similar to: Re: kernel panic in skb_copy_bits

On Fri, 2013-06-28 at 12:17 +0800, Joe Jin wrote: > Find a similar issue http://www.gossamer-threads.com/lists/xen/devel/265611 > So copied to Xen developer as well. > > On 06/27/13 13:31, Eric Dumazet wrote: > > On Thu, 2013-06-27 at 10:58 +0800, Joe Jin wrote: > >> Hi, > >> > >> When we do fail over test with iscsi + multipath by reset the switches

skb_copy_bits() can return an err, so have netif_be_start_xmit() crash informatively.. thanks, Nivedita _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel

On Tue, Aug 08, 2023 at 01:20:36PM +0200, Przemek Kitszel wrote: > On 7/31/23 09:17, Joel Granados wrote: > > Move from register_net_sysctl to register_net_sysctl_sz for all the > > networking related files. Do this while making sure to mirror the NULL > > assignments with a table_size of zero for the unprivileged users. > > ... > > const char *dev_name_source;

Hello! I like to announce sch_ooo, a new queue discipline that, attached to a class (or a device, as root) reorder the packets that pass by delaying some. Example: tc qdisc add dev eth0 root ooo limit 100 gap 4 wait 1100 This queue will create a pfifo with limit 100 and will delay every 4th packet with 1100ms. An stream of 6 packets like this: 1 2 3 4 5 6, generated by ping will be reordered

This error is not 100% reproducible. However, kernel panic has been occurred many times for last two months. It usually happens when multi VMs (in our case, 14 VMs) are booting together. After we made three big changes to gain more availibility, it began to happen. Changes are : 1. Use *NAS* as vm storage for migration from local disk 2. Use *two bondings* for switch HA (with 4 nics) from

We can only process 1 packet at one time during sendmsg(). This often lead bad cache utilization under heavy load. So this patch tries to do some batching during rx before submitting them to host network stack. This is done through accepting MSG_MORE as a hint from sendmsg() caller, if it was set, batch the packet temporarily in a linked list and submit them all once MSG_MORE were cleared. Tests

We can only process 1 packet at one time during sendmsg(). This often lead bad cache utilization under heavy load. So this patch tries to do some batching during rx before submitting them to host network stack. This is done through accepting MSG_MORE as a hint from sendmsg() caller, if it was set, batch the packet temporarily in a linked list and submit them all once MSG_MORE were cleared. Tests

There is a need for communication channel between host and various agents that are running inside a VM guest. The channel will be used for statistic gathering, logging, cut & paste, host screen resolution changes notifications, guest configuration etc. It is undesirable to use TCP/IP for this purpose since network connectivity may not exist between host and guest and if it exists the traffic

There is a need for communication channel between host and various agents that are running inside a VM guest. The channel will be used for statistic gathering, logging, cut & paste, host screen resolution changes notifications, guest configuration etc. It is undesirable to use TCP/IP for this purpose since network connectivity may not exist between host and guest and if it exists the traffic

We can only process 1 packet at one time during sendmsg(). This often lead bad cache utilization under heavy load. So this patch tries to do some batching during rx before submitting them to host network stack. This is done through accepting MSG_MORE as a hint from sendmsg() caller, if it was set, batch the packet temporarily in a linked list and submit them all once MSG_MORE were cleared. Tests

We can only process 1 packet at one time during sendmsg(). This often lead bad cache utilization under heavy load. So this patch tries to do some batching during rx before submitting them to host network stack. This is done through accepting MSG_MORE as a hint from sendmsg() caller, if it was set, batch the packet temporarily in a linked list and submit them all once MSG_MORE were cleared. Tests

On Fri, Jan 06, 2017 at 10:13:17AM +0800, Jason Wang wrote: > We can only process 1 packet at one time during sendmsg(). This often > lead bad cache utilization under heavy load. So this patch tries to do > some batching during rx before submitting them to host network > stack. This is done through accepting MSG_MORE as a hint from > sendmsg() caller, if it was set, batch the packet

On Fri, Jan 06, 2017 at 10:13:17AM +0800, Jason Wang wrote: > We can only process 1 packet at one time during sendmsg(). This often > lead bad cache utilization under heavy load. So this patch tries to do > some batching during rx before submitting them to host network > stack. This is done through accepting MSG_MORE as a hint from > sendmsg() caller, if it was set, batch the packet

We used to queue tx packets in sk_receive_queue, this is less efficient since it requires spinlocks to synchronize between producer and consumer. This patch tries to address this by: - switch from sk_receive_queue to a skb_array, and resize it when tx_queue_len was changed. - introduce a new proto_ops peek_len which was used for peeking the skb length. - implement a tun version of peek_len

On Wed, Jun 15, 2016 at 04:38:17PM +0800, Jason Wang wrote: > We used to queue tx packets in sk_receive_queue, this is less > efficient since it requires spinlocks to synchronize between producer > and consumer. > > This patch tries to address this by: > > - introduce a new mode which will be only enabled with IFF_TX_ARRAY > set and switch from sk_receive_queue to a

Hi all, I am trying to compile openswitch's kernel module in a CentOS 6.4 host, but fails in rpm-check: Requires: kernel(__alloc_percpu) = 0x55f2580b kernel(__alloc_skb) = 0x25421969 kernel(__dev_get_by_index) = 0x6a6d551b kernel(__init_waitqueue_head) = 0xffc7c184 kernel(__ip_select_ident) = 0x848695b3 kernel(__kmalloc) = 0x5a34a45c kernel(__list_add) = 0x0343a1a8 kernel(__nla_put) =

We used to queue tx packets in sk_receive_queue, this is less efficient since it requires spinlocks to synchronize between producer and consumer. This patch tries to address this by: - introduce a new mode which will be only enabled with IFF_TX_ARRAY set and switch from sk_receive_queue to a fixed size of skb array with 256 entries in this mode. - introduce a new proto_ops peek_len which was

We used to queue tx packets in sk_receive_queue, this is less efficient since it requires spinlocks to synchronize between producer and consumer. This patch tries to address this by: - introduce a new mode which will be only enabled with IFF_TX_ARRAY set and switch from sk_receive_queue to a fixed size of skb array with 256 entries in this mode. - introduce a new proto_ops peek_len which was

This patch updates the network emulation packet scheduler. * name changed from delay to netem since it does more than just delay * Catalin''s merged code to do packet reordering * uses a socket queue''s directly rather than layering on qdisc(fifo) because this is used in performance tests. * adds placeholder in API for future enhancements (rate and duplicate).

From: Sjur Br?ndeland <sjur.brandeland at stericsson.com> This driver depends on Rusty's new host virtio ring implementation, so this patch-set is based on the vringh branch in Rusty's git. Changes since V1: - Use the new iov helper functions, and simplify iov handling. However this triggers compile warnings, as it takes struct iov while kernel api uses struct kiov - Introduced