[sheepdog] [PATCH v8 0/7] shepherd: a new cluster manager specialized for sheepdog

[MORITA Kazutaka]

At Tue, 12 Mar 2013 10:50:54 +0900,
Hitoshi Mitake wrote:
> 
> At Tue, 12 Mar 2013 09:20:44 +0900,
> MORITA Kazutaka wrote:
> > 
> > At Mon, 11 Mar 2013 20:46:32 +0900,
> > Hitoshi Mitake wrote:
> > > 
> > > This patchset adds shepherd: a new cluster manager specialized for
> > > sheepdog. The 6th and 7th patches actually adds shepherd and its
> > > driver, 1 - 5th do preparations for it.
> > > 
> > > Now shepherd can pass all tests. And valgrind doesn't report memory
> > > errors. I believe current version can satisfy least quality for
> > > applying. I'm grad if I can hear your opinions.
> > 
> > This version still don't pass 001, 052, and 053 with -valgrind option.
> > It is reproducible on my environment.  Can you check the following
> > command several times and see the problem happens on your environment
> > too?
> > 
> 
> Thanks for your report. I could reproduce the memory error caused by
> 052. But I couldn't find any memory errors with 001 and 052.
> 
> I could find fails of 052 when valgrind is used. But these are not
> memory errors. And I couldn't find any errors caused by 001.
> Can I see the output on your environment produced by 001 and 052?

Here is the output:

  $ sudo DRIVER=shepherd:localhost ./check -valgrind 1 52
  PLATFORM      -- Linux/x86_64 dfs1301 3.2.21-dfs
  
  001  Test master node killing and master transfer - output mismatch (see 001.out.bad)
  --- 001.out     2013-03-12 12:40:33.000000000 +0900
  +++ 001.out.bad 2013-03-12 13:04:32.000000000 +0900
  @@ -17,7 +17,7 @@
  
   Epoch Time           Version
   DATE      6 [127.0.0.1:7000, 127.0.0.1:7001, 127.0.0.1:7002]
  -DATE      5 [127.0.0.1:7000, 127.0.0.1:7002]
  +DATE      5 [::, 127.0.0.1:7000, 127.0.0.1:7002]
   DATE      4 [127.0.0.1:7002]
   DATE      3 [127.0.0.1:7001, 127.0.0.1:7002]
   DATE      2 [127.0.0.1:7001]
  @@ -28,7 +28,7 @@
  
   Epoch Time           Version
   DATE      6 [127.0.0.1:7000, 127.0.0.1:7001, 127.0.0.1:7002]
  -DATE      5 [127.0.0.1:7000, 127.0.0.1:7002]
  +DATE      5 [::, 127.0.0.1:7000, 127.0.0.1:7002]
   DATE      4 [127.0.0.1:7002]
   DATE      3 [127.0.0.1:7001, 127.0.0.1:7002]
   DATE      2 [127.0.0.1:7001]
  @@ -39,7 +39,7 @@
  
   Epoch Time           Version
   DATE      6 [127.0.0.1:7000, 127.0.0.1:7001, 127.0.0.1:7002]
  -DATE      5 [127.0.0.1:7000, 127.0.0.1:7002]
  +DATE      5 [::, 127.0.0.1:7000, 127.0.0.1:7002]
   DATE      4 [127.0.0.1:7002]
   DATE      3 [127.0.0.1:7001, 127.0.0.1:7002]
   DATE      2 [127.0.0.1:7001]
  052  Test force cluster recovery with new nodes - output mismatch (see 052.out.bad)
  --- 052.out     2013-03-12 12:59:54.000000000 +0900
  +++ 052.out.bad 2013-03-12 13:06:15.000000000 +0900
  @@ -122,7 +122,7 @@
  
   Epoch Time           Version
   DATE      3 [127.0.0.1:7000, 127.0.0.1:7001, 127.0.0.1:7002, 127.0.0.1:7003, 127.0.0.1:7004]
  -DATE      2 [127.0.0.1:7000, 127.0.0.1:7001, 127.0.0.1:7002, 127.0.0.1:7004]
  +DATE      2 [127.0.0.1:7000, 127.0.0.1:7002, 127.0.0.1:7003]
   DATE      1 [127.0.0.1:7000, 127.0.0.1:7001, 127.0.0.1:7002, 127.0.0.1:7003]
     Name        Id    Size    Used  Shared    Creation time   VDI id  Copies  Tag
     test         0   20 MB   20 MB  0.0 MB DATE   7c2b25     3
  Failures: 001 052
  Failed 2 of 2 tests