On 29/01/18 09:05, Ed Greshko wrote:
On 01/29/18 15:47, Terry Barnaby wrote:
On 19/01/18 15:11, Terry Barnaby wrote:
When doing a tar -xzf ... of a big source tar on an NFSv4 file system the time
taken is huge. I am seeing an overall data rate of about 1 MByte per second across
the network interface.
If I copy a single large file I see a network data rate of about 110 MBytes/sec
which is about the limit of the Gigabit Ethernet interface I am using.
Now, in the past I have used the NFS "async" mount option to help with write speed
(lots of small files in the case of an untar of a set of source files).
However, this does not seem to speed this up in Fedora27 and also I don't see the
"async" option listed when I run the "mount" command. When I use the "sync" option
it does show up in the "mount" list.
The question is, is the "async" option actually working with the NFS v4 in Fedora27 ?
_______________________________________________
users mailing list -- users@xxxxxxxxxxxxxxxxxxxxxxx
To unsubscribe send an email to users-leave@xxxxxxxxxxxxxxxxxxxxxxx
Anyone using NFS these days ?
Yes, but only as a client at the moment.
Server is a Fedora27 as well. vers=4.2 the default. Same issue at other sites with
Fedora27.
Server export: "/data *.kingnet(rw,async,fsid=17)"
Client fstab: "king.kingnet:/data /data nfs async,nocto 0 0"
Client mount: "king.kingnet:/data on /data type nfs4
(rw,relatime,vers=4.2,rsize=1048576,wsize=1048576,namlen=255,hard,nocto,proto=tcp,timeo=600,retrans=2,sec=sys,clientaddr=192.168.202.2,local_lock=none,addr=192.168.202.1)"
If I have time (my) tomorrow I'll have a look at testing it. But, could you define
what you mean by "big source tar" and "single large file"?
In particular the "tar" procedure. I'm not sure if you have an nfs mounted file
system and you are creating a tar from data on that file system, which would need to
be read and then compressed locally and written back to the nfs mounted file system.
So, I just want to get the data flow to match.
And what is the size of the single large file and are you doing a copy from a local
file system to the nfs partition?
Thanks for the reply.
As a simple test I am using a Linux kernel tar archive such as:
https://www.kernel.org/pub/linux/kernel/v4.x/linux-4.14.15.tar.gz
Untaring this "tar -xf linux-4.14.15.tar.gz" while in an NFS mounted
directory across a Gigabit LAN takes about 3 minutes. Ksysguard reports
an overall network rate of about 2.4 MBytes per second.
The single large "file" I have been using is 1 GByte. This is created in
the NFS directory with a simple 'C' test program that opens the file and
writes 1GByte to it followed by an fsync() timing the procedure.
Ksysguard reports an overall network rate of about 110 MBytes per second
during this.
Now I understand that NFS's latency with writes is a performance
bottleneck, but in the past I have used the "async" mount option to good
effect to minimise this. It does not appear to have any effect on my
systems. The "async" mount option is not listed when you run "mount" to
get a list of the mounts on the client.
_______________________________________________
users mailing list -- users@xxxxxxxxxxxxxxxxxxxxxxx
To unsubscribe send an email to users-leave@xxxxxxxxxxxxxxxxxxxxxxx
