Re: bluestore min alloc size vs. wasted space

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 





On 2/20/2018 11:57 AM, Flemming Frandsen wrote:
I have set up a little ceph installation and added about 80k files of various sizes, then I added 1M files of 1 byte each totalling 1 MB, to see what kind of overhead is incurred per object.

The overhead for adding 1M objects seems to be 12252M/1000000 = 0.012252M or 122 kB per file, which is a bit high, but in line with a min allocation size of 64 kB.
0.012M = 12Kb, not 122.


My ceph.conf file contained this line from when I initially deployed the cluster:
    bluestore min alloc size = 4096

So your  min alloc size settings for the cluster in question is 4K not 64K, right?
And pool replication factor is 3, isn't it?
Then one can probably explain additional 12Gb of raw space as:
1M objects * min_alloc_size * replication_factor = 1E6 * 4096 * 3 = 12GB

How do I set the min alloc size if not in the ceph.conf file?

Is it possible to change bluestore min alloc size for an existing cluster? How?
This is per-osd setting that can't be altered after OSD deployment. So you should either redeploy the cluster totally or redeploy OSDs one by one if you want to preserve your data.


Even at this level of overhead I'm nowhere near to the 1129 kB per file was lost with the real data.


GLOBAL:
    SIZE     AVAIL     RAW USED     %RAW USED     OBJECTS
    273G      253G       19906M          7.12       81059
POOLS:
    NAME                    ID     QUOTA OBJECTS QUOTA BYTES USED       %USED     MAX AVAIL     OBJECTS DIRTY     READ WRITE     RAW USED     .rgw.root               1      N/A N/A 1113         0          120G 4         4       108 4         2226     default.rgw.control     2      N/A N/A 0         0          120G 8         8         0 0            0     default.rgw.meta        3      N/A N/A 0         0          120G 0         0         0 0            0     default.rgw.log         4      N/A N/A 0         0          120G         207 207     54085 36014            0     fs1_data                5      N/A N/A              7890M 3.11          120G       80001 80001         0      715k 15781M     fs1_metadata            6      N/A N/A             40951k 0.02          120G         839 839       682      103k 81902k

Overhead per object: (19586M-15781M) / 81059 = 0.046M = 46 kB per object



Added 1M files of 1 byte each totalling 1 MB:


GLOBAL:
    SIZE     AVAIL     RAW USED     %RAW USED     OBJECTS
    273G      241G       32158M         11.50       1056k
POOLS:
    NAME                    ID     QUOTA OBJECTS QUOTA BYTES USED       %USED     MAX AVAIL     OBJECTS DIRTY     READ WRITE     RAW USED     .rgw.root               1      N/A N/A 1113         0          114G 4         4       108 4         2226     default.rgw.control     2      N/A N/A 0         0          114G 8         8         0 0            0     default.rgw.meta        3      N/A N/A 0         0          114G 0         0         0 0            0     default.rgw.log         4      N/A N/A 0         0          114G         207 207     56374 37540            0     fs1_data                5      N/A N/A              7891M 3.27          114G     1080001 1054k      287k     3645k 15783M     fs1_metadata            6      N/A N/A             29854k 0.01          114G        1837 1837      5739      118k 59708k

Delta:
   fs1_data: +2M raw space as expected
   fs1_metadata: -22M raw space, because who the fuck knows?
   RAW USED: +12252M


_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com




[Index of Archives]     [Information on CEPH]     [Linux Filesystem Development]     [Ceph Development]     [Ceph Large]     [Ceph Dev]     [Linux USB Development]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [xfs]


  Powered by Linux