netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Maciej Sosnowski <maciej.sosnowski@intel.com>
To: dan.j.williams@intel.com
Cc: snakebyte@gmx.de, shannon.nelson@intel.com,
	jeffrey.t.krisher@intel.com, linux-kernel@vger.kernel.org,
	netdev@vger.kernel.org
Subject: [PATCH 5/7] I/OAT: set tcp_dma_copybreak to 256k for I/OAT ver.3
Date: Thu, 26 Feb 2009 11:05:17 +0100	[thread overview]
Message-ID: <20090226100515.3615.70407.stgit@linux.site> (raw)
In-Reply-To: <20090226100327.3615.21419.stgit@linux.site>

Upcoming server platforms from Intel based on the Nehalem performance
have significantly improved CPU based copy performance.
However, the DMA engine can still be effective at higher I/O sizes
for TCP traffic and at this time copybreak
should be set to 256k for TCP traffic only.

Signed-off-by: Maciej Sosnowski <maciej.sosnowski@intel.com>
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Acked-by: Jeff Kirsher <jeffrey.t.krisher@intel.com>
---

 drivers/dma/ioatdma.h |    4 +++-
 1 files changed, 3 insertions(+), 1 deletions(-)

diff --git a/drivers/dma/ioatdma.h b/drivers/dma/ioatdma.h
index a3306d0..dcf8db5 100644
--- a/drivers/dma/ioatdma.h
+++ b/drivers/dma/ioatdma.h
@@ -135,12 +135,14 @@ static inline void ioat_set_tcp_copy_bre
 	#ifdef CONFIG_NET_DMA
 	switch (dev->version) {
 	case IOAT_VER_1_2:
-	case IOAT_VER_3_0:
 		sysctl_tcp_dma_copybreak = 4096;
 		break;
 	case IOAT_VER_2_0:
 		sysctl_tcp_dma_copybreak = 2048;
 		break;
+	case IOAT_VER_3_0:
+		sysctl_tcp_dma_copybreak = 262144;
+		break;
 	}
 	#endif
 }


  parent reply	other threads:[~2009-02-26 10:14 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-02-26 10:04 [PATCH 0/7] I/OAT update Maciej Sosnowski
2009-02-26 10:04 ` [PATCH 1/7] I/OAT: add verification for proper APICID_TAG_MAP setting by BIOS Maciej Sosnowski
2009-02-26 10:04 ` [PATCH 2/7] I/OAT: do not set DCACTRL_CMPL_WRITE_ENABLE for I/OAT ver.3 Maciej Sosnowski
2009-02-26 10:04 ` [PATCH 3/7] I/OAT: fail initialization on zero channels detection Maciej Sosnowski
2009-02-26 10:05 ` [PATCH 4/7] I/OAT: cancel watchdog before dma remove Maciej Sosnowski
2009-02-26 10:05 ` Maciej Sosnowski [this message]
2009-02-26 10:05 ` [PATCH 6/7] I/OAT: list usage cleanup Maciej Sosnowski
2009-02-26 10:05 ` [PATCH 7/7] I/OAT: update driver version and copyright dates Maciej Sosnowski
2009-02-26 10:31 ` [PATCH 0/7] I/OAT update Jeff Kirsher
2009-02-26 10:48   ` David Miller

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=20090226100515.3615.70407.stgit@linux.site \
    --to=maciej.sosnowski@intel.com \
    --cc=dan.j.williams@intel.com \
    --cc=jeffrey.t.krisher@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=shannon.nelson@intel.com \
    --cc=snakebyte@gmx.de \
    /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;
as well as URLs for NNTP newsgroup(s).