NFS Help! Terrible performance with sync, fast performance with async

[Chris Wornell]

>Are you using tcp as transport?

 

I've tried both UDP and TCP and the same results on both.  My
understanding is that if you have only one switch between the devices,
then UDP should be fine as long as there isn't any packet loss.  

 

>From what I can tell, its not so much the transport of data between the
client and server, just the commit time on the server.  I think the
steps are:

 

*         NFS server receives data

*         NFS server requests a commit of the data

*         Data gets handed off to the file system

*         File system writes the data

*         A response is sent back to the NFS server that the commit was
successful

*         NFS server sends a response back to the client that it can
send more data

 

I'm trying to get more detail on this process though and the above is
just an educated guess.  I even increased the amount of nfsd processes
(the daemons) from 8 to the 32 with the exact same results.  Changing
the rsize and wsize didn't do anything either.  From my understanding,
meta-data changes are small so increasing the size of the data chunks
shouldn't really make a difference.  

 

________________________________

From: redhat-sysadmin-list-bounces at redhat.com
[mailto:redhat-sysadmin-list-bounces at redhat.com] On Behalf Of Chris
Wornell
Sent: Sunday, November 19, 2006 1:59 AM
To: redhat-sysadmin-list at redhat.com
Subject: NFS Help! Terrible performance with sync,fast performance with
async

 

I've got a problem that I've spent quite a bit of time on, though I'm
not an expert at NFS. In summary, operations that require meta-data
changes (such as file/directory creations/deletions), perform extremely
slow over sync, but over 10x faster using async.

I have two systems, connected to a GigE switch using intel pro 1000 NICs
(jumbo frames is currently not enabled on any of the points). 

The NFS server is a dual-core opteron system with 1GB of RAM and 3x300
SAS disk RAID-5 on a Perc5/i controller with 256MB battery backed cache
(write cache is enabled). The file system is ext3. I've configured nfsd
to spawn 32 processes upon startup. I'm using defaults for export the
nfs shares, no changes to rsize or wsize.

The NFS client is a dual Xeon with 4GB of RAM and a single 7200rpm SATA
disk. Both systems are running RHEL WS 3 Update 8 and kernel
2.4.21-47.0.1.ELsmp. 

For testing, I'm using bonnie++. The following are some sample test
results that sum up the problem:

Test on NFS server directly (not NFS loopback)
-Sequential File Creation: 2976
-Sequential File Deletion: N/A
-Random File Creation: 3077
-Random File Deletion: 9922

NFS test with sync enabled
-Sequential File Creation: 39
-Sequential File Deletion: 79
-Random File Creation: 39
-Random File Delection: 65

NFS test with async enabled
-Sequential File Creation: 575
-Sequential File Deletion: 1718
-Random File Creation: 543
-Random File Deletion: 1228

Based on the local performance of the NFS server, it does not appear the
IO setup is the culprit. My understanding of the sync operation is a
commit happens which means the NFS server doesn't reply back until the
change has actually been committed to stable storage. There is something
happening behind the scenes though which is causing a huge delay before
the NFS server replies back the commit was complete.

This question is actually work related and I'm planning to put the NFS
server into production, but I'd rather not use async, even with a UPS
and dual PSU's on the server. With the newer nfs-utils, sync is the
default option as well so it seems like sync should perform relatively
well.

Another question is I don't quite understand how the data corruption
happens if a power loss occurs on an NFS server using async. Even with
sync, data transferred over the wire maybe loss if the nfs server gets
shut down before that data is committed. Can anyone go into more detail
on how the data corruption happens?

Thanks a bunch!

 

Thanks,

Chris Wornell
Network Administrator, Information Technology
Peerless Systems Corporation
http://www.peerless.com <http://www.peerless.com/> 
office: 310.727.5723
fax: 310.727.5715
mailto:cwornell at peerless.com <mailto:cwornell at peerless.com>  

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listman.redhat.com/archives/redhat-sysadmin-list/attachments/20061119/c791f3c3/attachment.htm>