public inbox for linux-scsi@vger.kernel.org
 help / color / mirror / Atom feed
From: "Nicholas A. Bellinger" <nab@linux-iscsi.org>
To: Andy Grover <agrover@redhat.com>, Christoph Hellwig <hch@lst.de>
Cc: target-devel <target-devel@vger.kernel.org>,
	linux-scsi <linux-scsi@vger.kernel.org>,
	Nicholas Bellinger <nab@linux-iscsi.org>
Subject: [PATCH 0/2] target/iscsi: Convert to RX context task mapping+queueing
Date: Fri,  3 Jun 2011 23:01:28 -0700	[thread overview]
Message-ID: <1307167290-24832-1-git-send-email-nab@linux-iscsi.org> (raw)

From: Nicholas Bellinger <nab@linux-iscsi.org>

Hi again Andy and Christoph,

These are two additional patches I am pushing into lio-core-2.6.git/master
for LIO v4.1 to properly enable the RX side direct queueing optimization with
iSCSI READs and non immediate iSCSI WRITE payloads.  Note the logic to enable
this for all cases was not merged originally in Patch #39 from Andy's series.

So for the moment in Patch #1, the optimization has been added as a seperate
new caller: transport_handle_cdb_direct(), and transport_generic_handle_cdb() has
been left as-is for existing fabric code (namely tcm_fc, ib_srpt and ibmvscsis)
that have not tested with these changes so far.

The other changes in Patch #2 are specific to iscsi-target for enabling
transport_handle_cdb_direct() usage.  This involves converting to a sleeping
sess->cmdsn_mutex for protecting the session wide CmdSN list in the path:

	iscsit_sequence_cmd() ->
		iscsit_execute_cmd() ->
			transport_handle_cdb_direct() ->
				transport_generic_new_cmd()

This is required because iscsit_execute_cmd() is being called with the CmdSN
lock held, and spinning here was causing issues during testing as we may
end up sleeping inside of transport_generic_new_cmd() while performing
allocations in transport_new_cmd_obj() -> transport_allocate_tasks().

Please have a look,

Thanks!

--nab

Nicholas Bellinger (2):
  target: Add transport_handle_cdb_direct optimization
  iscsi-target: Convert to cmdsn_mutex and transport_handle_cdb_direct
    usage

 drivers/target/iscsi/iscsi_target_core.h   |    2 +-
 drivers/target/iscsi/iscsi_target_device.c |    4 ++--
 drivers/target/iscsi/iscsi_target_erl1.c   |   18 +++++++++---------
 drivers/target/iscsi/iscsi_target_erl2.c   |    4 ++--
 drivers/target/iscsi/iscsi_target_login.c  |    2 +-
 drivers/target/iscsi/iscsi_target_nego.c   |    4 ++--
 drivers/target/iscsi/iscsi_target_util.c   |    4 ++--
 drivers/target/target_core_transport.c     |   24 ++++++++++++++++++++++++
 include/target/target_core_transport.h     |    1 +
 9 files changed, 44 insertions(+), 19 deletions(-)

-- 
1.7.2.5


             reply	other threads:[~2011-06-04  6:01 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-06-04  6:01 Nicholas A. Bellinger [this message]
2011-06-04  6:01 ` [PATCH 1/2] target: Add transport_handle_cdb_direct optimization Nicholas A. Bellinger
2011-06-04 14:03   ` Christoph Hellwig
2011-06-16 19:13     ` Andy Grover
2011-06-16 19:22       ` Christoph Hellwig
2011-06-16 22:29         ` Andy Grover
2011-06-17 12:01           ` Christoph Hellwig
2011-06-17 14:41             ` Christoph Hellwig
2011-06-04  6:01 ` [PATCH 2/2] iscsi-target: Convert to cmdsn_mutex and transport_handle_cdb_direct usage Nicholas A. Bellinger

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=1307167290-24832-1-git-send-email-nab@linux-iscsi.org \
    --to=nab@linux-iscsi.org \
    --cc=agrover@redhat.com \
    --cc=hch@lst.de \
    --cc=linux-scsi@vger.kernel.org \
    --cc=target-devel@vger.kernel.org \
    /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