I have a custom kernel with most Xen features enabled. I get a good amount of these in my logs:

May 15 07:06:55 server kernel: [3614188.528061] xennet: skb rides the rocket: 22 slots
May 15 07:17:58 server kernel: [3614851.381129] xennet: skb rides the rocket: 20 slots
May 15 07:35:45 server kernel: [3615917.707348] xennet: skb rides the rocket: 19 slots
May 15 07:39:13 server kernel: [3616126.353221] xennet: skb rides the rocket: 20 slots
May 15 07:39:52 server kernel: [3616164.994578] xennet: skb rides the rocket: 20 slots
May 15 07:40:34 server kernel: [3616207.404462] xennet: skb rides the rocket: 19 slots
May 15 07:45:56 server kernel: [3616528.893985] xennet: skb rides the rocket: 19 slots
May 15 07:46:22 server kernel: [3616554.969467] xennet: skb rides the rocket: 22 slots
May 15 07:46:22 server kernel: [3616555.065629] xennet: skb rides the rocket: 20 slots
May 15 07:46:37 server kernel: [3616569.867038] xennet: skb rides the rocket: 20 slots
May 15 07:46:37 server kernel: [3616570.199862] xennet: skb rides the rocket: 26 slots
May 15 07:53:41 server kernel: [3616994.095117] xennet: skb rides the rocket: 20 slots

# uname -a
Linux server 3.7.10-gentoo-r1 #1 SMP Fri May 3 11:25:14 EDT 2013 x86_64 Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz GenuineIntel GNU/Linux
# zcat /proc/config.gz | grep XEN
CONFIG_XEN=y
CONFIG_XEN_DOM0=y
CONFIG_XEN_PRIVILEGED_GUEST=y
CONFIG_XEN_PVHVM=y
CONFIG_XEN_MAX_DOMAIN_MEMORY=500
CONFIG_XEN_SAVE_RESTORE=y
CONFIG_XEN_DEBUG_FS=y
CONFIG_PCI_XEN=y
CONFIG_XEN_PCIDEV_FRONTEND=y
CONFIG_XEN_BLKDEV_FRONTEND=y
CONFIG_XEN_BLKDEV_BACKEND=y
# CONFIG_NETXEN_NIC is not set
CONFIG_XEN_NETDEV_FRONTEND=y
CONFIG_XEN_NETDEV_BACKEND=y
CONFIG_INPUT_XEN_KBDDEV_FRONTEND=y
CONFIG_HVC_XEN=y
CONFIG_HVC_XEN_FRONTEND=y
# CONFIG_XEN_WDT is not set
CONFIG_XEN_FBDEV_FRONTEND=y
# Xen driver support
CONFIG_XEN_BALLOON=y
CONFIG_XEN_SCRUB_PAGES=y
CONFIG_XEN_DEV_EVTCHN=y
CONFIG_XEN_BACKEND=y
CONFIG_XENFS=y
CONFIG_XEN_COMPAT_XENFS=y
CONFIG_XEN_SYS_HYPERVISOR=y
CONFIG_XEN_XENBUS_FRONTEND=y
CONFIG_XEN_GNTDEV=y
CONFIG_XEN_GRANT_DEV_ALLOC=y
CONFIG_SWIOTLB_XEN=y
CONFIG_XEN_PCIDEV_BACKEND=y
CONFIG_XEN_PRIVCMD=y
CONFIG_XEN_ACPI_PROCESSOR=y
CONFIG_XEN_MCE_LOG=y

I've done some googling about "xennet: skb rides the rocket" and it seems to be related to some internal Xen networking stuff, maybe too many packets than the kernel can handle? (In particular this thread: http://lists.xen.org/archives/html/xen- ... 00198.html )

Has anyone else encountered this or know anything about it?

I receive this message as well. Haven't really found a fix for it though. The little that's been posted about it was mostly developer talk. Have you learned anything about it?

No. I suspect it's related to an active server I have but I have no evidence. I don't really have time to debug it, but I will update this thread if I learn more (likely not for a few months.)

I recently formatted and rebuilt the machine so at the moment I'm only running SSH and a very lightly loaded lighttpd daemon. It may just be another undocumented Linode quirk like having to disable barriers on some of their olders virtual machines. Not that I would expect them to tell us if it actually was...

I have seen it, and I would assume a lot of other have seen it as well. It happens with the Linode provided kernels as well if you have a lot of traffic so I don't think your custom kernel is at fault.

It doesn't appear to cause any disasters, though, so I haven't really much investigation.

I've experienced dropped connections due to the packet loss. Mostly while I'm using SOCKS5 through SSH. Pretty easy to reproduce (for me) by watching a YouTube video over SOCKS5. Not even consuming that much bandwidth either. It just drops it occasionally. Nothing that a refresh doesn't fix, but annoying none the less.