[lustre-discuss] overstriping
John Bauer
bauerj at iodoctors.com
Wed Jun 15 15:56:07 PDT 2022
Just a note that the man page for lfs setstripe seems a bit misleading
for the -C --overstripe-count option. The man page states "creating > 1
stripe per OST if count exceeds the number of OSTs in the file
system". It appears that lustre creates more than one stripe on an OST
if the number of stripes exceeds the number of OSTs in the pool being
used. In my example below I selected a pool with 8 OSTs, and striped 16
wide. The file system has 64 OSTs. 16 is less than 64, but I still got
2 stripes per OST.
-C, --overstripe-count <stripe_count>
The number of stripes to create, creating > 1 stripe per
OST if count exceeds the number of OSTs in the file
system. 0 means to use the filesystem-wide default
stripe count (default 1), and -1 means to stripe over all
available OSTs.
pfe22.jbauer2 908> lfs setstripe --pool 1_hdd -C 16 this.dat
pfe22.jbauer2 909> lfs getstripe this.dat
this.dat
lmm_stripe_count: 16
lmm_stripe_size: 1048576
lmm_pattern: raid0,overstriped
lmm_layout_gen: 0
lmm_stripe_offset: 7
lmm_pool: 1_hdd
obdidx objid objid group
7 23665469 0x1691b3d 0
0 22497141 0x1574775 0
4 23541897 0x1673889 0
2 23308778 0x163a9ea 0
1 23033000 0x15f74a8 0
6 23687573 0x1697195 0
5 23635915 0x168a7cb 0
3 23446533 0x165c405 0
7 23665470 0x1691b3e 0
0 22497142 0x1574776 0
4 23541898 0x167388a 0
2 23308779 0x163a9eb 0
1 23033001 0x15f74a9 0
6 23687574 0x1697196 0
5 23635916 0x168a7cc 0
3 23446534 0x165c406 0
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20220615/a9177902/attachment.htm>
More information about the lustre-discuss
mailing list