Hello:
I have been unable to debug this problem, so far.
Any attempt to connect to tgtd from a Centos 6.6 system with its included infiniband drivers fails.
Server is
The most obvious symptom of this is that when the initiator contacts the target, tgtd requests 1GB of shared memory, which fails:
In response to initiatior:
[root@e5node05 iscsi]# iscsiadm -m discovery -t sendtargets -p 192.168.170.188:3260 -I iser
[root@e5san01 etc]# tgtd -f
tgtd: work_timer_start(146) use timer_fd based scheduler
tgtd: bs_init_signalfd(267) could not open backing-store module directory /usr/lib/tgt/backing-store
tgtd: bs_init(386) use signalfd notification
tgtd: iser_alloc_pool(571) shmget rdma pool sz:1073741824 failed
tgtd: iser_cm_conn_established(1613) conn:0x12db840 cm_id:0x12beac0, 192.168.170.85 -> 192.168.170.188, established
tgtd: iser_cm_disconnected(1633) conn:0x12db840 cm_id:0x12beac0 event:10, RDMA_CM_EVENT_DISCONNECTED
tgtd: iser_conn_close(1292) conn:0x12db840 cm_id:0x0x12beac0 state: CLOSE, refcnt:394
tgtd: iser_cm_timewait_exit(1648) conn:0x12db840 refcnt:1 cm_id:0x12beac0
tgtd: iser_cm_timewait_exit(1666) conn:0x12db840 refcnt:1 cm_id:0x12beac0 (after cleanup)
This happens with the stock tgtd 1.0.24, or the newest 1,0,55 tgtd (this listed above).
Any help would be greatly appreciated!
/etc/tgt/targets.conf:
[root@e5san01 etc]# cat /etc/tgt/targets.conf
<target iqn.2015-02.entwiz.com:target00>
backing-store /iscsi_disks/disk01.img
driver iser
</target>
target modules:
ib_iser 42254 0
iscsi_tcp 9891 0
be2iscsi 105183 0
iscsi_boot_sysfs 9458 1 be2iscsi
libiscsi_tcp 15964 4 cxgb4i,cxgb3i,iscsi_tcp,libcxgbi
libiscsi 48300 8 bnx2i,cxgb4i,cxgb3i,ib_iser,iscsi_tcp,be2iscsi,libcxgbi,libiscsi_tcp
scsi_transport_iscsi 99144 8 bnx2i,ib_iser,iscsi_tcp,be2iscsi,libcxgbi,libiscsi
ib_ipoib 81126 0
rdma_ucm 15500 0
ib_ucm 12121 0
ib_uverbs 39106 6 rdma_ucm,ib_ucm
ib_umad 11802 8
rdma_cm 36322 2 ib_iser,rdma_ucm
ib_cm 36996 3 ib_ipoib,ib_ucm,rdma_cm
iw_cm 8516 1 rdma_cm
ib_sa 24060 4 ib_ipoib,rdma_ucm,rdma_cm,ib_cm
ib_mthca 127327 1
ib_mad 39811 4 ib_umad,ib_cm,ib_sa,ib_mthca
ib_core 81443 13 ib_iser,iw_cxgb3,ib_ipoib,rdma_ucm,ib_ucm,ib_uverbs,ib_umad,rdma_cm,ib_cm,iw_cm,ib_sa,ib_mthca,ib_mad
ib_addr 8304 3 rdma_ucm,rdma_cm,ib_core
ipv6 334740 40 cnic,ip6t_REJECT,nf_conntrack_ipv6,nf_defrag_ipv6,ib_ipoib,ib_addr
initiator modules:
[root@e5node05 iscsi]# lsmod|grep -E "ib_|rdma|scsi"
be2iscsi 105183 0
iscsi_boot_sysfs 9458 1 be2iscsi
iscsi_tcp 9891 0
libiscsi_tcp 15964 4 cxgb4i,cxgb3i,libcxgbi,iscsi_tcp
scsi_transport_sas 35588 2 mpt3sas,mpt2sas
ib_iser 42254 0
libiscsi 48300 8 be2iscsi,bnx2i,cxgb4i,cxgb3i,libcxgbi,iscsi_tcp,libiscsi_tcp,ib_iser
scsi_transport_iscsi 99144 8 be2iscsi,bnx2i,libcxgbi,iscsi_tcp,ib_iser,libiscsi
ib_ipoib 81126 0
rdma_ucm 15500 0
ib_ucm 12121 0
ib_uverbs 39106 6 rdma_ucm,ib_ucm
ib_umad 11802 4
rdma_cm 36322 2 ib_iser,rdma_ucm
ib_cm 36996 3 ib_ipoib,ib_ucm,rdma_cm
iw_cm 8516 1 rdma_cm
ib_sa 24060 4 ib_ipoib,rdma_ucm,rdma_cm,ib_cm
ib_mthca 127327 1
ib_mad 39811 4 ib_umad,ib_cm,ib_sa,ib_mthca
ib_core 81443 13 iw_cxgb3,ib_iser,ib_ipoib,rdma_ucm,ib_ucm,ib_uverbs,ib_umad,rdma_cm,ib_cm,iw_cm,ib_sa,ib_mthca,ib_mad
ib_addr 8304 3 rdma_ucm,rdma_cm,ib_core
ipv6 334740 552 cnic,ip6t_REJECT,nf_conntrack_ipv6,nf_defrag_ipv6,ib_ipoib,ib_addr
SAN RAM: [root@e5san01 ~]# free -g
total used free shared buffers cached
Mem: 62 2 60 0 0 0
-/+ buffers/cache: 1 61
Swap: 1 0 1
Please, any help on this would be greatly apopreciated!
--
To unsubscribe from this list: send the line "unsubscribe stgt" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
