* [tarantool-patches] [PATCH v2] vshard reload mechanism
@ 2018-07-23 11:14 AKhatskevich
2018-07-23 11:14 ` [tarantool-patches] [PATCH 1/4] Add test on error during reconfigure AKhatskevich
` (3 more replies)
0 siblings, 4 replies; 14+ messages in thread
From: AKhatskevich @ 2018-07-23 11:14 UTC (permalink / raw)
To: v.shpilevoy, tarantool-patches
Issue1: https://github.com/tarantool/vshard/issues/112
Issue2: https://github.com/tarantool/vshard/issues/125
Branch: https://github.com/tarantool/vshard/tree/kh/gh-112-reload-mt-2
This patcheset improves vshard reload mechanism.
AKhatskevich (4):
Add test on error during reconfigure
Complete module reload
Tests: separate bootstrap routine to a lua_libs
Introduce storage reload evolution
.travis.yml | 2 +-
rpm/prebuild.sh | 2 +
test/lua_libs/bootstrap_test_storage.lua | 50 +++++
test/lua_libs/git_util.lua | 51 +++++
test/lua_libs/util.lua | 44 ++++
test/rebalancer/box_1_a.lua | 47 +---
test/rebalancer/errinj.result | 2 +-
test/rebalancer/errinj.test.lua | 2 +-
test/rebalancer/rebalancer.result | 2 +-
test/rebalancer/rebalancer.test.lua | 2 +-
test/rebalancer/rebalancer_lock_and_pin.result | 2 +-
test/rebalancer/rebalancer_lock_and_pin.test.lua | 2 +-
test/rebalancer/restart_during_rebalancing.result | 2 +-
.../rebalancer/restart_during_rebalancing.test.lua | 2 +-
test/rebalancer/stress_add_remove_rs.result | 2 +-
test/rebalancer/stress_add_remove_rs.test.lua | 2 +-
.../rebalancer/stress_add_remove_several_rs.result | 2 +-
.../stress_add_remove_several_rs.test.lua | 2 +-
test/rebalancer/suite.ini | 2 +-
test/reload_evolution/storage.result | 248 +++++++++++++++++++++
test/reload_evolution/storage.test.lua | 88 ++++++++
test/reload_evolution/storage_1_a.lua | 48 ++++
test/reload_evolution/storage_1_b.lua | 1 +
test/reload_evolution/storage_2_a.lua | 1 +
test/reload_evolution/storage_2_b.lua | 1 +
test/reload_evolution/suite.ini | 6 +
test/reload_evolution/test.lua | 9 +
test/router/reload.result | 126 +++++++++++
test/router/reload.test.lua | 36 +++
test/router/router.result | 33 ++-
test/router/router.test.lua | 9 +
test/storage/reload.result | 29 +++
test/storage/reload.test.lua | 10 +
test/storage/storage.result | 39 ++++
test/storage/storage.test.lua | 12 +
test/unit/reload_evolution.result | 45 ++++
test/unit/reload_evolution.test.lua | 18 ++
vshard/cfg.lua | 5 +
vshard/error.lua | 5 +
vshard/replicaset.lua | 102 +++++++--
vshard/router/init.lua | 54 +++--
vshard/storage/init.lua | 65 ++++--
vshard/storage/reload_evolution.lua | 58 +++++
vshard/util.lua | 20 ++
44 files changed, 1177 insertions(+), 113 deletions(-)
create mode 100644 test/lua_libs/bootstrap_test_storage.lua
create mode 100644 test/lua_libs/git_util.lua
create mode 100644 test/reload_evolution/storage.result
create mode 100644 test/reload_evolution/storage.test.lua
create mode 100755 test/reload_evolution/storage_1_a.lua
create mode 120000 test/reload_evolution/storage_1_b.lua
create mode 120000 test/reload_evolution/storage_2_a.lua
create mode 120000 test/reload_evolution/storage_2_b.lua
create mode 100644 test/reload_evolution/suite.ini
create mode 100644 test/reload_evolution/test.lua
create mode 100644 test/unit/reload_evolution.result
create mode 100644 test/unit/reload_evolution.test.lua
create mode 100644 vshard/storage/reload_evolution.lua
--
2.14.1
^ permalink raw reply [flat|nested] 14+ messages in thread
* [tarantool-patches] [PATCH 1/4] Add test on error during reconfigure
2018-07-23 11:14 [tarantool-patches] [PATCH v2] vshard reload mechanism AKhatskevich
@ 2018-07-23 11:14 ` AKhatskevich
2018-07-23 13:18 ` [tarantool-patches] " Vladislav Shpilevoy
2018-07-23 11:14 ` [tarantool-patches] [PATCH 2/4] Complete module reload AKhatskevich
` (2 subsequent siblings)
3 siblings, 1 reply; 14+ messages in thread
From: AKhatskevich @ 2018-07-23 11:14 UTC (permalink / raw)
To: v.shpilevoy, tarantool-patches
In case reconfigure process fails, the node should continue
work properly.
---
test/lua_libs/util.lua | 24 ++++++++++++++++++++++++
test/router/router.result | 30 ++++++++++++++++++++++++++++++
test/router/router.test.lua | 9 +++++++++
test/storage/storage.result | 39 +++++++++++++++++++++++++++++++++++++++
test/storage/storage.test.lua | 12 ++++++++++++
vshard/router/init.lua | 7 +++++++
vshard/storage/init.lua | 9 +++++++++
7 files changed, 130 insertions(+)
diff --git a/test/lua_libs/util.lua b/test/lua_libs/util.lua
index f2d3b48..f40d3a6 100644
--- a/test/lua_libs/util.lua
+++ b/test/lua_libs/util.lua
@@ -69,9 +69,33 @@ local function wait_master(test_run, replicaset, master)
log.info('Slaves are connected to a master "%s"', master)
end
+--
+-- Check that data has at least all etalon's fields and they are
+-- equal.
+-- @param etalon Table which fields should be found in `data`.
+-- @param data Table which is checked against `etalon`.
+--
+-- @retval Boolean indicator of equality and if is not equal, then
+-- table of names of fields which are different in `data`.
+--
+local function has_same_fields(etalon, data)
+ assert(type(etalon) == 'table' and type(data) == 'table')
+ local diff = {}
+ for k, v in pairs(etalon) do
+ if v ~= data[k] then
+ table.insert(diff, k)
+ end
+ end
+ if #diff > 0 then
+ return false, diff
+ end
+ return true
+end
+
return {
check_error = check_error,
shuffle_masters = shuffle_masters,
collect_timeouts = collect_timeouts,
wait_master = wait_master,
+ has_same_fields = has_same_fields,
}
diff --git a/test/router/router.result b/test/router/router.result
index 15f4fd0..4919962 100644
--- a/test/router/router.result
+++ b/test/router/router.result
@@ -1156,6 +1156,36 @@ util.check_error(vshard.router.cfg, non_dynamic_cfg)
---
- Non-dynamic option shard_index cannot be reconfigured
...
+-- Error during reconfigure process.
+vshard.router.route(1):callro('echo', {'some_data'})
+---
+- some_data
+- null
+- null
+...
+vshard.router.internal.errinj.ERRINJ_CFG = true
+---
+...
+old_internal = table.copy(vshard.router.internal)
+---
+...
+util.check_error(vshard.router.cfg, cfg)
+---
+- 'Error injection: cfg'
+...
+vshard.router.internal.errinj.ERRINJ_CFG = false
+---
+...
+util.has_same_fields(old_internal, vshard.router.internal)
+---
+- true
+...
+vshard.router.route(1):callro('echo', {'some_data'})
+---
+- some_data
+- null
+- null
+...
_ = test_run:cmd("switch default")
---
...
diff --git a/test/router/router.test.lua b/test/router/router.test.lua
index 8006e5d..df2f381 100644
--- a/test/router/router.test.lua
+++ b/test/router/router.test.lua
@@ -444,6 +444,15 @@ non_dynamic_cfg = table.copy(cfg)
non_dynamic_cfg.shard_index = 'non_default_name'
util.check_error(vshard.router.cfg, non_dynamic_cfg)
+-- Error during reconfigure process.
+vshard.router.route(1):callro('echo', {'some_data'})
+vshard.router.internal.errinj.ERRINJ_CFG = true
+old_internal = table.copy(vshard.router.internal)
+util.check_error(vshard.router.cfg, cfg)
+vshard.router.internal.errinj.ERRINJ_CFG = false
+util.has_same_fields(old_internal, vshard.router.internal)
+vshard.router.route(1):callro('echo', {'some_data'})
+
_ = test_run:cmd("switch default")
test_run:drop_cluster(REPLICASET_2)
diff --git a/test/storage/storage.result b/test/storage/storage.result
index 4399ff0..ff07fe9 100644
--- a/test/storage/storage.result
+++ b/test/storage/storage.result
@@ -732,6 +732,45 @@ util.check_error(vshard.storage.cfg, non_dynamic_cfg, names.storage_1_a)
---
- Non-dynamic option bucket_count cannot be reconfigured
...
+-- Error during reconfigure process.
+_, rs = next(vshard.storage.internal.replicasets)
+---
+...
+rs:callro('echo', {'some_data'})
+---
+- some_data
+- null
+- null
+...
+vshard.storage.internal.errinj.ERRINJ_CFG = true
+---
+...
+old_internal = table.copy(vshard.storage.internal)
+---
+...
+_, err = pcall(vshard.storage.cfg, cfg, names.storage_1_a)
+---
+...
+err:match('Error injection:.*')
+---
+- 'Error injection: cfg'
+...
+vshard.storage.internal.errinj.ERRINJ_CFG = false
+---
+...
+util.has_same_fields(old_internal, vshard.storage.internal)
+---
+- true
+...
+_, rs = next(vshard.storage.internal.replicasets)
+---
+...
+rs:callro('echo', {'some_data'})
+---
+- some_data
+- null
+- null
+...
_ = test_run:cmd("switch default")
---
...
diff --git a/test/storage/storage.test.lua b/test/storage/storage.test.lua
index 72564e1..04bb608 100644
--- a/test/storage/storage.test.lua
+++ b/test/storage/storage.test.lua
@@ -182,6 +182,18 @@ non_dynamic_cfg = table.copy(cfg)
non_dynamic_cfg.bucket_count = require('vshard.consts').DEFAULT_BUCKET_COUNT + 1
util.check_error(vshard.storage.cfg, non_dynamic_cfg, names.storage_1_a)
+-- Error during reconfigure process.
+_, rs = next(vshard.storage.internal.replicasets)
+rs:callro('echo', {'some_data'})
+vshard.storage.internal.errinj.ERRINJ_CFG = true
+old_internal = table.copy(vshard.storage.internal)
+_, err = pcall(vshard.storage.cfg, cfg, names.storage_1_a)
+err:match('Error injection:.*')
+vshard.storage.internal.errinj.ERRINJ_CFG = false
+util.has_same_fields(old_internal, vshard.storage.internal)
+_, rs = next(vshard.storage.internal.replicasets)
+rs:callro('echo', {'some_data'})
+
_ = test_run:cmd("switch default")
test_run:drop_cluster(REPLICASET_2)
diff --git a/vshard/router/init.lua b/vshard/router/init.lua
index 4531f3a..a143070 100644
--- a/vshard/router/init.lua
+++ b/vshard/router/init.lua
@@ -11,6 +11,7 @@ local M = rawget(_G, '__module_vshard_router')
if not M then
M = {
errinj = {
+ ERRINJ_CFG = false,
ERRINJ_FAILOVER_CHANGE_CFG = false,
ERRINJ_RELOAD = false,
ERRINJ_LONG_DISCOVERY = false,
@@ -486,6 +487,12 @@ local function router_cfg(cfg)
for k, v in pairs(cfg) do
log.info({[k] = v})
end
+ -- It is considered that all possible errors during cfg
+ -- process occur only before this place.
+ -- This check should be placed as late as possible.
+ if M.errinj.ERRINJ_CFG then
+ error('Error injection: cfg')
+ end
box.cfg(cfg)
log.info("Box has been configured")
M.total_bucket_count = total_bucket_count
diff --git a/vshard/storage/init.lua b/vshard/storage/init.lua
index ff204a4..052e94f 100644
--- a/vshard/storage/init.lua
+++ b/vshard/storage/init.lua
@@ -33,6 +33,7 @@ if not M then
-- Bucket count stored on all replicasets.
total_bucket_count = 0,
errinj = {
+ ERRINJ_CFG = false,
ERRINJ_BUCKET_FIND_GARBAGE_DELAY = false,
ERRINJ_RELOAD = false,
ERRINJ_CFG_DELAY = false,
@@ -1560,6 +1561,14 @@ local function storage_cfg(cfg, this_replica_uuid)
local shard_index = cfg.shard_index
local collect_bucket_garbage_interval = cfg.collect_bucket_garbage_interval
local collect_lua_garbage = cfg.collect_lua_garbage
+
+ -- It is considered that all possible errors during cfg
+ -- process occur only before this place.
+ -- This check should be placed as late as possible.
+ if M.errinj.ERRINJ_CFG then
+ error('Error injection: cfg')
+ end
+
--
-- Sync timeout is a special case - it must be updated before
-- all other options to allow a user to demote a master with
--
2.14.1
^ permalink raw reply [flat|nested] 14+ messages in thread
* [tarantool-patches] [PATCH 2/4] Complete module reload
2018-07-23 11:14 [tarantool-patches] [PATCH v2] vshard reload mechanism AKhatskevich
2018-07-23 11:14 ` [tarantool-patches] [PATCH 1/4] Add test on error during reconfigure AKhatskevich
@ 2018-07-23 11:14 ` AKhatskevich
2018-07-23 13:31 ` [tarantool-patches] " Vladislav Shpilevoy
2018-07-23 11:14 ` [tarantool-patches] [PATCH 3/4] Tests: separate bootstrap routine to a lua_libs AKhatskevich
2018-07-23 11:14 ` [tarantool-patches] [PATCH 4/4] Introduce storage reload evolution AKhatskevich
3 siblings, 1 reply; 14+ messages in thread
From: AKhatskevich @ 2018-07-23 11:14 UTC (permalink / raw)
To: v.shpilevoy, tarantool-patches
In case one need to upgrade vshard to a new version, this commit
improves reload mechanism to allow to do that for a wider variety of
possible changes (between two versions).
Changes:
* introduce cfg option `connection_outdate_delay`
* improve reload mechanism
* add `util.async_task` method, which runs a function after a
delay
* delete replicaset:rebind_connections method as it is replaced
with `rebind_replicasets` which updates all replicasets at once
Reload mechanism:
* reload all vshard modules
* create new `replicaset` and `replica` objects
* reuse old netbox connections in new replica objects if
possible
* update router/storage.internal table
* after a `connection_outdate_delay` disable old instances of
`replicaset` and `replica` objects
Reload works for modules:
* vshard.router
* vshard.storage
Here is a module reload algorithm:
* old vshard is working
* delete old vshard src
* install new vshard
* call: package.loaded['vshard.router'] = nil
* call: old_router = vshard.router -- Save working router copy.
* call: vshard.router = require('vshard.router')
* if require fails: continue using old_router
* if require succeeds: use vshard.router
In case reload process fails, old router/storage module, replicaset and
replica objects continue working properly. If reload succeeds, all old
objects would be deprecated.
Extra changes:
* introduce MODULE_INTERNALS which stores name of the module
internal data in the global namespace
Part of #112
---
test/router/reload.result | 126 +++++++++++++++++++++++++++++++++++++++++++
test/router/reload.test.lua | 36 +++++++++++++
test/router/router.result | 3 +-
test/storage/reload.result | 29 ++++++++++
test/storage/reload.test.lua | 10 ++++
vshard/cfg.lua | 5 ++
vshard/error.lua | 5 ++
vshard/replicaset.lua | 102 ++++++++++++++++++++++++++---------
vshard/router/init.lua | 47 +++++++++++-----
vshard/storage/init.lua | 45 ++++++++++------
vshard/util.lua | 20 +++++++
11 files changed, 373 insertions(+), 55 deletions(-)
diff --git a/test/router/reload.result b/test/router/reload.result
index 47f3c2e..88122aa 100644
--- a/test/router/reload.result
+++ b/test/router/reload.result
@@ -174,6 +174,132 @@ vshard.router.module_version()
check_reloaded()
---
...
+--
+-- Outdate old replicaset and replica objects.
+--
+rs = vshard.router.route(1)
+---
+...
+rs:callro('echo', {'some_data'})
+---
+- some_data
+- null
+- null
+...
+package.loaded["vshard.router"] = nil
+---
+...
+_ = require('vshard.router')
+---
+...
+-- Make sure outdate async task has had cpu time.
+while not rs.is_outdated do fiber.sleep(0.001) end
+---
+...
+rs.callro(rs, 'echo', {'some_data'})
+---
+- null
+- type: ShardingError
+ name: OBJECT_IS_OUTDATED
+ message: Object is outdated after module reload/reconfigure. Use new instance.
+ code: 20
+...
+vshard.router = require('vshard.router')
+---
+...
+rs = vshard.router.route(1)
+---
+...
+rs:callro('echo', {'some_data'})
+---
+- some_data
+- null
+- null
+...
+-- Test `connection_outdate_delay`.
+old_connection_delay = cfg.connection_outdate_delay
+---
+...
+cfg.connection_outdate_delay = 0.3
+---
+...
+vshard.router.cfg(cfg)
+---
+...
+cfg.connection_outdate_delay = old_connection_delay
+---
+...
+vshard.router.internal.connection_outdate_delay = nil
+---
+...
+rs_new = vshard.router.route(1)
+---
+...
+rs_old = rs
+---
+...
+_, replica_old = next(rs_old.replicas)
+---
+...
+rs_new:callro('echo', {'some_data'})
+---
+- some_data
+- null
+- null
+...
+-- Check old objets are still valid.
+rs_old:callro('echo', {'some_data'})
+---
+- some_data
+- null
+- null
+...
+replica_old.conn ~= nil
+---
+- true
+...
+fiber.sleep(0.2)
+---
+...
+rs_old:callro('echo', {'some_data'})
+---
+- some_data
+- null
+- null
+...
+replica_old.conn ~= nil
+---
+- true
+...
+replica_old.is_outdated == nil
+---
+- true
+...
+fiber.sleep(0.2)
+---
+...
+rs_old:callro('echo', {'some_data'})
+---
+- null
+- type: ShardingError
+ name: OBJECT_IS_OUTDATED
+ message: Object is outdated after module reload/reconfigure. Use new instance.
+ code: 20
+...
+replica_old.conn == nil
+---
+- true
+...
+replica_old.is_outdated == true
+---
+- true
+...
+rs_new:callro('echo', {'some_data'})
+---
+- some_data
+- null
+- null
+...
test_run:switch('default')
---
- true
diff --git a/test/router/reload.test.lua b/test/router/reload.test.lua
index af2939d..01b7163 100644
--- a/test/router/reload.test.lua
+++ b/test/router/reload.test.lua
@@ -86,6 +86,42 @@ _ = require('vshard.router')
vshard.router.module_version()
check_reloaded()
+--
+-- Outdate old replicaset and replica objects.
+--
+rs = vshard.router.route(1)
+rs:callro('echo', {'some_data'})
+package.loaded["vshard.router"] = nil
+_ = require('vshard.router')
+-- Make sure outdate async task has had cpu time.
+while not rs.is_outdated do fiber.sleep(0.001) end
+rs.callro(rs, 'echo', {'some_data'})
+vshard.router = require('vshard.router')
+rs = vshard.router.route(1)
+rs:callro('echo', {'some_data'})
+-- Test `connection_outdate_delay`.
+old_connection_delay = cfg.connection_outdate_delay
+cfg.connection_outdate_delay = 0.3
+vshard.router.cfg(cfg)
+cfg.connection_outdate_delay = old_connection_delay
+vshard.router.internal.connection_outdate_delay = nil
+rs_new = vshard.router.route(1)
+rs_old = rs
+_, replica_old = next(rs_old.replicas)
+rs_new:callro('echo', {'some_data'})
+-- Check old objets are still valid.
+rs_old:callro('echo', {'some_data'})
+replica_old.conn ~= nil
+fiber.sleep(0.2)
+rs_old:callro('echo', {'some_data'})
+replica_old.conn ~= nil
+replica_old.is_outdated == nil
+fiber.sleep(0.2)
+rs_old:callro('echo', {'some_data'})
+replica_old.conn == nil
+replica_old.is_outdated == true
+rs_new:callro('echo', {'some_data'})
+
test_run:switch('default')
test_run:cmd('stop server router_1')
test_run:cmd('cleanup server router_1')
diff --git a/test/router/router.result b/test/router/router.result
index 4919962..45394e1 100644
--- a/test/router/router.result
+++ b/test/router/router.result
@@ -1024,11 +1024,10 @@ error_messages
- - Use replicaset:callro(...) instead of replicaset.callro(...)
- Use replicaset:connect_master(...) instead of replicaset.connect_master(...)
- Use replicaset:connect_replica(...) instead of replicaset.connect_replica(...)
- - Use replicaset:rebind_connections(...) instead of replicaset.rebind_connections(...)
- Use replicaset:down_replica_priority(...) instead of replicaset.down_replica_priority(...)
- Use replicaset:call(...) instead of replicaset.call(...)
- - Use replicaset:up_replica_priority(...) instead of replicaset.up_replica_priority(...)
- Use replicaset:connect(...) instead of replicaset.connect(...)
+ - Use replicaset:up_replica_priority(...) instead of replicaset.up_replica_priority(...)
- Use replicaset:callrw(...) instead of replicaset.callrw(...)
- Use replicaset:connect_all(...) instead of replicaset.connect_all(...)
...
diff --git a/test/storage/reload.result b/test/storage/reload.result
index 531d984..b91b622 100644
--- a/test/storage/reload.result
+++ b/test/storage/reload.result
@@ -174,6 +174,35 @@ vshard.storage.module_version()
check_reloaded()
---
...
+--
+-- Outdate old replicaset and replica objects.
+--
+_, rs = next(vshard.storage.internal.replicasets)
+---
+...
+package.loaded["vshard.storage"] = nil
+---
+...
+_ = require('vshard.storage')
+---
+...
+rs.callro(rs, 'echo', {'some_data'})
+---
+- null
+- type: ShardingError
+ name: OBJECT_IS_OUTDATED
+ message: Object is outdated after module reload/reconfigure. Use new instance.
+ code: 20
+...
+_, rs = next(vshard.storage.internal.replicasets)
+---
+...
+rs.callro(rs, 'echo', {'some_data'})
+---
+- some_data
+- null
+- null
+...
test_run:switch('default')
---
- true
diff --git a/test/storage/reload.test.lua b/test/storage/reload.test.lua
index 64c3a60..9140299 100644
--- a/test/storage/reload.test.lua
+++ b/test/storage/reload.test.lua
@@ -87,6 +87,16 @@ _ = require('vshard.storage')
vshard.storage.module_version()
check_reloaded()
+--
+-- Outdate old replicaset and replica objects.
+--
+_, rs = next(vshard.storage.internal.replicasets)
+package.loaded["vshard.storage"] = nil
+_ = require('vshard.storage')
+rs.callro(rs, 'echo', {'some_data'})
+_, rs = next(vshard.storage.internal.replicasets)
+rs.callro(rs, 'echo', {'some_data'})
+
test_run:switch('default')
test_run:drop_cluster(REPLICASET_2)
test_run:drop_cluster(REPLICASET_1)
diff --git a/vshard/cfg.lua b/vshard/cfg.lua
index d5429af..bba12cc 100644
--- a/vshard/cfg.lua
+++ b/vshard/cfg.lua
@@ -217,6 +217,10 @@ local cfg_template = {
type = 'non-negative number', name = 'Sync timeout', is_optional = true,
default = consts.DEFAULT_SYNC_TIMEOUT
}},
+ {'connection_outdate_delay', {
+ type = 'non-negative number', name = 'Object outdate timeout',
+ is_optional = true
+ }},
}
--
@@ -264,6 +268,7 @@ local function remove_non_box_options(cfg)
cfg.collect_bucket_garbage_interval = nil
cfg.collect_lua_garbage = nil
cfg.sync_timeout = nil
+ cfg.connection_outdate_delay = nil
end
return {
diff --git a/vshard/error.lua b/vshard/error.lua
index cf2f9d2..f79107b 100644
--- a/vshard/error.lua
+++ b/vshard/error.lua
@@ -100,6 +100,11 @@ local error_message_template = {
[19] = {
name = 'REPLICASET_IS_LOCKED',
msg = 'Replicaset is locked'
+ },
+ [20] = {
+ name = 'OBJECT_IS_OUTDATED',
+ msg = 'Object is outdated after module reload/reconfigure. ' ..
+ 'Use new instance.'
}
}
diff --git a/vshard/replicaset.lua b/vshard/replicaset.lua
index 99f59aa..6c8d477 100644
--- a/vshard/replicaset.lua
+++ b/vshard/replicaset.lua
@@ -21,6 +21,7 @@
-- requests to the replica>,
-- net_sequential_fail = <count of sequential failed
-- requests to the replica>,
+-- is_outdated = nil/true,
-- }
-- },
-- master = <master server from the array above>,
@@ -34,6 +35,7 @@
-- etalon_bucket_count = <bucket count, that must be stored
-- on this replicaset to reach the
-- balance in a cluster>,
+-- is_outdated = nil/true,
-- }
--
-- replicasets = {
@@ -48,7 +50,8 @@ local lerror = require('vshard.error')
local fiber = require('fiber')
local luri = require('uri')
local ffi = require('ffi')
-local gsc = require('vshard.util').generate_self_checker
+local util = require('vshard.util')
+local gsc = util.generate_self_checker
--
-- on_connect() trigger for net.box
@@ -337,27 +340,39 @@ local function replicaset_tostring(replicaset)
master)
end
+local outdate_replicasets
--
--- Rebind connections of old replicas to new ones.
+-- Copy netbox connections from old replica objects to new ones
+-- and outdate old objects.
+-- @param replicasets New replicasets
+-- @param old_replicasets Replicasets and replicas to be outdated.
+-- @param outdate_delay Number of seconds; delay to outdate
+-- old objects.
--
-local function replicaset_rebind_connections(replicaset)
- for _, replica in pairs(replicaset.replicas) do
- local old_replica = replica.old_replica
- if old_replica then
- local conn = old_replica.conn
- replica.conn = conn
- replica.down_ts = old_replica.down_ts
- replica.net_timeout = old_replica.net_timeout
- replica.net_sequential_ok = old_replica.net_sequential_ok
- replica.net_sequential_fail = old_replica.net_sequential_fail
- if conn then
- conn.replica = replica
- conn.replicaset = replicaset
- old_replica.conn = nil
+local function rebind_replicasets(replicasets, old_replicasets, outdate_delay)
+ for replicaset_uuid, replicaset in pairs(replicasets) do
+ local old_replicaset = old_replicasets and
+ old_replicasets[replicaset_uuid]
+ for replica_uuid, replica in pairs(replicaset.replicas) do
+ local old_replica = old_replicaset and
+ old_replicaset.replicas[replica_uuid]
+ if old_replica then
+ local conn = old_replica.conn
+ replica.conn = conn
+ replica.down_ts = old_replica.down_ts
+ replica.net_timeout = old_replica.net_timeout
+ replica.net_sequential_ok = old_replica.net_sequential_ok
+ replica.net_sequential_fail = old_replica.net_sequential_fail
+ if conn then
+ conn.replica = replica
+ conn.replicaset = replicaset
+ end
end
- replica.old_replica = nil
end
end
+ if old_replicasets then
+ util.async_task(outdate_delay, outdate_replicasets, old_replicasets)
+ end
end
--
@@ -369,7 +384,6 @@ local replicaset_mt = {
connect_master = replicaset_connect_master;
connect_all = replicaset_connect_all;
connect_replica = replicaset_connect_to_replica;
- rebind_connections = replicaset_rebind_connections;
down_replica_priority = replicaset_down_replica_priority;
up_replica_priority = replicaset_up_replica_priority;
call = replicaset_master_call;
@@ -412,6 +426,49 @@ for name, func in pairs(replica_mt.__index) do
end
replica_mt.__index = index
+--
+-- Meta-methods of outdated objects.
+-- They define only attributes from corresponding metatables to
+-- make user able to access fields of old objects.
+--
+local function outdated_warning(...)
+ return nil, lerror.vshard(lerror.code.OBJECT_IS_OUTDATED)
+end
+
+local outdated_replicaset_mt = {
+ __index = {
+ is_outdated = true
+ }
+}
+for fname, func in pairs(replicaset_mt.__index) do
+ outdated_replicaset_mt.__index[fname] = outdated_warning
+end
+
+local outdated_replica_mt = {
+ __index = {
+ is_outdated = true
+ }
+}
+for fname, func in pairs(replica_mt.__index) do
+ outdated_replica_mt.__index[fname] = outdated_warning
+end
+
+--
+-- Outdate replicaset and replica objects:
+-- * Set outdated_metatables.
+-- * Remove connections.
+--
+outdate_replicasets = function(replicasets)
+ for _, replicaset in pairs(replicasets) do
+ setmetatable(replicaset, outdated_replicaset_mt)
+ for _, replica in pairs(replicaset.replicas) do
+ setmetatable(replica, outdated_replica_mt)
+ replica.conn = nil
+ end
+ end
+ log.info('Old replicaset and replica objects are outdated.')
+end
+
--
-- Calculate for each replicaset its etalon bucket count.
-- Iterative algorithm is used to learn the best balance in a
@@ -503,7 +560,7 @@ end
--
-- Update/build replicasets from configuration
--
-local function buildall(sharding_cfg, old_replicasets)
+local function buildall(sharding_cfg)
local new_replicasets = {}
local weights = sharding_cfg.weights
local zone = sharding_cfg.zone
@@ -515,8 +572,6 @@ local function buildall(sharding_cfg, old_replicasets)
end
local curr_ts = fiber.time()
for replicaset_uuid, replicaset in pairs(sharding_cfg.sharding) do
- local old_replicaset = old_replicasets and
- old_replicasets[replicaset_uuid]
local new_replicaset = setmetatable({
replicas = {},
uuid = replicaset_uuid,
@@ -526,8 +581,6 @@ local function buildall(sharding_cfg, old_replicasets)
}, replicaset_mt)
local priority_list = {}
for replica_uuid, replica in pairs(replicaset.replicas) do
- local old_replica = old_replicaset and
- old_replicaset.replicas[replica_uuid]
-- The old replica is saved in the new object to
-- rebind its connection at the end of a
-- router/storage reconfiguration.
@@ -535,7 +588,7 @@ local function buildall(sharding_cfg, old_replicasets)
uri = replica.uri, name = replica.name, uuid = replica_uuid,
zone = replica.zone, net_timeout = consts.CALL_TIMEOUT_MIN,
net_sequential_ok = 0, net_sequential_fail = 0,
- down_ts = curr_ts, old_replica = old_replica,
+ down_ts = curr_ts,
}, replica_mt)
new_replicaset.replicas[replica_uuid] = new_replica
if replica.master then
@@ -596,4 +649,5 @@ return {
buildall = buildall,
calculate_etalon_balance = cluster_calculate_etalon_balance,
wait_masters_connect = wait_masters_connect,
+ rebind_replicasets = rebind_replicasets,
}
diff --git a/vshard/router/init.lua b/vshard/router/init.lua
index a143070..142ddb6 100644
--- a/vshard/router/init.lua
+++ b/vshard/router/init.lua
@@ -1,5 +1,17 @@
local log = require('log')
local lfiber = require('fiber')
+
+local MODULE_INTERNALS = '__module_vshard_router'
+-- Reload requirements, in case this module is reloaded manually.
+if rawget(_G, MODULE_INTERNALS) then
+ local vshard_modules = {
+ 'vshard.consts', 'vshard.error', 'vshard.cfg',
+ 'vshard.hash', 'vshard.replicaset', 'vshard.util',
+ }
+ for _, module in pairs(vshard_modules) do
+ package.loaded[module] = nil
+ end
+end
local consts = require('vshard.consts')
local lerror = require('vshard.error')
local lcfg = require('vshard.cfg')
@@ -7,15 +19,20 @@ local lhash = require('vshard.hash')
local lreplicaset = require('vshard.replicaset')
local util = require('vshard.util')
-local M = rawget(_G, '__module_vshard_router')
+local M = rawget(_G, MODULE_INTERNALS)
if not M then
M = {
+ ---------------- Common module attributes ----------------
+ -- The last passed configuration.
+ current_cfg = nil,
errinj = {
ERRINJ_CFG = false,
ERRINJ_FAILOVER_CHANGE_CFG = false,
ERRINJ_RELOAD = false,
ERRINJ_LONG_DISCOVERY = false,
},
+ -- Time to outdate old objects on reload.
+ connection_outdate_delay = nil,
-- Bucket map cache.
route_map = {},
-- All known replicasets used for bucket re-balancing
@@ -479,12 +496,13 @@ local function router_cfg(cfg)
else
log.info('Starting router reconfiguration')
end
- local new_replicasets = lreplicaset.buildall(cfg, M.replicasets)
+ local new_replicasets = lreplicaset.buildall(cfg)
local total_bucket_count = cfg.bucket_count
local collect_lua_garbage = cfg.collect_lua_garbage
- lcfg.remove_non_box_options(cfg)
+ local box_cfg = table.copy(cfg)
+ lcfg.remove_non_box_options(box_cfg)
log.info("Calling box.cfg()...")
- for k, v in pairs(cfg) do
+ for k, v in pairs(box_cfg) do
log.info({[k] = v})
end
-- It is considered that all possible errors during cfg
@@ -493,18 +511,18 @@ local function router_cfg(cfg)
if M.errinj.ERRINJ_CFG then
error('Error injection: cfg')
end
- box.cfg(cfg)
+ box.cfg(box_cfg)
log.info("Box has been configured")
+ M.connection_outdate_delay = cfg.connection_outdate_delay
M.total_bucket_count = total_bucket_count
M.collect_lua_garbage = collect_lua_garbage
- M.replicasets = new_replicasets
M.current_cfg = new_cfg
-- Move connections from an old configuration to a new one.
-- It must be done with no yields to prevent usage both of not
-- fully moved old replicasets, and not fully built new ones.
- for _, replicaset in pairs(new_replicasets) do
- replicaset:rebind_connections()
- end
+ lreplicaset.rebind_replicasets(new_replicasets, M.replicasets,
+ M.connection_outdate_delay)
+ M.replicasets = new_replicasets
-- Now the new replicasets are fully built. Can establish
-- connections and yield.
for _, replicaset in pairs(new_replicasets) do
@@ -793,15 +811,16 @@ end
-- About functions, saved in M, and reloading see comment in
-- storage/init.lua.
--
-M.discovery_f = discovery_f
-M.failover_f = failover_f
-
-if not rawget(_G, '__module_vshard_router') then
- rawset(_G, '__module_vshard_router', M)
+if not rawget(_G, MODULE_INTERNALS) then
+ rawset(_G, MODULE_INTERNALS, M)
else
+ router_cfg(M.current_cfg)
M.module_version = M.module_version + 1
end
+M.discovery_f = discovery_f
+M.failover_f = failover_f
+
return {
cfg = router_cfg;
info = router_info;
diff --git a/vshard/storage/init.lua b/vshard/storage/init.lua
index 052e94f..07bd00c 100644
--- a/vshard/storage/init.lua
+++ b/vshard/storage/init.lua
@@ -2,20 +2,34 @@ local log = require('log')
local luri = require('uri')
local lfiber = require('fiber')
local netbox = require('net.box') -- for net.box:self()
+local trigger = require('internal.trigger')
+
+local MODULE_INTERNALS = '__module_vshard_storage'
+-- Reload requirements, in case this module is reloaded manually.
+if rawget(_G, MODULE_INTERNALS) then
+ local vshard_modules = {
+ 'vshard.consts', 'vshard.error', 'vshard.cfg',
+ 'vshard.replicaset', 'vshard.util',
+ }
+ for _, module in pairs(vshard_modules) do
+ package.loaded[module] = nil
+ end
+end
local consts = require('vshard.consts')
local lerror = require('vshard.error')
-local util = require('vshard.util')
local lcfg = require('vshard.cfg')
local lreplicaset = require('vshard.replicaset')
-local trigger = require('internal.trigger')
+local util = require('vshard.util')
-local M = rawget(_G, '__module_vshard_storage')
+local M = rawget(_G, MODULE_INTERNALS)
if not M then
--
-- The module is loaded for the first time.
--
M = {
---------------- Common module attributes ----------------
+ -- The last passed configuration.
+ current_cfg = nil,
--
-- All known replicasets used for bucket re-balancing.
-- See format in replicaset.lua.
@@ -1497,7 +1511,7 @@ local function storage_cfg(cfg, this_replica_uuid)
local this_replicaset
local this_replica
- local new_replicasets = lreplicaset.buildall(cfg, M.replicasets)
+ local new_replicasets = lreplicaset.buildall(cfg)
local min_master
for rs_uuid, rs in pairs(new_replicasets) do
for replica_uuid, replica in pairs(rs.replicas) do
@@ -1576,7 +1590,6 @@ local function storage_cfg(cfg, this_replica_uuid)
--
local old_sync_timeout = M.sync_timeout
M.sync_timeout = cfg.sync_timeout
- lcfg.remove_non_box_options(cfg)
if was_master and not is_master then
local_on_master_disable_prepare()
@@ -1585,7 +1598,9 @@ local function storage_cfg(cfg, this_replica_uuid)
local_on_master_enable_prepare()
end
- local ok, err = pcall(box.cfg, cfg)
+ local box_cfg = table.copy(cfg)
+ lcfg.remove_non_box_options(box_cfg)
+ local ok, err = pcall(box.cfg, box_cfg)
while M.errinj.ERRINJ_CFG_DELAY do
lfiber.sleep(0.01)
end
@@ -1604,10 +1619,8 @@ local function storage_cfg(cfg, this_replica_uuid)
local uri = luri.parse(this_replica.uri)
box.once("vshard:storage:1", storage_schema_v1, uri.login, uri.password)
+ lreplicaset.rebind_replicasets(new_replicasets, M.replicasets)
M.replicasets = new_replicasets
- for _, replicaset in pairs(new_replicasets) do
- replicaset:rebind_connections()
- end
M.this_replicaset = this_replicaset
M.this_replica = this_replica
M.total_bucket_count = total_bucket_count
@@ -1846,6 +1859,14 @@ end
-- restarted (or is restarted from M.background_f, which is not
-- changed) and continues use old func1 and func2.
--
+
+if not rawget(_G, MODULE_INTERNALS) then
+ rawset(_G, MODULE_INTERNALS, M)
+else
+ storage_cfg(M.current_cfg, M.this_replica.uuid)
+ M.module_version = M.module_version + 1
+end
+
M.recovery_f = recovery_f
M.collect_garbage_f = collect_garbage_f
M.rebalancer_f = rebalancer_f
@@ -1861,12 +1882,6 @@ M.rebalancer_build_routes = rebalancer_build_routes
M.rebalancer_calculate_metrics = rebalancer_calculate_metrics
M.cached_find_sharded_spaces = find_sharded_spaces
-if not rawget(_G, '__module_vshard_storage') then
- rawset(_G, '__module_vshard_storage', M)
-else
- M.module_version = M.module_version + 1
-end
-
return {
sync = sync,
bucket_force_create = bucket_force_create,
diff --git a/vshard/util.lua b/vshard/util.lua
index ce79930..fb875ce 100644
--- a/vshard/util.lua
+++ b/vshard/util.lua
@@ -100,9 +100,29 @@ end
-- Update latest versions of function
M.reloadable_fiber_f = reloadable_fiber_f
+local function sync_task(delay, task, ...)
+ if delay then
+ fiber.sleep(delay)
+ end
+ task(...)
+end
+
+--
+-- Run a function without interrupting current fiber.
+-- @param delay Delay in seconds before the task should be
+-- executed.
+-- @param task Function to be executed.
+-- @param ... Arguments which would be passed to the `task`.
+--
+local function async_task(delay, task, ...)
+ assert(delay == nil or type(delay) == 'number')
+ fiber.create(sync_task, delay, task, ...)
+end
+
return {
tuple_extract_key = tuple_extract_key,
reloadable_fiber_f = reloadable_fiber_f,
generate_self_checker = generate_self_checker,
+ async_task = async_task,
internal = M,
}
--
2.14.1
^ permalink raw reply [flat|nested] 14+ messages in thread
* [tarantool-patches] [PATCH 3/4] Tests: separate bootstrap routine to a lua_libs
2018-07-23 11:14 [tarantool-patches] [PATCH v2] vshard reload mechanism AKhatskevich
2018-07-23 11:14 ` [tarantool-patches] [PATCH 1/4] Add test on error during reconfigure AKhatskevich
2018-07-23 11:14 ` [tarantool-patches] [PATCH 2/4] Complete module reload AKhatskevich
@ 2018-07-23 11:14 ` AKhatskevich
2018-07-23 13:36 ` [tarantool-patches] " Vladislav Shpilevoy
2018-07-23 11:14 ` [tarantool-patches] [PATCH 4/4] Introduce storage reload evolution AKhatskevich
3 siblings, 1 reply; 14+ messages in thread
From: AKhatskevich @ 2018-07-23 11:14 UTC (permalink / raw)
To: v.shpilevoy, tarantool-patches
What is moved to `test/lul_libs/bootstrap_test_storage.lua`:
1. create schema
2. create main stored procedures
3. `wait_rebalancer_state` procedure
This code would be reused it further commits.
---
test/lua_libs/bootstrap_test_storage.lua | 50 ++++++++++++++++++++++
test/rebalancer/box_1_a.lua | 47 ++------------------
test/rebalancer/errinj.result | 2 +-
test/rebalancer/errinj.test.lua | 2 +-
test/rebalancer/rebalancer.result | 2 +-
test/rebalancer/rebalancer.test.lua | 2 +-
test/rebalancer/rebalancer_lock_and_pin.result | 2 +-
test/rebalancer/rebalancer_lock_and_pin.test.lua | 2 +-
test/rebalancer/restart_during_rebalancing.result | 2 +-
.../rebalancer/restart_during_rebalancing.test.lua | 2 +-
test/rebalancer/stress_add_remove_rs.result | 2 +-
test/rebalancer/stress_add_remove_rs.test.lua | 2 +-
.../rebalancer/stress_add_remove_several_rs.result | 2 +-
.../stress_add_remove_several_rs.test.lua | 2 +-
test/rebalancer/suite.ini | 2 +-
15 files changed, 66 insertions(+), 57 deletions(-)
create mode 100644 test/lua_libs/bootstrap_test_storage.lua
diff --git a/test/lua_libs/bootstrap_test_storage.lua b/test/lua_libs/bootstrap_test_storage.lua
new file mode 100644
index 0000000..62c2f78
--- /dev/null
+++ b/test/lua_libs/bootstrap_test_storage.lua
@@ -0,0 +1,50 @@
+local log = require('log')
+
+function init_schema()
+ local format = {}
+ format[1] = {name = 'field', type = 'unsigned'}
+ format[2] = {name = 'bucket_id', type = 'unsigned'}
+ local s = box.schema.create_space('test', {format = format})
+ local pk = s:create_index('pk')
+ local bucket_id_idx =
+ s:create_index('vbucket', {parts = {'bucket_id'},
+ unique = false})
+end
+
+box.once('schema', function()
+ box.schema.func.create('do_replace')
+ box.schema.role.grant('public', 'execute', 'function', 'do_replace')
+ box.schema.func.create('do_select')
+ box.schema.role.grant('public', 'execute', 'function', 'do_select')
+ init_schema()
+end)
+
+function do_replace(...)
+ box.space.test:replace(...)
+ return true
+end
+
+function do_select(...)
+ return box.space.test:select(...)
+end
+
+function check_consistency()
+ for _, tuple in box.space.test:pairs() do
+ assert(box.space._bucket:get{tuple.bucket_id})
+ end
+ return true
+end
+
+--
+-- Wait a specified log message.
+-- Requirements:
+-- * Should be executed from a storage with a rebalancer.
+-- * NAME - global variable, name of instance should be set.
+function wait_rebalancer_state(state, test_run)
+ log.info(string.rep('a', 1000))
+ vshard.storage.rebalancer_wakeup()
+ while not test_run:grep_log(NAME, state, 1000) do
+ fiber.sleep(0.1)
+ vshard.storage.rebalancer_wakeup()
+ end
+end
diff --git a/test/rebalancer/box_1_a.lua b/test/rebalancer/box_1_a.lua
index 8fddcf0..8ab3444 100644
--- a/test/rebalancer/box_1_a.lua
+++ b/test/rebalancer/box_1_a.lua
@@ -2,7 +2,7 @@
-- Get instance name
require('strict').on()
local fio = require('fio')
-local NAME = fio.basename(arg[0], '.lua')
+NAME = fio.basename(arg[0], '.lua')
log = require('log')
require('console').listen(os.getenv('ADMIN'))
fiber = require('fiber')
@@ -23,40 +23,8 @@ if NAME == 'box_4_a' or NAME == 'box_4_b' or
end
vshard.storage.cfg(cfg, names.replica_uuid[NAME])
-function init_schema()
- local format = {}
- format[1] = {name = 'field', type = 'unsigned'}
- format[2] = {name = 'bucket_id', type = 'unsigned'}
- local s = box.schema.create_space('test', {format = format})
- local pk = s:create_index('pk')
- local bucket_id_idx =
- s:create_index('vbucket', {parts = {'bucket_id'},
- unique = false})
-end
-
-box.once('schema', function()
- box.schema.func.create('do_replace')
- box.schema.role.grant('public', 'execute', 'function', 'do_replace')
- box.schema.func.create('do_select')
- box.schema.role.grant('public', 'execute', 'function', 'do_select')
- init_schema()
-end)
-
-function do_replace(...)
- box.space.test:replace(...)
- return true
-end
-
-function do_select(...)
- return box.space.test:select(...)
-end
-
-function check_consistency()
- for _, tuple in box.space.test:pairs() do
- assert(box.space._bucket:get{tuple.bucket_id})
- end
- return true
-end
+-- Bootstrap storage.
+require('lua_libs.bootstrap_test_storage')
function switch_rs1_master()
local replica_uuid = names.replica_uuid
@@ -68,12 +36,3 @@ end
function nullify_rs_weight()
cfg.sharding[names.rs_uuid[1]].weight = 0
end
-
-function wait_rebalancer_state(state, test_run)
- log.info(string.rep('a', 1000))
- vshard.storage.rebalancer_wakeup()
- while not test_run:grep_log(NAME, state, 1000) do
- fiber.sleep(0.1)
- vshard.storage.rebalancer_wakeup()
- end
-end
diff --git a/test/rebalancer/errinj.result b/test/rebalancer/errinj.result
index d09349e..826c2c6 100644
--- a/test/rebalancer/errinj.result
+++ b/test/rebalancer/errinj.result
@@ -13,7 +13,7 @@ test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
---
...
-util = require('util')
+util = require('lua_libs.util')
---
...
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
diff --git a/test/rebalancer/errinj.test.lua b/test/rebalancer/errinj.test.lua
index d6a2920..fc0730c 100644
--- a/test/rebalancer/errinj.test.lua
+++ b/test/rebalancer/errinj.test.lua
@@ -5,7 +5,7 @@ REPLICASET_2 = { 'box_2_a', 'box_2_b' }
test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
-util = require('util')
+util = require('lua_libs.util')
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
util.wait_master(test_run, REPLICASET_2, 'box_2_a')
diff --git a/test/rebalancer/rebalancer.result b/test/rebalancer/rebalancer.result
index 88cbaae..71e43e1 100644
--- a/test/rebalancer/rebalancer.result
+++ b/test/rebalancer/rebalancer.result
@@ -13,7 +13,7 @@ test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
---
...
-util = require('util')
+util = require('lua_libs.util')
---
...
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
diff --git a/test/rebalancer/rebalancer.test.lua b/test/rebalancer/rebalancer.test.lua
index 01f2061..1b7ddae 100644
--- a/test/rebalancer/rebalancer.test.lua
+++ b/test/rebalancer/rebalancer.test.lua
@@ -5,7 +5,7 @@ REPLICASET_2 = { 'box_2_a', 'box_2_b' }
test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
-util = require('util')
+util = require('lua_libs.util')
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
util.wait_master(test_run, REPLICASET_2, 'box_2_a')
diff --git a/test/rebalancer/rebalancer_lock_and_pin.result b/test/rebalancer/rebalancer_lock_and_pin.result
index dd9fe47..0f2921c 100644
--- a/test/rebalancer/rebalancer_lock_and_pin.result
+++ b/test/rebalancer/rebalancer_lock_and_pin.result
@@ -16,7 +16,7 @@ test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
---
...
-util = require('util')
+util = require('lua_libs.util')
---
...
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
diff --git a/test/rebalancer/rebalancer_lock_and_pin.test.lua b/test/rebalancer/rebalancer_lock_and_pin.test.lua
index fe866c4..3a2daa0 100644
--- a/test/rebalancer/rebalancer_lock_and_pin.test.lua
+++ b/test/rebalancer/rebalancer_lock_and_pin.test.lua
@@ -6,7 +6,7 @@ REPLICASET_3 = { 'box_3_a', 'box_3_b' }
test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
-util = require('util')
+util = require('lua_libs.util')
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
util.wait_master(test_run, REPLICASET_2, 'box_2_a')
diff --git a/test/rebalancer/restart_during_rebalancing.result b/test/rebalancer/restart_during_rebalancing.result
index d2b8a12..0eb0f2e 100644
--- a/test/rebalancer/restart_during_rebalancing.result
+++ b/test/rebalancer/restart_during_rebalancing.result
@@ -25,7 +25,7 @@ test_run:create_cluster(REPLICASET_3, 'rebalancer')
test_run:create_cluster(REPLICASET_4, 'rebalancer')
---
...
-util = require('util')
+util = require('lua_libs.util')
---
...
util.wait_master(test_run, REPLICASET_1, 'fullbox_1_a')
diff --git a/test/rebalancer/restart_during_rebalancing.test.lua b/test/rebalancer/restart_during_rebalancing.test.lua
index 5b1a8df..7b707ca 100644
--- a/test/rebalancer/restart_during_rebalancing.test.lua
+++ b/test/rebalancer/restart_during_rebalancing.test.lua
@@ -9,7 +9,7 @@ test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
test_run:create_cluster(REPLICASET_3, 'rebalancer')
test_run:create_cluster(REPLICASET_4, 'rebalancer')
-util = require('util')
+util = require('lua_libs.util')
util.wait_master(test_run, REPLICASET_1, 'fullbox_1_a')
util.wait_master(test_run, REPLICASET_2, 'fullbox_2_a')
util.wait_master(test_run, REPLICASET_3, 'fullbox_3_a')
diff --git a/test/rebalancer/stress_add_remove_rs.result b/test/rebalancer/stress_add_remove_rs.result
index 8a955e2..10bcaac 100644
--- a/test/rebalancer/stress_add_remove_rs.result
+++ b/test/rebalancer/stress_add_remove_rs.result
@@ -16,7 +16,7 @@ test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
---
...
-util = require('util')
+util = require('lua_libs.util')
---
...
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
diff --git a/test/rebalancer/stress_add_remove_rs.test.lua b/test/rebalancer/stress_add_remove_rs.test.lua
index c80df40..b9bb027 100644
--- a/test/rebalancer/stress_add_remove_rs.test.lua
+++ b/test/rebalancer/stress_add_remove_rs.test.lua
@@ -6,7 +6,7 @@ REPLICASET_3 = { 'box_3_a', 'box_3_b' }
test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
-util = require('util')
+util = require('lua_libs.util')
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
util.wait_master(test_run, REPLICASET_2, 'box_2_a')
diff --git a/test/rebalancer/stress_add_remove_several_rs.result b/test/rebalancer/stress_add_remove_several_rs.result
index d6008b8..611362c 100644
--- a/test/rebalancer/stress_add_remove_several_rs.result
+++ b/test/rebalancer/stress_add_remove_several_rs.result
@@ -19,7 +19,7 @@ test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
---
...
-util = require('util')
+util = require('lua_libs.util')
---
...
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
diff --git a/test/rebalancer/stress_add_remove_several_rs.test.lua b/test/rebalancer/stress_add_remove_several_rs.test.lua
index 3cc105e..9acb8de 100644
--- a/test/rebalancer/stress_add_remove_several_rs.test.lua
+++ b/test/rebalancer/stress_add_remove_several_rs.test.lua
@@ -7,7 +7,7 @@ REPLICASET_4 = { 'box_4_a', 'box_4_b' }
test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
-util = require('util')
+util = require('lua_libs.util')
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
util.wait_master(test_run, REPLICASET_2, 'box_2_a')
diff --git a/test/rebalancer/suite.ini b/test/rebalancer/suite.ini
index afc5141..8689da5 100644
--- a/test/rebalancer/suite.ini
+++ b/test/rebalancer/suite.ini
@@ -4,6 +4,6 @@ description = Rebalancer tests
script = test.lua
is_parallel = False
release_disabled = errinj.test.lua
-lua_libs = ../lua_libs/util.lua config.lua names.lua router_1.lua
+lua_libs = ../lua_libs config.lua names.lua router_1.lua
box_1_a.lua box_1_b.lua box_2_a.lua box_2_b.lua
box_3_a.lua box_3_b.lua rebalancer_utils.lua
--
2.14.1
^ permalink raw reply [flat|nested] 14+ messages in thread
* [tarantool-patches] [PATCH 4/4] Introduce storage reload evolution
2018-07-23 11:14 [tarantool-patches] [PATCH v2] vshard reload mechanism AKhatskevich
` (2 preceding siblings ...)
2018-07-23 11:14 ` [tarantool-patches] [PATCH 3/4] Tests: separate bootstrap routine to a lua_libs AKhatskevich
@ 2018-07-23 11:14 ` AKhatskevich
2018-07-23 14:44 ` [tarantool-patches] " Vladislav Shpilevoy
3 siblings, 1 reply; 14+ messages in thread
From: AKhatskevich @ 2018-07-23 11:14 UTC (permalink / raw)
To: v.shpilevoy, tarantool-patches
Changes:
1. Introduce storage reload evolution.
2. Setup cross-version reload testing.
1:
This mechanism updates Lua objects on reload in case they are
changed in a new vshard.storage version.
Since this commit, any change in vshard.storage.M has to be
reflected in vshard.storage.reload_evolution to guarantee
correct reload.
2:
The testing uses git infrastructure and is performed in the following
way:
1. Copy old version of vshard to a temp folder.
2. Run vshard on this code.
3. Checkout the latest version of the vshard sources.
4. Reload vshard storage.
5. Make sure it works (Perform simple tests).
Notes:
* this patch contains some legacy-driven decisions:
1. SOURCEDIR path retrieved differently in case of
packpack build.
2. git directory in the `reload_evolution/storage` test
is copied with respect to Centos 7 and `ro` mode of
SOURCEDIR.
Closes #112 #125
---
.travis.yml | 2 +-
rpm/prebuild.sh | 2 +
test/lua_libs/git_util.lua | 51 +++++++
test/lua_libs/util.lua | 20 +++
test/reload_evolution/storage.result | 248 +++++++++++++++++++++++++++++++++
test/reload_evolution/storage.test.lua | 88 ++++++++++++
test/reload_evolution/storage_1_a.lua | 48 +++++++
test/reload_evolution/storage_1_b.lua | 1 +
test/reload_evolution/storage_2_a.lua | 1 +
test/reload_evolution/storage_2_b.lua | 1 +
test/reload_evolution/suite.ini | 6 +
test/reload_evolution/test.lua | 9 ++
test/unit/reload_evolution.result | 45 ++++++
test/unit/reload_evolution.test.lua | 18 +++
vshard/storage/init.lua | 11 ++
vshard/storage/reload_evolution.lua | 58 ++++++++
16 files changed, 608 insertions(+), 1 deletion(-)
create mode 100644 test/lua_libs/git_util.lua
create mode 100644 test/reload_evolution/storage.result
create mode 100644 test/reload_evolution/storage.test.lua
create mode 100755 test/reload_evolution/storage_1_a.lua
create mode 120000 test/reload_evolution/storage_1_b.lua
create mode 120000 test/reload_evolution/storage_2_a.lua
create mode 120000 test/reload_evolution/storage_2_b.lua
create mode 100644 test/reload_evolution/suite.ini
create mode 100644 test/reload_evolution/test.lua
create mode 100644 test/unit/reload_evolution.result
create mode 100644 test/unit/reload_evolution.test.lua
create mode 100644 vshard/storage/reload_evolution.lua
diff --git a/.travis.yml b/.travis.yml
index 54bfe44..eff4a51 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -41,7 +41,7 @@ env:
script:
- git describe --long
- git clone https://github.com/packpack/packpack.git packpack
- - packpack/packpack
+ - packpack/packpack -e PACKPACK_GIT_SOURCEDIR=/source/
before_deploy:
- ls -l build/
diff --git a/rpm/prebuild.sh b/rpm/prebuild.sh
index 768b22b..554032b 100755
--- a/rpm/prebuild.sh
+++ b/rpm/prebuild.sh
@@ -1 +1,3 @@
curl -s https://packagecloud.io/install/repositories/tarantool/1_9/script.rpm.sh | sudo bash
+sudo yum -y install python-devel python-pip
+sudo pip install tarantool msgpack
diff --git a/test/lua_libs/git_util.lua b/test/lua_libs/git_util.lua
new file mode 100644
index 0000000..a75bb08
--- /dev/null
+++ b/test/lua_libs/git_util.lua
@@ -0,0 +1,51 @@
+--
+-- Lua bridge for some of the git commands.
+--
+local os = require('os')
+
+local temp_file = 'some_strange_rare_unique_file_name_for_git_util'
+
+--
+-- Exec a git command.
+-- @param params Table of parameters:
+-- * options - git options.
+-- * cmd - git command.
+-- * args - command arguments.
+-- * dir - working directory.
+-- * fout - write output to the file.
+local function exec_cmd(params)
+ local fout = params.fout
+ local shell_cmd = {'git'}
+ for _, param in pairs({'options', 'cmd', 'args'}) do
+ table.insert(shell_cmd, params[param])
+ end
+ if fout then
+ table.insert(shell_cmd, ' >' .. fout)
+ end
+ shell_cmd = table.concat(shell_cmd, ' ')
+ if params.dir then
+ shell_cmd = string.format('cd %s && %s', params.dir, shell_cmd)
+ end
+ local res = os.execute(shell_cmd)
+ assert(res == 0, 'Git cmd error: ' .. res)
+end
+
+local function log_hashes(params)
+ params.args = "--format='%h' " .. params.args
+ local local_temp_file = string.format('%s/%s', os.getenv('PWD'), temp_file)
+ params.fout = local_temp_file
+ params.cmd = 'log'
+ exec_cmd(params)
+ local lines = {}
+ for line in io.lines(local_temp_file) do
+ table.insert(lines, line)
+ end
+ os.remove(local_temp_file)
+ return lines
+end
+
+
+return {
+ exec_cmd = exec_cmd,
+ log_hashes = log_hashes
+}
diff --git a/test/lua_libs/util.lua b/test/lua_libs/util.lua
index f40d3a6..935ff41 100644
--- a/test/lua_libs/util.lua
+++ b/test/lua_libs/util.lua
@@ -1,5 +1,6 @@
local fiber = require('fiber')
local log = require('log')
+local fio = require('fio')
local function check_error(func, ...)
local pstatus, status, err = pcall(func, ...)
@@ -92,10 +93,29 @@ local function has_same_fields(etalon, data)
return true
end
+-- Git directory of the project. Used in evolution tests to
+-- fetch old versions of vshard.
+local SOURCEDIR = os.getenv('PACKPACK_GIT_SOURCEDIR')
+if not SOURCEDIR then
+ SOURCEDIR = os.getenv('SOURCEDIR')
+end
+if not SOURCEDIR then
+ local script_path = debug.getinfo(1).source:match("@?(.*/)")
+ script_path = fio.abspath(script_path)
+ SOURCEDIR = fio.abspath(script_path .. '/../../../')
+end
+
+local BUILDDIR = os.getenv('BUILDDIR')
+if not BUILDDIR then
+ BUILDDIR = SOURCEDIR
+end
+
return {
check_error = check_error,
shuffle_masters = shuffle_masters,
collect_timeouts = collect_timeouts,
wait_master = wait_master,
has_same_fields = has_same_fields,
+ SOURCEDIR = SOURCEDIR,
+ BUILDDIR = BUILDDIR,
}
diff --git a/test/reload_evolution/storage.result b/test/reload_evolution/storage.result
new file mode 100644
index 0000000..54ff6b7
--- /dev/null
+++ b/test/reload_evolution/storage.result
@@ -0,0 +1,248 @@
+test_run = require('test_run').new()
+---
+...
+git_util = require('lua_libs.git_util')
+---
+...
+util = require('lua_libs.util')
+---
+...
+vshard_copy_path = util.BUILDDIR .. '/test/var/vshard_git_tree_copy'
+---
+...
+evolution_log = git_util.log_hashes({args='vshard/storage/reload_evolution.lua', dir=util.SOURCEDIR})
+---
+...
+-- Cleanup the directory after a previous build.
+_ = os.execute('rm -rf ' .. vshard_copy_path)
+---
+...
+-- 1. `git worktree` cannot be used because PACKPACK mounts
+-- `/source/` in `ro` mode.
+-- 2. Just `cp -rf` cannot be used due to a little different
+-- behavior in Centos 7.
+_ = os.execute('mkdir ' .. vshard_copy_path)
+---
+...
+_ = os.execute("cd " .. util.SOURCEDIR .. ' && cp -rf `ls -A --ignore=build` ' .. vshard_copy_path)
+---
+...
+-- Checkout the first commit with a reload_evolution mechanism.
+git_util.exec_cmd({cmd='checkout', args='-f', dir=vshard_copy_path})
+---
+...
+git_util.exec_cmd({cmd='checkout', args=evolution_log[#evolution_log] .. '~1', dir=vshard_copy_path})
+---
+...
+REPLICASET_1 = { 'storage_1_a', 'storage_1_b' }
+---
+...
+REPLICASET_2 = { 'storage_2_a', 'storage_2_b' }
+---
+...
+test_run:create_cluster(REPLICASET_1, 'reload_evolution')
+---
+...
+test_run:create_cluster(REPLICASET_2, 'reload_evolution')
+---
+...
+util = require('lua_libs.util')
+---
+...
+util.wait_master(test_run, REPLICASET_1, 'storage_1_a')
+---
+...
+util.wait_master(test_run, REPLICASET_2, 'storage_2_a')
+---
+...
+test_run:switch('storage_1_a')
+---
+- true
+...
+vshard.storage.bucket_force_create(1, vshard.consts.DEFAULT_BUCKET_COUNT / 2)
+---
+- true
+...
+bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
+---
+...
+test_run:switch('storage_2_a')
+---
+- true
+...
+fiber = require('fiber')
+---
+...
+vshard.storage.bucket_force_create(vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1, vshard.consts.DEFAULT_BUCKET_COUNT / 2)
+---
+- true
+...
+bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
+---
+...
+vshard.storage.internal.reload_evolution_version
+---
+- null
+...
+box.space.test:insert({42, bucket_id_to_move})
+---
+- [42, 3000]
+...
+while test_run:grep_log('storage_2_a', 'The cluster is balanced ok') == nil do vshard.storage.rebalancer_wakeup() fiber.sleep(0.1) end
+---
+...
+test_run:switch('default')
+---
+- true
+...
+git_util.exec_cmd({cmd='checkout', args=evolution_log[1], dir=vshard_copy_path})
+---
+...
+test_run:switch('storage_2_a')
+---
+- true
+...
+package.loaded["vshard.storage"] = nil
+---
+...
+vshard.storage = require("vshard.storage")
+---
+...
+test_run:grep_log('storage_2_a', 'vshard.storage.reload_evolution: upgraded to') ~= nil
+---
+- true
+...
+vshard.storage.internal.reload_evolution_version
+---
+- 1
+...
+-- Make sure storage operates well.
+vshard.storage.bucket_force_drop(2000)
+---
+- true
+...
+vshard.storage.bucket_force_create(2000)
+---
+- true
+...
+vshard.storage.buckets_info()[2000]
+---
+- status: active
+ id: 2000
+...
+vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
+---
+- true
+- - [42, 3000]
+...
+vshard.storage.bucket_send(bucket_id_to_move, replicaset1_uuid)
+---
+- true
+...
+vshard.storage.garbage_collector_wakeup()
+---
+...
+fiber = require('fiber')
+---
+...
+while box.space._bucket:get({bucket_id_to_move}) do fiber.sleep(0.01) end
+---
+...
+test_run:switch('storage_1_a')
+---
+- true
+...
+vshard.storage.bucket_send(bucket_id_to_move, replicaset2_uuid)
+---
+- true
+...
+test_run:switch('storage_2_a')
+---
+- true
+...
+vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
+---
+- true
+- - [42, 3000]
+...
+-- Check info() does not fail.
+vshard.storage.info() ~= nil
+---
+- true
+...
+--
+-- Send buckets to create a disbalance. Wait until the rebalancer
+-- repairs it. Similar to `tests/rebalancer/rebalancer.test.lua`.
+--
+vshard.storage.rebalancer_disable()
+---
+...
+move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
+---
+...
+move_cnt = 100
+---
+...
+assert(move_start + move_cnt < vshard.consts.DEFAULT_BUCKET_COUNT)
+---
+- true
+...
+for i = move_start, move_start + move_cnt - 1 do box.space._bucket:delete{i} end
+---
+...
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+---
+- 1400
+...
+test_run:switch('storage_1_a')
+---
+- true
+...
+move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
+---
+...
+move_cnt = 100
+---
+...
+vshard.storage.bucket_force_create(move_start, move_cnt)
+---
+- true
+...
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+---
+- 1600
+...
+test_run:switch('storage_2_a')
+---
+- true
+...
+vshard.storage.rebalancer_enable()
+---
+...
+vshard.storage.rebalancer_wakeup()
+---
+...
+wait_rebalancer_state("Rebalance routes are sent", test_run)
+---
+...
+wait_rebalancer_state('The cluster is balanced ok', test_run)
+---
+...
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+---
+- 1500
+...
+test_run:switch('default')
+---
+- true
+...
+test_run:drop_cluster(REPLICASET_2)
+---
+...
+test_run:drop_cluster(REPLICASET_1)
+---
+...
+test_run:cmd('clear filter')
+---
+- true
+...
diff --git a/test/reload_evolution/storage.test.lua b/test/reload_evolution/storage.test.lua
new file mode 100644
index 0000000..5817667
--- /dev/null
+++ b/test/reload_evolution/storage.test.lua
@@ -0,0 +1,88 @@
+test_run = require('test_run').new()
+
+git_util = require('lua_libs.git_util')
+util = require('lua_libs.util')
+vshard_copy_path = util.BUILDDIR .. '/test/var/vshard_git_tree_copy'
+evolution_log = git_util.log_hashes({args='vshard/storage/reload_evolution.lua', dir=util.SOURCEDIR})
+-- Cleanup the directory after a previous build.
+_ = os.execute('rm -rf ' .. vshard_copy_path)
+-- 1. `git worktree` cannot be used because PACKPACK mounts
+-- `/source/` in `ro` mode.
+-- 2. Just `cp -rf` cannot be used due to a little different
+-- behavior in Centos 7.
+_ = os.execute('mkdir ' .. vshard_copy_path)
+_ = os.execute("cd " .. util.SOURCEDIR .. ' && cp -rf `ls -A --ignore=build` ' .. vshard_copy_path)
+-- Checkout the first commit with a reload_evolution mechanism.
+git_util.exec_cmd({cmd='checkout', args='-f', dir=vshard_copy_path})
+git_util.exec_cmd({cmd='checkout', args=evolution_log[#evolution_log] .. '~1', dir=vshard_copy_path})
+
+REPLICASET_1 = { 'storage_1_a', 'storage_1_b' }
+REPLICASET_2 = { 'storage_2_a', 'storage_2_b' }
+test_run:create_cluster(REPLICASET_1, 'reload_evolution')
+test_run:create_cluster(REPLICASET_2, 'reload_evolution')
+util = require('lua_libs.util')
+util.wait_master(test_run, REPLICASET_1, 'storage_1_a')
+util.wait_master(test_run, REPLICASET_2, 'storage_2_a')
+
+test_run:switch('storage_1_a')
+vshard.storage.bucket_force_create(1, vshard.consts.DEFAULT_BUCKET_COUNT / 2)
+bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
+
+test_run:switch('storage_2_a')
+fiber = require('fiber')
+vshard.storage.bucket_force_create(vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1, vshard.consts.DEFAULT_BUCKET_COUNT / 2)
+bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
+vshard.storage.internal.reload_evolution_version
+box.space.test:insert({42, bucket_id_to_move})
+while test_run:grep_log('storage_2_a', 'The cluster is balanced ok') == nil do vshard.storage.rebalancer_wakeup() fiber.sleep(0.1) end
+
+test_run:switch('default')
+git_util.exec_cmd({cmd='checkout', args=evolution_log[1], dir=vshard_copy_path})
+
+test_run:switch('storage_2_a')
+package.loaded["vshard.storage"] = nil
+vshard.storage = require("vshard.storage")
+test_run:grep_log('storage_2_a', 'vshard.storage.reload_evolution: upgraded to') ~= nil
+vshard.storage.internal.reload_evolution_version
+-- Make sure storage operates well.
+vshard.storage.bucket_force_drop(2000)
+vshard.storage.bucket_force_create(2000)
+vshard.storage.buckets_info()[2000]
+vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
+vshard.storage.bucket_send(bucket_id_to_move, replicaset1_uuid)
+vshard.storage.garbage_collector_wakeup()
+fiber = require('fiber')
+while box.space._bucket:get({bucket_id_to_move}) do fiber.sleep(0.01) end
+test_run:switch('storage_1_a')
+vshard.storage.bucket_send(bucket_id_to_move, replicaset2_uuid)
+test_run:switch('storage_2_a')
+vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
+-- Check info() does not fail.
+vshard.storage.info() ~= nil
+
+--
+-- Send buckets to create a disbalance. Wait until the rebalancer
+-- repairs it. Similar to `tests/rebalancer/rebalancer.test.lua`.
+--
+vshard.storage.rebalancer_disable()
+move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
+move_cnt = 100
+assert(move_start + move_cnt < vshard.consts.DEFAULT_BUCKET_COUNT)
+for i = move_start, move_start + move_cnt - 1 do box.space._bucket:delete{i} end
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+test_run:switch('storage_1_a')
+move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
+move_cnt = 100
+vshard.storage.bucket_force_create(move_start, move_cnt)
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+test_run:switch('storage_2_a')
+vshard.storage.rebalancer_enable()
+vshard.storage.rebalancer_wakeup()
+wait_rebalancer_state("Rebalance routes are sent", test_run)
+wait_rebalancer_state('The cluster is balanced ok', test_run)
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+
+test_run:switch('default')
+test_run:drop_cluster(REPLICASET_2)
+test_run:drop_cluster(REPLICASET_1)
+test_run:cmd('clear filter')
diff --git a/test/reload_evolution/storage_1_a.lua b/test/reload_evolution/storage_1_a.lua
new file mode 100755
index 0000000..a971457
--- /dev/null
+++ b/test/reload_evolution/storage_1_a.lua
@@ -0,0 +1,48 @@
+#!/usr/bin/env tarantool
+
+require('strict').on()
+
+local log = require('log')
+local fiber = require('fiber')
+local util = require('lua_libs.util')
+local fio = require('fio')
+
+-- Get instance name
+NAME = fio.basename(arg[0], '.lua')
+
+-- test-run gate.
+test_run = require('test_run').new()
+require('console').listen(os.getenv('ADMIN'))
+
+-- Run one storage on a different vshard version.
+-- To do that, place vshard src to
+-- BUILDDIR/test/var/vshard_git_tree_copy/.
+if NAME == 'storage_2_a' then
+ local script_path = debug.getinfo(1).source:match("@?(.*/)")
+ vshard_copy = util.BUILDDIR .. '/test/var/vshard_git_tree_copy'
+ package.path = string.format(
+ '%s/?.lua;%s/?/init.lua;%s',
+ vshard_copy, vshard_copy, package.path
+ )
+end
+
+-- Call a configuration provider
+cfg = require('localcfg')
+-- Name to uuid map
+names = {
+ ['storage_1_a'] = '8a274925-a26d-47fc-9e1b-af88ce939412',
+ ['storage_1_b'] = '3de2e3e1-9ebe-4d0d-abb1-26d301b84633',
+ ['storage_2_a'] = '1e02ae8a-afc0-4e91-ba34-843a356b8ed7',
+ ['storage_2_b'] = '001688c3-66f8-4a31-8e19-036c17d489c2',
+}
+
+replicaset1_uuid = 'cbf06940-0790-498b-948d-042b62cf3d29'
+replicaset2_uuid = 'ac522f65-aa94-4134-9f64-51ee384f1a54'
+replicasets = {replicaset1_uuid, replicaset2_uuid}
+
+-- Start the database with sharding
+vshard = require('vshard')
+vshard.storage.cfg(cfg, names[NAME])
+
+-- Bootstrap storage.
+require('lua_libs.bootstrap_test_storage')
diff --git a/test/reload_evolution/storage_1_b.lua b/test/reload_evolution/storage_1_b.lua
new file mode 120000
index 0000000..02572da
--- /dev/null
+++ b/test/reload_evolution/storage_1_b.lua
@@ -0,0 +1 @@
+storage_1_a.lua
\ No newline at end of file
diff --git a/test/reload_evolution/storage_2_a.lua b/test/reload_evolution/storage_2_a.lua
new file mode 120000
index 0000000..02572da
--- /dev/null
+++ b/test/reload_evolution/storage_2_a.lua
@@ -0,0 +1 @@
+storage_1_a.lua
\ No newline at end of file
diff --git a/test/reload_evolution/storage_2_b.lua b/test/reload_evolution/storage_2_b.lua
new file mode 120000
index 0000000..02572da
--- /dev/null
+++ b/test/reload_evolution/storage_2_b.lua
@@ -0,0 +1 @@
+storage_1_a.lua
\ No newline at end of file
diff --git a/test/reload_evolution/suite.ini b/test/reload_evolution/suite.ini
new file mode 100644
index 0000000..5f55418
--- /dev/null
+++ b/test/reload_evolution/suite.ini
@@ -0,0 +1,6 @@
+[default]
+core = tarantool
+description = Reload evolution tests
+script = test.lua
+is_parallel = False
+lua_libs = ../lua_libs ../../example/localcfg.lua
diff --git a/test/reload_evolution/test.lua b/test/reload_evolution/test.lua
new file mode 100644
index 0000000..ad0543a
--- /dev/null
+++ b/test/reload_evolution/test.lua
@@ -0,0 +1,9 @@
+#!/usr/bin/env tarantool
+
+require('strict').on()
+
+box.cfg{
+ listen = os.getenv("LISTEN"),
+}
+
+require('console').listen(os.getenv('ADMIN'))
diff --git a/test/unit/reload_evolution.result b/test/unit/reload_evolution.result
new file mode 100644
index 0000000..342ac24
--- /dev/null
+++ b/test/unit/reload_evolution.result
@@ -0,0 +1,45 @@
+test_run = require('test_run').new()
+---
+...
+fiber = require('fiber')
+---
+...
+log = require('log')
+---
+...
+util = require('util')
+---
+...
+reload_evolution = require('vshard.storage.reload_evolution')
+---
+...
+-- Init with the latest version.
+fake_M = { reload_evolution_version = reload_evolution.version }
+---
+...
+-- Test reload to the same version.
+reload_evolution.upgrade(fake_M)
+---
+...
+test_run:grep_log('default', 'vshard.storage.evolution') == nil
+---
+- true
+...
+-- Test downgrage version.
+log.info(string.rep('a', 1000))
+---
+...
+fake_M.reload_evolution_version = fake_M.reload_evolution_version + 1
+---
+...
+err = util.check_error(reload_evolution.upgrade, fake_M)
+---
+...
+err:match('auto%-downgrade is not implemented')
+---
+- auto-downgrade is not implemented
+...
+test_run:grep_log('default', 'vshard.storage.evolution', 1000) ~= nil
+---
+- false
+...
diff --git a/test/unit/reload_evolution.test.lua b/test/unit/reload_evolution.test.lua
new file mode 100644
index 0000000..c0fcdcd
--- /dev/null
+++ b/test/unit/reload_evolution.test.lua
@@ -0,0 +1,18 @@
+test_run = require('test_run').new()
+fiber = require('fiber')
+log = require('log')
+util = require('util')
+reload_evolution = require('vshard.storage.reload_evolution')
+-- Init with the latest version.
+fake_M = { reload_evolution_version = reload_evolution.version }
+
+-- Test reload to the same version.
+reload_evolution.upgrade(fake_M)
+test_run:grep_log('default', 'vshard.storage.evolution') == nil
+
+-- Test downgrage version.
+log.info(string.rep('a', 1000))
+fake_M.reload_evolution_version = fake_M.reload_evolution_version + 1
+err = util.check_error(reload_evolution.upgrade, fake_M)
+err:match('auto%-downgrade is not implemented')
+test_run:grep_log('default', 'vshard.storage.evolution', 1000) ~= nil
diff --git a/vshard/storage/init.lua b/vshard/storage/init.lua
index 07bd00c..3bec09f 100644
--- a/vshard/storage/init.lua
+++ b/vshard/storage/init.lua
@@ -10,6 +10,7 @@ if rawget(_G, MODULE_INTERNALS) then
local vshard_modules = {
'vshard.consts', 'vshard.error', 'vshard.cfg',
'vshard.replicaset', 'vshard.util',
+ 'vshard.storage.reload_evolution'
}
for _, module in pairs(vshard_modules) do
package.loaded[module] = nil
@@ -20,12 +21,16 @@ local lerror = require('vshard.error')
local lcfg = require('vshard.cfg')
local lreplicaset = require('vshard.replicaset')
local util = require('vshard.util')
+local reload_evolution = require('vshard.storage.reload_evolution')
local M = rawget(_G, MODULE_INTERNALS)
if not M then
--
-- The module is loaded for the first time.
--
+ -- !!!WARNING: any change of this table must be reflected in
+ -- `vshard.storage.reload_evolution` module to guarantee
+ -- reloadability of the module.
M = {
---------------- Common module attributes ----------------
-- The last passed configuration.
@@ -105,6 +110,11 @@ if not M then
-- a destination replicaset must drop already received
-- data.
rebalancer_sending_bucket = 0,
+
+ ------------------------- Reload -------------------------
+ -- Version of the loaded module. This number is used on
+ -- reload to determine which upgrade scripts to run.
+ reload_evolution_version = reload_evolution.version,
}
end
@@ -1863,6 +1873,7 @@ end
if not rawget(_G, MODULE_INTERNALS) then
rawset(_G, MODULE_INTERNALS, M)
else
+ reload_evolution.upgrade(M)
storage_cfg(M.current_cfg, M.this_replica.uuid)
M.module_version = M.module_version + 1
end
diff --git a/vshard/storage/reload_evolution.lua b/vshard/storage/reload_evolution.lua
new file mode 100644
index 0000000..f25ad49
--- /dev/null
+++ b/vshard/storage/reload_evolution.lua
@@ -0,0 +1,58 @@
+--
+-- This module is used to upgrade the vshard.storage on the fly.
+-- It updates internal Lua structures in case they are changed
+-- in a commit.
+--
+local log = require('log')
+
+--
+-- Array of upgrade functions.
+-- migrations[version] = function which upgrades module version
+-- from `version` to `version + 1`.
+--
+local migrations = {}
+
+-- Initialize reload_upgrade mechanism
+migrations[#migrations + 1] = function (M)
+ -- Code to update Lua objects.
+end
+
+--
+-- Perform an update based on a version stored in `M` (internals).
+-- @param M Old module internals which should be updated.
+--
+local function upgrade(M)
+ local start_version = M.reload_evolution_version or 1
+ if start_version > #migrations then
+ local err_msg = string.format(
+ 'vshard.storage.reload_evolution: ' ..
+ 'auto-downgrade is not implemented; ' ..
+ 'loaded version is %d, upgrade script version is %d',
+ start_version, #migrations
+ )
+ log.error(err_msg)
+ error(err_msg)
+ end
+ for i = start_version, #migrations do
+ local ok, err = pcall(migrations[i], M)
+ if ok then
+ log.info('vshard.storage.reload_evolution: upgraded to %d version',
+ i)
+ else
+ local err_msg = string.format(
+ 'vshard.storage.reload_evolution: ' ..
+ 'error during upgrade to %d version: %s', i, err
+ )
+ log.error(err_msg)
+ error(err_msg)
+ end
+ -- Update the version just after upgrade to have an
+ -- actual version in case of an error.
+ M.reload_evolution_version = i
+ end
+end
+
+return {
+ version = #migrations,
+ upgrade = upgrade,
+}
--
2.14.1
^ permalink raw reply [flat|nested] 14+ messages in thread
* [tarantool-patches] Re: [PATCH 1/4] Add test on error during reconfigure
2018-07-23 11:14 ` [tarantool-patches] [PATCH 1/4] Add test on error during reconfigure AKhatskevich
@ 2018-07-23 13:18 ` Vladislav Shpilevoy
0 siblings, 0 replies; 14+ messages in thread
From: Vladislav Shpilevoy @ 2018-07-23 13:18 UTC (permalink / raw)
To: tarantool-patches, AKhatskevich
Pushed to the master with one minor change:
* use util.check_error in storage/storage.test.lua.
On 23/07/2018 14:14, AKhatskevich wrote:
> In case reconfigure process fails, the node should continue
> work properly.
> ---
> test/lua_libs/util.lua | 24 ++++++++++++++++++++++++
> test/router/router.result | 30 ++++++++++++++++++++++++++++++
> test/router/router.test.lua | 9 +++++++++
> test/storage/storage.result | 39 +++++++++++++++++++++++++++++++++++++++
> test/storage/storage.test.lua | 12 ++++++++++++
> vshard/router/init.lua | 7 +++++++
> vshard/storage/init.lua | 9 +++++++++
> 7 files changed, 130 insertions(+)
>
^ permalink raw reply [flat|nested] 14+ messages in thread
* [tarantool-patches] Re: [PATCH 2/4] Complete module reload
2018-07-23 11:14 ` [tarantool-patches] [PATCH 2/4] Complete module reload AKhatskevich
@ 2018-07-23 13:31 ` Vladislav Shpilevoy
2018-07-23 13:45 ` Alex Khatskevich
0 siblings, 1 reply; 14+ messages in thread
From: Vladislav Shpilevoy @ 2018-07-23 13:31 UTC (permalink / raw)
To: tarantool-patches, AKhatskevich
Hi! Thanks for the patch!
> diff --git a/vshard/replicaset.lua b/vshard/replicaset.lua
> index 99f59aa..6c8d477 100644
> --- a/vshard/replicaset.lua
> +++ b/vshard/replicaset.lua
> @@ -21,6 +21,7 @@
> -- requests to the replica>,
> -- net_sequential_fail = <count of sequential failed
> -- requests to the replica>,
> +-- is_outdated = nil/true,
https://github.com/tarantool/vshard/blob/kh/gh-112-reload-mt-2/vshard/replicaset.lua#L24
Looks like the version on the branch actually is outdated
instead of the replica object. Please, push the latest
version.
> -- }
> -- },
> -- master = <master server from the array above>,
> @@ -34,6 +35,7 @@
> -- etalon_bucket_count = <bucket count, that must be stored
> -- on this replicaset to reach the
> -- balance in a cluster>,
> +-- is_outdated = nil/true,
> -- }
> --
> -- replicasets = {
^ permalink raw reply [flat|nested] 14+ messages in thread
* [tarantool-patches] Re: [PATCH 3/4] Tests: separate bootstrap routine to a lua_libs
2018-07-23 11:14 ` [tarantool-patches] [PATCH 3/4] Tests: separate bootstrap routine to a lua_libs AKhatskevich
@ 2018-07-23 13:36 ` Vladislav Shpilevoy
2018-07-23 17:19 ` Alex Khatskevich
0 siblings, 1 reply; 14+ messages in thread
From: Vladislav Shpilevoy @ 2018-07-23 13:36 UTC (permalink / raw)
To: tarantool-patches, AKhatskevich
Thank you for working on the patch!
1. Please, do not start commit title with capital letter,
when it is related to a subsystem. Here you should write
test: separate bootstrap ...
On 23/07/2018 14:14, AKhatskevich wrote:
> What is moved to `test/lul_libs/bootstrap_test_storage.lua`:
2. 'lul' libs?
> 1. create schema
> 2. create main stored procedures
> 3. `wait_rebalancer_state` procedure
>
> This code would be reused it further commits.
> ---
> test/lua_libs/bootstrap_test_storage.lua | 50 ++++++++++++++++++++++
> test/rebalancer/box_1_a.lua | 47 ++------------------
> test/rebalancer/errinj.result | 2 +-
> test/rebalancer/errinj.test.lua | 2 +-
> test/rebalancer/rebalancer.result | 2 +-
> test/rebalancer/rebalancer.test.lua | 2 +-
> test/rebalancer/rebalancer_lock_and_pin.result | 2 +-
> test/rebalancer/rebalancer_lock_and_pin.test.lua | 2 +-
> test/rebalancer/restart_during_rebalancing.result | 2 +-
> .../rebalancer/restart_during_rebalancing.test.lua | 2 +-
> test/rebalancer/stress_add_remove_rs.result | 2 +-
> test/rebalancer/stress_add_remove_rs.test.lua | 2 +-
> .../rebalancer/stress_add_remove_several_rs.result | 2 +-
> .../stress_add_remove_several_rs.test.lua | 2 +-
> test/rebalancer/suite.ini | 2 +-
> 15 files changed, 66 insertions(+), 57 deletions(-)
> create mode 100644 test/lua_libs/bootstrap_test_storage.lua
>
> diff --git a/test/lua_libs/bootstrap_test_storage.lua b/test/lua_libs/bootstrap_test_storage.lua
> new file mode 100644
> index 0000000..62c2f78
> --- /dev/null
> +++ b/test/lua_libs/bootstrap_test_storage.lua
3. Please, just merge it into util. It is actually just util.
> diff --git a/test/rebalancer/errinj.result b/test/rebalancer/errinj.result
> index d09349e..826c2c6 100644
> --- a/test/rebalancer/errinj.result
> +++ b/test/rebalancer/errinj.result
> @@ -13,7 +13,7 @@ test_run:create_cluster(REPLICASET_1, 'rebalancer')
> test_run:create_cluster(REPLICASET_2, 'rebalancer')
> ---
> ...
> -util = require('util')
> +util = require('lua_libs.util')
4. Please, don't. This should disappear when you merge the utils
into util.lua.
> ---
> ...
> util.wait_master(test_run, REPLICASET_1, 'box_1_a')
^ permalink raw reply [flat|nested] 14+ messages in thread
* [tarantool-patches] Re: [PATCH 2/4] Complete module reload
2018-07-23 13:31 ` [tarantool-patches] " Vladislav Shpilevoy
@ 2018-07-23 13:45 ` Alex Khatskevich
2018-07-23 14:58 ` Vladislav Shpilevoy
0 siblings, 1 reply; 14+ messages in thread
From: Alex Khatskevich @ 2018-07-23 13:45 UTC (permalink / raw)
To: Vladislav Shpilevoy, tarantool-patches
On 23.07.2018 16:31, Vladislav Shpilevoy wrote:
> Hi! Thanks for the patch!
>
>> diff --git a/vshard/replicaset.lua b/vshard/replicaset.lua
>> index 99f59aa..6c8d477 100644
>> --- a/vshard/replicaset.lua
>> +++ b/vshard/replicaset.lua
>> @@ -21,6 +21,7 @@
>> -- requests to the replica>,
>> -- net_sequential_fail = <count of sequential failed
>> -- requests to the replica>,
>> +-- is_outdated = nil/true,
>
> https://github.com/tarantool/vshard/blob/kh/gh-112-reload-mt-2/vshard/replicaset.lua#L24
>
>
> Looks like the version on the branch actually is outdated
> instead of the replica object. Please, push the latest
> version.
Sorry. Pushed.
^ permalink raw reply [flat|nested] 14+ messages in thread
* [tarantool-patches] Re: [PATCH 4/4] Introduce storage reload evolution
2018-07-23 11:14 ` [tarantool-patches] [PATCH 4/4] Introduce storage reload evolution AKhatskevich
@ 2018-07-23 14:44 ` Vladislav Shpilevoy
2018-07-23 20:10 ` Alex Khatskevich
0 siblings, 1 reply; 14+ messages in thread
From: Vladislav Shpilevoy @ 2018-07-23 14:44 UTC (permalink / raw)
To: tarantool-patches, AKhatskevich
Thanks for the patch! See 4 comments below.
On 23/07/2018 14:14, AKhatskevich wrote:
> Changes:
> 1. Introduce storage reload evolution.
> 2. Setup cross-version reload testing.
>
> 1:
> This mechanism updates Lua objects on reload in case they are
> changed in a new vshard.storage version.
>
> Since this commit, any change in vshard.storage.M has to be
> reflected in vshard.storage.reload_evolution to guarantee
> correct reload.
>
> 2:
> The testing uses git infrastructure and is performed in the following
> way:
> 1. Copy old version of vshard to a temp folder.
> 2. Run vshard on this code.
> 3. Checkout the latest version of the vshard sources.
> 4. Reload vshard storage.
> 5. Make sure it works (Perform simple tests).
>
> Notes:
> * this patch contains some legacy-driven decisions:
> 1. SOURCEDIR path retrieved differently in case of
> packpack build.
> 2. git directory in the `reload_evolution/storage` test
> is copied with respect to Centos 7 and `ro` mode of
> SOURCEDIR.
>
> diff --git a/test/reload_evolution/storage.result b/test/reload_evolution/storage.result
> new file mode 100644
> index 0000000..54ff6b7
> --- /dev/null
> +++ b/test/reload_evolution/storage.result
> @@ -0,0 +1,248 @@
> +test_run = require('test_run').new()
> +---
> +...
> +git_util = require('lua_libs.git_util')
> +---
> +...
> +util = require('lua_libs.util')
> +---
> +...
> +vshard_copy_path = util.BUILDDIR .. '/test/var/vshard_git_tree_copy'
> +---
> +...
> +evolution_log = git_util.log_hashes({args='vshard/storage/reload_evolution.lua', dir=util.SOURCEDIR})
> +---
> +...
> +-- Cleanup the directory after a previous build.
> +_ = os.execute('rm -rf ' .. vshard_copy_path)
> +---
> +...
> +-- 1. `git worktree` cannot be used because PACKPACK mounts
> +-- `/source/` in `ro` mode.
> +-- 2. Just `cp -rf` cannot be used due to a little different
> +-- behavior in Centos 7.
> +_ = os.execute('mkdir ' .. vshard_copy_path)
> +---
> +...
> +_ = os.execute("cd " .. util.SOURCEDIR .. ' && cp -rf `ls -A --ignore=build` ' .. vshard_copy_path)
> +---
> +...
> +-- Checkout the first commit with a reload_evolution mechanism.
> +git_util.exec_cmd({cmd='checkout', args='-f', dir=vshard_copy_path})
> +---
> +...
> +git_util.exec_cmd({cmd='checkout', args=evolution_log[#evolution_log] .. '~1', dir=vshard_copy_path})
> +---
> +...
> +REPLICASET_1 = { 'storage_1_a', 'storage_1_b' }
> +---
> +...
> +REPLICASET_2 = { 'storage_2_a', 'storage_2_b' }
> +---
> +...
> +test_run:create_cluster(REPLICASET_1, 'reload_evolution')
> +---
> +...
> +test_run:create_cluster(REPLICASET_2, 'reload_evolution')
> +---
> +...
> +util = require('lua_libs.util')
> +---
> +...
> +util.wait_master(test_run, REPLICASET_1, 'storage_1_a')
> +---
> +...
> +util.wait_master(test_run, REPLICASET_2, 'storage_2_a')
> +---
> +...
> +test_run:switch('storage_1_a')
> +---
> +- true
> +...
> +vshard.storage.bucket_force_create(1, vshard.consts.DEFAULT_BUCKET_COUNT / 2)
> +---
> +- true
> +...
> +bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
> +---
> +...
> +test_run:switch('storage_2_a')
> +---
> +- true
> +...
> +fiber = require('fiber')
> +---
> +...
> +vshard.storage.bucket_force_create(vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1, vshard.consts.DEFAULT_BUCKET_COUNT / 2)
> +---
> +- true
> +...
> +bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
> +---
> +...
> +vshard.storage.internal.reload_evolution_version
> +---
> +- null
> +...
> +box.space.test:insert({42, bucket_id_to_move})
> +---
> +- [42, 3000]
> +...
> +while test_run:grep_log('storage_2_a', 'The cluster is balanced ok') == nil do vshard.storage.rebalancer_wakeup() fiber.sleep(0.1) end
1. Now you have wait_rebalancer_state util from the previous commit.
> +---
> +...
> +test_run:switch('default')
> +---
> +- true
> +...
> +git_util.exec_cmd({cmd='checkout', args=evolution_log[1], dir=vshard_copy_path})
> +---
> +...
> +test_run:switch('storage_2_a')
> +---
> +- true
> +...
> +package.loaded["vshard.storage"] = nil
> +---
> +...
> +vshard.storage = require("vshard.storage")
> +---
> +...
> +test_run:grep_log('storage_2_a', 'vshard.storage.reload_evolution: upgraded to') ~= nil
> +---
> +- true
> +...
> +vshard.storage.internal.reload_evolution_version
> +---
> +- 1
> +...
> +-- Make sure storage operates well.
> +vshard.storage.bucket_force_drop(2000)
> +---
> +- true
> +...
> +vshard.storage.bucket_force_create(2000)
> +---
> +- true
> +...
> +vshard.storage.buckets_info()[2000]
> +---
> +- status: active
> + id: 2000
> +...
> +vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
> +---
> +- true
> +- - [42, 3000]
> +...
> +vshard.storage.bucket_send(bucket_id_to_move, replicaset1_uuid)
> +---
> +- true
> +...
> +vshard.storage.garbage_collector_wakeup()
> +---
> +...
> +fiber = require('fiber')
> +---
> +...
> +while box.space._bucket:get({bucket_id_to_move}) do fiber.sleep(0.01) end
> +---
> +...
> +test_run:switch('storage_1_a')
> +---
> +- true
> +...
> +vshard.storage.bucket_send(bucket_id_to_move, replicaset2_uuid)
> +---
> +- true
> +...
> +test_run:switch('storage_2_a')
> +---
> +- true
> +...
> +vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
> +---
> +- true
> +- - [42, 3000]
> +...
> +-- Check info() does not fail.
> +vshard.storage.info() ~= nil
> +---
> +- true
> +...
> +--
> +-- Send buckets to create a disbalance. Wait until the rebalancer
> +-- repairs it. Similar to `tests/rebalancer/rebalancer.test.lua`.
> +--
> +vshard.storage.rebalancer_disable()
> +---
> +...
> +move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
> +---
> +...
> +move_cnt = 100
> +---
> +...
> +assert(move_start + move_cnt < vshard.consts.DEFAULT_BUCKET_COUNT)
> +---
> +- true
> +...
> +for i = move_start, move_start + move_cnt - 1 do box.space._bucket:delete{i} end
> +---
> +...
> +box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
> +---
> +- 1400
> +...
> +test_run:switch('storage_1_a')
> +---
> +- true
> +...
> +move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
> +---
> +...
> +move_cnt = 100
> +---
> +...
> +vshard.storage.bucket_force_create(move_start, move_cnt)
> +---
> +- true
> +...
> +box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
> +---
> +- 1600
> +...
> +test_run:switch('storage_2_a')
> +---
> +- true
> +...
> +vshard.storage.rebalancer_enable()
> +---
> +...
> +vshard.storage.rebalancer_wakeup()
2. You do not need explicit rebalancer_wakeup. wait_rebalancer_state
calls it.
> +---
> +...
> +wait_rebalancer_state("Rebalance routes are sent", test_run)
> +---
> +...
> +wait_rebalancer_state('The cluster is balanced ok', test_run)
> +---
> +...
> +box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
> +---
> +- 1500
> +...
> +test_run:switch('default')
> +---
> +- true
> +...
> +test_run:drop_cluster(REPLICASET_2)
> +---
> +...
> +test_run:drop_cluster(REPLICASET_1)
> +---
> +...
> +test_run:cmd('clear filter')
> +---
> +- true
> +...
> diff --git a/test/unit/reload_evolution.result b/test/unit/reload_evolution.result
> new file mode 100644
> index 0000000..342ac24
> --- /dev/null
> +++ b/test/unit/reload_evolution.result
> @@ -0,0 +1,45 @@
> +test_run = require('test_run').new()
> +---
> +...
> +fiber = require('fiber')
> +---
> +...
> +log = require('log')
> +---
> +...
> +util = require('util')
> +---
> +...
> +reload_evolution = require('vshard.storage.reload_evolution')
> +---
> +...
> +-- Init with the latest version.
> +fake_M = { reload_evolution_version = reload_evolution.version }
> +---
> +...
> +-- Test reload to the same version.
> +reload_evolution.upgrade(fake_M)
> +---
> +...
> +test_run:grep_log('default', 'vshard.storage.evolution') == nil
> +---
> +- true
> +...
> +-- Test downgrage version.
> +log.info(string.rep('a', 1000))
> +---
> +...
> +fake_M.reload_evolution_version = fake_M.reload_evolution_version + 1
> +---
> +...
> +err = util.check_error(reload_evolution.upgrade, fake_M)
> +---
> +...
> +err:match('auto%-downgrade is not implemented')
> +---
> +- auto-downgrade is not implemented
3. Why do you need match? check_error output is ok already. And
what is 'auto%'? I see that you always print exactly "auto-downgrade"
in reload_evolution.lua.
> +...
> +test_run:grep_log('default', 'vshard.storage.evolution', 1000) ~= nil
> +---
> +- false
> +...
> @@ -105,6 +110,11 @@ if not M then
> -- a destination replicaset must drop already received
> -- data.
> rebalancer_sending_bucket = 0,
> +
> + ------------------------- Reload -------------------------
> + -- Version of the loaded module. This number is used on
> + -- reload to determine which upgrade scripts to run.
> + reload_evolution_version = reload_evolution.version,
4. Please, rename it to just 'version' or 'reload_version' or
'module_version'. 'Reload_evolution_version' is too long and
complex.
> }
> end
>
^ permalink raw reply [flat|nested] 14+ messages in thread
* [tarantool-patches] Re: [PATCH 2/4] Complete module reload
2018-07-23 13:45 ` Alex Khatskevich
@ 2018-07-23 14:58 ` Vladislav Shpilevoy
0 siblings, 0 replies; 14+ messages in thread
From: Vladislav Shpilevoy @ 2018-07-23 14:58 UTC (permalink / raw)
To: Alex Khatskevich, tarantool-patches
On 23/07/2018 16:45, Alex Khatskevich wrote:
>
>
> On 23.07.2018 16:31, Vladislav Shpilevoy wrote:
>> Hi! Thanks for the patch!
>>
>>> diff --git a/vshard/replicaset.lua b/vshard/replicaset.lua
>>> index 99f59aa..6c8d477 100644
>>> --- a/vshard/replicaset.lua
>>> +++ b/vshard/replicaset.lua
>>> @@ -21,6 +21,7 @@
>>> -- requests to the replica>,
>>> -- net_sequential_fail = <count of sequential failed
>>> -- requests to the replica>,
>>> +-- is_outdated = nil/true,
>>
>> https://github.com/tarantool/vshard/blob/kh/gh-112-reload-mt-2/vshard/replicaset.lua#L24
>>
>> Looks like the version on the branch actually is outdated
>> instead of the replica object. Please, push the latest
>> version.
> Sorry. Pushed.
Thanks! Merged into the master.
^ permalink raw reply [flat|nested] 14+ messages in thread
* [tarantool-patches] Re: [PATCH 3/4] Tests: separate bootstrap routine to a lua_libs
2018-07-23 13:36 ` [tarantool-patches] " Vladislav Shpilevoy
@ 2018-07-23 17:19 ` Alex Khatskevich
0 siblings, 0 replies; 14+ messages in thread
From: Alex Khatskevich @ 2018-07-23 17:19 UTC (permalink / raw)
To: Vladislav Shpilevoy, tarantool-patches
On 23.07.2018 16:36, Vladislav Shpilevoy wrote:
> Thank you for working on the patch!
>
> 1. Please, do not start commit title with capital letter,
> when it is related to a subsystem. Here you should write
>
> test: separate bootstrap ...
fixed: `tests: separate bootstrap routine to a lua_libs`
>
> On 23/07/2018 14:14, AKhatskevich wrote:
>> What is moved to `test/lul_libs/bootstrap_test_storage.lua`:
>
> 2. 'lul' libs?
fixed
>
>>
>> diff --git a/test/lua_libs/bootstrap_test_storage.lua
>> b/test/lua_libs/bootstrap_test_storage.lua
>> new file mode 100644
>> index 0000000..62c2f78
>> --- /dev/null
>> +++ b/test/lua_libs/bootstrap_test_storage.lua
>
> 3. Please, just merge it into util. It is actually just util.
3. discussed verbally. file renamed to bootstrap.lua
>
>> diff --git a/test/rebalancer/errinj.result
>> b/test/rebalancer/errinj.result
>> index d09349e..826c2c6 100644
>> --- a/test/rebalancer/errinj.result
>> +++ b/test/rebalancer/errinj.result
>> @@ -13,7 +13,7 @@ test_run:create_cluster(REPLICASET_1, 'rebalancer')
>> test_run:create_cluster(REPLICASET_2, 'rebalancer')
>> ---
>> ...
>> -util = require('util')
>> +util = require('lua_libs.util')
>
> 4. Please, don't. This should disappear when you merge the utils
> into util.lua.
4. Same as (3)
full diff:
commit c4c5a3a9678153e7e3315bd11f2f7c882dafbb0c
Author: AKhatskevich <avkhatskevich@tarantool.org>
Date: Sat Jul 21 02:25:08 2018 +0300
tests: separate bootstrap routine to a lua_libs
What is moved to `test/lua_libs/bootstrap.lua`:
1. create schema
2. create main stored procedures
3. `wait_rebalancer_state` procedure
This code will be reused in further commits.
diff --git a/test/lua_libs/bootstrap.lua b/test/lua_libs/bootstrap.lua
new file mode 100644
index 0000000..62c2f78
--- /dev/null
+++ b/test/lua_libs/bootstrap.lua
@@ -0,0 +1,50 @@
+local log = require('log')
+
+function init_schema()
+ local format = {}
+ format[1] = {name = 'field', type = 'unsigned'}
+ format[2] = {name = 'bucket_id', type = 'unsigned'}
+ local s = box.schema.create_space('test', {format = format})
+ local pk = s:create_index('pk')
+ local bucket_id_idx =
+ s:create_index('vbucket', {parts = {'bucket_id'},
+ unique = false})
+end
+
+box.once('schema', function()
+ box.schema.func.create('do_replace')
+ box.schema.role.grant('public', 'execute', 'function', 'do_replace')
+ box.schema.func.create('do_select')
+ box.schema.role.grant('public', 'execute', 'function', 'do_select')
+ init_schema()
+end)
+
+function do_replace(...)
+ box.space.test:replace(...)
+ return true
+end
+
+function do_select(...)
+ return box.space.test:select(...)
+end
+
+function check_consistency()
+ for _, tuple in box.space.test:pairs() do
+ assert(box.space._bucket:get{tuple.bucket_id})
+ end
+ return true
+end
+
+--
+-- Wait a specified log message.
+-- Requirements:
+-- * Should be executed from a storage with a rebalancer.
+-- * NAME - global variable, name of instance should be set.
+function wait_rebalancer_state(state, test_run)
+ log.info(string.rep('a', 1000))
+ vshard.storage.rebalancer_wakeup()
+ while not test_run:grep_log(NAME, state, 1000) do
+ fiber.sleep(0.1)
+ vshard.storage.rebalancer_wakeup()
+ end
+end
diff --git a/test/rebalancer/box_1_a.lua b/test/rebalancer/box_1_a.lua
index 8fddcf0..2ca8306 100644
--- a/test/rebalancer/box_1_a.lua
+++ b/test/rebalancer/box_1_a.lua
@@ -2,7 +2,7 @@
-- Get instance name
require('strict').on()
local fio = require('fio')
-local NAME = fio.basename(arg[0], '.lua')
+NAME = fio.basename(arg[0], '.lua')
log = require('log')
require('console').listen(os.getenv('ADMIN'))
fiber = require('fiber')
@@ -23,40 +23,8 @@ if NAME == 'box_4_a' or NAME == 'box_4_b' or
end
vshard.storage.cfg(cfg, names.replica_uuid[NAME])
-function init_schema()
- local format = {}
- format[1] = {name = 'field', type = 'unsigned'}
- format[2] = {name = 'bucket_id', type = 'unsigned'}
- local s = box.schema.create_space('test', {format = format})
- local pk = s:create_index('pk')
- local bucket_id_idx =
- s:create_index('vbucket', {parts = {'bucket_id'},
- unique = false})
-end
-
-box.once('schema', function()
- box.schema.func.create('do_replace')
- box.schema.role.grant('public', 'execute', 'function', 'do_replace')
- box.schema.func.create('do_select')
- box.schema.role.grant('public', 'execute', 'function', 'do_select')
- init_schema()
-end)
-
-function do_replace(...)
- box.space.test:replace(...)
- return true
-end
-
-function do_select(...)
- return box.space.test:select(...)
-end
-
-function check_consistency()
- for _, tuple in box.space.test:pairs() do
- assert(box.space._bucket:get{tuple.bucket_id})
- end
- return true
-end
+-- Bootstrap storage.
+require('lua_libs.bootstrap')
function switch_rs1_master()
local replica_uuid = names.replica_uuid
@@ -68,12 +36,3 @@ end
function nullify_rs_weight()
cfg.sharding[names.rs_uuid[1]].weight = 0
end
-
-function wait_rebalancer_state(state, test_run)
- log.info(string.rep('a', 1000))
- vshard.storage.rebalancer_wakeup()
- while not test_run:grep_log(NAME, state, 1000) do
- fiber.sleep(0.1)
- vshard.storage.rebalancer_wakeup()
- end
-end
diff --git a/test/rebalancer/errinj.result b/test/rebalancer/errinj.result
index d09349e..826c2c6 100644
--- a/test/rebalancer/errinj.result
+++ b/test/rebalancer/errinj.result
@@ -13,7 +13,7 @@ test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
---
...
-util = require('util')
+util = require('lua_libs.util')
---
...
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
diff --git a/test/rebalancer/errinj.test.lua
b/test/rebalancer/errinj.test.lua
index d6a2920..fc0730c 100644
--- a/test/rebalancer/errinj.test.lua
+++ b/test/rebalancer/errinj.test.lua
@@ -5,7 +5,7 @@ REPLICASET_2 = { 'box_2_a', 'box_2_b' }
test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
-util = require('util')
+util = require('lua_libs.util')
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
util.wait_master(test_run, REPLICASET_2, 'box_2_a')
diff --git a/test/rebalancer/rebalancer.result
b/test/rebalancer/rebalancer.result
index 88cbaae..71e43e1 100644
--- a/test/rebalancer/rebalancer.result
+++ b/test/rebalancer/rebalancer.result
@@ -13,7 +13,7 @@ test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
---
...
-util = require('util')
+util = require('lua_libs.util')
---
...
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
diff --git a/test/rebalancer/rebalancer.test.lua
b/test/rebalancer/rebalancer.test.lua
index 01f2061..1b7ddae 100644
--- a/test/rebalancer/rebalancer.test.lua
+++ b/test/rebalancer/rebalancer.test.lua
@@ -5,7 +5,7 @@ REPLICASET_2 = { 'box_2_a', 'box_2_b' }
test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
-util = require('util')
+util = require('lua_libs.util')
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
util.wait_master(test_run, REPLICASET_2, 'box_2_a')
diff --git a/test/rebalancer/rebalancer_lock_and_pin.result
b/test/rebalancer/rebalancer_lock_and_pin.result
index dd9fe47..0f2921c 100644
--- a/test/rebalancer/rebalancer_lock_and_pin.result
+++ b/test/rebalancer/rebalancer_lock_and_pin.result
@@ -16,7 +16,7 @@ test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
---
...
-util = require('util')
+util = require('lua_libs.util')
---
...
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
diff --git a/test/rebalancer/rebalancer_lock_and_pin.test.lua
b/test/rebalancer/rebalancer_lock_and_pin.test.lua
index fe866c4..3a2daa0 100644
--- a/test/rebalancer/rebalancer_lock_and_pin.test.lua
+++ b/test/rebalancer/rebalancer_lock_and_pin.test.lua
@@ -6,7 +6,7 @@ REPLICASET_3 = { 'box_3_a', 'box_3_b' }
test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
-util = require('util')
+util = require('lua_libs.util')
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
util.wait_master(test_run, REPLICASET_2, 'box_2_a')
diff --git a/test/rebalancer/restart_during_rebalancing.result
b/test/rebalancer/restart_during_rebalancing.result
index d2b8a12..0eb0f2e 100644
--- a/test/rebalancer/restart_during_rebalancing.result
+++ b/test/rebalancer/restart_during_rebalancing.result
@@ -25,7 +25,7 @@ test_run:create_cluster(REPLICASET_3, 'rebalancer')
test_run:create_cluster(REPLICASET_4, 'rebalancer')
---
...
-util = require('util')
+util = require('lua_libs.util')
---
...
util.wait_master(test_run, REPLICASET_1, 'fullbox_1_a')
diff --git a/test/rebalancer/restart_during_rebalancing.test.lua
b/test/rebalancer/restart_during_rebalancing.test.lua
index 5b1a8df..7b707ca 100644
--- a/test/rebalancer/restart_during_rebalancing.test.lua
+++ b/test/rebalancer/restart_during_rebalancing.test.lua
@@ -9,7 +9,7 @@ test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
test_run:create_cluster(REPLICASET_3, 'rebalancer')
test_run:create_cluster(REPLICASET_4, 'rebalancer')
-util = require('util')
+util = require('lua_libs.util')
util.wait_master(test_run, REPLICASET_1, 'fullbox_1_a')
util.wait_master(test_run, REPLICASET_2, 'fullbox_2_a')
util.wait_master(test_run, REPLICASET_3, 'fullbox_3_a')
diff --git a/test/rebalancer/stress_add_remove_rs.result
b/test/rebalancer/stress_add_remove_rs.result
index 8a955e2..10bcaac 100644
--- a/test/rebalancer/stress_add_remove_rs.result
+++ b/test/rebalancer/stress_add_remove_rs.result
@@ -16,7 +16,7 @@ test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
---
...
-util = require('util')
+util = require('lua_libs.util')
---
...
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
diff --git a/test/rebalancer/stress_add_remove_rs.test.lua
b/test/rebalancer/stress_add_remove_rs.test.lua
index c80df40..b9bb027 100644
--- a/test/rebalancer/stress_add_remove_rs.test.lua
+++ b/test/rebalancer/stress_add_remove_rs.test.lua
@@ -6,7 +6,7 @@ REPLICASET_3 = { 'box_3_a', 'box_3_b' }
test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
-util = require('util')
+util = require('lua_libs.util')
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
util.wait_master(test_run, REPLICASET_2, 'box_2_a')
diff --git a/test/rebalancer/stress_add_remove_several_rs.result
b/test/rebalancer/stress_add_remove_several_rs.result
index d6008b8..611362c 100644
--- a/test/rebalancer/stress_add_remove_several_rs.result
+++ b/test/rebalancer/stress_add_remove_several_rs.result
@@ -19,7 +19,7 @@ test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
---
...
-util = require('util')
+util = require('lua_libs.util')
---
...
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
diff --git a/test/rebalancer/stress_add_remove_several_rs.test.lua
b/test/rebalancer/stress_add_remove_several_rs.test.lua
index 3cc105e..9acb8de 100644
--- a/test/rebalancer/stress_add_remove_several_rs.test.lua
+++ b/test/rebalancer/stress_add_remove_several_rs.test.lua
@@ -7,7 +7,7 @@ REPLICASET_4 = { 'box_4_a', 'box_4_b' }
test_run:create_cluster(REPLICASET_1, 'rebalancer')
test_run:create_cluster(REPLICASET_2, 'rebalancer')
-util = require('util')
+util = require('lua_libs.util')
util.wait_master(test_run, REPLICASET_1, 'box_1_a')
util.wait_master(test_run, REPLICASET_2, 'box_2_a')
diff --git a/test/rebalancer/suite.ini b/test/rebalancer/suite.ini
index afc5141..8689da5 100644
--- a/test/rebalancer/suite.ini
+++ b/test/rebalancer/suite.ini
@@ -4,6 +4,6 @@ description = Rebalancer tests
script = test.lua
is_parallel = False
release_disabled = errinj.test.lua
-lua_libs = ../lua_libs/util.lua config.lua names.lua router_1.lua
+lua_libs = ../lua_libs config.lua names.lua router_1.lua
box_1_a.lua box_1_b.lua box_2_a.lua box_2_b.lua
box_3_a.lua box_3_b.lua rebalancer_utils.lua
^ permalink raw reply [flat|nested] 14+ messages in thread
* [tarantool-patches] Re: [PATCH 4/4] Introduce storage reload evolution
2018-07-23 14:44 ` [tarantool-patches] " Vladislav Shpilevoy
@ 2018-07-23 20:10 ` Alex Khatskevich
0 siblings, 0 replies; 14+ messages in thread
From: Alex Khatskevich @ 2018-07-23 20:10 UTC (permalink / raw)
To: Vladislav Shpilevoy, tarantool-patches
On 23.07.2018 17:44, Vladislav Shpilevoy wrote:
> Thanks for the patch! See 4 comments below.
>
> On 23/07/2018 14:14, AKhatskevich wrote:
>> Changes:
>> 1. Introduce storage reload evolution.
>> 2. Setup cross-version reload testing.
>>
>> 1:
>> This mechanism updates Lua objects on reload in case they are
>> changed in a new vshard.storage version.
>>
>> Since this commit, any change in vshard.storage.M has to be
>> reflected in vshard.storage.reload_evolution to guarantee
>> correct reload.
>>
>> 2:
>> The testing uses git infrastructure and is performed in the following
>> way:
>> 1. Copy old version of vshard to a temp folder.
>> 2. Run vshard on this code.
>> 3. Checkout the latest version of the vshard sources.
>> 4. Reload vshard storage.
>> 5. Make sure it works (Perform simple tests).
>>
>> Notes:
>> * this patch contains some legacy-driven decisions:
>> 1. SOURCEDIR path retrieved differently in case of
>> packpack build.
>> 2. git directory in the `reload_evolution/storage` test
>> is copied with respect to Centos 7 and `ro` mode of
>> SOURCEDIR.
>>
>> diff --git a/test/reload_evolution/storage.result
>> b/test/reload_evolution/storage.result
>> new file mode 100644
>> index 0000000..54ff6b7
>> --- /dev/null
>> +++ b/test/reload_evolution/storage.result
>> @@ -0,0 +1,248 @@
>> +test_run = require('test_run').new()
>> +---
>> +...
>> +git_util = require('lua_libs.git_util')
>> +---
>> +...
>> +util = require('lua_libs.util')
>> +---
>> +...
>> +vshard_copy_path = util.BUILDDIR .. '/test/var/vshard_git_tree_copy'
>> +---
>> +...
>> +evolution_log =
>> git_util.log_hashes({args='vshard/storage/reload_evolution.lua',
>> dir=util.SOURCEDIR})
>> +---
>> +...
>> +-- Cleanup the directory after a previous build.
>> +_ = os.execute('rm -rf ' .. vshard_copy_path)
>> +---
>> +...
>> +-- 1. `git worktree` cannot be used because PACKPACK mounts
>> +-- `/source/` in `ro` mode.
>> +-- 2. Just `cp -rf` cannot be used due to a little different
>> +-- behavior in Centos 7.
>> +_ = os.execute('mkdir ' .. vshard_copy_path)
>> +---
>> +...
>> +_ = os.execute("cd " .. util.SOURCEDIR .. ' && cp -rf `ls -A
>> --ignore=build` ' .. vshard_copy_path)
>> +---
>> +...
>> +-- Checkout the first commit with a reload_evolution mechanism.
>> +git_util.exec_cmd({cmd='checkout', args='-f', dir=vshard_copy_path})
>> +---
>> +...
>> +git_util.exec_cmd({cmd='checkout',
>> args=evolution_log[#evolution_log] .. '~1', dir=vshard_copy_path})
>> +---
>> +...
>> +REPLICASET_1 = { 'storage_1_a', 'storage_1_b' }
>> +---
>> +...
>> +REPLICASET_2 = { 'storage_2_a', 'storage_2_b' }
>> +---
>> +...
>> +test_run:create_cluster(REPLICASET_1, 'reload_evolution')
>> +---
>> +...
>> +test_run:create_cluster(REPLICASET_2, 'reload_evolution')
>> +---
>> +...
>> +util = require('lua_libs.util')
>> +---
>> +...
>> +util.wait_master(test_run, REPLICASET_1, 'storage_1_a')
>> +---
>> +...
>> +util.wait_master(test_run, REPLICASET_2, 'storage_2_a')
>> +---
>> +...
>> +test_run:switch('storage_1_a')
>> +---
>> +- true
>> +...
>> +vshard.storage.bucket_force_create(1,
>> vshard.consts.DEFAULT_BUCKET_COUNT / 2)
>> +---
>> +- true
>> +...
>> +bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
>> +---
>> +...
>> +test_run:switch('storage_2_a')
>> +---
>> +- true
>> +...
>> +fiber = require('fiber')
>> +---
>> +...
>> +vshard.storage.bucket_force_create(vshard.consts.DEFAULT_BUCKET_COUNT
>> / 2 + 1, vshard.consts.DEFAULT_BUCKET_COUNT / 2)
>> +---
>> +- true
>> +...
>> +bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
>> +---
>> +...
>> +vshard.storage.internal.reload_evolution_version
>> +---
>> +- null
>> +...
>> +box.space.test:insert({42, bucket_id_to_move})
>> +---
>> +- [42, 3000]
>> +...
>> +while test_run:grep_log('storage_2_a', 'The cluster is balanced ok')
>> == nil do vshard.storage.rebalancer_wakeup() fiber.sleep(0.1) end
>
> 1. Now you have wait_rebalancer_state util from the previous commit.
I thought that it is possible at this point that the cluster is already
balanced.
But it seems that it is close to impossible.
Fixed
>
>> +---
>> +...
>> +test_run:switch('default')
>> +---
>> +- true
>> +...
>> +git_util.exec_cmd({cmd='checkout', args=evolution_log[1],
>> dir=vshard_copy_path})
>> +---
>> +...
>> +test_run:switch('storage_2_a')
>> +---
>> +- true
>> +...
>> +package.loaded["vshard.storage"] = nil
>> +---
>> +...
>> +vshard.storage = require("vshard.storage")
>> +---
>> +...
>> +test_run:grep_log('storage_2_a', 'vshard.storage.reload_evolution:
>> upgraded to') ~= nil
>> +---
>> +- true
>> +...
>> +vshard.storage.internal.reload_evolution_version
>> +---
>> +- 1
>> +...
>> +-- Make sure storage operates well.
>> +vshard.storage.bucket_force_drop(2000)
>> +---
>> +- true
>> +...
>> +vshard.storage.bucket_force_create(2000)
>> +---
>> +- true
>> +...
>> +vshard.storage.buckets_info()[2000]
>> +---
>> +- status: active
>> + id: 2000
>> +...
>> +vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
>> +---
>> +- true
>> +- - [42, 3000]
>> +...
>> +vshard.storage.bucket_send(bucket_id_to_move, replicaset1_uuid)
>> +---
>> +- true
>> +...
>> +vshard.storage.garbage_collector_wakeup()
>> +---
>> +...
>> +fiber = require('fiber')
>> +---
>> +...
>> +while box.space._bucket:get({bucket_id_to_move}) do
>> fiber.sleep(0.01) end
>> +---
>> +...
>> +test_run:switch('storage_1_a')
>> +---
>> +- true
>> +...
>> +vshard.storage.bucket_send(bucket_id_to_move, replicaset2_uuid)
>> +---
>> +- true
>> +...
>> +test_run:switch('storage_2_a')
>> +---
>> +- true
>> +...
>> +vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
>> +---
>> +- true
>> +- - [42, 3000]
>> +...
>> +-- Check info() does not fail.
>> +vshard.storage.info() ~= nil
>> +---
>> +- true
>> +...
>> +--
>> +-- Send buckets to create a disbalance. Wait until the rebalancer
>> +-- repairs it. Similar to `tests/rebalancer/rebalancer.test.lua`.
>> +--
>> +vshard.storage.rebalancer_disable()
>> +---
>> +...
>> +move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
>> +---
>> +...
>> +move_cnt = 100
>> +---
>> +...
>> +assert(move_start + move_cnt < vshard.consts.DEFAULT_BUCKET_COUNT)
>> +---
>> +- true
>> +...
>> +for i = move_start, move_start + move_cnt - 1 do
>> box.space._bucket:delete{i} end
>> +---
>> +...
>> +box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
>> +---
>> +- 1400
>> +...
>> +test_run:switch('storage_1_a')
>> +---
>> +- true
>> +...
>> +move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
>> +---
>> +...
>> +move_cnt = 100
>> +---
>> +...
>> +vshard.storage.bucket_force_create(move_start, move_cnt)
>> +---
>> +- true
>> +...
>> +box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
>> +---
>> +- 1600
>> +...
>> +test_run:switch('storage_2_a')
>> +---
>> +- true
>> +...
>> +vshard.storage.rebalancer_enable()
>> +---
>> +...
>> +vshard.storage.rebalancer_wakeup()
>
> 2. You do not need explicit rebalancer_wakeup. wait_rebalancer_state
> calls it.
Fixed
>
>> +---
>> +...
>> +wait_rebalancer_state("Rebalance routes are sent", test_run)
>> +---
>> +...
>> +wait_rebalancer_state('The cluster is balanced ok', test_run)
>> +---
>> +...
>> +box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
>> +---
>> +- 1500
>> +...
>> +test_run:switch('default')
>> +---
>> +- true
>> +...
>> +test_run:drop_cluster(REPLICASET_2)
>> +---
>> +...
>> +test_run:drop_cluster(REPLICASET_1)
>> +---
>> +...
>> +test_run:cmd('clear filter')
>> +---
>> +- true
>> +...
>> diff --git a/test/unit/reload_evolution.result
>> b/test/unit/reload_evolution.result
>> new file mode 100644
>> index 0000000..342ac24
>> --- /dev/null
>> +++ b/test/unit/reload_evolution.result
>> @@ -0,0 +1,45 @@
>> +test_run = require('test_run').new()
>> +---
>> +...
>> +fiber = require('fiber')
>> +---
>> +...
>> +log = require('log')
>> +---
>> +...
>> +util = require('util')
>> +---
>> +...
>> +reload_evolution = require('vshard.storage.reload_evolution')
>> +---
>> +...
>> +-- Init with the latest version.
>> +fake_M = { reload_evolution_version = reload_evolution.version }
>> +---
>> +...
>> +-- Test reload to the same version.
>> +reload_evolution.upgrade(fake_M)
>> +---
>> +...
>> +test_run:grep_log('default', 'vshard.storage.evolution') == nil
>> +---
>> +- true
>> +...
>> +-- Test downgrage version.
>> +log.info(string.rep('a', 1000))
>> +---
>> +...
>> +fake_M.reload_evolution_version = fake_M.reload_evolution_version + 1
>> +---
>> +...
>> +err = util.check_error(reload_evolution.upgrade, fake_M)
>> +---
>> +...
>> +err:match('auto%-downgrade is not implemented')
>> +---
>> +- auto-downgrade is not implemented
>
> 3. Why do you need match? check_error output is ok already. And
> what is 'auto%'? I see that you always print exactly "auto-downgrade"
> in reload_evolution.lua.
I need match to cut numbers which may change from the output.
% is used to escape '-' (which is a special character.
>
>> +...
>> +test_run:grep_log('default', 'vshard.storage.evolution', 1000) ~= nil
>> +---
>> +- false
>> +...
>> @@ -105,6 +110,11 @@ if not M then
>> -- a destination replicaset must drop already received
>> -- data.
>> rebalancer_sending_bucket = 0,
>> +
>> + ------------------------- Reload -------------------------
>> + -- Version of the loaded module. This number is used on
>> + -- reload to determine which upgrade scripts to run.
>> + reload_evolution_version = reload_evolution.version,
>
> 4. Please, rename it to just 'version' or 'reload_version' or
> 'module_version'. 'Reload_evolution_version' is too long and
> complex.
Renamed to reload_version.
I like `reload_evolution_version` though.
>
>> }
>> end
Full diff:
commit ad151e7c3fb4c15dd49859b28113195cf74ad418
Author: AKhatskevich <avkhatskevich@tarantool.org>
Date: Fri Jun 29 20:34:26 2018 +0300
Introduce storage reload evolution
Changes:
1. Introduce storage reload evolution.
2. Setup cross-version reload testing.
1:
This mechanism updates Lua objects on reload in case they are
changed in a new vshard.storage version.
Since this commit, any change in vshard.storage.M has to be
reflected in vshard.storage.reload_evolution to guarantee
correct reload.
2:
The testing uses git infrastructure and is performed in the following
way:
1. Copy old version of vshard to a temp folder.
2. Run vshard on this code.
3. Checkout the latest version of the vshard sources.
4. Reload vshard storage.
5. Make sure it works (Perform simple tests).
Notes:
* this patch contains some legacy-driven decisions:
1. SOURCEDIR path retrieved differently in case of
packpack build.
2. git directory in the `reload_evolution/storage` test
is copied with respect to Centos 7 and `ro` mode of
SOURCEDIR.
Closes #112 #125
diff --git a/.travis.yml b/.travis.yml
index 54bfe44..eff4a51 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -41,7 +41,7 @@ env:
script:
- git describe --long
- git clone https://github.com/packpack/packpack.git packpack
- - packpack/packpack
+ - packpack/packpack -e PACKPACK_GIT_SOURCEDIR=/source/
before_deploy:
- ls -l build/
diff --git a/rpm/prebuild.sh b/rpm/prebuild.sh
index 768b22b..554032b 100755
--- a/rpm/prebuild.sh
+++ b/rpm/prebuild.sh
@@ -1 +1,3 @@
curl -s
https://packagecloud.io/install/repositories/tarantool/1_9/script.rpm.sh
| sudo bash
+sudo yum -y install python-devel python-pip
+sudo pip install tarantool msgpack
diff --git a/test/lua_libs/git_util.lua b/test/lua_libs/git_util.lua
new file mode 100644
index 0000000..a75bb08
--- /dev/null
+++ b/test/lua_libs/git_util.lua
@@ -0,0 +1,51 @@
+--
+-- Lua bridge for some of the git commands.
+--
+local os = require('os')
+
+local temp_file = 'some_strange_rare_unique_file_name_for_git_util'
+
+--
+-- Exec a git command.
+-- @param params Table of parameters:
+-- * options - git options.
+-- * cmd - git command.
+-- * args - command arguments.
+-- * dir - working directory.
+-- * fout - write output to the file.
+local function exec_cmd(params)
+ local fout = params.fout
+ local shell_cmd = {'git'}
+ for _, param in pairs({'options', 'cmd', 'args'}) do
+ table.insert(shell_cmd, params[param])
+ end
+ if fout then
+ table.insert(shell_cmd, ' >' .. fout)
+ end
+ shell_cmd = table.concat(shell_cmd, ' ')
+ if params.dir then
+ shell_cmd = string.format('cd %s && %s', params.dir, shell_cmd)
+ end
+ local res = os.execute(shell_cmd)
+ assert(res == 0, 'Git cmd error: ' .. res)
+end
+
+local function log_hashes(params)
+ params.args = "--format='%h' " .. params.args
+ local local_temp_file = string.format('%s/%s', os.getenv('PWD'),
temp_file)
+ params.fout = local_temp_file
+ params.cmd = 'log'
+ exec_cmd(params)
+ local lines = {}
+ for line in io.lines(local_temp_file) do
+ table.insert(lines, line)
+ end
+ os.remove(local_temp_file)
+ return lines
+end
+
+
+return {
+ exec_cmd = exec_cmd,
+ log_hashes = log_hashes
+}
diff --git a/test/lua_libs/util.lua b/test/lua_libs/util.lua
index f40d3a6..935ff41 100644
--- a/test/lua_libs/util.lua
+++ b/test/lua_libs/util.lua
@@ -1,5 +1,6 @@
local fiber = require('fiber')
local log = require('log')
+local fio = require('fio')
local function check_error(func, ...)
local pstatus, status, err = pcall(func, ...)
@@ -92,10 +93,29 @@ local function has_same_fields(etalon, data)
return true
end
+-- Git directory of the project. Used in evolution tests to
+-- fetch old versions of vshard.
+local SOURCEDIR = os.getenv('PACKPACK_GIT_SOURCEDIR')
+if not SOURCEDIR then
+ SOURCEDIR = os.getenv('SOURCEDIR')
+end
+if not SOURCEDIR then
+ local script_path = debug.getinfo(1).source:match("@?(.*/)")
+ script_path = fio.abspath(script_path)
+ SOURCEDIR = fio.abspath(script_path .. '/../../../')
+end
+
+local BUILDDIR = os.getenv('BUILDDIR')
+if not BUILDDIR then
+ BUILDDIR = SOURCEDIR
+end
+
return {
check_error = check_error,
shuffle_masters = shuffle_masters,
collect_timeouts = collect_timeouts,
wait_master = wait_master,
has_same_fields = has_same_fields,
+ SOURCEDIR = SOURCEDIR,
+ BUILDDIR = BUILDDIR,
}
diff --git a/test/reload_evolution/storage.result
b/test/reload_evolution/storage.result
new file mode 100644
index 0000000..007192c
--- /dev/null
+++ b/test/reload_evolution/storage.result
@@ -0,0 +1,245 @@
+test_run = require('test_run').new()
+---
+...
+git_util = require('lua_libs.git_util')
+---
+...
+util = require('lua_libs.util')
+---
+...
+vshard_copy_path = util.BUILDDIR .. '/test/var/vshard_git_tree_copy'
+---
+...
+evolution_log =
git_util.log_hashes({args='vshard/storage/reload_evolution.lua',
dir=util.SOURCEDIR})
+---
+...
+-- Cleanup the directory after a previous build.
+_ = os.execute('rm -rf ' .. vshard_copy_path)
+---
+...
+-- 1. `git worktree` cannot be used because PACKPACK mounts
+-- `/source/` in `ro` mode.
+-- 2. Just `cp -rf` cannot be used due to a little different
+-- behavior in Centos 7.
+_ = os.execute('mkdir ' .. vshard_copy_path)
+---
+...
+_ = os.execute("cd " .. util.SOURCEDIR .. ' && cp -rf `ls -A
--ignore=build` ' .. vshard_copy_path)
+---
+...
+-- Checkout the first commit with a reload_evolution mechanism.
+git_util.exec_cmd({cmd='checkout', args='-f', dir=vshard_copy_path})
+---
+...
+git_util.exec_cmd({cmd='checkout', args=evolution_log[#evolution_log]
.. '~1', dir=vshard_copy_path})
+---
+...
+REPLICASET_1 = { 'storage_1_a', 'storage_1_b' }
+---
+...
+REPLICASET_2 = { 'storage_2_a', 'storage_2_b' }
+---
+...
+test_run:create_cluster(REPLICASET_1, 'reload_evolution')
+---
+...
+test_run:create_cluster(REPLICASET_2, 'reload_evolution')
+---
+...
+util = require('lua_libs.util')
+---
+...
+util.wait_master(test_run, REPLICASET_1, 'storage_1_a')
+---
+...
+util.wait_master(test_run, REPLICASET_2, 'storage_2_a')
+---
+...
+test_run:switch('storage_1_a')
+---
+- true
+...
+vshard.storage.bucket_force_create(1,
vshard.consts.DEFAULT_BUCKET_COUNT / 2)
+---
+- true
+...
+bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
+---
+...
+test_run:switch('storage_2_a')
+---
+- true
+...
+fiber = require('fiber')
+---
+...
+vshard.storage.bucket_force_create(vshard.consts.DEFAULT_BUCKET_COUNT /
2 + 1, vshard.consts.DEFAULT_BUCKET_COUNT / 2)
+---
+- true
+...
+bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
+---
+...
+vshard.storage.internal.reload_version
+---
+- null
+...
+wait_rebalancer_state('The cluster is balanced ok', test_run)
+---
+...
+box.space.test:insert({42, bucket_id_to_move})
+---
+- [42, 3000]
+...
+test_run:switch('default')
+---
+- true
+...
+git_util.exec_cmd({cmd='checkout', args=evolution_log[1],
dir=vshard_copy_path})
+---
+...
+test_run:switch('storage_2_a')
+---
+- true
+...
+package.loaded['vshard.storage'] = nil
+---
+...
+vshard.storage = require("vshard.storage")
+---
+...
+test_run:grep_log('storage_2_a', 'vshard.storage.reload_evolution:
upgraded to') ~= nil
+---
+- true
+...
+vshard.storage.internal.reload_version
+---
+- 1
+...
+-- Make sure storage operates well.
+vshard.storage.bucket_force_drop(2000)
+---
+- true
+...
+vshard.storage.bucket_force_create(2000)
+---
+- true
+...
+vshard.storage.buckets_info()[2000]
+---
+- status: active
+ id: 2000
+...
+vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
+---
+- true
+- - [42, 3000]
+...
+vshard.storage.bucket_send(bucket_id_to_move, replicaset1_uuid)
+---
+- true
+...
+vshard.storage.garbage_collector_wakeup()
+---
+...
+fiber = require('fiber')
+---
+...
+while box.space._bucket:get({bucket_id_to_move}) do fiber.sleep(0.01) end
+---
+...
+test_run:switch('storage_1_a')
+---
+- true
+...
+vshard.storage.bucket_send(bucket_id_to_move, replicaset2_uuid)
+---
+- true
+...
+test_run:switch('storage_2_a')
+---
+- true
+...
+vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
+---
+- true
+- - [42, 3000]
+...
+-- Check info() does not fail.
+vshard.storage.info() ~= nil
+---
+- true
+...
+--
+-- Send buckets to create a disbalance. Wait until the rebalancer
+-- repairs it. Similar to `tests/rebalancer/rebalancer.test.lua`.
+--
+vshard.storage.rebalancer_disable()
+---
+...
+move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
+---
+...
+move_cnt = 100
+---
+...
+assert(move_start + move_cnt < vshard.consts.DEFAULT_BUCKET_COUNT)
+---
+- true
+...
+for i = move_start, move_start + move_cnt - 1 do
box.space._bucket:delete{i} end
+---
+...
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+---
+- 1400
+...
+test_run:switch('storage_1_a')
+---
+- true
+...
+move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
+---
+...
+move_cnt = 100
+---
+...
+vshard.storage.bucket_force_create(move_start, move_cnt)
+---
+- true
+...
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+---
+- 1600
+...
+test_run:switch('storage_2_a')
+---
+- true
+...
+vshard.storage.rebalancer_enable()
+---
+...
+wait_rebalancer_state('Rebalance routes are sent', test_run)
+---
+...
+wait_rebalancer_state('The cluster is balanced ok', test_run)
+---
+...
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+---
+- 1500
+...
+test_run:switch('default')
+---
+- true
+...
+test_run:drop_cluster(REPLICASET_2)
+---
+...
+test_run:drop_cluster(REPLICASET_1)
+---
+...
+test_run:cmd('clear filter')
+---
+- true
+...
diff --git a/test/reload_evolution/storage.test.lua
b/test/reload_evolution/storage.test.lua
new file mode 100644
index 0000000..7af464b
--- /dev/null
+++ b/test/reload_evolution/storage.test.lua
@@ -0,0 +1,87 @@
+test_run = require('test_run').new()
+
+git_util = require('lua_libs.git_util')
+util = require('lua_libs.util')
+vshard_copy_path = util.BUILDDIR .. '/test/var/vshard_git_tree_copy'
+evolution_log =
git_util.log_hashes({args='vshard/storage/reload_evolution.lua',
dir=util.SOURCEDIR})
+-- Cleanup the directory after a previous build.
+_ = os.execute('rm -rf ' .. vshard_copy_path)
+-- 1. `git worktree` cannot be used because PACKPACK mounts
+-- `/source/` in `ro` mode.
+-- 2. Just `cp -rf` cannot be used due to a little different
+-- behavior in Centos 7.
+_ = os.execute('mkdir ' .. vshard_copy_path)
+_ = os.execute("cd " .. util.SOURCEDIR .. ' && cp -rf `ls -A
--ignore=build` ' .. vshard_copy_path)
+-- Checkout the first commit with a reload_evolution mechanism.
+git_util.exec_cmd({cmd='checkout', args='-f', dir=vshard_copy_path})
+git_util.exec_cmd({cmd='checkout', args=evolution_log[#evolution_log]
.. '~1', dir=vshard_copy_path})
+
+REPLICASET_1 = { 'storage_1_a', 'storage_1_b' }
+REPLICASET_2 = { 'storage_2_a', 'storage_2_b' }
+test_run:create_cluster(REPLICASET_1, 'reload_evolution')
+test_run:create_cluster(REPLICASET_2, 'reload_evolution')
+util = require('lua_libs.util')
+util.wait_master(test_run, REPLICASET_1, 'storage_1_a')
+util.wait_master(test_run, REPLICASET_2, 'storage_2_a')
+
+test_run:switch('storage_1_a')
+vshard.storage.bucket_force_create(1,
vshard.consts.DEFAULT_BUCKET_COUNT / 2)
+bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
+
+test_run:switch('storage_2_a')
+fiber = require('fiber')
+vshard.storage.bucket_force_create(vshard.consts.DEFAULT_BUCKET_COUNT /
2 + 1, vshard.consts.DEFAULT_BUCKET_COUNT / 2)
+bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
+vshard.storage.internal.reload_version
+wait_rebalancer_state('The cluster is balanced ok', test_run)
+box.space.test:insert({42, bucket_id_to_move})
+
+test_run:switch('default')
+git_util.exec_cmd({cmd='checkout', args=evolution_log[1],
dir=vshard_copy_path})
+
+test_run:switch('storage_2_a')
+package.loaded['vshard.storage'] = nil
+vshard.storage = require("vshard.storage")
+test_run:grep_log('storage_2_a', 'vshard.storage.reload_evolution:
upgraded to') ~= nil
+vshard.storage.internal.reload_version
+-- Make sure storage operates well.
+vshard.storage.bucket_force_drop(2000)
+vshard.storage.bucket_force_create(2000)
+vshard.storage.buckets_info()[2000]
+vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
+vshard.storage.bucket_send(bucket_id_to_move, replicaset1_uuid)
+vshard.storage.garbage_collector_wakeup()
+fiber = require('fiber')
+while box.space._bucket:get({bucket_id_to_move}) do fiber.sleep(0.01) end
+test_run:switch('storage_1_a')
+vshard.storage.bucket_send(bucket_id_to_move, replicaset2_uuid)
+test_run:switch('storage_2_a')
+vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
+-- Check info() does not fail.
+vshard.storage.info() ~= nil
+
+--
+-- Send buckets to create a disbalance. Wait until the rebalancer
+-- repairs it. Similar to `tests/rebalancer/rebalancer.test.lua`.
+--
+vshard.storage.rebalancer_disable()
+move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
+move_cnt = 100
+assert(move_start + move_cnt < vshard.consts.DEFAULT_BUCKET_COUNT)
+for i = move_start, move_start + move_cnt - 1 do
box.space._bucket:delete{i} end
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+test_run:switch('storage_1_a')
+move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
+move_cnt = 100
+vshard.storage.bucket_force_create(move_start, move_cnt)
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+test_run:switch('storage_2_a')
+vshard.storage.rebalancer_enable()
+wait_rebalancer_state('Rebalance routes are sent', test_run)
+wait_rebalancer_state('The cluster is balanced ok', test_run)
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+
+test_run:switch('default')
+test_run:drop_cluster(REPLICASET_2)
+test_run:drop_cluster(REPLICASET_1)
+test_run:cmd('clear filter')
diff --git a/test/reload_evolution/storage_1_a.lua
b/test/reload_evolution/storage_1_a.lua
new file mode 100755
index 0000000..f1a2981
--- /dev/null
+++ b/test/reload_evolution/storage_1_a.lua
@@ -0,0 +1,48 @@
+#!/usr/bin/env tarantool
+
+require('strict').on()
+
+local log = require('log')
+local fiber = require('fiber')
+local util = require('lua_libs.util')
+local fio = require('fio')
+
+-- Get instance name
+NAME = fio.basename(arg[0], '.lua')
+
+-- test-run gate.
+test_run = require('test_run').new()
+require('console').listen(os.getenv('ADMIN'))
+
+-- Run one storage on a different vshard version.
+-- To do that, place vshard src to
+-- BUILDDIR/test/var/vshard_git_tree_copy/.
+if NAME == 'storage_2_a' then
+ local script_path = debug.getinfo(1).source:match("@?(.*/)")
+ vshard_copy = util.BUILDDIR .. '/test/var/vshard_git_tree_copy'
+ package.path = string.format(
+ '%s/?.lua;%s/?/init.lua;%s',
+ vshard_copy, vshard_copy, package.path
+ )
+end
+
+-- Call a configuration provider
+cfg = require('localcfg')
+-- Name to uuid map
+names = {
+ ['storage_1_a'] = '8a274925-a26d-47fc-9e1b-af88ce939412',
+ ['storage_1_b'] = '3de2e3e1-9ebe-4d0d-abb1-26d301b84633',
+ ['storage_2_a'] = '1e02ae8a-afc0-4e91-ba34-843a356b8ed7',
+ ['storage_2_b'] = '001688c3-66f8-4a31-8e19-036c17d489c2',
+}
+
+replicaset1_uuid = 'cbf06940-0790-498b-948d-042b62cf3d29'
+replicaset2_uuid = 'ac522f65-aa94-4134-9f64-51ee384f1a54'
+replicasets = {replicaset1_uuid, replicaset2_uuid}
+
+-- Start the database with sharding
+vshard = require('vshard')
+vshard.storage.cfg(cfg, names[NAME])
+
+-- Bootstrap storage.
+require('lua_libs.bootstrap')
diff --git a/test/reload_evolution/storage_1_b.lua
b/test/reload_evolution/storage_1_b.lua
new file mode 120000
index 0000000..02572da
--- /dev/null
+++ b/test/reload_evolution/storage_1_b.lua
@@ -0,0 +1 @@
+storage_1_a.lua
\ No newline at end of file
diff --git a/test/reload_evolution/storage_2_a.lua
b/test/reload_evolution/storage_2_a.lua
new file mode 120000
index 0000000..02572da
--- /dev/null
+++ b/test/reload_evolution/storage_2_a.lua
@@ -0,0 +1 @@
+storage_1_a.lua
\ No newline at end of file
diff --git a/test/reload_evolution/storage_2_b.lua
b/test/reload_evolution/storage_2_b.lua
new file mode 120000
index 0000000..02572da
--- /dev/null
+++ b/test/reload_evolution/storage_2_b.lua
@@ -0,0 +1 @@
+storage_1_a.lua
\ No newline at end of file
diff --git a/test/reload_evolution/suite.ini
b/test/reload_evolution/suite.ini
new file mode 100644
index 0000000..5f55418
--- /dev/null
+++ b/test/reload_evolution/suite.ini
@@ -0,0 +1,6 @@
+[default]
+core = tarantool
+description = Reload evolution tests
+script = test.lua
+is_parallel = False
+lua_libs = ../lua_libs ../../example/localcfg.lua
diff --git a/test/reload_evolution/test.lua b/test/reload_evolution/test.lua
new file mode 100644
index 0000000..ad0543a
--- /dev/null
+++ b/test/reload_evolution/test.lua
@@ -0,0 +1,9 @@
+#!/usr/bin/env tarantool
+
+require('strict').on()
+
+box.cfg{
+ listen = os.getenv("LISTEN"),
+}
+
+require('console').listen(os.getenv('ADMIN'))
diff --git a/test/unit/reload_evolution.result
b/test/unit/reload_evolution.result
new file mode 100644
index 0000000..342ac24
--- /dev/null
+++ b/test/unit/reload_evolution.result
@@ -0,0 +1,45 @@
+test_run = require('test_run').new()
+---
+...
+fiber = require('fiber')
+---
+...
+log = require('log')
+---
+...
+util = require('util')
+---
+...
+reload_evolution = require('vshard.storage.reload_evolution')
+---
+...
+-- Init with the latest version.
+fake_M = { reload_evolution_version = reload_evolution.version }
+---
+...
+-- Test reload to the same version.
+reload_evolution.upgrade(fake_M)
+---
+...
+test_run:grep_log('default', 'vshard.storage.evolution') == nil
+---
+- true
+...
+-- Test downgrage version.
+log.info(string.rep('a', 1000))
+---
+...
+fake_M.reload_evolution_version = fake_M.reload_evolution_version + 1
+---
+...
+err = util.check_error(reload_evolution.upgrade, fake_M)
+---
+...
+err:match('auto%-downgrade is not implemented')
+---
+- auto-downgrade is not implemented
+...
+test_run:grep_log('default', 'vshard.storage.evolution', 1000) ~= nil
+---
+- false
+...
diff --git a/test/unit/reload_evolution.test.lua
b/test/unit/reload_evolution.test.lua
new file mode 100644
index 0000000..b8a3ca8
--- /dev/null
+++ b/test/unit/reload_evolution.test.lua
@@ -0,0 +1,18 @@
+test_run = require('test_run').new()
+fiber = require('fiber')
+log = require('log')
+util = require('util')
+reload_evolution = require('vshard.storage.reload_evolution')
+-- Init with the latest version.
+fake_M = { reload_version = reload_evolution.version }
+
+-- Test reload to the same version.
+reload_evolution.upgrade(fake_M)
+test_run:grep_log('default', 'vshard.storage.evolution') == nil
+
+-- Test downgrage version.
+log.info(string.rep('a', 1000))
+fake_M.reload_evolution_version = fake_M.reload_evolution_version + 1
+err = util.check_error(reload_evolution.upgrade, fake_M)
+err:match('auto%-downgrade is not implemented')
+test_run:grep_log('default', 'vshard.storage.evolution', 1000) ~= nil
diff --git a/vshard/storage/init.lua b/vshard/storage/init.lua
index 07bd00c..69e858a 100644
--- a/vshard/storage/init.lua
+++ b/vshard/storage/init.lua
@@ -10,6 +10,7 @@ if rawget(_G, MODULE_INTERNALS) then
local vshard_modules = {
'vshard.consts', 'vshard.error', 'vshard.cfg',
'vshard.replicaset', 'vshard.util',
+ 'vshard.storage.reload_evolution'
}
for _, module in pairs(vshard_modules) do
package.loaded[module] = nil
@@ -20,12 +21,16 @@ local lerror = require('vshard.error')
local lcfg = require('vshard.cfg')
local lreplicaset = require('vshard.replicaset')
local util = require('vshard.util')
+local reload_evolution = require('vshard.storage.reload_evolution')
local M = rawget(_G, MODULE_INTERNALS)
if not M then
--
-- The module is loaded for the first time.
--
+ -- !!!WARNING: any change of this table must be reflected in
+ -- `vshard.storage.reload_evolution` module to guarantee
+ -- reloadability of the module.
M = {
---------------- Common module attributes ----------------
-- The last passed configuration.
@@ -105,6 +110,11 @@ if not M then
-- a destination replicaset must drop already received
-- data.
rebalancer_sending_bucket = 0,
+
+ ------------------------- Reload -------------------------
+ -- Version of the loaded module. This number is used on
+ -- reload to determine which upgrade scripts to run.
+ reload_version = reload_evolution.version,
}
end
@@ -1863,6 +1873,7 @@ end
if not rawget(_G, MODULE_INTERNALS) then
rawset(_G, MODULE_INTERNALS, M)
else
+ reload_evolution.upgrade(M)
storage_cfg(M.current_cfg, M.this_replica.uuid)
M.module_version = M.module_version + 1
end
diff --git a/vshard/storage/reload_evolution.lua
b/vshard/storage/reload_evolution.lua
new file mode 100644
index 0000000..8502a33
--- /dev/null
+++ b/vshard/storage/reload_evolution.lua
@@ -0,0 +1,58 @@
+--
+-- This module is used to upgrade the vshard.storage on the fly.
+-- It updates internal Lua structures in case they are changed
+-- in a commit.
+--
+local log = require('log')
+
+--
+-- Array of upgrade functions.
+-- migrations[version] = function which upgrades module version
+-- from `version` to `version + 1`.
+--
+local migrations = {}
+
+-- Initialize reload_upgrade mechanism
+migrations[#migrations + 1] = function (M)
+ -- Code to update Lua objects.
+end
+
+--
+-- Perform an update based on a version stored in `M` (internals).
+-- @param M Old module internals which should be updated.
+--
+local function upgrade(M)
+ local start_version = M.reload_version or 1
+ if start_version > #migrations then
+ local err_msg = string.format(
+ 'vshard.storage.reload_evolution: ' ..
+ 'auto-downgrade is not implemented; ' ..
+ 'loaded version is %d, upgrade script version is %d',
+ start_version, #migrations
+ )
+ log.error(err_msg)
+ error(err_msg)
+ end
+ for i = start_version, #migrations do
+ local ok, err = pcall(migrations[i], M)
+ if ok then
+ log.info('vshard.storage.reload_evolution: upgraded to %d
version',
+ i)
+ else
+ local err_msg = string.format(
+ 'vshard.storage.reload_evolution: ' ..
+ 'error during upgrade to %d version: %s', i, err
+ )
+ log.error(err_msg)
+ error(err_msg)
+ end
+ -- Update the version just after upgrade to have an
+ -- actual version in case of an error.
+ M.reload_version = i
+ end
+end
+
+return {
+ version = #migrations,
+ upgrade = upgrade,
+}
^ permalink raw reply [flat|nested] 14+ messages in thread
* [tarantool-patches] [PATCH 4/4] Introduce storage reload evolution
2018-07-30 8:56 [tarantool-patches] [PATCH v4] vshard module reload AKhatskevich
@ 2018-07-30 8:56 ` AKhatskevich
0 siblings, 0 replies; 14+ messages in thread
From: AKhatskevich @ 2018-07-30 8:56 UTC (permalink / raw)
To: v.shpilevoy, tarantool-patches
Changes:
1. Introduce storage reload evolution.
2. Setup cross-version reload testing.
1:
This mechanism updates Lua objects on reload in case they are
changed in a new vshard.storage version.
Since this commit, any change in vshard.storage.M has to be
reflected in vshard.storage.reload_evolution to guarantee
correct reload.
2:
The testing uses git infrastructure and is performed in the following
way:
1. Copy old version of vshard to a temp folder.
2. Run vshard on this code.
3. Checkout the latest version of the vshard sources.
4. Reload vshard storage.
5. Make sure it works (Perform simple tests).
Notes:
* this patch contains some legacy-driven decisions:
1. SOURCEDIR path retrieved differently in case of
packpack build.
2. git directory in the `reload_evolution/storage` test
is copied with respect to Centos 7 and `ro` mode of
SOURCEDIR.
Closes #112 #125
---
.travis.yml | 2 +-
rpm/prebuild.sh | 2 +
test/lua_libs/git_util.lua | 51 +++++++
test/lua_libs/util.lua | 20 +++
test/reload_evolution/storage.result | 245 +++++++++++++++++++++++++++++++++
test/reload_evolution/storage.test.lua | 87 ++++++++++++
test/reload_evolution/storage_1_a.lua | 48 +++++++
test/reload_evolution/storage_1_b.lua | 1 +
test/reload_evolution/storage_2_a.lua | 1 +
test/reload_evolution/storage_2_b.lua | 1 +
test/reload_evolution/suite.ini | 6 +
test/reload_evolution/test.lua | 9 ++
test/unit/reload_evolution.result | 45 ++++++
test/unit/reload_evolution.test.lua | 18 +++
vshard/storage/init.lua | 11 ++
vshard/storage/reload_evolution.lua | 58 ++++++++
16 files changed, 604 insertions(+), 1 deletion(-)
create mode 100644 test/lua_libs/git_util.lua
create mode 100644 test/reload_evolution/storage.result
create mode 100644 test/reload_evolution/storage.test.lua
create mode 100755 test/reload_evolution/storage_1_a.lua
create mode 120000 test/reload_evolution/storage_1_b.lua
create mode 120000 test/reload_evolution/storage_2_a.lua
create mode 120000 test/reload_evolution/storage_2_b.lua
create mode 100644 test/reload_evolution/suite.ini
create mode 100644 test/reload_evolution/test.lua
create mode 100644 test/unit/reload_evolution.result
create mode 100644 test/unit/reload_evolution.test.lua
create mode 100644 vshard/storage/reload_evolution.lua
diff --git a/.travis.yml b/.travis.yml
index 54bfe44..eff4a51 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -41,7 +41,7 @@ env:
script:
- git describe --long
- git clone https://github.com/packpack/packpack.git packpack
- - packpack/packpack
+ - packpack/packpack -e PACKPACK_GIT_SOURCEDIR=/source/
before_deploy:
- ls -l build/
diff --git a/rpm/prebuild.sh b/rpm/prebuild.sh
index 768b22b..554032b 100755
--- a/rpm/prebuild.sh
+++ b/rpm/prebuild.sh
@@ -1 +1,3 @@
curl -s https://packagecloud.io/install/repositories/tarantool/1_9/script.rpm.sh | sudo bash
+sudo yum -y install python-devel python-pip
+sudo pip install tarantool msgpack
diff --git a/test/lua_libs/git_util.lua b/test/lua_libs/git_util.lua
new file mode 100644
index 0000000..a75bb08
--- /dev/null
+++ b/test/lua_libs/git_util.lua
@@ -0,0 +1,51 @@
+--
+-- Lua bridge for some of the git commands.
+--
+local os = require('os')
+
+local temp_file = 'some_strange_rare_unique_file_name_for_git_util'
+
+--
+-- Exec a git command.
+-- @param params Table of parameters:
+-- * options - git options.
+-- * cmd - git command.
+-- * args - command arguments.
+-- * dir - working directory.
+-- * fout - write output to the file.
+local function exec_cmd(params)
+ local fout = params.fout
+ local shell_cmd = {'git'}
+ for _, param in pairs({'options', 'cmd', 'args'}) do
+ table.insert(shell_cmd, params[param])
+ end
+ if fout then
+ table.insert(shell_cmd, ' >' .. fout)
+ end
+ shell_cmd = table.concat(shell_cmd, ' ')
+ if params.dir then
+ shell_cmd = string.format('cd %s && %s', params.dir, shell_cmd)
+ end
+ local res = os.execute(shell_cmd)
+ assert(res == 0, 'Git cmd error: ' .. res)
+end
+
+local function log_hashes(params)
+ params.args = "--format='%h' " .. params.args
+ local local_temp_file = string.format('%s/%s', os.getenv('PWD'), temp_file)
+ params.fout = local_temp_file
+ params.cmd = 'log'
+ exec_cmd(params)
+ local lines = {}
+ for line in io.lines(local_temp_file) do
+ table.insert(lines, line)
+ end
+ os.remove(local_temp_file)
+ return lines
+end
+
+
+return {
+ exec_cmd = exec_cmd,
+ log_hashes = log_hashes
+}
diff --git a/test/lua_libs/util.lua b/test/lua_libs/util.lua
index f40d3a6..935ff41 100644
--- a/test/lua_libs/util.lua
+++ b/test/lua_libs/util.lua
@@ -1,5 +1,6 @@
local fiber = require('fiber')
local log = require('log')
+local fio = require('fio')
local function check_error(func, ...)
local pstatus, status, err = pcall(func, ...)
@@ -92,10 +93,29 @@ local function has_same_fields(etalon, data)
return true
end
+-- Git directory of the project. Used in evolution tests to
+-- fetch old versions of vshard.
+local SOURCEDIR = os.getenv('PACKPACK_GIT_SOURCEDIR')
+if not SOURCEDIR then
+ SOURCEDIR = os.getenv('SOURCEDIR')
+end
+if not SOURCEDIR then
+ local script_path = debug.getinfo(1).source:match("@?(.*/)")
+ script_path = fio.abspath(script_path)
+ SOURCEDIR = fio.abspath(script_path .. '/../../../')
+end
+
+local BUILDDIR = os.getenv('BUILDDIR')
+if not BUILDDIR then
+ BUILDDIR = SOURCEDIR
+end
+
return {
check_error = check_error,
shuffle_masters = shuffle_masters,
collect_timeouts = collect_timeouts,
wait_master = wait_master,
has_same_fields = has_same_fields,
+ SOURCEDIR = SOURCEDIR,
+ BUILDDIR = BUILDDIR,
}
diff --git a/test/reload_evolution/storage.result b/test/reload_evolution/storage.result
new file mode 100644
index 0000000..007192c
--- /dev/null
+++ b/test/reload_evolution/storage.result
@@ -0,0 +1,245 @@
+test_run = require('test_run').new()
+---
+...
+git_util = require('lua_libs.git_util')
+---
+...
+util = require('lua_libs.util')
+---
+...
+vshard_copy_path = util.BUILDDIR .. '/test/var/vshard_git_tree_copy'
+---
+...
+evolution_log = git_util.log_hashes({args='vshard/storage/reload_evolution.lua', dir=util.SOURCEDIR})
+---
+...
+-- Cleanup the directory after a previous build.
+_ = os.execute('rm -rf ' .. vshard_copy_path)
+---
+...
+-- 1. `git worktree` cannot be used because PACKPACK mounts
+-- `/source/` in `ro` mode.
+-- 2. Just `cp -rf` cannot be used due to a little different
+-- behavior in Centos 7.
+_ = os.execute('mkdir ' .. vshard_copy_path)
+---
+...
+_ = os.execute("cd " .. util.SOURCEDIR .. ' && cp -rf `ls -A --ignore=build` ' .. vshard_copy_path)
+---
+...
+-- Checkout the first commit with a reload_evolution mechanism.
+git_util.exec_cmd({cmd='checkout', args='-f', dir=vshard_copy_path})
+---
+...
+git_util.exec_cmd({cmd='checkout', args=evolution_log[#evolution_log] .. '~1', dir=vshard_copy_path})
+---
+...
+REPLICASET_1 = { 'storage_1_a', 'storage_1_b' }
+---
+...
+REPLICASET_2 = { 'storage_2_a', 'storage_2_b' }
+---
+...
+test_run:create_cluster(REPLICASET_1, 'reload_evolution')
+---
+...
+test_run:create_cluster(REPLICASET_2, 'reload_evolution')
+---
+...
+util = require('lua_libs.util')
+---
+...
+util.wait_master(test_run, REPLICASET_1, 'storage_1_a')
+---
+...
+util.wait_master(test_run, REPLICASET_2, 'storage_2_a')
+---
+...
+test_run:switch('storage_1_a')
+---
+- true
+...
+vshard.storage.bucket_force_create(1, vshard.consts.DEFAULT_BUCKET_COUNT / 2)
+---
+- true
+...
+bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
+---
+...
+test_run:switch('storage_2_a')
+---
+- true
+...
+fiber = require('fiber')
+---
+...
+vshard.storage.bucket_force_create(vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1, vshard.consts.DEFAULT_BUCKET_COUNT / 2)
+---
+- true
+...
+bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
+---
+...
+vshard.storage.internal.reload_version
+---
+- null
+...
+wait_rebalancer_state('The cluster is balanced ok', test_run)
+---
+...
+box.space.test:insert({42, bucket_id_to_move})
+---
+- [42, 3000]
+...
+test_run:switch('default')
+---
+- true
+...
+git_util.exec_cmd({cmd='checkout', args=evolution_log[1], dir=vshard_copy_path})
+---
+...
+test_run:switch('storage_2_a')
+---
+- true
+...
+package.loaded['vshard.storage'] = nil
+---
+...
+vshard.storage = require("vshard.storage")
+---
+...
+test_run:grep_log('storage_2_a', 'vshard.storage.reload_evolution: upgraded to') ~= nil
+---
+- true
+...
+vshard.storage.internal.reload_version
+---
+- 1
+...
+-- Make sure storage operates well.
+vshard.storage.bucket_force_drop(2000)
+---
+- true
+...
+vshard.storage.bucket_force_create(2000)
+---
+- true
+...
+vshard.storage.buckets_info()[2000]
+---
+- status: active
+ id: 2000
+...
+vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
+---
+- true
+- - [42, 3000]
+...
+vshard.storage.bucket_send(bucket_id_to_move, replicaset1_uuid)
+---
+- true
+...
+vshard.storage.garbage_collector_wakeup()
+---
+...
+fiber = require('fiber')
+---
+...
+while box.space._bucket:get({bucket_id_to_move}) do fiber.sleep(0.01) end
+---
+...
+test_run:switch('storage_1_a')
+---
+- true
+...
+vshard.storage.bucket_send(bucket_id_to_move, replicaset2_uuid)
+---
+- true
+...
+test_run:switch('storage_2_a')
+---
+- true
+...
+vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
+---
+- true
+- - [42, 3000]
+...
+-- Check info() does not fail.
+vshard.storage.info() ~= nil
+---
+- true
+...
+--
+-- Send buckets to create a disbalance. Wait until the rebalancer
+-- repairs it. Similar to `tests/rebalancer/rebalancer.test.lua`.
+--
+vshard.storage.rebalancer_disable()
+---
+...
+move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
+---
+...
+move_cnt = 100
+---
+...
+assert(move_start + move_cnt < vshard.consts.DEFAULT_BUCKET_COUNT)
+---
+- true
+...
+for i = move_start, move_start + move_cnt - 1 do box.space._bucket:delete{i} end
+---
+...
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+---
+- 1400
+...
+test_run:switch('storage_1_a')
+---
+- true
+...
+move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
+---
+...
+move_cnt = 100
+---
+...
+vshard.storage.bucket_force_create(move_start, move_cnt)
+---
+- true
+...
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+---
+- 1600
+...
+test_run:switch('storage_2_a')
+---
+- true
+...
+vshard.storage.rebalancer_enable()
+---
+...
+wait_rebalancer_state('Rebalance routes are sent', test_run)
+---
+...
+wait_rebalancer_state('The cluster is balanced ok', test_run)
+---
+...
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+---
+- 1500
+...
+test_run:switch('default')
+---
+- true
+...
+test_run:drop_cluster(REPLICASET_2)
+---
+...
+test_run:drop_cluster(REPLICASET_1)
+---
+...
+test_run:cmd('clear filter')
+---
+- true
+...
diff --git a/test/reload_evolution/storage.test.lua b/test/reload_evolution/storage.test.lua
new file mode 100644
index 0000000..7af464b
--- /dev/null
+++ b/test/reload_evolution/storage.test.lua
@@ -0,0 +1,87 @@
+test_run = require('test_run').new()
+
+git_util = require('lua_libs.git_util')
+util = require('lua_libs.util')
+vshard_copy_path = util.BUILDDIR .. '/test/var/vshard_git_tree_copy'
+evolution_log = git_util.log_hashes({args='vshard/storage/reload_evolution.lua', dir=util.SOURCEDIR})
+-- Cleanup the directory after a previous build.
+_ = os.execute('rm -rf ' .. vshard_copy_path)
+-- 1. `git worktree` cannot be used because PACKPACK mounts
+-- `/source/` in `ro` mode.
+-- 2. Just `cp -rf` cannot be used due to a little different
+-- behavior in Centos 7.
+_ = os.execute('mkdir ' .. vshard_copy_path)
+_ = os.execute("cd " .. util.SOURCEDIR .. ' && cp -rf `ls -A --ignore=build` ' .. vshard_copy_path)
+-- Checkout the first commit with a reload_evolution mechanism.
+git_util.exec_cmd({cmd='checkout', args='-f', dir=vshard_copy_path})
+git_util.exec_cmd({cmd='checkout', args=evolution_log[#evolution_log] .. '~1', dir=vshard_copy_path})
+
+REPLICASET_1 = { 'storage_1_a', 'storage_1_b' }
+REPLICASET_2 = { 'storage_2_a', 'storage_2_b' }
+test_run:create_cluster(REPLICASET_1, 'reload_evolution')
+test_run:create_cluster(REPLICASET_2, 'reload_evolution')
+util = require('lua_libs.util')
+util.wait_master(test_run, REPLICASET_1, 'storage_1_a')
+util.wait_master(test_run, REPLICASET_2, 'storage_2_a')
+
+test_run:switch('storage_1_a')
+vshard.storage.bucket_force_create(1, vshard.consts.DEFAULT_BUCKET_COUNT / 2)
+bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
+
+test_run:switch('storage_2_a')
+fiber = require('fiber')
+vshard.storage.bucket_force_create(vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1, vshard.consts.DEFAULT_BUCKET_COUNT / 2)
+bucket_id_to_move = vshard.consts.DEFAULT_BUCKET_COUNT
+vshard.storage.internal.reload_version
+wait_rebalancer_state('The cluster is balanced ok', test_run)
+box.space.test:insert({42, bucket_id_to_move})
+
+test_run:switch('default')
+git_util.exec_cmd({cmd='checkout', args=evolution_log[1], dir=vshard_copy_path})
+
+test_run:switch('storage_2_a')
+package.loaded['vshard.storage'] = nil
+vshard.storage = require("vshard.storage")
+test_run:grep_log('storage_2_a', 'vshard.storage.reload_evolution: upgraded to') ~= nil
+vshard.storage.internal.reload_version
+-- Make sure storage operates well.
+vshard.storage.bucket_force_drop(2000)
+vshard.storage.bucket_force_create(2000)
+vshard.storage.buckets_info()[2000]
+vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
+vshard.storage.bucket_send(bucket_id_to_move, replicaset1_uuid)
+vshard.storage.garbage_collector_wakeup()
+fiber = require('fiber')
+while box.space._bucket:get({bucket_id_to_move}) do fiber.sleep(0.01) end
+test_run:switch('storage_1_a')
+vshard.storage.bucket_send(bucket_id_to_move, replicaset2_uuid)
+test_run:switch('storage_2_a')
+vshard.storage.call(bucket_id_to_move, 'read', 'do_select', {42})
+-- Check info() does not fail.
+vshard.storage.info() ~= nil
+
+--
+-- Send buckets to create a disbalance. Wait until the rebalancer
+-- repairs it. Similar to `tests/rebalancer/rebalancer.test.lua`.
+--
+vshard.storage.rebalancer_disable()
+move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
+move_cnt = 100
+assert(move_start + move_cnt < vshard.consts.DEFAULT_BUCKET_COUNT)
+for i = move_start, move_start + move_cnt - 1 do box.space._bucket:delete{i} end
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+test_run:switch('storage_1_a')
+move_start = vshard.consts.DEFAULT_BUCKET_COUNT / 2 + 1
+move_cnt = 100
+vshard.storage.bucket_force_create(move_start, move_cnt)
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+test_run:switch('storage_2_a')
+vshard.storage.rebalancer_enable()
+wait_rebalancer_state('Rebalance routes are sent', test_run)
+wait_rebalancer_state('The cluster is balanced ok', test_run)
+box.space._bucket.index.status:count({vshard.consts.BUCKET.ACTIVE})
+
+test_run:switch('default')
+test_run:drop_cluster(REPLICASET_2)
+test_run:drop_cluster(REPLICASET_1)
+test_run:cmd('clear filter')
diff --git a/test/reload_evolution/storage_1_a.lua b/test/reload_evolution/storage_1_a.lua
new file mode 100755
index 0000000..f1a2981
--- /dev/null
+++ b/test/reload_evolution/storage_1_a.lua
@@ -0,0 +1,48 @@
+#!/usr/bin/env tarantool
+
+require('strict').on()
+
+local log = require('log')
+local fiber = require('fiber')
+local util = require('lua_libs.util')
+local fio = require('fio')
+
+-- Get instance name
+NAME = fio.basename(arg[0], '.lua')
+
+-- test-run gate.
+test_run = require('test_run').new()
+require('console').listen(os.getenv('ADMIN'))
+
+-- Run one storage on a different vshard version.
+-- To do that, place vshard src to
+-- BUILDDIR/test/var/vshard_git_tree_copy/.
+if NAME == 'storage_2_a' then
+ local script_path = debug.getinfo(1).source:match("@?(.*/)")
+ vshard_copy = util.BUILDDIR .. '/test/var/vshard_git_tree_copy'
+ package.path = string.format(
+ '%s/?.lua;%s/?/init.lua;%s',
+ vshard_copy, vshard_copy, package.path
+ )
+end
+
+-- Call a configuration provider
+cfg = require('localcfg')
+-- Name to uuid map
+names = {
+ ['storage_1_a'] = '8a274925-a26d-47fc-9e1b-af88ce939412',
+ ['storage_1_b'] = '3de2e3e1-9ebe-4d0d-abb1-26d301b84633',
+ ['storage_2_a'] = '1e02ae8a-afc0-4e91-ba34-843a356b8ed7',
+ ['storage_2_b'] = '001688c3-66f8-4a31-8e19-036c17d489c2',
+}
+
+replicaset1_uuid = 'cbf06940-0790-498b-948d-042b62cf3d29'
+replicaset2_uuid = 'ac522f65-aa94-4134-9f64-51ee384f1a54'
+replicasets = {replicaset1_uuid, replicaset2_uuid}
+
+-- Start the database with sharding
+vshard = require('vshard')
+vshard.storage.cfg(cfg, names[NAME])
+
+-- Bootstrap storage.
+require('lua_libs.bootstrap')
diff --git a/test/reload_evolution/storage_1_b.lua b/test/reload_evolution/storage_1_b.lua
new file mode 120000
index 0000000..02572da
--- /dev/null
+++ b/test/reload_evolution/storage_1_b.lua
@@ -0,0 +1 @@
+storage_1_a.lua
\ No newline at end of file
diff --git a/test/reload_evolution/storage_2_a.lua b/test/reload_evolution/storage_2_a.lua
new file mode 120000
index 0000000..02572da
--- /dev/null
+++ b/test/reload_evolution/storage_2_a.lua
@@ -0,0 +1 @@
+storage_1_a.lua
\ No newline at end of file
diff --git a/test/reload_evolution/storage_2_b.lua b/test/reload_evolution/storage_2_b.lua
new file mode 120000
index 0000000..02572da
--- /dev/null
+++ b/test/reload_evolution/storage_2_b.lua
@@ -0,0 +1 @@
+storage_1_a.lua
\ No newline at end of file
diff --git a/test/reload_evolution/suite.ini b/test/reload_evolution/suite.ini
new file mode 100644
index 0000000..5f55418
--- /dev/null
+++ b/test/reload_evolution/suite.ini
@@ -0,0 +1,6 @@
+[default]
+core = tarantool
+description = Reload evolution tests
+script = test.lua
+is_parallel = False
+lua_libs = ../lua_libs ../../example/localcfg.lua
diff --git a/test/reload_evolution/test.lua b/test/reload_evolution/test.lua
new file mode 100644
index 0000000..ad0543a
--- /dev/null
+++ b/test/reload_evolution/test.lua
@@ -0,0 +1,9 @@
+#!/usr/bin/env tarantool
+
+require('strict').on()
+
+box.cfg{
+ listen = os.getenv("LISTEN"),
+}
+
+require('console').listen(os.getenv('ADMIN'))
diff --git a/test/unit/reload_evolution.result b/test/unit/reload_evolution.result
new file mode 100644
index 0000000..10e606d
--- /dev/null
+++ b/test/unit/reload_evolution.result
@@ -0,0 +1,45 @@
+test_run = require('test_run').new()
+---
+...
+fiber = require('fiber')
+---
+...
+log = require('log')
+---
+...
+util = require('util')
+---
+...
+reload_evolution = require('vshard.storage.reload_evolution')
+---
+...
+-- Init with the latest version.
+fake_M = { reload_version = reload_evolution.version }
+---
+...
+-- Test reload to the same version.
+reload_evolution.upgrade(fake_M)
+---
+...
+test_run:grep_log('default', 'vshard.storage.evolution') == nil
+---
+- true
+...
+-- Test downgrage version.
+log.info(string.rep('a', 1000))
+---
+...
+fake_M.reload_version = fake_M.reload_version + 1
+---
+...
+err = util.check_error(reload_evolution.upgrade, fake_M)
+---
+...
+err:match('auto%-downgrade is not implemented')
+---
+- auto-downgrade is not implemented
+...
+test_run:grep_log('default', 'vshard.storage.evolution', 1000) ~= nil
+---
+- false
+...
diff --git a/test/unit/reload_evolution.test.lua b/test/unit/reload_evolution.test.lua
new file mode 100644
index 0000000..2e99152
--- /dev/null
+++ b/test/unit/reload_evolution.test.lua
@@ -0,0 +1,18 @@
+test_run = require('test_run').new()
+fiber = require('fiber')
+log = require('log')
+util = require('util')
+reload_evolution = require('vshard.storage.reload_evolution')
+-- Init with the latest version.
+fake_M = { reload_version = reload_evolution.version }
+
+-- Test reload to the same version.
+reload_evolution.upgrade(fake_M)
+test_run:grep_log('default', 'vshard.storage.evolution') == nil
+
+-- Test downgrage version.
+log.info(string.rep('a', 1000))
+fake_M.reload_version = fake_M.reload_version + 1
+err = util.check_error(reload_evolution.upgrade, fake_M)
+err:match('auto%-downgrade is not implemented')
+test_run:grep_log('default', 'vshard.storage.evolution', 1000) ~= nil
diff --git a/vshard/storage/init.lua b/vshard/storage/init.lua
index 8ca81f6..6be66d2 100644
--- a/vshard/storage/init.lua
+++ b/vshard/storage/init.lua
@@ -10,6 +10,7 @@ if rawget(_G, MODULE_INTERNALS) then
local vshard_modules = {
'vshard.consts', 'vshard.error', 'vshard.cfg',
'vshard.replicaset', 'vshard.util',
+ 'vshard.storage.reload_evolution'
}
for _, module in pairs(vshard_modules) do
package.loaded[module] = nil
@@ -20,12 +21,16 @@ local lerror = require('vshard.error')
local lcfg = require('vshard.cfg')
local lreplicaset = require('vshard.replicaset')
local util = require('vshard.util')
+local reload_evolution = require('vshard.storage.reload_evolution')
local M = rawget(_G, MODULE_INTERNALS)
if not M then
--
-- The module is loaded for the first time.
--
+ -- !!!WARNING: any change of this table must be reflected in
+ -- `vshard.storage.reload_evolution` module to guarantee
+ -- reloadability of the module.
M = {
---------------- Common module attributes ----------------
-- The last passed configuration.
@@ -105,6 +110,11 @@ if not M then
-- a destination replicaset must drop already received
-- data.
rebalancer_sending_bucket = 0,
+
+ ------------------------- Reload -------------------------
+ -- Version of the loaded module. This number is used on
+ -- reload to determine which upgrade scripts to run.
+ reload_version = reload_evolution.version,
}
end
@@ -1863,6 +1873,7 @@ end
if not rawget(_G, MODULE_INTERNALS) then
rawset(_G, MODULE_INTERNALS, M)
else
+ reload_evolution.upgrade(M)
storage_cfg(M.current_cfg, M.this_replica.uuid)
M.module_version = M.module_version + 1
end
diff --git a/vshard/storage/reload_evolution.lua b/vshard/storage/reload_evolution.lua
new file mode 100644
index 0000000..8502a33
--- /dev/null
+++ b/vshard/storage/reload_evolution.lua
@@ -0,0 +1,58 @@
+--
+-- This module is used to upgrade the vshard.storage on the fly.
+-- It updates internal Lua structures in case they are changed
+-- in a commit.
+--
+local log = require('log')
+
+--
+-- Array of upgrade functions.
+-- migrations[version] = function which upgrades module version
+-- from `version` to `version + 1`.
+--
+local migrations = {}
+
+-- Initialize reload_upgrade mechanism
+migrations[#migrations + 1] = function (M)
+ -- Code to update Lua objects.
+end
+
+--
+-- Perform an update based on a version stored in `M` (internals).
+-- @param M Old module internals which should be updated.
+--
+local function upgrade(M)
+ local start_version = M.reload_version or 1
+ if start_version > #migrations then
+ local err_msg = string.format(
+ 'vshard.storage.reload_evolution: ' ..
+ 'auto-downgrade is not implemented; ' ..
+ 'loaded version is %d, upgrade script version is %d',
+ start_version, #migrations
+ )
+ log.error(err_msg)
+ error(err_msg)
+ end
+ for i = start_version, #migrations do
+ local ok, err = pcall(migrations[i], M)
+ if ok then
+ log.info('vshard.storage.reload_evolution: upgraded to %d version',
+ i)
+ else
+ local err_msg = string.format(
+ 'vshard.storage.reload_evolution: ' ..
+ 'error during upgrade to %d version: %s', i, err
+ )
+ log.error(err_msg)
+ error(err_msg)
+ end
+ -- Update the version just after upgrade to have an
+ -- actual version in case of an error.
+ M.reload_version = i
+ end
+end
+
+return {
+ version = #migrations,
+ upgrade = upgrade,
+}
--
2.14.1
^ permalink raw reply [flat|nested] 14+ messages in thread
end of thread, other threads:[~2018-07-30 8:56 UTC | newest]
Thread overview: 14+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-07-23 11:14 [tarantool-patches] [PATCH v2] vshard reload mechanism AKhatskevich
2018-07-23 11:14 ` [tarantool-patches] [PATCH 1/4] Add test on error during reconfigure AKhatskevich
2018-07-23 13:18 ` [tarantool-patches] " Vladislav Shpilevoy
2018-07-23 11:14 ` [tarantool-patches] [PATCH 2/4] Complete module reload AKhatskevich
2018-07-23 13:31 ` [tarantool-patches] " Vladislav Shpilevoy
2018-07-23 13:45 ` Alex Khatskevich
2018-07-23 14:58 ` Vladislav Shpilevoy
2018-07-23 11:14 ` [tarantool-patches] [PATCH 3/4] Tests: separate bootstrap routine to a lua_libs AKhatskevich
2018-07-23 13:36 ` [tarantool-patches] " Vladislav Shpilevoy
2018-07-23 17:19 ` Alex Khatskevich
2018-07-23 11:14 ` [tarantool-patches] [PATCH 4/4] Introduce storage reload evolution AKhatskevich
2018-07-23 14:44 ` [tarantool-patches] " Vladislav Shpilevoy
2018-07-23 20:10 ` Alex Khatskevich
2018-07-30 8:56 [tarantool-patches] [PATCH v4] vshard module reload AKhatskevich
2018-07-30 8:56 ` [tarantool-patches] [PATCH 4/4] Introduce storage reload evolution AKhatskevich
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox