Job hangs on a NFS share with shared workload

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



The following job is executed from two systems on the same NFS share.
>From host-1 the job is readwrite and host-2 the job is only write. I
am trying to simulate writes to the same share from multiple clients.

# cat file_lock_nfs.fio
[global]
readwrite=readwrite
ioengine=libaio
refill_buffers
randrepeat=0
overwrite=0
end_fsync=1
lockfile=readwrite
iodepth=8
direct=1
;runtime=3600
;time_based
create_on_open=1

[shared_nfs_job1]
directory=/schamart
;opendir=/schamart
filename_format=parent.$jobnum.$filenum
numjobs=2
nrfiles=2500
size=100g
filesize=20m
blocksize=512k
openfiles=64
;file_service_type=random
fsync=1024
fsync_on_close=1
;rwmixread=30
norandommap

After writing approx 100G of data with 5000 files, Host-2 with write
exited as expectd, but the host-1 with readwrite workload seems to
hang.

# fio file_lock_nfs.fio
shared_nfs_job1: (g=0): rw=rw, bs=512K-512K/512K-512K/512K-512K,
ioengine=libaio, iodepth=8
...
fio-2.2.11-15-g236d
Starting 2 processes
Jobs: 2 (f=0): [F(2)] [100.0% done] [0KB/0KB/0KB /s] [0/0/0 iops] [eta
00m:00s]0s]

>From strace, i see that is continuously opening and closing files sequentially.

open("/schamart/parent.0.1599", O_RDWR|O_CREAT|O_DIRECT, 0600) = 3
fadvise64(3, 0, 20971520, POSIX_FADV_DONTNEED) = 0
fadvise64(3, 0, 20971520, POSIX_FADV_SEQUENTIAL) = 0
fsync(3)                                = 0
close(3)                                = 0
open("/schamart/parent.0.1600", O_RDWR|O_CREAT|O_DIRECT, 0600) = 3
fadvise64(3, 0, 20971520, POSIX_FADV_DONTNEED) = 0
fadvise64(3, 0, 20971520, POSIX_FADV_SEQUENTIAL) = 0
fsync(3)                                = 0
close(3)                                = 0
open("/schamart/parent.0.1601", O_RDWR|O_CREAT|O_DIRECT, 0600) = 3
fadvise64(3, 0, 20971520, POSIX_FADV_DONTNEED) = 0
fadvise64(3, 0, 20971520, POSIX_FADV_SEQUENTIAL) = 0
fsync(3)                                = 0
close(3)                                = 0
open("/schamart/parent.0.1602", O_RDWR|O_CREAT|O_DIRECT, 0600) = 3
fadvise64(3, 0, 20971520, POSIX_FADV_DONTNEED) = 0
fadvise64(3, 0, 20971520, POSIX_FADV_SEQUENTIAL) = 0
fsync(3)                                = 0
close(3)                                = 0
open("/schamart/parent.0.1603", O_RDWR|O_CREAT|O_DIRECT, 0600) = 3
fadvise64(3, 0, 20971520, POSIX_FADV_DONTNEED) = 0
fadvise64(3, 0, 20971520, POSIX_FADV_SEQUENTIAL) = 0
fsync(3)                                = 0
close(3)                                = 0
open("/schamart/parent.0.1604", O_RDWR|O_CREAT|O_DIRECT, 0600) = 3
fadvise64(3, 0, 20971520, POSIX_FADV_DONTNEED) = 0
fadvise64(3, 0, 20971520, POSIX_FADV_SEQUENTIAL) = 0
fsync(3)                                = 0
close(3)                                = 0
open("/schamart/parent.0.1605", O_RDWR|O_CREAT|O_DIRECT, 0600) = 3
fadvise64(3, 0, 20971520, POSIX_FADV_DONTNEED) = 0
fadvise64(3, 0, 20971520, POSIX_FADV_SEQUENTIAL) = 0
fsync(3)                                = 0
close(3)                                = 0

Is there something wrong, or there is some problem with the job file?

Thanks for your support.

--
Srinivasa R Chamarthy
--
To unsubscribe from this list: send the line "unsubscribe fio" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html




[Index of Archives]     [Linux Kernel]     [Linux SCSI]     [Linux IDE]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux SCSI]

  Powered by Linux