[Samba] Samba write performance in kernel

[Volker Lendecke]

On Thu, Sep 11, 2008 at 04:55:01PM +0800, Lin Mac wrote:
> Hi,
> 
> > > Is there any kernel patch to fix this issue? or any discussion, clues?
> > Not that I know of at the moment. I'm waiting for the Linux
> > kernel to support splice from socket -> file. Code's all
> > there in Samba.
> 
> Does using splice would really do help in performance much? 
> Since the performance improvement might comes from two advantage: 
> 1. no going to user space.
> 2. no memory copy
> splice surely have advantage 1, but doest it have the
> second? Can we avoid  memory copy with splice, while
> writing files to samba? (scatter-gather in block write?)

Just to get things straight: Recently I've seen a Xeon box
ship almost 500 megabytes (!) per second to smbclient using
a single SMB connection via
RAMdisk->smbd->10GigE->smbclient->/dev/null. This was
without sendfile. So unless you want to squeeze the last 5%
out of a heavily loaded server, I'd say the advantages of
sendfile/recvfile are close to negligible. I might be wrong
here, but the network latencies together with non-optimally
queued requests by the client have a MUCH greater influence.

Volker
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: not available
Url : http://lists.samba.org/archive/samba/attachments/20080911/bba3f699/attachment.bin