search for: tx_timeout

Em seg, 7 de out de 2019 ?s 11:15, Julian Wiedmann <jwi at linux.ibm.com> escreveu: > > On 06.10.19 20:45, jcfaracco at gmail.com wrote: > > From: Julio Faracco <jcfaracco at gmail.com> > > > > For debug purpose of TX timeout events, a tx_timeout entry was added to > > monitor this special case: when dev_watchdog identifies a tx_timeout and > > throw an exception. We can both consider this event as an error, but > > driver should report as a tx_timeout statistic. > > > > Hi Julio, > dev_watchdog() updates tx...

From: Julio Faracco <jcfaracco at gmail.com> Driver virtio_net is not handling error events for TX provided by dev_watchdog. This event is reached when transmission queue is having problems to transmit packets. To enable it, driver should have .ndo_tx_timeout implemented. This serie has two commits: In the past, we implemented a function to recover driver state when this kind of event happens, but the structure was to complex for virtio_net that moment. Alternativelly, this skeleton should be enough for now. For further details, see thread: https://lk...

From: Julio Faracco <jcfaracco at gmail.com> Driver virtio_net is not handling error events for TX provided by dev_watchdog. This event is reached when transmission queue is having problems to transmit packets. To enable it, driver should have .ndo_tx_timeout implemented. This serie has two commits: In the past, we implemented a function to recover driver state when this kind of event happens, but the structure was to complex for virtio_net that moment. Alternativelly, this skeleton should be enough for now. For further details, see thread: https://lk...

From: Julio Faracco <jcfaracco at gmail.com> To enable dev_watchdog, virtio_net should have a tx_timeout defined (.ndo_tx_timeout). This is only a skeleton to throw a warn message. It notifies the event in some specific queue of device. This function still counts tx_timeout statistic and consider this event as an error (one error per queue), reporting it. Signed-off-by: Julio Faracco <jcfaracc...

On Sun, Oct 06, 2019 at 03:45:15PM -0300, jcfaracco at gmail.com wrote: > From: Julio Faracco <jcfaracco at gmail.com> > > To enable dev_watchdog, virtio_net should have a tx_timeout defined > (.ndo_tx_timeout). This is only a skeleton to throw a warn message. It > notifies the event in some specific queue of device. This function > still counts tx_timeout statistic and consider this event as an error > (one error per queue), reporting it. > > Signed-off-...

On Sun, Oct 06, 2019 at 03:45:15PM -0300, jcfaracco at gmail.com wrote: > From: Julio Faracco <jcfaracco at gmail.com> > > To enable dev_watchdog, virtio_net should have a tx_timeout defined > (.ndo_tx_timeout). This is only a skeleton to throw a warn message. It > notifies the event in some specific queue of device. This function > still counts tx_timeout statistic and consider this event as an error > (one error per queue), reporting it. > > Signed-off-...

...seg, 7 de out de 2019 ?s 04:51, Michael S. Tsirkin <mst at redhat.com> escreveu: > > On Sun, Oct 06, 2019 at 03:45:15PM -0300, jcfaracco at gmail.com wrote: > > From: Julio Faracco <jcfaracco at gmail.com> > > > > To enable dev_watchdog, virtio_net should have a tx_timeout defined > > (.ndo_tx_timeout). This is only a skeleton to throw a warn message. It > > notifies the event in some specific queue of device. This function > > still counts tx_timeout statistic and consider this event as an error > > (one error per queue), reporting it. > &...

On Tue, Jun 23, 2015 at 10:44:29PM -0300, Julio Faracco wrote: > virtio_net paravirtualized driver does not have a tx_timeout() function to > guarantee that the driver will recover properly after receiving a timeout > during a transmission of a packet. This patch add this feature and throw a > timeout exception after 5 HZ. Considering some tests, this is the best > time to use here. > > Signed-off-by: J...

On Wed, Jun 24, 2015 at 10:31:09PM -0300, Julio Faracco wrote: > 2015-06-24 3:10 GMT-03:00 Michael S. Tsirkin <mst at redhat.com>: > > > > On Tue, Jun 23, 2015 at 10:44:29PM -0300, Julio Faracco wrote: > > > virtio_net paravirtualized driver does not have a tx_timeout() function to > > > guarantee that the driver will recover properly after receiving a timeout > > > during a transmission of a packet. This patch add this feature and throw a > > > timeout exception after 5 HZ. Considering some tests, this is the best > > > time...

On 06/25/2015 09:31 AM, Julio Faracco wrote: > 2015-06-24 3:10 GMT-03:00 Michael S. Tsirkin <mst at redhat.com>: >> On Tue, Jun 23, 2015 at 10:44:29PM -0300, Julio Faracco wrote: >>> virtio_net paravirtualized driver does not have a tx_timeout() function to >>> guarantee that the driver will recover properly after receiving a timeout >>> during a transmission of a packet. This patch add this feature and throw a >>> timeout exception after 5 HZ. Considering some tests, this is the best >>> time to use h...

Driver virtio_net is not handling error events for TX provided by dev_watchdog. This event is reached when transmission queue is having problems to transmit packets. This could happen for any reason. To enable it, driver should have .ndo_tx_timeout implemented. This commit brings back virtnet_reset method to recover TX queues from a error state. That function is called by schedule_work method and it puts the reset function into work queue. As the error cause is unknown at this moment, it would be better to reset all queues. Signed-off-by:...

Driver virtio_net is not handling error events for TX provided by dev_watchdog. This event is reached when transmission queue is having problems to transmit packets. This could happen for any reason. To enable it, driver should have .ndo_tx_timeout implemented. This commit brings back virtnet_reset method to recover TX queues from a error state. That function is called by schedule_work method and it puts the reset function into work queue. As the error cause is unknown at this moment, it would be better to reset all queues. Signed-off-by:...

virtio_net paravirtualized driver does not have a tx_timeout() function to guarantee that the driver will recover properly after receiving a timeout during a transmission of a packet. This patch add this feature and throw a timeout exception after 5 HZ. Considering some tests, this is the best time to use here. Signed-off-by: Julio Faracco <jcfaracco at...

virtio_net paravirtualized driver does not have a tx_timeout() function to guarantee that the driver will recover properly after receiving a timeout during a transmission of a packet. This patch add this feature and throw a timeout exception after 5 HZ. Considering some tests, this is the best time to use here. Signed-off-by: Julio Faracco <jcfaracco at...

...Jun 24, 2015 at 10:31:09PM -0300, Julio Faracco wrote: > > 2015-06-24 3:10 GMT-03:00 Michael S. Tsirkin <mst at redhat.com>: > > > > > > On Tue, Jun 23, 2015 at 10:44:29PM -0300, Julio Faracco wrote: > > > > virtio_net paravirtualized driver does not have a tx_timeout() function > > > > to > > > > guarantee that the driver will recover properly after receiving a > > > > timeout > > > > during a transmission of a packet. This patch add this feature and > > > > throw a > > > > timeout exceptio...

...Jun 24, 2015 at 10:31:09PM -0300, Julio Faracco wrote: > > 2015-06-24 3:10 GMT-03:00 Michael S. Tsirkin <mst at redhat.com>: > > > > > > On Tue, Jun 23, 2015 at 10:44:29PM -0300, Julio Faracco wrote: > > > > virtio_net paravirtualized driver does not have a tx_timeout() function > > > > to > > > > guarantee that the driver will recover properly after receiving a > > > > timeout > > > > during a transmission of a packet. This patch add this feature and > > > > throw a > > > > timeout exceptio...

...2.6.18-7 > > I have a nvidia chipset and I am using the onboard gigabit ethernet > controller. > > From time to time, the networking hangs and gives the output > > Dec 21 19:09:40 xen kernel: NETDEV WATCHDOG: peth0: transmit timed out > Dec 21 19:09:40 xen kernel: peth0: Got tx_timeout. irq: 00000000 > Dec 21 19:09:40 xen kernel: peth0: Ring at 4923c000: next 25635708 > nic 25635452 > Dec 21 19:09:40 xen kernel: peth0: Dumping tx registers > (full output below) > > After rebooting the machine, I get a Kernel Bug: > Dec 21 19:53:18 xen kernel: Kernel BUG at &g...

Driver virtio_net is not handling error events for TX provided by dev_watchdog. This event is reached when transmission queue is having problems to transmit packets. This could happen for any reason. To enable it, driver should have .ndo_tx_timeout implemented. This commit brings back virtnet_reset method to recover TX queues from a error state. That function is called by schedule_work method and it puts the reset function into work queue. As the error cause is unknown at this moment, it would be better to reset all queues, including RX (be...

Driver virtio_net is not handling error events for TX provided by dev_watchdog. This event is reached when transmission queue is having problems to transmit packets. This could happen for any reason. To enable it, driver should have .ndo_tx_timeout implemented. This commit brings back virtnet_reset method to recover TX queues from a error state. That function is called by schedule_work method and it puts the reset function into work queue. As the error cause is unknown at this moment, it would be better to reset all queues. Signed-off-by:...

2015-06-24 3:10 GMT-03:00 Michael S. Tsirkin <mst at redhat.com>: > > On Tue, Jun 23, 2015 at 10:44:29PM -0300, Julio Faracco wrote: > > virtio_net paravirtualized driver does not have a tx_timeout() function to > > guarantee that the driver will recover properly after receiving a timeout > > during a transmission of a packet. This patch add this feature and throw a > > timeout exception after 5 HZ. Considering some tests, this is the best > > time to use here. > &g...