Forum Stats

  • 3,839,047 Users
  • 2,262,441 Discussions
  • 7,900,839 Comments

Discussions

vdbench * Slave localhost-0 aborting: Shutdown took more than 5 minutes; Run aborted *

User_5XSLI
User_5XSLI Member Posts: 1 Green Ribbon

Hello, experts; I encountered a vdbench problem; Can you guide me? When testing the directory mounted by cephfs, it often interrupts, and then exits after five minutes, but it does not always happen. The files that vdbench runs are as follows;Hope to get a reply!


file:

debug=25

fsd=fsd1,anchor=/mnt/replicated/vdbench_dir0/sub1,depth=1,width=1,files=10000,size=64k,openflags=o_direct,shared=yes

fsd=fsd2,anchor=/mnt/replicated/vdbench_dir1/sub2,depth=1,width=1,files=10000,size=64k,openflags=o_direct,shared=yes

fsd=fsd3,anchor=/mnt/replicated/vdbench_dir2/sub3,depth=1,width=1,files=10000,size=64k,openflags=o_direct,shared=yes

fwd=format,xfersize=64k,threads=64

fwd=fwd1,fsd=fsd*,operation=read,xfersize=4k,fileio=sequential,fileselect=random,threads=64

rd=rd1,fwd=fwd*,fwdrate=max,format=restart,elapsed=600,interval=1


errors:

09:34:20.958 Message from slave localhost-0:

09:34:20.958 task_wait_all(): Waiting 257 seconds for active threads to complete:

09:34:20.958 FwgThread read /mnt/replicated/vdbench_dir0/sub1 4: 21 threads

09:34:20.958 FwgThread read /mnt/replicated/vdbench_dir1/sub2 4: 20 threads

09:34:20.958 FwgThread read /mnt/replicated/vdbench_dir2/sub3 4: 20 threads

09:34:33.536 SlaveList.waitForSlaveWorkCompletion(): localhost-0

09:34:36.129

09:34:36.129 Message from slave localhost-0:

09:34:36.129 task_wait_all(): Waiting 272 seconds for active threads to complete:

09:34:36.129 FwgThread read /mnt/replicated/vdbench_dir0/sub1 4: 21 threads

09:34:36.129 FwgThread read /mnt/replicated/vdbench_dir1/sub2 4: 20 threads

09:34:36.129 FwgThread read /mnt/replicated/vdbench_dir2/sub3 4: 20 threads

09:34:51.299

09:34:51.299 Message from slave localhost-0:

09:34:51.299 task_wait_all(): Waiting 288 seconds for active threads to complete:

09:34:51.299 FwgThread read /mnt/replicated/vdbench_dir0/sub1 4: 21 threads

09:34:51.299 FwgThread read /mnt/replicated/vdbench_dir1/sub2 4: 20 threads

09:34:51.299 FwgThread read /mnt/replicated/vdbench_dir2/sub3 4: 20 threads

09:35:03.235 *

09:35:03.235 ******************************************************************************

09:35:03.235 * Slave localhost-0 aborting: Shutdown took more than 5 minutes; Run aborted *

09:35:03.235 ******************************************************************************

09:35:03.235 *

09:35:03.580 SlaveList.waitForSlaveWorkCompletion(): localhost-0

09:35:05.583

09:35:05.584 Slave localhost-0 prematurely terminated.

09:35:05.584

09:35:05.584 Slave aborted. Abort message received:

09:35:05.584 Shutdown took more than 5 minutes; Run aborted

09:35:05.584

09:35:05.584 Look at file localhost-0.stdout.html for more information.

09:35:06.090

09:35:06.090 Slave localhost-0 prematurely terminated.

09:35:06.090

java.lang.RuntimeException: Slave localhost-0 prematurely terminated.

    at Vdb.common.failure(common.java:335)

    at Vdb.SlaveStarter.startSlave(SlaveStarter.java:198)

    at Vdb.SlaveStarter.run(SlaveStarter.java:47)