Heiko Schröter
2010-Aug-11 07:53 UTC
[Lustre-discuss] lfs --obd discrepancy to lctl dl (1.8.3)
Hello, lfs prints different obd(idx) compared to lctl dl. We use single striping. cluster1 tmp # lfs find --obd scia-OST0017_UUID /data/scia/L0/V0.00/20100327/SCI_NL__0PNPDE20100327_193441_000040582088_00071_42209_1158.N1 /data/scia/L0/V0.00/20100327/SCI_NL__0PNPDE20100327_193441_000040582088_00071_42209_1158.N1 cluster1 tmp # lfs getstripe /data/scia/L0/V0.00/20100327/SCI_NL__0PNPDE20100327_193441_000040582088_00071_42209_1158.N1 /data/scia/L0/V0.00/20100327/SCI_NL__0PNPDE20100327_193441_000040582088_00071_42209_1158.N1 lmm_stripe_count: 1 lmm_stripe_size: 1048576 lmm_stripe_offset: 23 obdidx objid objid group 23 41020 0xa03c 0 cluster1 tmp # lctl dl <snip> 19 UP osc scia-OST0010-osc-ffff8800bb076000 c50eddc4-14c3-66a0-0f8d-7bc8e2b9a1e8 4 20 UP osc scia-OST0011-osc-ffff8800bb076000 c50eddc4-14c3-66a0-0f8d-7bc8e2b9a1e8 4 21 UP osc scia-OST0012-osc-ffff8800bb076000 c50eddc4-14c3-66a0-0f8d-7bc8e2b9a1e8 4 22 UP osc scia-OST0013-osc-ffff8800bb076000 c50eddc4-14c3-66a0-0f8d-7bc8e2b9a1e8 4 23 UP osc scia-OST0014-osc-ffff8800bb076000 c50eddc4-14c3-66a0-0f8d-7bc8e2b9a1e8 5 24 UP osc scia-OST0015-osc-ffff8800bb076000 c50eddc4-14c3-66a0-0f8d-7bc8e2b9a1e8 5 25 UP osc scia-OST0016-osc-ffff8800bb076000 c50eddc4-14c3-66a0-0f8d-7bc8e2b9a1e8 5 26 UP osc scia-OST0017-osc-ffff8800bb076000 c50eddc4-14c3-66a0-0f8d-7bc8e2b9a1e8 5 27 UP osc scia-OST0018-osc-ffff8800bb076000 c50eddc4-14c3-66a0-0f8d-7bc8e2b9a1e8 5 28 UP osc scia-OST0019-osc-ffff8800bb076000 c50eddc4-14c3-66a0-0f8d-7bc8e2b9a1e8 5 <snap> According to "lfs find" the stripe should be on scia-OST0017_UUID. "lfs gestripe" reports to have it on obdidx 23 , which is scia-OST0014 according to lctl dl. Which one is true ? As fas as i remember it worked correctly in 1.6.6. We updated currently from 1.6.6 to 1.8.3. Could have been something broken during upgrade ? Thanks and Regards Heiko
Daniel Kobras
2010-Aug-11 08:38 UTC
[Lustre-discuss] lfs --obd discrepancy to lctl dl (1.8.3)
Hi! On Wed, Aug 11, 2010 at 09:53:01AM +0200, Heiko Schr?ter wrote:> According to "lfs find" the stripe should be on scia-OST0017_UUID. "lfs > gestripe" reports to have it on obdidx 23 , which is scia-OST0014 according > to lctl dl. Which one is true ?lctl dl returns a list of all Lustre components running on the local machine, prefixed by a sequential number. It depends on the order in which components have been started on the machine, and has nothing to do with obdidx. Your file resides on OST 23 (== 0x17), therefore. Regards, Daniel.
Christopher J. Morrone
2010-Aug-13 01:07 UTC
[Lustre-discuss] lfs --obd discrepancy to lctl dl (1.8.3)
On 08/11/2010 01:38 AM, Daniel Kobras wrote:> On Wed, Aug 11, 2010 at 09:53:01AM +0200, Heiko Schr?ter wrote: >> According to "lfs find" the stripe should be on scia-OST0017_UUID. "lfs >> gestripe" reports to have it on obdidx 23 , which is scia-OST0014 according >> to lctl dl. Which one is true ? > > lctl dl returns a list of all Lustre components running on the local machine, > prefixed by a sequential number. It depends on the order in which components > have been started on the machine, and has nothing to do with obdidx. Your > file resides on OST 23 (== 0x17), therefore.If you don''t want to do the math (or your indexes somehow don''t match your ost names), you can use the "lfs osts" command to get a mapping of indices to ost names. Chris
Heiko Schröter
2010-Aug-13 05:53 UTC
[Lustre-discuss] lfs --obd discrepancy to lctl dl (1.8.3)
Am Freitag 13 August 2010, um 03:07:31 schrieb Christopher J. Morrone: Thanks a lot. "lfs osts" is the one i''ve been looking for. and if this one would print out the IP as well ... but i think this is asking for too much.... Regards Heiko> On 08/11/2010 01:38 AM, Daniel Kobras wrote: > > > On Wed, Aug 11, 2010 at 09:53:01AM +0200, Heiko Schr?ter wrote: > >> According to "lfs find" the stripe should be on scia-OST0017_UUID. "lfs > >> gestripe" reports to have it on obdidx 23 , which is scia-OST0014 according > >> to lctl dl. Which one is true ? > > > > lctl dl returns a list of all Lustre components running on the local machine, > > prefixed by a sequential number. It depends on the order in which components > > have been started on the machine, and has nothing to do with obdidx. Your > > file resides on OST 23 (== 0x17), therefore. > > If you don''t want to do the math (or your indexes somehow don''t match > your ost names), you can use the "lfs osts" command to get a mapping of > indices to ost names. > > Chris > _______________________________________________ > Lustre-discuss mailing list > Lustre-discuss at lists.lustre.org > http://lists.lustre.org/mailman/listinfo/lustre-discuss >