[Tarantool-patches] [PATCH 1/3 v2] replication: test clear_synchro_queue() function

[Serge Petrenko]

16.11.2020 14:11, Sergey Bronnikov пишет:
> Hi, Serge!
>
> thanks for review!

Thanks for the fixes!

LGTM.

>
> On 13.11.2020 16:12, Serge Petrenko wrote:
>>
>> 12.11.2020 12:10, sergeyb at tarantool.org пишет:
>>> From: Sergey Bronnikov <sergeyb at tarantool.org>
>>>
>>> Part of #5055
>>> Part of #4849
>>
>> Hi! Thanks for the patch!
>>
>> Please see 2 comments below.
>>
>>> ---
>>>   test/replication/qsync_basic.result   | 136 
>>> ++++++++++++++++++++++++++
>>>   test/replication/qsync_basic.test.lua |  50 ++++++++++
>>>   2 files changed, 186 insertions(+)
>>>
>>> diff --git a/test/replication/qsync_basic.result 
>>> b/test/replication/qsync_basic.result
>>> index bd3c3cce1..e848e305a 100644
>>> --- a/test/replication/qsync_basic.result
>>> +++ b/test/replication/qsync_basic.result
>>> @@ -32,6 +32,13 @@ s2.is_sync
>>>    | - false
>>>    | ...
>>>   +--
>>> +-- gh-4849: clear synchro queue with unconfigured box
>>> +--
>>
>> What do you mean by `unconfigured box`?
>>
>> box.cfg is called when the default instance (master.lua) is started, 
>> before
>> the first test line.
>
> Missed it.
>
>>
>> If you really  want to test `box.ctl.clear_synchro_queue` before 
>> box.cfg,
>> you need to do it in `app-tap/cfg.test.lua`. It has all the tests for 
>> `box.ctl` options.
>
> Removed testcase from qsync_basic.test.lua and added it to 
> app-tap/cfg.test.lua:
>
> --- a/test/replication/qsync_basic.test.lua
> +++ b/test/replication/qsync_basic.test.lua
> @@ -13,11 +13,6 @@ s1:select{}
>  s2 = box.schema.create_space('test2')
>  s2.is_sync
>
> ---
> --- gh-4849: clear synchro queue with unconfigured box
> ---
> -box.ctl.clear_synchro_queue()
> -
>  -- Net.box takes sync into account.
>  box.schema.user.grant('guest', 'super')
>  netbox = require('net.box')
>
> --- a/test/app-tap/cfg.test.lua
> +++ b/test/app-tap/cfg.test.lua
> @@ -3,7 +3,13 @@ local fiber = require('fiber')
>  local tap = require('tap')
>  local test = tap.test("cfg")
>
> -test:plan(11)
> +test:plan(12)
> +
> +--
> +-- gh-4849: clear synchro queue is null with unconfigured box
> +--
> +local ok, err = pcall(box.ctl.clear_synchro_queue(), nil)
> +test:isnil(ok, 'execute clear_synchro_queue with unconfigured box')
>
>  --
>  -- gh-4282: box.cfg should not allow nor just ignore nil UUID.
>
>>> +box.ctl.clear_synchro_queue()
>>> + | ---
>>> + | ...
>>> +
>>>   -- Net.box takes sync into account.
>>>   box.schema.user.grant('guest', 'super')
>>>    | ---
>>> @@ -637,6 +644,135 @@ box.space.sync:count()
>>>    | - 0
>>>    | ...
>>>   +--
>>> +-- gh-4849: clear synchro queue on a master
>>> +--
>>> +test_run:switch('default')
>>> + | ---
>>> + | - true
>>> + | ...
>>> +box.cfg{replication_synchro_quorum = 3, replication_synchro_timeout 
>>> = 1000}
>>> + | ---
>>> + | ...
>>> +ok, err = nil
>>> + | ---
>>> + | ...
>>> +f = fiber.create(function()                            \
>>> +    ok, err = pcall(box.space.sync.insert, box.space.sync, 
>>> {10})        \
>>> +end)
>>> + | ---
>>> + | ...
>>> +f:status()
>>> + | ---
>>> + | - suspended
>>> + | ...
>>> +test_run:switch('replica')
>>> + | ---
>>> + | - true
>>> + | ...
>>> +test_run:wait_cond(function() return box.space.sync:get{10} ~= nil 
>>> end)
>>> + | ---
>>> + | - true
>>> + | ...
>>> +test_run:switch('default')
>>> + | ---
>>> + | - true
>>> + | ...
>>> +box.cfg{replication_synchro_timeout = 0.1}
>>> + | ---
>>> + | ...
>>> +box.ctl.clear_synchro_queue()
>>> + | ---
>>> + | ...
>>> +test_run:switch('replica')
>>> + | ---
>>> + | - true
>>> + | ...
>>> +test_run:wait_cond(function() return box.space.sync:get{10} == nil 
>>> end)
>>> + | ---
>>> + | - true
>>> + | ...
>>> +test_run:switch('default')
>>> + | ---
>>> + | - true
>>> + | ...
>>> +test_run:wait_cond(function() return f:status() == 'dead' end)
>>> + | ---
>>> + | - true
>>> + | ...
>>> +ok, err
>>> + | ---
>>> + | - false
>>> + | - Quorum collection for a synchronous transaction is timed out
>>> + | ...
>>> +test_run:wait_cond(function() return box.space.sync:get{10} == nil 
>>> end)
>>> + | ---
>>> + | - true
>>> + | ...
>>> +
>>> +--
>>> +-- gh-4849: clear synchro queue on a replica, make sure no crashes
>>> +--
>>> +test_run:switch('default')
>>> + | ---
>>> + | - true
>>> + | ...
>>> +box.cfg{replication_synchro_quorum = 3, replication_synchro_timeout 
>>> = 1000}
>>> + | ---
>>> + | ...
>>> +ok, err = nil
>>> + | ---
>>> + | ...
>>> +f = fiber.create(function() \
>>> +    ok, err = pcall(box.space.sync.insert, box.space.sync, 
>>> {9})                 \
>>> +end)
>>> + | ---
>>> + | ...
>>> +f.status()
>>> + | ---
>>> + | - running
>>> + | ...
>>
>>
>> typo: should be `f:status()`
>
> Updated:
>
> --- a/test/replication/qsync_basic.test.lua
> +++ b/test/replication/qsync_basic.test.lua
> @@ -284,7 +284,7 @@ ok, err = nil
>  f = fiber.create(function() \
>      ok, err = pcall(box.space.sync.insert, box.space.sync, 
> {9})                 \
>  end)
> -f.status()
> +f:status()
>  test_run:wait_cond(function() return box.space.sync:get{9} ~= nil end)
>  test_run:switch('replica')
>  box.cfg{replication_synchro_quorum = 3, 
> replication_synchro_timeout=0.01}
>
>>
>>
>>> +test_run:wait_cond(function() return box.space.sync:get{9} ~= nil end)
>>> + | ---
>>> + | - true
>>> + | ...
>>> +test_run:switch('replica')
>>> + | ---
>>> + | - true
>>> + | ...
>>> +box.cfg{replication_synchro_quorum = 3, 
>>> replication_synchro_timeout=0.01}
>>> + | ---
>>> + | ...
>>> +box.ctl.clear_synchro_queue()
>>> + | ---
>>> + | ...
>>> +test_run:wait_cond(function() return box.space.sync:get{9} == nil end)
>>> + | ---
>>> + | - true
>>> + | ...
>>> +test_run:switch('default')
>>> + | ---
>>> + | - true
>>> + | ...
>>> +box.cfg{replication_synchro_timeout=0.01}
>>> + | ---
>>> + | ...
>>> +test_run:wait_cond(function() return f:status() == 'dead' end)
>>> + | ---
>>> + | - true
>>> + | ...
>>> +ok, err
>>> + | ---
>>> + | - false
>>> + | - Quorum collection for a synchronous transaction is timed out
>>> + | ...
>>> +test_run:wait_cond(function() return box.space.sync:get{9} == nil end)
>>> + | ---
>>> + | - true
>>> + | ...
>>> +
>>> +-- Note: cluster may be in a broken state here due to nature of 
>>> previous test.
>>> +
>>>   -- Cleanup.
>>>   test_run:cmd('switch default')
>>>    | ---
>>> diff --git a/test/replication/qsync_basic.test.lua 
>>> b/test/replication/qsync_basic.test.lua
>>> index 94235547d..523dfa779 100644
>>> --- a/test/replication/qsync_basic.test.lua
>>> +++ b/test/replication/qsync_basic.test.lua
>>> @@ -13,6 +13,11 @@ s1:select{}
>>>   s2 = box.schema.create_space('test2')
>>>   s2.is_sync
>>>   +--
>>> +-- gh-4849: clear synchro queue with unconfigured box
>>> +--
>>> +box.ctl.clear_synchro_queue()
>>> +
>>>   -- Net.box takes sync into account.
>>>   box.schema.user.grant('guest', 'super')
>>>   netbox = require('net.box')
>>> @@ -248,6 +253,51 @@ for i = 1, 100 do box.space.sync:delete{i} end
>>>   test_run:cmd('switch replica')
>>>   box.space.sync:count()
>>>   +--
>>> +-- gh-4849: clear synchro queue on a master
>>> +--
>>> +test_run:switch('default')
>>> +box.cfg{replication_synchro_quorum = 3, replication_synchro_timeout 
>>> = 1000}
>>> +ok, err = nil
>>> +f = fiber.create(function()                            \
>>> +    ok, err = pcall(box.space.sync.insert, box.space.sync, 
>>> {10})        \
>>> +end)
>>> +f:status()
>>> +test_run:switch('replica')
>>> +test_run:wait_cond(function() return box.space.sync:get{10} ~= nil 
>>> end)
>>> +test_run:switch('default')
>>> +box.cfg{replication_synchro_timeout = 0.1}
>>> +box.ctl.clear_synchro_queue()
>>> +test_run:switch('replica')
>>> +test_run:wait_cond(function() return box.space.sync:get{10} == nil 
>>> end)
>>> +test_run:switch('default')
>>> +test_run:wait_cond(function() return f:status() == 'dead' end)
>>> +ok, err
>>> +test_run:wait_cond(function() return box.space.sync:get{10} == nil 
>>> end)
>>> +
>>> +--
>>> +-- gh-4849: clear synchro queue on a replica, make sure no crashes
>>> +--
>>> +test_run:switch('default')
>>> +box.cfg{replication_synchro_quorum = 3, replication_synchro_timeout 
>>> = 1000}
>>> +ok, err = nil
>>> +f = fiber.create(function() \
>>> +    ok, err = pcall(box.space.sync.insert, box.space.sync, 
>>> {9})                 \
>>> +end)
>>> +f.status()
>>> +test_run:wait_cond(function() return box.space.sync:get{9} ~= nil end)
>>> +test_run:switch('replica')
>>> +box.cfg{replication_synchro_quorum = 3, 
>>> replication_synchro_timeout=0.01}
>>> +box.ctl.clear_synchro_queue()
>>> +test_run:wait_cond(function() return box.space.sync:get{9} == nil end)
>>> +test_run:switch('default')
>>> +box.cfg{replication_synchro_timeout=0.01}
>>> +test_run:wait_cond(function() return f:status() == 'dead' end)
>>> +ok, err
>>> +test_run:wait_cond(function() return box.space.sync:get{9} == nil end)
>>> +
>>> +-- Note: cluster may be in a broken state here due to nature of 
>>> previous test.
>>> +
>>>   -- Cleanup.
>>>   test_run:cmd('switch default')
>>
-- 
Serge Petrenko