DAOS on a VM


ganyushin@...
 

Hello DAOS developers and users,

I am trying to start a DAOS server of a centos 7 virtual machine for tests.  I used RPMs version 1.0.3 from the Intel website and tmpfs for /mnt/daos. 
If I try to execute command like "dmg pool create --scm--size=1G" the daos_server dies with the message in the log: 

daostest ERROR 2021/04/06 13:09:18 DAOS I/O Server exited with error: /usr/bin/daos_io_server (instance 0) exited: signal: aborted
daostest INFO 2021/04/06 13:09:20 DAOS Control Server (pid 13335) listening on 0.0.0.0:10001
daostest INFO 2021/04/06 13:09:20 Waiting for DAOS I/O Server instance storage to be ready...
daostest INFO 2021/04/06 13:09:20 SCM @ /mnt/daos: 4.3 GB Total/4.2 GB Avail
daostest INFO 2021/04/06 13:09:20 Starting I/O server instance 0: /usr/bin/daos_io_server
daostest INFO 2021/04/06 13:09:20 daos_io_server:0 Using legacy core allocation algorithm
1 target XS(xstream) requested (#cores 1); use (-1) target XS
daostest INFO 2021/04/06 13:09:20 daos_io_server:0 Starting SPDK v19.04.1 / DPDK 19.02.0 initialization...
[ DPDK EAL parameters: daos -c 0x1 --log-level=lib.eal:6 --base-virtaddr=0x200000000000 --match-allocations --file-prefix=spdk13336 --proc-type=auto ]
daostest INFO 2021/04/06 13:09:20 daos_io_server:0 EAL: WARNING: cpu flags constant_tsc=no nonstop_tsc=no -> using unreliable clock cycles !
daostest ERROR 2021/04/06 13:09:20 daos_io_server:0 04/06-13:09:20.47 daostest DAOS[14099/14099] server EMRG src/iosrv/srv_internal.h:160 dss_xs2tgt() invalid xs_id 1, dss_tgt_nr -1, dss_tgt_offload_xs_nr
 0.
daos_io_server: src/iosrv/srv_internal.h:160: dss_xs2tgt: Assertion `xs_id >= 0 && xs_id < (dss_tgt_nr * (dss_tgt_offload_xs_nr + 1) + dss_sys_xs_nr)' failed.
*** Process 14099 received signal 6 ***
Associated errno: Success (0)
/lib64/libpthread.so.0(+0xf630)[0x7f4fe758e630]
/lib64/libc.so.6(gsignal+0x37)[0x7f4fe692d3d7]
/lib64/libc.so.6(abort+0x148)[0x7f4fe692eac8]
/lib64/libc.so.6(+0x2f1a6)[0x7f4fe69261a6]
/lib64/libc.so.6(+0x2f252)[0x7f4fe6926252]
/usr/bin/daos_io_server[0x41abd1]
/usr/bin/daos_io_server(dss_srv_init+0x44a)[0x42093a]
/usr/bin/daos_io_server(main+0xec8)[0x408de8]
/lib64/libc.so.6(__libc_start_main+0xf5)[0x7f4fe6919555]
/usr/bin/daos_io_server[0x40a56b]
 
I suspect that some config parameters are not good and here is my config file:
# For a single-server system
 
name: daos_server
access_points: ['localhost']
# port: 10001
provider: ofi+sockets
nr_hugepages: 4096
control_log_file: /tmp/daos_server.log
transport_config:
   allow_insecure: true
 
engines:
-
  targets: 1
  first_core: 0
  nr_xs_helpers: 0
  fabric_iface: eth0
  fabric_iface_port: 31416
  log_file: /tmp/daos_engine.0.log

  env_vars:
  - DAOS_MD_CAP=1024
  - CRT_CTX_SHARE_ADDR=0
  - CRT_TIMEOUT=30
  - FI_SOCKETS_MAX_CONN_RETRY=1
  - FI_SOCKETS_CONN_TIMEOUT=2000
 
  # Storage definitions
 
  # When scm_class is set to ram, tmpfs will be used to emulate SCM.
  # The size of ram is specified by scm_size in GB units.
  scm_mount: /mnt/daos  # map to -s /mnt/daos
  scm_class: ram
  scm_size: 4
 
  # When bdev_class is set to file, Linux AIO will be used to emulate NVMe.
  # The size of file that will be created is specified by bdev_size in GB units.
  # The location of the files that will be created is specified in bdev_list.
  bdev_class: file
  bdev_size: 16
  bdev_list: [/tmp/daos-bdev]

Could you please help me to figure this out.

Best wishes

Dmitry 
 

Join daos@daos.groups.io to automatically receive all group messages.