Bug#615860: bnx2 adapter periodically dropping received packets (pause frames)
On 02/28/2011 03:21 PM, Joerg Morbitzer wrote: On 02/28/2011 03:14 PM, Ben Hutchings wrote: On Mon, 2011-02-28 at 14:22 +0100, Joerg Morbitzer wrote: Package: bnx2 Version: 2.6.32-5-amd64 Severity: normal Hi all, on my two Debian 6.0 (Squeeze) servers from HP (ProLiant DL380 G7) I have issues with the on-board Broadcom NetXtreme II BCM5709 Gigabit Ethernet adapters: they constantly drop received network packets, and the Cisco routing swtich 4948 is reporting pause frames coming from the network card during this time. I found the exact same bug report description including an upstream fix by David Miller here : I think that's a different bug. And I don't see any fix by David Miller there. Hi Ben, thanks for your replay. I thought there was an upstream fix due to this answer from Andy Gospodarek (Comment 30 in the Red Hat bug report). https://bugzilla.redhat.com/show_bug.cgi?id=640026 They increased the ring buffer size as far as I understand. [...] They increased the maximum allowed RX descriptor ring size. You should first try changing the value to the current maximum yourself, with ethtool -C. Ok, thanks for the hint with ethtool -G, I will try to increase the RX value from 255 to the maximum of 1020. Just for info: increasing the RX descriptor ring size to 1020 probably fixed this issue, they was no further incident so far. Thanks for the hint, kind regards, Joerg. -- To UNSUBSCRIBE, email to debian-kernel-requ...@lists.debian.org with a subject of unsubscribe. Trouble? Contact listmas...@lists.debian.org Archive: http://lists.debian.org/4d6cd76d.7090...@morbitzer.de
Bug#615860: bnx2 adapter periodically dropping received packets (pause frames)
Package: bnx2 Version: 2.6.32-5-amd64 Severity: normal Hi all, on my two Debian 6.0 (Squeeze) servers from HP (ProLiant DL380 G7) I have issues with the on-board Broadcom NetXtreme II BCM5709 Gigabit Ethernet adapters: they constantly drop received network packets, and the Cisco routing swtich 4948 is reporting pause frames coming from the network card during this time. I found the exact same bug report description including an upstream fix by David Miller here : https://bugzilla.redhat.com/show_bug.cgi?id=640026 They increased the ring buffer size as far as I understand. Please find further details concerning the network card and ethtool settings bekow. Kind regards, Joerg. cut - root@test-name:~# ethtool -a eth1 Pause parameters for eth1: Autonegotiate: on RX: on TX: on root@test-name:~# root@test-name:~# ethtool -c eth1 Coalesce parameters for eth1: Adaptive RX: off TX: off stats-block-usecs: 36 sample-interval: 0 pkt-rate-low: 0 pkt-rate-high: 0 rx-usecs: 18 rx-frames: 12 rx-usecs-irq: 18 rx-frames-irq: 2 tx-usecs: 80 tx-frames: 20 tx-usecs-irq: 18 tx-frames-irq: 2 rx-usecs-low: 0 rx-frame-low: 0 tx-usecs-low: 0 tx-frame-low: 0 rx-usecs-high: 0 rx-frame-high: 0 tx-usecs-high: 0 tx-frame-high: 0 root@test-name:~# lspci -v: -- 03:00.0 Ethernet controller: Broadcom Corporation NetXtreme II BCM5709 Gigabit Ethernet (rev 20) Subsystem: Hewlett-Packard Company NC382i Integrated Quad Port PCI Express Gigabit Server Adapter Flags: bus master, fast devsel, latency 0, IRQ 16 Memory at f400 (64-bit, non-prefetchable) [size=32M] [virtual] Expansion ROM at e410 [disabled] [size=64K] Capabilities: [48] Power Management version 3 Capabilities: [50] Vital Product Data Capabilities: [58] MSI: Enable- Count=1/16 Maskable- 64bit+ Capabilities: [a0] MSI-X: Enable+ Count=9 Masked- Capabilities: [ac] Express Endpoint, MSI 00 Capabilities: [100] Device Serial Number 68-b5-99-ff-fe-6f-e5-f6 Capabilities: [110] Advanced Error Reporting Capabilities: [150] Power Budgeting ? Capabilities: [160] Virtual Channel Kernel driver in use: bnx2 cut - -- To UNSUBSCRIBE, email to debian-kernel-requ...@lists.debian.org with a subject of unsubscribe. Trouble? Contact listmas...@lists.debian.org Archive: http://lists.debian.org/20110228132233.17984.88745.report...@mars.sol-3.de
Processed: Re: Bug#615860: bnx2 adapter periodically dropping received packets (pause frames)
Processing commands for cont...@bugs.debian.org: reassign 615860 linux-2.6 Bug #615860 [bnx2] bnx2 adapter periodically dropping received packets (pause frames) Warning: Unknown package 'bnx2' Bug reassigned from package 'bnx2' to 'linux-2.6'. Bug No longer marked as found in versions 2.6.32-5-amd64. -- Stopping processing here. Please contact me if you need assistance. -- 615860: http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=615860 Debian Bug Tracking System Contact ow...@bugs.debian.org with problems -- To UNSUBSCRIBE, email to debian-kernel-requ...@lists.debian.org with a subject of unsubscribe. Trouble? Contact listmas...@lists.debian.org Archive: http://lists.debian.org/handler.s.c.129890133725343.transcr...@bugs.debian.org
Bug#615860: bnx2 adapter periodically dropping received packets (pause frames)
On Mon, 2011-02-28 at 14:22 +0100, Joerg Morbitzer wrote: Package: bnx2 Version: 2.6.32-5-amd64 Severity: normal Hi all, on my two Debian 6.0 (Squeeze) servers from HP (ProLiant DL380 G7) I have issues with the on-board Broadcom NetXtreme II BCM5709 Gigabit Ethernet adapters: they constantly drop received network packets, and the Cisco routing swtich 4948 is reporting pause frames coming from the network card during this time. I found the exact same bug report description including an upstream fix by David Miller here : I think that's a different bug. And I don't see any fix by David Miller there. https://bugzilla.redhat.com/show_bug.cgi?id=640026 They increased the ring buffer size as far as I understand. [...] They increased the maximum allowed RX descriptor ring size. You should first try changing the value to the current maximum yourself, with ethtool -C. Ben. -- Ben Hutchings Once a job is fouled up, anything done to improve it makes it worse. signature.asc Description: This is a digitally signed message part
Bug#615860: bnx2 adapter periodically dropping received packets (pause frames)
On Mon, 2011-02-28 at 14:14 +, Ben Hutchings wrote: On Mon, 2011-02-28 at 14:22 +0100, Joerg Morbitzer wrote: Package: bnx2 Version: 2.6.32-5-amd64 Severity: normal Hi all, on my two Debian 6.0 (Squeeze) servers from HP (ProLiant DL380 G7) I have issues with the on-board Broadcom NetXtreme II BCM5709 Gigabit Ethernet adapters: they constantly drop received network packets, and the Cisco routing swtich 4948 is reporting pause frames coming from the network card during this time. I found the exact same bug report description including an upstream fix by David Miller here : I think that's a different bug. And I don't see any fix by David Miller there. https://bugzilla.redhat.com/show_bug.cgi?id=640026 They increased the ring buffer size as far as I understand. [...] They increased the maximum allowed RX descriptor ring size. You should first try changing the value to the current maximum yourself, with ethtool -C. Sorry, ethtool -G. Ben. -- Ben Hutchings Once a job is fouled up, anything done to improve it makes it worse. signature.asc Description: This is a digitally signed message part
Bug#615860: bnx2 adapter periodically dropping received packets (pause frames)
On 02/28/2011 03:14 PM, Ben Hutchings wrote: On Mon, 2011-02-28 at 14:22 +0100, Joerg Morbitzer wrote: Package: bnx2 Version: 2.6.32-5-amd64 Severity: normal Hi all, on my two Debian 6.0 (Squeeze) servers from HP (ProLiant DL380 G7) I have issues with the on-board Broadcom NetXtreme II BCM5709 Gigabit Ethernet adapters: they constantly drop received network packets, and the Cisco routing swtich 4948 is reporting pause frames coming from the network card during this time. I found the exact same bug report description including an upstream fix by David Miller here : I think that's a different bug. And I don't see any fix by David Miller there. Hi Ben, thanks for your replay. I thought there was an upstream fix due to this answer from Andy Gospodarek (Comment 30 in the Red Hat bug report). https://bugzilla.redhat.com/show_bug.cgi?id=640026 They increased the ring buffer size as far as I understand. [...] They increased the maximum allowed RX descriptor ring size. You should first try changing the value to the current maximum yourself, with ethtool -C. Ok, thanks for the hint with ethtool -G, I will try to increase the RX value from 255 to the maximum of 1020. Kind regards, Joerg. -- To UNSUBSCRIBE, email to debian-kernel-requ...@lists.debian.org with a subject of unsubscribe. Trouble? Contact listmas...@lists.debian.org Archive: http://lists.debian.org/4d6baf83.9060...@morbitzer.de