[lustre-discuss] Error in lfsck: "NOT IMPLEMETED YET"

Joao Carlos Mendes Luis jonny at corp.globo.com
Mon Jul 22 19:35:26 PDT 2019


On 7/22/19 11:10 PM, Andreas Dilger wrote:
> If you are trying to delete MDT0000 then that is definitely not 
> implemented yet...


No, no, no...


This was my first idea, but then I understood that the root directory is 
always on MDT0, so I had to migrate it to another server (after having 
created two more, and crashed during migration).

I will later try to migrate to another server, and then delete MDT2.  
But first I need to finish this lfsck...   :-(


These "NOT IMPLEMETED (sic)" messages are just from running lfsck_start -A


>
> Cheers, Andreas
>
> On Jul 22, 2019, at 16:08, João Carlos Mendes Luís 
> <jonny at corp.globo.com <mailto:jonny at corp.globo.com>> wrote:
>
>> Hi,
>>
>>     I'm running some lab tests with lustre 2.12.2 in Oracle Linux 
>> Server release 7.6.  Last test I did was about migration and MDT 
>> splitting.  I started with a MGS+MDS node, and two OSS nodes, and one 
>> of the tests was to create two more MDSs and migrate data between 
>> then, until, after some time, I could delete the original MDS.  But 
>> something happened in the middle and the servers panicked/rebooted.
>>
>>     I am now in what appears to be an lfsck bug.  After many other 
>> tests, I run lfsck_start, and after some time get this message on the 
>> nodes:
>>
>> MGS/MDS0:
>>
>> *[Mon Jul 22 17:42:25 2019] LustreError: 
>> 24107:0:(osd_index.c:1872:osd_index_it_get()) NOT IMPLEMETED YET 
>> (move to 0x2481000002000000)*
>>
>> OSS1/MDS1
>>
>> *[Mon Jul 22 17:40:29 2019] LustreError: 
>> 31558:0:(osd_index.c:1872:osd_index_it_get()) NOT IMPLEMETED YET 
>> (move to 0xa41300c002000000)*
>>
>> OST2/MDS2
>>
>> *[Mon Jul 22 17:40:32 2019] LustreError: 
>> 8935:0:(osd_index.c:1872:osd_index_it_get()) NOT IMPLEMETED YET (move 
>> to 0xa013000003000000)*
>>
>>
>>     And for current lfsck status, I run *lctl get_param *.*.lfsck* | 
>> grep -E 'status|\.lfsck_lay|\.lfsck_name'*
>>
>> MGS/MDS0:
>>
>> *mdd.mirror01-MDT0000.lfsck_layout=**
>> **status: completed**
>> **mdd.mirror01-MDT0000.lfsck_namespace=**
>> **status: partial*
>>
>> OSS1/MDS1
>>
>> *mdd.mirror01-MDT0001.lfsck_layout=**
>> **status: completed**
>> **mdd.mirror01-MDT0001.lfsck_namespace=**
>> **status: partial**
>> **obdfilter.mirror01-OST0065.lfsck_layout=**
>> **status: completed*
>>
>> OST2/MDS2
>>
>> *mdd.mirror01-MDT0002.lfsck_layout=**
>> **status: completed**
>> **mdd.mirror01-MDT0002.lfsck_namespace=**
>> **status: partial**
>> **obdfilter.mirror01-OST0066.lfsck_layout=**
>> **status: completed*
>>
>>     Is this a known bug?  How do I fix these "partial" lsfck runs?
>>
>>     Thanks for any help,
>>
>>
>>         Jonny
>>
>>
>> ------------------------------------------------------------------------
>> globo.com 	
>> *João Carlos Mendes Luís*
>> *Senior DevOps Engineer*
>> jonny at corp.globo.com <mailto:jonny at corp.globo.com>
>> +55-21-2483-6893
>> +55-21-99218-1222
>>
>>
>> _______________________________________________
>> lustre-discuss mailing list
>> lustre-discuss at lists.lustre.org <mailto:lustre-discuss at lists.lustre.org>
>> http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org


     Atenciosamente,

         Jonny

-- 
João Carlos Mendes Luís
Globo.COM - +55-21-2483-6893

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20190722/f2699739/attachment-0001.html>


More information about the lustre-discuss mailing list