Linux NFS development
 help / color / mirror / Atom feed
From: Greg Banks <gnb@sgi.com>
To: Neil Brown <neilb@suse.de>
Cc: Tom Talpey <Thomas.Talpey@netapp.com>,
	Linux NFS Mailing List <nfs@lists.sourceforge.net>,
	Peter Leckie <pleckie@melbourne.sgi.com>
Subject: Re: [RFC,PATCH 11/15] knfsd: RDMA transport core
Date: Mon, 21 May 2007 20:02:59 +1000	[thread overview]
Message-ID: <20070521100259.GN7482@sgi.com> (raw)
In-Reply-To: <18001.17958.145762.704892@notabene.brown>

On Mon, May 21, 2007 at 05:11:34PM +1000, Neil Brown wrote:
> On Friday May 18, tom@opengridcomputing.com wrote:
> > 
> > This file implements the core transport data management and I/O
> > path. The I/O path for RDMA involves receiving callbacks on interrupt 
> > context. Since all the svc transport locks are _bh locks we enqueue the 
> > transport on a list, schedule a tasklet to dequeue data indications from 
> > the RDMA completion queue. The tasklet in turn takes _bh locks to 
> > enqueue receive data indications on a list for the transport. The 
> > svc_rdma_recvfrom transport function dequeues data from this list in an 
> > NFSD thread context.
> 
> Cannot we simply change the usage of ->sp_lock to always disable
> interrupts?

We could, but the question then is what impact will locking out
interrupts more often have on throughout or latency over Ethernet?

> That would make this much simpler. 

Yes it would.

> How much would it cost?

???

> Alternatively, why can the network layer deliver these notification in
> "bh" context, but the ib layer wants to deliver them in irq context?
> Does doing it in irq context have lower latency or something?

The problem is wider than it appears.  The kernel verbs interface
reports a *lot* of stuff in irq context, not just incoming data.
Many of those events would be best handled by disconnecting the
svc_sock, which implies setting SK_CLOSE and causing svc_sock_enqueue()
to be called.  The former happens; the latter doesn't.  For example,
see qp_event_handler() in net/sunrpc/svc_rdma_transport.c.  This
means that error conditions are not notified until some other event
causes svc_sock_enqueue() to be called.

Greg.
-- 
Greg Banks, R&D Software Engineer, SGI Australian Software Group.
Apparently, I'm Bedevere.  Which MPHG character are you?
I don't speak for SGI.

-------------------------------------------------------------------------
This SF.net email is sponsored by DB2 Express
Download DB2 Express C - the FREE version of DB2 express and take
control of your XML. No limits. Just data. Click to get it now.
http://sourceforge.net/powerbar/db2/
_______________________________________________
NFS maillist  -  NFS@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/nfs

  reply	other threads:[~2007-05-21 10:03 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-05-18 17:45 [RFC,PATCH 11/15] knfsd: RDMA transport core Tom Tucker
2007-05-18 19:07 ` Trond Myklebust
2007-05-18 20:07   ` Tom Tucker
2007-05-18 21:17     ` Trond Myklebust
2007-05-19  4:32       ` Tom Tucker
2007-05-21  7:16     ` Neil Brown
2007-05-21 16:02       ` Tom Tucker
2007-05-22  5:36         ` Neil Brown
2007-05-22 15:23           ` Tom Tucker
2007-05-18 19:24 ` J. Bruce Fields
2007-05-18 19:36   ` Tom Tucker
2007-05-18 19:42     ` J. Bruce Fields
2007-05-23 14:09     ` Greg Banks
2007-05-23 14:43       ` Tom Tucker
2007-05-23 14:55         ` Greg Banks
2007-05-23 15:03           ` Trond Myklebust
2007-05-23 15:12             ` Tom Tucker
2007-05-23 15:37               ` Trond Myklebust
2007-05-23 16:02                 ` Tom Tucker
2007-05-23 16:35                   ` Greg Banks
2007-05-23 16:29             ` Greg Banks
2007-05-23 18:07               ` Trond Myklebust
2007-05-23 18:19               ` Talpey, Thomas
2007-05-23 18:37                 ` Trond Myklebust
2007-05-23 18:59                   ` Talpey, Thomas
2007-05-23 20:01                     ` Trond Myklebust
2007-05-23 21:00                       ` Talpey, Thomas
2007-05-24  8:35                         ` Greg Banks
2007-05-24 13:45                           ` Talpey, Thomas
2007-05-23 15:03           ` Tom Tucker
2007-05-21  7:11 ` Neil Brown
2007-05-21 10:02   ` Greg Banks [this message]
2007-05-21 15:58   ` Tom Tucker

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20070521100259.GN7482@sgi.com \
    --to=gnb@sgi.com \
    --cc=Thomas.Talpey@netapp.com \
    --cc=neilb@suse.de \
    --cc=nfs@lists.sourceforge.net \
    --cc=pleckie@melbourne.sgi.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox