Hello,

I’m completely new to Robinhood, so forgive my ignorance, but I’m having a 
problem with some of the stats being reported by robinhood. For example, our 
Lustre filesystem is mounted on /scratch and there is a user directory 
/scratch/mkg52 that has well over 40GB of data in it. However, when I run 
`rbh-report -u mkg52`, i get a response telling me that there is far less. Here 
is the relevant output:

[root@tillit ~]# rbh-report -u mkg52
Using config file '/etc/robinhood.d/lustre.conf'.
      user,     type,      count,     volume,   spc_used,   avg_size
     mkg52,      dir,         15,   60.00 KB,   60.00 KB,    4.00 KB
     mkg52,     file,        327,  399.32 MB,  400.20 MB,    1.22 MB

Now when I run du you can see I have much more than 400MB of data being used

[mkg52@wind /scratch/mkg52 ]$ du -smh *
217M    archive
108K    bigdata_snd73
4.0K    build_wine.sh
4.0K    cd833.out
1.5G    CESM
578M    cesm1_2_2
68K     clr96_bigdata
4.0K    clr96_lazy.out
4.0K    clr96_lazy.txt
4.0K    clr96_output.out
16K     cmdstan_testing
1.4G    drivers

[root@tillit ~]# rbh-du -s -H /scratch/mkg52
Using config file '/etc/robinhood.d/lustre.conf'.
4.4M    total

I am very confused by this output. There are other user folders where this 
information is completely accurate, but specifically /scratch/mkg52 is missing 
a bunch of information.

Here is the output of the errors in readlog:

[root@tillit ~]# robinhood --readlog --once -L stderr
Using config file '/etc/robinhood.d/lustre.conf'.
2016/12/15 16:07:13 [45806/1] CheckFS | '/scratch' matches mount point 
'/scratch', type=lustre, fs=mds1.ib@o2ib:mds2.ib@o2ib:/blizzard
2016/12/15 16:07:13 [45806/1] EntryProc | No fileclass defined in 
configuration, disabling fileclass matching.
2016/12/15 16:07:13 [45806/1] llapi | warning: llapi_changelog_start() called 
w/o CHANGELOG_FLAG_JOBID
2016/12/15 16:07:13 [45806/2] ChangeLog | LU-1331 is fixed in this version of 
Lustre.
2016/12/15 16:07:13 [45806/2] ChangeLog | Changelog reader thread terminating
2016/12/15 16:07:13 [45806/1] Main | Event Processing finished
2016/12/15 16:07:13 [45806/1] EntryProc | Pipeline successfully flushed
2016/12/15 16:07:13 [45806/1] STATS | ==== EntryProcessor Pipeline Stats ===
2016/12/15 16:07:13 [45806/1] STATS | Idle threads: 0
2016/12/15 16:07:13 [45806/1] STATS | Id constraints count: 0 (hash 
min=0/max=0/avg=0.0)
2016/12/15 16:07:13 [45806/1] STATS | Name constraints count: 0 (hash 
min=0/max=0/avg=0.0)
2016/12/15 16:07:13 [45806/1] STATS | Stage              | Wait | Curr | Done | 
    Total | ms/op |
2016/12/15 16:07:13 [45806/1] STATS |  0: GET_FID        |    0 |    0 |    0 | 
        0 |  0.00 |
2016/12/15 16:07:13 [45806/1] STATS |  1: GET_INFO_DB    |    0 |    0 |    0 | 
      248 |  0.37 |
2016/12/15 16:07:13 [45806/1] STATS |  2: GET_INFO_FS    |    0 |    0 |    0 | 
      148 |  1.60 |
2016/12/15 16:07:13 [45806/1] STATS |  3: PRE_APPLY      |    0 |    0 |    0 | 
      242 |  0.00 |
2016/12/15 16:07:13 [45806/1] STATS |  4: DB_APPLY       |    0 |    0 |    0 | 
      242 |  0.78 | 11.57% batched (avg batch size: 2.0)
2016/12/15 16:07:13 [45806/1] STATS |  5: CHGLOG_CLR     |    0 |    0 |    0 | 
      248 |  0.01 |
2016/12/15 16:07:13 [45806/1] STATS |  6: RM_OLD_ENTRIES |    0 |    0 |    0 | 
        0 |  0.00 |
2016/12/15 16:07:13 [45806/1] STATS | DB ops: get=192/ins=54/upd=89/rm=99
2016/12/15 16:07:13 [45806/1] STATS | ChangeLog reader #0:
2016/12/15 16:07:13 [45806/1] STATS |    fs_name    =   blizzard
2016/12/15 16:07:13 [45806/1] STATS |    mdt_name   =   MDT0000
2016/12/15 16:07:13 [45806/1] STATS |    reader_id  =   cl1
2016/12/15 16:07:13 [45806/1] STATS |    records read        = 252
2016/12/15 16:07:13 [45806/1] STATS |    interesting records = 160
2016/12/15 16:07:13 [45806/1] STATS |    suppressed records  = 92
2016/12/15 16:07:13 [45806/1] STATS |    records pending     = 0
2016/12/15 16:07:13 [45806/1] STATS |    last received            = 2016/12/15 
16:07:13
2016/12/15 16:07:13 [45806/1] STATS |    last read record time    = 2016/12/15 
16:07:13.445247
2016/12/15 16:07:13 [45806/1] STATS |    last read record id      = 16147371
2016/12/15 16:07:13 [45806/1] STATS |    last pushed record id    = 16147371
2016/12/15 16:07:13 [45806/1] STATS |    last committed record id = 16147371
2016/12/15 16:07:13 [45806/1] STATS |    last cleared record id   = 16147371
2016/12/15 16:07:13 [45806/1] STATS |    status                   = almost idle
2016/12/15 16:07:13 [45806/1] STATS |    ChangeLog stats:
2016/12/15 16:07:13 [45806/1] STATS |    MARK: 0, CREAT: 55, MKDIR: 0, HLINK: 
0, SLINK: 0, MKNOD: 0, UNLNK: 12, RMDIR: 0, RENME: 45
2016/12/15 16:07:13 [45806/1] STATS |    RNMTO: 0, OPEN: 0, CLOSE: 99, LYOUT: 
0, TRUNC: 40, SATTR: 1, XATTR: 0, HSM: 0, MTIME: 0
2016/12/15 16:07:13 [45806/1] STATS |    CTIME: 0, ATIME: 0, MIGRT: 0

Here is my lustre.conf file:

General {
    fs_path = "/scratch";
    # filesystem type, as displayed by 'mount' (e.g. ext4, xfs, lustre, ...)
    fs_type = lustre;
}

Log {
    log_file = "/var/log/robinhood/robinhood.log";
    report_file = "/var/log/robinhood/robinhood_actions.log";
    alert_file = "/var/log/robinhood/robinhood_alerts.log";
}

ListManager {
    MySQL {
        server = localhost;
        db = robinhood_lustre;
        user = robinhood;
        password_file = /etc/robinhood.d/.dbpassword;
    }
}

# Lustre 2.x only
ChangeLog {
    MDT {
        mdt_name = "MDT0000";
        reader_id = "cl1";
    }
}

Any help would be greatly appreciated!

Thank you,

Mike

------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most 
engaging tech sites, SlashDot.org! http://sdm.link/slashdot
_______________________________________________
robinhood-support mailing list
robinhood-support@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/robinhood-support

Reply via email to