diff for duplicates of <1497004478.32667.16.camel@redhat.com> diff --git a/a/1.txt b/N1/1.txt index 87fc953..889ef25 100644 --- a/a/1.txt +++ b/N1/1.txt @@ -49,9 +49,9 @@ On Thu, 2017-06-01 at 19:18 +0000, Duyck, Alexander H wrote: > > > > > > > > > > > > > > Best regards, / S pozdravom, > > > > > > > -> > > > > > > Adri?n Toma?ov +> > > > > > > Adrián Tomašov > > > > > > > Kernel Performance QE -> > > > > > > atomasov at redhat.com +> > > > > > > atomasov@redhat.com > > > > > > > > > > > > I have added the i40e driver maintainer and the intel- > > > > > > wired-lan @@ -107,41 +107,41 @@ On Thu, 2017-06-01 at 19:18 +0000, Duyck, Alexander H wrote: > > > - Alex > > > > There isn't MTU mismatch. Traffic path is : server -> switch -> -> > server.? +> > server. > > > > > > Output from switch: > > -> > ????> show interfaces et-0/0/18???? -> > ????Physical interface: et-0/0/18, Enabled, Physical link is Up -> > ????? Interface index: 644, SNMP ifIndex: 538 -> > ????? Link-level type: Ethernet, MTU: 1514, Speed: 40Gbps, BPDU +> > > show interfaces et-0/0/18 +> > Physical interface: et-0/0/18, Enabled, Physical link is Up +> > Interface index: 644, SNMP ifIndex: 538 +> > Link-level type: Ethernet, MTU: 1514, Speed: 40Gbps, BPDU > > Error: -> > ????None, MAC-REWRITE Error: None, Loopback: Disabled, Source +> > None, MAC-REWRITE Error: None, Loopback: Disabled, Source > > filtering: -> > ????Disabled, Flow control: Disabled, Media type: Fiber -> > ????? Device flags???: Present Running -> > ????? Interface flags: SNMP-Traps Internal: 0x4000 -> > ????? Link flags?????: None -> > ????? CoS queues?????: 12 supported, 12 maximum usable queues -> > ????? Current address: d4:04:ff:90:5a:4b, Hardware address: -> > ????d4:04:ff:90:5a:4b -> > ????? Last flapped???: 2017-06-01 10:09:32 CEST (01:21:29 ago) -> > ????? Input rate?????: 432 bps (0 pps) -> > ????? Output rate????: 8336 bps (11 pps) -> > ????? Active alarms??: None -> > ????? Active defects : None -> > ????? Interface transmit statistics: Disabled +> > Disabled, Flow control: Disabled, Media type: Fiber +> > Device flags : Present Running +> > Interface flags: SNMP-Traps Internal: 0x4000 +> > Link flags : None +> > CoS queues : 12 supported, 12 maximum usable queues +> > Current address: d4:04:ff:90:5a:4b, Hardware address: +> > d4:04:ff:90:5a:4b +> > Last flapped : 2017-06-01 10:09:32 CEST (01:21:29 ago) +> > Input rate : 432 bps (0 pps) +> > Output rate : 8336 bps (11 pps) +> > Active alarms : None +> > Active defects : None +> > Interface transmit statistics: Disabled > > -> > ????? Logical interface et-0/0/18.0 (Index 552) (SNMP ifIndex 539) -> > ????????Flags: SNMP-Traps 0x24024000 Encapsulation: Ethernet-Bridge -> > ????????Input packets : 464041 -> > ????????Output packets: 209210 -> > ????????Protocol eth-switch, MTU: 1514 -> > ??????????Flags: Is-Primary, Trunk-Mode +> > Logical interface et-0/0/18.0 (Index 552) (SNMP ifIndex 539) +> > Flags: SNMP-Traps 0x24024000 Encapsulation: Ethernet-Bridge +> > Input packets : 464041 +> > Output packets: 209210 +> > Protocol eth-switch, MTU: 1514 +> > Flags: Is-Primary, Trunk-Mode > > > > -> > MTU is same for all et-0/0/x interfaces.? +> > MTU is same for all et-0/0/x interfaces. > > > > - Adrian > @@ -171,7 +171,7 @@ On Thu, 2017-06-01 at 19:18 +0000, Duyck, Alexander H wrote: > > - Alex -Hello Alex,? +Hello Alex, I updated firmware in NIC and it didn't make any changes. Current firmware version is "firmware-version: 5.05 0x800028a6 1.1568.0". @@ -179,61 +179,61 @@ firmware version is "firmware-version: 5.05 0x800028a6 1.1568.0". I tried bisect this issue with new firmware and successfully found first bad commit. Log from bisecting is pasted in the end. For testing -of kernel builds I used clear distribution install of ?RHEL7 and turn +of kernel builds I used clear distribution install of RHEL7 and turn of irqbalance. Test run between 2 servers with same HW an SW configuration. NIC was put into different IPv4 subnet to avoid undesirable communication. -testing command :?netperf -L 192.168.0.1 -H 192.168.0.2 -T 0,0 -t +testing command : netperf -L 192.168.0.1 -H 192.168.0.2 -T 0,0 -t TCP_STREAM -l 30 -- -m 4096 -[root at vales1 linux]# git bisect good? +[root@vales1 linux]# git bisect good 47994c119a36e28e1779efabc92d6ab5329a6f75 is the first bad commit commit 47994c119a36e28e1779efabc92d6ab5329a6f75 Author: Jacob Keller <jacob.e.keller@intel.com> -Date:???Wed Apr 19 09:25:57 2017 -0400 +Date: Wed Apr 19 09:25:57 2017 -0400 -????i40e: remove hw_disabled_flags in favor of using separate flag bits -???? -????The hw_disabled_flags field was added as a way of signifying that -????a feature was automatically or temporarily disabled. However, we -????actually only use this for FDir features. Replace its use with new -????_AUTO_DISABLED flags instead. This is more readable, because you + i40e: remove hw_disabled_flags in favor of using separate flag bits + + The hw_disabled_flags field was added as a way of signifying that + a feature was automatically or temporarily disabled. However, we + actually only use this for FDir features. Replace its use with new + _AUTO_DISABLED flags instead. This is more readable, because you aren't -????setting an *_ENABLED flag to *disable* the feature. -???? -????Additionally, clean up a few areas where we used these bits. First, + setting an *_ENABLED flag to *disable* the feature. + + Additionally, clean up a few areas where we used these bits. First, we -????don't really need to set the auto-disable flag for ATR if we're + don't really need to set the auto-disable flag for ATR if we're fully -????disabling the feature via ethtool. -???? -????Second, we should always clear the auto-disable bits in case they + disabling the feature via ethtool. + + Second, we should always clear the auto-disable bits in case they somehow -????got set when the feature was disabled. However, avoid displaying -????a message that we've re-enabled the feature. -???? -????Third, we shouldn't be re-enabling ATR in the SB ntuple add flow, -????because it might have been disabled due to space constraints. + got set when the feature was disabled. However, avoid displaying + a message that we've re-enabled the feature. + + Third, we shouldn't be re-enabling ATR in the SB ntuple add flow, + because it might have been disabled due to space constraints. Instead, -????we should just wait for the fdir_check_and_reenable to be called by + we should just wait for the fdir_check_and_reenable to be called by the -????watchdog. -???? -????Overall, this change allows us to simplify some code by removing an -????extra field we didn't need, and the result should make it more + watchdog. + + Overall, this change allows us to simplify some code by removing an + extra field we didn't need, and the result should make it more clear as -????to what we're actually doing with these flags. -???? -????Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> -????Tested-by: Andrew Bowers <andrewx.bowers@intel.com> -????Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> + to what we're actually doing with these flags. + + Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> + Tested-by: Andrew Bowers <andrewx.bowers@intel.com> + Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> :040000 040000 e2f7724e0e857b902ebfeb7104ac18ecf6b90e36 524e5f2381a64fb152ec00638d738a4f28968455 M drivers -[root at vales1 linux]# git bisect log +[root@vales1 linux]# git bisect log git bisect start # good: [5a7ad1146caa895ad718a534399e38bd2ba721b7] Linux 4.11-rc8 git bisect good 5a7ad1146caa895ad718a534399e38bd2ba721b7 @@ -282,11 +282,11 @@ git bisect good 789f38ca70e0b2848472aaf5f278aa3deabd4a4e # first bad commit: [47994c119a36e28e1779efabc92d6ab5329a6f75] i40e: remove hw_disabled_flags in favor of using separate flag bits -[root at vales1 linux]# ethtool -i ens1f0 +[root@vales1 linux]# ethtool -i ens1f0 driver: i40e version: 2.1.14-k firmware-version: 5.05 0x800028a6 1.1568.0 -expansion-rom-version:? +expansion-rom-version: bus-info: 0000:04:00.0 supports-statistics: yes supports-test: yes @@ -296,4 +296,3 @@ supports-priv-flags: yes - Adrian -? diff --git a/a/content_digest b/N1/content_digest index 910371e..2449aac 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -6,9 +6,16 @@ "ref\01496312080.3758.7.camel@redhat.com\0" "ref\01496344683.27073.306.camel@intel.com\0" "From\0Adrian Tomasov <atomasov@redhat.com>\0" - "Subject\0[Intel-wired-lan] [i40e] regression on TCP stream and TCP maerts, kernel-4.12.0-0.rc2\0" + "Subject\0Re: [Intel-wired-lan] [i40e] regression on TCP stream and TCP maerts, kernel-4.12.0-0.rc2\0" "Date\0Fri, 09 Jun 2017 12:34:38 +0200\0" - "To\0intel-wired-lan@osuosl.org\0" + "To\0Duyck" + Alexander H <alexander.h.duyck@intel.com> + " alexander.duyck@gmail.com <alexander.duyck@gmail.com>\0" + "Cc\0osabart@redhat.com <osabart@redhat.com>" + netdev@vger.kernel.org <netdev@vger.kernel.org> + aokuliar@redhat.com <aokuliar@redhat.com> + intel-wired-lan@lists.osuosl.org <intel-wired-lan@lists.osuosl.org> + " jhladky@redhat.com <jhladky@redhat.com>\0" "\00:1\0" "b\0" "On Thu, 2017-06-01 at 19:18 +0000, Duyck, Alexander H wrote:\n" @@ -62,9 +69,9 @@ "> > > > > > > \n" "> > > > > > > Best regards, / S pozdravom,\n" "> > > > > > > \n" - "> > > > > > > Adri?n Toma?ov\n" + "> > > > > > > Adri\303\241n Toma\305\241ov\n" "> > > > > > > Kernel Performance QE\n" - "> > > > > > > atomasov at redhat.com\n" + "> > > > > > > atomasov@redhat.com\n" "> > > > > > \n" "> > > > > > I have added the i40e driver maintainer and the intel-\n" "> > > > > > wired-lan\n" @@ -120,41 +127,41 @@ "> > > - Alex\n" "> > \n" "> > There isn't MTU mismatch. Traffic path is : server -> switch ->\n" - "> > server.?\n" + "> > server.\302\240\n" "> > \n" "> > \n" "> > Output from switch:\n" "> > \n" - "> > ????> show interfaces et-0/0/18????\n" - "> > ????Physical interface: et-0/0/18, Enabled, Physical link is Up\n" - "> > ????? Interface index: 644, SNMP ifIndex: 538\n" - "> > ????? Link-level type: Ethernet, MTU: 1514, Speed: 40Gbps, BPDU\n" + "> > \302\240\302\240\302\240\302\240> show interfaces et-0/0/18\302\240\302\240\302\240\302\240\n" + "> > \302\240\302\240\302\240\302\240Physical interface: et-0/0/18, Enabled, Physical link is Up\n" + "> > \302\240\302\240\302\240\302\240\302\240 Interface index: 644, SNMP ifIndex: 538\n" + "> > \302\240\302\240\302\240\302\240\302\240 Link-level type: Ethernet, MTU: 1514, Speed: 40Gbps, BPDU\n" "> > Error:\n" - "> > ????None, MAC-REWRITE Error: None, Loopback: Disabled, Source\n" + "> > \302\240\302\240\302\240\302\240None, MAC-REWRITE Error: None, Loopback: Disabled, Source\n" "> > filtering:\n" - "> > ????Disabled, Flow control: Disabled, Media type: Fiber\n" - "> > ????? Device flags???: Present Running\n" - "> > ????? Interface flags: SNMP-Traps Internal: 0x4000\n" - "> > ????? Link flags?????: None\n" - "> > ????? CoS queues?????: 12 supported, 12 maximum usable queues\n" - "> > ????? Current address: d4:04:ff:90:5a:4b, Hardware address:\n" - "> > ????d4:04:ff:90:5a:4b\n" - "> > ????? Last flapped???: 2017-06-01 10:09:32 CEST (01:21:29 ago)\n" - "> > ????? Input rate?????: 432 bps (0 pps)\n" - "> > ????? Output rate????: 8336 bps (11 pps)\n" - "> > ????? Active alarms??: None\n" - "> > ????? Active defects : None\n" - "> > ????? Interface transmit statistics: Disabled\n" + "> > \302\240\302\240\302\240\302\240Disabled, Flow control: Disabled, Media type: Fiber\n" + "> > \302\240\302\240\302\240\302\240\302\240 Device flags\302\240\302\240\302\240: Present Running\n" + "> > \302\240\302\240\302\240\302\240\302\240 Interface flags: SNMP-Traps Internal: 0x4000\n" + "> > \302\240\302\240\302\240\302\240\302\240 Link flags\302\240\302\240\302\240\302\240\302\240: None\n" + "> > \302\240\302\240\302\240\302\240\302\240 CoS queues\302\240\302\240\302\240\302\240\302\240: 12 supported, 12 maximum usable queues\n" + "> > \302\240\302\240\302\240\302\240\302\240 Current address: d4:04:ff:90:5a:4b, Hardware address:\n" + "> > \302\240\302\240\302\240\302\240d4:04:ff:90:5a:4b\n" + "> > \302\240\302\240\302\240\302\240\302\240 Last flapped\302\240\302\240\302\240: 2017-06-01 10:09:32 CEST (01:21:29 ago)\n" + "> > \302\240\302\240\302\240\302\240\302\240 Input rate\302\240\302\240\302\240\302\240\302\240: 432 bps (0 pps)\n" + "> > \302\240\302\240\302\240\302\240\302\240 Output rate\302\240\302\240\302\240\302\240: 8336 bps (11 pps)\n" + "> > \302\240\302\240\302\240\302\240\302\240 Active alarms\302\240\302\240: None\n" + "> > \302\240\302\240\302\240\302\240\302\240 Active defects : None\n" + "> > \302\240\302\240\302\240\302\240\302\240 Interface transmit statistics: Disabled\n" "> > \n" - "> > ????? Logical interface et-0/0/18.0 (Index 552) (SNMP ifIndex 539)\n" - "> > ????????Flags: SNMP-Traps 0x24024000 Encapsulation: Ethernet-Bridge\n" - "> > ????????Input packets : 464041\n" - "> > ????????Output packets: 209210\n" - "> > ????????Protocol eth-switch, MTU: 1514\n" - "> > ??????????Flags: Is-Primary, Trunk-Mode\n" + "> > \302\240\302\240\302\240\302\240\302\240 Logical interface et-0/0/18.0 (Index 552) (SNMP ifIndex 539)\n" + "> > \302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240Flags: SNMP-Traps 0x24024000 Encapsulation: Ethernet-Bridge\n" + "> > \302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240Input packets : 464041\n" + "> > \302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240Output packets: 209210\n" + "> > \302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240Protocol eth-switch, MTU: 1514\n" + "> > \302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240\302\240Flags: Is-Primary, Trunk-Mode\n" "> > \n" "> > \n" - "> > MTU is same for all et-0/0/x interfaces.?\n" + "> > MTU is same for all et-0/0/x interfaces.\302\240\n" "> > \n" "> > - Adrian\n" "> \n" @@ -184,7 +191,7 @@ "> \n" "> - Alex\n" "\n" - "Hello Alex,?\n" + "Hello Alex,\302\240\n" "\n" "I updated firmware in NIC and it didn't make any changes. Current\n" "firmware version is \"firmware-version: 5.05 0x800028a6 1.1568.0\".\n" @@ -192,61 +199,61 @@ "\n" "I tried bisect this issue with new firmware and successfully found\n" "first bad commit. Log from bisecting is pasted in the end. For testing\n" - "of kernel builds I used clear distribution install of ?RHEL7 and turn\n" + "of kernel builds I used clear distribution install of \302\240RHEL7 and turn\n" "of irqbalance. Test run between 2 servers with same HW an SW\n" "configuration. NIC was put into different IPv4 subnet to avoid\n" "undesirable communication.\n" "\n" "\n" - "testing command :?netperf -L 192.168.0.1 -H 192.168.0.2 -T 0,0 -t\n" + "testing command :\302\240netperf -L 192.168.0.1 -H 192.168.0.2 -T 0,0 -t\n" "TCP_STREAM -l 30 -- -m 4096\n" "\n" "\n" - "[root at vales1 linux]# git bisect good?\n" + "[root@vales1 linux]# git bisect good\302\240\n" "47994c119a36e28e1779efabc92d6ab5329a6f75 is the first bad commit\n" "commit 47994c119a36e28e1779efabc92d6ab5329a6f75\n" "Author: Jacob Keller <jacob.e.keller@intel.com>\n" - "Date:???Wed Apr 19 09:25:57 2017 -0400\n" + "Date:\302\240\302\240\302\240Wed Apr 19 09:25:57 2017 -0400\n" "\n" - "????i40e: remove hw_disabled_flags in favor of using separate flag bits\n" - "????\n" - "????The hw_disabled_flags field was added as a way of signifying that\n" - "????a feature was automatically or temporarily disabled. However, we\n" - "????actually only use this for FDir features. Replace its use with new\n" - "????_AUTO_DISABLED flags instead. This is more readable, because you\n" + "\302\240\302\240\302\240\302\240i40e: remove hw_disabled_flags in favor of using separate flag bits\n" + "\302\240\302\240\302\240\302\240\n" + "\302\240\302\240\302\240\302\240The hw_disabled_flags field was added as a way of signifying that\n" + "\302\240\302\240\302\240\302\240a feature was automatically or temporarily disabled. However, we\n" + "\302\240\302\240\302\240\302\240actually only use this for FDir features. Replace its use with new\n" + "\302\240\302\240\302\240\302\240_AUTO_DISABLED flags instead. This is more readable, because you\n" "aren't\n" - "????setting an *_ENABLED flag to *disable* the feature.\n" - "????\n" - "????Additionally, clean up a few areas where we used these bits. First,\n" + "\302\240\302\240\302\240\302\240setting an *_ENABLED flag to *disable* the feature.\n" + "\302\240\302\240\302\240\302\240\n" + "\302\240\302\240\302\240\302\240Additionally, clean up a few areas where we used these bits. First,\n" "we\n" - "????don't really need to set the auto-disable flag for ATR if we're\n" + "\302\240\302\240\302\240\302\240don't really need to set the auto-disable flag for ATR if we're\n" "fully\n" - "????disabling the feature via ethtool.\n" - "????\n" - "????Second, we should always clear the auto-disable bits in case they\n" + "\302\240\302\240\302\240\302\240disabling the feature via ethtool.\n" + "\302\240\302\240\302\240\302\240\n" + "\302\240\302\240\302\240\302\240Second, we should always clear the auto-disable bits in case they\n" "somehow\n" - "????got set when the feature was disabled. However, avoid displaying\n" - "????a message that we've re-enabled the feature.\n" - "????\n" - "????Third, we shouldn't be re-enabling ATR in the SB ntuple add flow,\n" - "????because it might have been disabled due to space constraints.\n" + "\302\240\302\240\302\240\302\240got set when the feature was disabled. However, avoid displaying\n" + "\302\240\302\240\302\240\302\240a message that we've re-enabled the feature.\n" + "\302\240\302\240\302\240\302\240\n" + "\302\240\302\240\302\240\302\240Third, we shouldn't be re-enabling ATR in the SB ntuple add flow,\n" + "\302\240\302\240\302\240\302\240because it might have been disabled due to space constraints.\n" "Instead,\n" - "????we should just wait for the fdir_check_and_reenable to be called by\n" + "\302\240\302\240\302\240\302\240we should just wait for the fdir_check_and_reenable to be called by\n" "the\n" - "????watchdog.\n" - "????\n" - "????Overall, this change allows us to simplify some code by removing an\n" - "????extra field we didn't need, and the result should make it more\n" + "\302\240\302\240\302\240\302\240watchdog.\n" + "\302\240\302\240\302\240\302\240\n" + "\302\240\302\240\302\240\302\240Overall, this change allows us to simplify some code by removing an\n" + "\302\240\302\240\302\240\302\240extra field we didn't need, and the result should make it more\n" "clear as\n" - "????to what we're actually doing with these flags.\n" - "????\n" - "????Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>\n" - "????Tested-by: Andrew Bowers <andrewx.bowers@intel.com>\n" - "????Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>\n" + "\302\240\302\240\302\240\302\240to what we're actually doing with these flags.\n" + "\302\240\302\240\302\240\302\240\n" + "\302\240\302\240\302\240\302\240Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>\n" + "\302\240\302\240\302\240\302\240Tested-by: Andrew Bowers <andrewx.bowers@intel.com>\n" + "\302\240\302\240\302\240\302\240Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>\n" "\n" ":040000 040000 e2f7724e0e857b902ebfeb7104ac18ecf6b90e36\n" "524e5f2381a64fb152ec00638d738a4f28968455 M\tdrivers\n" - "[root at vales1 linux]# git bisect log\n" + "[root@vales1 linux]# git bisect log\n" "git bisect start\n" "# good: [5a7ad1146caa895ad718a534399e38bd2ba721b7] Linux 4.11-rc8\n" "git bisect good 5a7ad1146caa895ad718a534399e38bd2ba721b7\n" @@ -295,11 +302,11 @@ "# first bad commit: [47994c119a36e28e1779efabc92d6ab5329a6f75] i40e:\n" "remove hw_disabled_flags in favor of using separate flag bits\n" "\n" - "[root at vales1 linux]# ethtool -i ens1f0\n" + "[root@vales1 linux]# ethtool -i ens1f0\n" "driver: i40e\n" "version: 2.1.14-k\n" "firmware-version: 5.05 0x800028a6 1.1568.0\n" - "expansion-rom-version:?\n" + "expansion-rom-version:\302\240\n" "bus-info: 0000:04:00.0\n" "supports-statistics: yes\n" "supports-test: yes\n" @@ -308,7 +315,6 @@ "supports-priv-flags: yes\n" "\n" "\n" - "- Adrian\n" - ? + - Adrian -87b71a113a2256db4a13464f9f0207a6aeb6cd1772015aa216a799b030a650b0 +3a4de00e1eaa3006b0804079fa6392e8b3c24525171dc7fa4a52a6cc49e0c9e3
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.