All of lore.kernel.org
 help / color / mirror / Atom feed
diff for duplicates of <552EA2BC.5000707@eu.citrix.com>

diff --git a/a/1.txt b/N1/1.txt
index 42ebfe6..1ab2c21 100644
--- a/a/1.txt
+++ b/N1/1.txt
@@ -90,11 +90,3 @@ tcp_write_xmit. */
 
  /* This limits the percentage of the congestion window which we
   * will allow a single TSO frame to consume.  Building TSO frames
-
--------------- next part --------------
-A non-text attachment was scrubbed...
-Name: tsq-raise-default-static.diff
-Type: text/x-patch
-Size: 1143 bytes
-Desc: not available
-URL: <http://lists.infradead.org/pipermail/linux-arm-kernel/attachments/20150415/06525925/attachment.bin>
diff --git a/N1/2.hdr b/N1/2.hdr
new file mode 100644
index 0000000..ad4980b
--- /dev/null
+++ b/N1/2.hdr
@@ -0,0 +1,3 @@
+Content-Type: text/x-patch; name="tsq-raise-default-static.diff"
+Content-Transfer-Encoding: 7bit
+Content-Disposition: attachment; filename="tsq-raise-default-static.diff"
diff --git a/N1/2.txt b/N1/2.txt
new file mode 100644
index 0000000..ebb52f0
--- /dev/null
+++ b/N1/2.txt
@@ -0,0 +1,28 @@
+TSQ: Raise default static TSQ limit
+    
+A new dynamic TSQ limit was introduced in c/s 605ad7f18 based on the
+size of actual packets and the amount of data being transmitted.
+Raise the default static limit to allow that new limit to actually
+come into effect.
+ 
+This fixes a regression where NICs with large transmit completion
+times (such as xennet) had a 30% hit unless the user manually tweaked
+the value in /proc.
+    
+Signed-off-by: George Dunlap <george.dunlap@eu.citrix.com>
+
+diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
+index 1db253e..8ad7cdf 100644
+--- a/net/ipv4/tcp_output.c
++++ b/net/ipv4/tcp_output.c
+@@ -50,8 +50,8 @@ int sysctl_tcp_retrans_collapse __read_mostly = 1;
+  */
+ int sysctl_tcp_workaround_signed_windows __read_mostly = 0;
+ 
+-/* Default TSQ limit of two TSO segments */
+-int sysctl_tcp_limit_output_bytes __read_mostly = 131072;
++/* Static TSQ limit.  A more dynamic limit is calculated in tcp_write_xmit. */
++int sysctl_tcp_limit_output_bytes __read_mostly = 1048576;
+ 
+ /* This limits the percentage of the congestion window which we
+  * will allow a single TSO frame to consume.  Building TSO frames
diff --git a/a/content_digest b/N1/content_digest
index c751d78..15c6db5 100644
--- a/a/content_digest
+++ b/N1/content_digest
@@ -7,11 +7,24 @@
  "ref\01429115934.7346.107.camel@edumazet-glaptop2.roam.corp.google.com\0"
  "ref\0552E9E8D.1080000@eu.citrix.com\0"
  "ref\01429118948.7346.114.camel@edumazet-glaptop2.roam.corp.google.com\0"
- "From\0george.dunlap@eu.citrix.com (George Dunlap)\0"
- "Subject\0[Xen-devel] \"tcp: refine TSO autosizing\" causes performance regression on Xen\0"
+ "From\0George Dunlap <george.dunlap@eu.citrix.com>\0"
+ "Subject\0Re: [Xen-devel] \"tcp: refine TSO autosizing\" causes performance regression on Xen\0"
  "Date\0Wed, 15 Apr 2015 18:41:16 +0100\0"
- "To\0linux-arm-kernel@lists.infradead.org\0"
- "\00:1\0"
+ "To\0Eric Dumazet <eric.dumazet@gmail.com>\0"
+ "Cc\0Jonathan Davies <Jonathan.Davies@citrix.com>"
+  xen-devel@lists.xensource.com <xen-devel@lists.xensource.com>
+  Wei Liu <wei.liu2@citrix.com>
+  Ian Campbell <Ian.Campbell@citrix.com>
+  Stefano Stabellini <stefano.stabellini@eu.citrix.com>
+  netdev <netdev@vger.kernel.org>
+  Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
+  Eric Dumazet <edumazet@google.com>
+  Paul Durrant <paul.durrant@citrix.com>
+  Christoffer Dall <christoffer.dall@linaro.org>
+  Felipe Franciosi <felipe.franciosi@citrix.com>
+  <linux-arm-kernel@lists.infradead.org>
+ " David Vrabel <david.vrabel@citrix.com>\0"
+ "\01:1\0"
  "b\0"
  "On 04/15/2015 06:29 PM, Eric Dumazet wrote:\n"
  "> On Wed, 2015-04-15 at 18:23 +0100, George Dunlap wrote:\n"
@@ -104,14 +117,37 @@
  "+int sysctl_tcp_limit_output_bytes __read_mostly = 1048576;\n"
  "\n"
  " /* This limits the percentage of the congestion window which we\n"
- "  * will allow a single TSO frame to consume.  Building TSO frames\n"
+   * will allow a single TSO frame to consume.  Building TSO frames
+ "\01:2\0"
+ "fn\0tsq-raise-default-static.diff\0"
+ "b\0"
+ "TSQ: Raise default static TSQ limit\n"
+ "    \n"
+ "A new dynamic TSQ limit was introduced in c/s 605ad7f18 based on the\n"
+ "size of actual packets and the amount of data being transmitted.\n"
+ "Raise the default static limit to allow that new limit to actually\n"
+ "come into effect.\n"
+ " \n"
+ "This fixes a regression where NICs with large transmit completion\n"
+ "times (such as xennet) had a 30% hit unless the user manually tweaked\n"
+ "the value in /proc.\n"
+ "    \n"
+ "Signed-off-by: George Dunlap <george.dunlap@eu.citrix.com>\n"
  "\n"
- "-------------- next part --------------\n"
- "A non-text attachment was scrubbed...\n"
- "Name: tsq-raise-default-static.diff\n"
- "Type: text/x-patch\n"
- "Size: 1143 bytes\n"
- "Desc: not available\n"
- URL: <http://lists.infradead.org/pipermail/linux-arm-kernel/attachments/20150415/06525925/attachment.bin>
+ "diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c\n"
+ "index 1db253e..8ad7cdf 100644\n"
+ "--- a/net/ipv4/tcp_output.c\n"
+ "+++ b/net/ipv4/tcp_output.c\n"
+ "@@ -50,8 +50,8 @@ int sysctl_tcp_retrans_collapse __read_mostly = 1;\n"
+ "  */\n"
+ " int sysctl_tcp_workaround_signed_windows __read_mostly = 0;\n"
+ " \n"
+ "-/* Default TSQ limit of two TSO segments */\n"
+ "-int sysctl_tcp_limit_output_bytes __read_mostly = 131072;\n"
+ "+/* Static TSQ limit.  A more dynamic limit is calculated in tcp_write_xmit. */\n"
+ "+int sysctl_tcp_limit_output_bytes __read_mostly = 1048576;\n"
+ " \n"
+ " /* This limits the percentage of the congestion window which we\n"
+   * will allow a single TSO frame to consume.  Building TSO frames
 
-85dc7564955d9c13499b94bcb3f5b7a84fca74fd57d3190fe055814d4f2bd85c
+5ba4df48722e5a97efa5508e77457517a81bef035bd11f14fc34c1e4fc967301

diff --git a/a/1.txt b/N2/1.txt
index 42ebfe6..1ab2c21 100644
--- a/a/1.txt
+++ b/N2/1.txt
@@ -90,11 +90,3 @@ tcp_write_xmit. */
 
  /* This limits the percentage of the congestion window which we
   * will allow a single TSO frame to consume.  Building TSO frames
-
--------------- next part --------------
-A non-text attachment was scrubbed...
-Name: tsq-raise-default-static.diff
-Type: text/x-patch
-Size: 1143 bytes
-Desc: not available
-URL: <http://lists.infradead.org/pipermail/linux-arm-kernel/attachments/20150415/06525925/attachment.bin>
diff --git a/N2/2.hdr b/N2/2.hdr
new file mode 100644
index 0000000..ad4980b
--- /dev/null
+++ b/N2/2.hdr
@@ -0,0 +1,3 @@
+Content-Type: text/x-patch; name="tsq-raise-default-static.diff"
+Content-Transfer-Encoding: 7bit
+Content-Disposition: attachment; filename="tsq-raise-default-static.diff"
diff --git a/N2/2.txt b/N2/2.txt
new file mode 100644
index 0000000..ebb52f0
--- /dev/null
+++ b/N2/2.txt
@@ -0,0 +1,28 @@
+TSQ: Raise default static TSQ limit
+    
+A new dynamic TSQ limit was introduced in c/s 605ad7f18 based on the
+size of actual packets and the amount of data being transmitted.
+Raise the default static limit to allow that new limit to actually
+come into effect.
+ 
+This fixes a regression where NICs with large transmit completion
+times (such as xennet) had a 30% hit unless the user manually tweaked
+the value in /proc.
+    
+Signed-off-by: George Dunlap <george.dunlap@eu.citrix.com>
+
+diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
+index 1db253e..8ad7cdf 100644
+--- a/net/ipv4/tcp_output.c
++++ b/net/ipv4/tcp_output.c
+@@ -50,8 +50,8 @@ int sysctl_tcp_retrans_collapse __read_mostly = 1;
+  */
+ int sysctl_tcp_workaround_signed_windows __read_mostly = 0;
+ 
+-/* Default TSQ limit of two TSO segments */
+-int sysctl_tcp_limit_output_bytes __read_mostly = 131072;
++/* Static TSQ limit.  A more dynamic limit is calculated in tcp_write_xmit. */
++int sysctl_tcp_limit_output_bytes __read_mostly = 1048576;
+ 
+ /* This limits the percentage of the congestion window which we
+  * will allow a single TSO frame to consume.  Building TSO frames
diff --git a/a/content_digest b/N2/content_digest
index c751d78..36a278c 100644
--- a/a/content_digest
+++ b/N2/content_digest
@@ -7,11 +7,24 @@
  "ref\01429115934.7346.107.camel@edumazet-glaptop2.roam.corp.google.com\0"
  "ref\0552E9E8D.1080000@eu.citrix.com\0"
  "ref\01429118948.7346.114.camel@edumazet-glaptop2.roam.corp.google.com\0"
- "From\0george.dunlap@eu.citrix.com (George Dunlap)\0"
- "Subject\0[Xen-devel] \"tcp: refine TSO autosizing\" causes performance regression on Xen\0"
+ "From\0George Dunlap <george.dunlap@eu.citrix.com>\0"
+ "Subject\0Re: [Xen-devel] \"tcp: refine TSO autosizing\" causes performance regression on Xen\0"
  "Date\0Wed, 15 Apr 2015 18:41:16 +0100\0"
- "To\0linux-arm-kernel@lists.infradead.org\0"
- "\00:1\0"
+ "To\0Eric Dumazet <eric.dumazet@gmail.com>\0"
+ "Cc\0Jonathan Davies <Jonathan.Davies@citrix.com>"
+  xen-devel@lists.xensource.com <xen-devel@lists.xensource.com>
+  Wei Liu <wei.liu2@citrix.com>
+  Ian Campbell <Ian.Campbell@citrix.com>
+  Stefano Stabellini <stefano.stabellini@eu.citrix.com>
+  netdev <netdev@vger.kernel.org>
+  Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
+  Eric Dumazet <edumazet@google.com>
+  Paul Durrant <paul.durrant@citrix.com>
+  Christoffer Dall <christoffer.dall@linaro.org>
+  Felipe Franciosi <felipe.franciosi@citrix.com>
+  linux-arm-kernel@lists.infradead.org
+ " David Vrabel <david.vrabel@citrix.com>\0"
+ "\01:1\0"
  "b\0"
  "On 04/15/2015 06:29 PM, Eric Dumazet wrote:\n"
  "> On Wed, 2015-04-15 at 18:23 +0100, George Dunlap wrote:\n"
@@ -104,14 +117,37 @@
  "+int sysctl_tcp_limit_output_bytes __read_mostly = 1048576;\n"
  "\n"
  " /* This limits the percentage of the congestion window which we\n"
- "  * will allow a single TSO frame to consume.  Building TSO frames\n"
+   * will allow a single TSO frame to consume.  Building TSO frames
+ "\01:2\0"
+ "fn\0tsq-raise-default-static.diff\0"
+ "b\0"
+ "TSQ: Raise default static TSQ limit\n"
+ "    \n"
+ "A new dynamic TSQ limit was introduced in c/s 605ad7f18 based on the\n"
+ "size of actual packets and the amount of data being transmitted.\n"
+ "Raise the default static limit to allow that new limit to actually\n"
+ "come into effect.\n"
+ " \n"
+ "This fixes a regression where NICs with large transmit completion\n"
+ "times (such as xennet) had a 30% hit unless the user manually tweaked\n"
+ "the value in /proc.\n"
+ "    \n"
+ "Signed-off-by: George Dunlap <george.dunlap@eu.citrix.com>\n"
  "\n"
- "-------------- next part --------------\n"
- "A non-text attachment was scrubbed...\n"
- "Name: tsq-raise-default-static.diff\n"
- "Type: text/x-patch\n"
- "Size: 1143 bytes\n"
- "Desc: not available\n"
- URL: <http://lists.infradead.org/pipermail/linux-arm-kernel/attachments/20150415/06525925/attachment.bin>
+ "diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c\n"
+ "index 1db253e..8ad7cdf 100644\n"
+ "--- a/net/ipv4/tcp_output.c\n"
+ "+++ b/net/ipv4/tcp_output.c\n"
+ "@@ -50,8 +50,8 @@ int sysctl_tcp_retrans_collapse __read_mostly = 1;\n"
+ "  */\n"
+ " int sysctl_tcp_workaround_signed_windows __read_mostly = 0;\n"
+ " \n"
+ "-/* Default TSQ limit of two TSO segments */\n"
+ "-int sysctl_tcp_limit_output_bytes __read_mostly = 131072;\n"
+ "+/* Static TSQ limit.  A more dynamic limit is calculated in tcp_write_xmit. */\n"
+ "+int sysctl_tcp_limit_output_bytes __read_mostly = 1048576;\n"
+ " \n"
+ " /* This limits the percentage of the congestion window which we\n"
+   * will allow a single TSO frame to consume.  Building TSO frames
 
-85dc7564955d9c13499b94bcb3f5b7a84fca74fd57d3190fe055814d4f2bd85c
+8aa498758a6f2915bce799527515986e33957c068127ea0e2c042869c3177b6c

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.