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 [email protected] with a subject of "unsubscribe". Trouble? Contact [email protected]
