create(function() pcall(box.cfg, {replication = {12345}}) c:put(true) end) end
+---
+...
+f()
+---
+...
+f()
+---
+...
+c:get()
+---
+- true
+...
+c:get()
+---
+- true
+...
box.cfg{replication_timeout = replication_timeout, replication_connect_timeout = replication_connect_timeout}
---
...
diff --git a/test/replication/misc.test.lua b/test/replication/misc.test.lua
index c05e5216..da5a9023 100644
--- a/test/replication/misc.test.lua
+++ b/test/replication/misc.test.lua
@@ -9,6 +9,16 @@ replication_timeout = box.cfg.replication_timeout
replication_connect_timeout = box.cfg.replication_connect_timeout
box.cfg{replication_timeout=0.05, replication_connect_timeout=0.05, replication={}}
box.cfg{replication = {'127.0.0.1:12345', box.cfg.listen}}
+
+-- gh-3606 - Tarantool crashes if box.cfg.replication is updated concurrently
+fiber = require('fiber')
+c = fiber.channel(2)
+f = function() fiber.create(function() pcall(box.cfg, {replication = {12345}}) c:put(true) end) end
+f()
+f()
+c:get()
+c:get()
+
box.cfg{replication_timeout = replication_timeout, replication_connect_timeout = replication_connect_timeout}
-- gh-3111 - Allow to rebootstrap a replica from a read-only master
--
2.11.0
More information about the Tarantool-patches
mailing list