Your message dated Mon, 17 Dec 2012 22:18:07 +0000
with message-id <[email protected]>
and subject line Bug#696063: fixed in qemu-kvm 1.1.2+dfsg-3
has caused the Debian Bug report #696063,
regarding possible network stalls/slowness in e1000 device emulation
to be marked as done.
This means that you claim that the problem has been dealt with.
If this is not the case it is now your responsibility to reopen the
Bug report if necessary, and/or fix the problem forthwith.
(NB: If you are a system administrator and have no idea what this
message is talking about, this may indicate a serious mail system
misconfiguration somewhere. Please contact [email protected]
immediately.)
--
696063: http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=696063
Debian Bug Tracking System
Contact [email protected] with problems
--- Begin Message ---
Package: qemu-kvm
Version: 1.1.2+dfsg-2
Severity: normal
Tags: upstream
>From upstream qemu commit series intro message
(http://lists.gnu.org/archive/html/qemu-devel/2012-08/msg01594.html):
----
When the guests replenish the receive ring buffer, the network device
should flush its queue of pending packets. This is done with
qemu_flush_queued_packets, and patches 2+3 add the missing call to
two drivers, e1000 and xen. More may come later---no time to test
them now.
However, the device should not just retry delivery of packets that were
already read from the tap device, it should also try to read more packets
from the tap device. The latter requires a qemu_notify_event to force
recomputation of the fd_sets. virtio already does this, but it is a
layering violation; patch 1 moves the call from virtio to the network
subsystem, so that e1000 and xen will then get it for free.
Paolo Bonzini (3):
net: notify iothread after flushing queue
e1000: flush queue whenever can_receive can go from false to true
xen: flush queue when getting an event
----
This means, among other things, that it is possible for e1000 to stall
under normal load, provided there's no other activity "around" the guest --
like (virtual) disk access, timers and so on - actions which causes
internal qemu FD# watchers to re-initialize. In usual conditions, when
the guest uses disk or has timers, the impact can be very low. But for
certain workload, like (virtual) diskless router, this might be more
problematic.
There are 2 patches needed from upstream to fix this:
987a9b4800003567b1a47a379255e886a77d57ea
net: notify iothread after flushing queue
e8b4c680b41bd960ecccd9ff076b7b058e0afcd4
e1000: flush queue whenever can_receive can go from false to true
(and also a98b140223d3a627eab7ee3ddec645bab630d756 for xen).
--- End Message ---
--- Begin Message ---
Source: qemu-kvm
Source-Version: 1.1.2+dfsg-3
We believe that the bug you reported is fixed in the latest version of
qemu-kvm, which is due to be installed in the Debian FTP archive.
A summary of the changes between this version and the previous one is
attached.
Thank you for reporting the bug, which will now be closed. If you
have further comments please address them to [email protected],
and the maintainer will reopen the bug report if appropriate.
Debian distribution maintenance software
pp.
Michael Tokarev <[email protected]> (supplier of updated qemu-kvm package)
(This message was generated automatically at their request; if you
believe that there is a problem with it please contact the archive
administrators by mailing [email protected])
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
Format: 1.8
Date: Sun, 16 Dec 2012 23:08:40 +0400
Source: qemu-kvm
Binary: qemu-kvm qemu-kvm-dbg kvm
Architecture: source i386
Version: 1.1.2+dfsg-3
Distribution: unstable
Urgency: low
Maintainer: Michael Tokarev <[email protected]>
Changed-By: Michael Tokarev <[email protected]>
Description:
kvm - dummy transitional package from kvm to qemu-kvm
qemu-kvm - Full virtualization on x86 hardware
qemu-kvm-dbg - Debugging info for qemu-kvm
Closes: 686776 688964 691343 691569 695905 696050 696051 696052 696057 696061
696063
Changes:
qemu-kvm (1.1.2+dfsg-3) unstable; urgency=low
.
*
intel_hda-do-not-call-msi_reset-when-only-device-state-needs-resetting.patch
patch to fix Fixing reset of MSI function in intel-hda virtual device.
The fix (applied to stable-1.1.1) was partially wrong, as it actually
added the msi_reset() call to two code paths instead of one as planned.
Fix this by splitting the function in question into two parts.
(Closes: #688964)
* blockdev-preserve-readonly-and-snapshot-states-across-media-changes.patch:
allow opening of read-only cdrom images/devices (Closes: #686776)
* ahci-properly-reset-PxCMD-on-HBA-reset.patch: fix windows install on ahci
(Closes: #696052)
* e1000-discard-packets-that-are-too-long-if-not-SBP-and-not-LPE.patch:
discard too long rx packets which may overflow guest buffer
(Closes: #696051)
* eepro100-fix-network-hang-when-rx-buffers-run-out.patch:
fix e100 stall (Closes: #696061)
* fix possible network stalls/slowness in e1000 device emulation:
net-notify-iothread-after-flushing-queue.patch
e1000-flush-queue-whenever-can_receive-can-go-from-false-to-true.patch
(Closes: #696063)
* fixes-related-to-processing-of-qemu-s-numa-option.patch:
fixes numa handling (Closes: #691343)
* qcow2-fix-avail_sectors-in-cluster-allocation-code.patch:
fixes data corruption in stacked qcow2 (Closes: #695905)
* qcow2-fix-refcount-table-size-calculation.patch: another possible
corruption or crash in qcow2 (Closes: #691569)
* tap-reset-vnet-header-size-on-open.patch: always ensure tap device is
in known state initially (Closes: #696057)
* vmdk-fix-data-corruption-bug-in-WRITE-and-READ-handling.patch:
possible data corruption bug in vmdk image format (Closes: #696050)
Checksums-Sha1:
4288d03e5dbbce17b98325e1c3c5dbf2b91309e0 1949 qemu-kvm_1.1.2+dfsg-3.dsc
ec4bd6412a1c999b582f37159837c6ebe81d29fb 48542
qemu-kvm_1.1.2+dfsg-3.debian.tar.gz
6b2660777bf3c5fa177955cb1ebd7d87a8a1913e 1756288 qemu-kvm_1.1.2+dfsg-3_i386.deb
84f8fda1d470ee3e17f1371aab59d29cbcfe7771 5098654
qemu-kvm-dbg_1.1.2+dfsg-3_i386.deb
b27aceda82c8543ee3218010c310dd9af7bebf6c 22976 kvm_1.1.2+dfsg-3_i386.deb
Checksums-Sha256:
f3b9978abda70ad11fb94eab91315ae3da8104f85540bb0ccdf3d485241c8ee4 1949
qemu-kvm_1.1.2+dfsg-3.dsc
2670ccd5f2d07a0e00e1b631b1f4abe0cba61390744cb82348c1825dcd173ad9 48542
qemu-kvm_1.1.2+dfsg-3.debian.tar.gz
95a9063e7535b702be99113dc6feb4c22c2d06cbe7be8a113b8950234fce234d 1756288
qemu-kvm_1.1.2+dfsg-3_i386.deb
d282d450633843193d39d0fc0008e8a7669847fa665d36b63bca4ef9c6300d85 5098654
qemu-kvm-dbg_1.1.2+dfsg-3_i386.deb
50ba25f736b5408e73f5c0a3c4c6f010cb7a6774267df55ce67660a64d1fb251 22976
kvm_1.1.2+dfsg-3_i386.deb
Files:
f19d1ac0052beaa0c4ab9b8e952f2560 1949 misc optional qemu-kvm_1.1.2+dfsg-3.dsc
eb29632fab2488aef650b519cf42825e 48542 misc optional
qemu-kvm_1.1.2+dfsg-3.debian.tar.gz
fdf45ed18e063a5c868ac29cf56f0421 1756288 misc optional
qemu-kvm_1.1.2+dfsg-3_i386.deb
cd186a71d7b55aaeded888be2a2a85db 5098654 debug extra
qemu-kvm-dbg_1.1.2+dfsg-3_i386.deb
9268cfd2c236f45ecd23c06ce8dc6002 22976 oldlibs extra kvm_1.1.2+dfsg-3_i386.deb
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.12 (GNU/Linux)
iJwEAQECAAYFAlDPlbwACgkQUlPFrXTwyDhUVQP8DnAttJAOVgAduFC65xLL3D8W
LeiQOMbneDinQOfDS9Ja8Wgf7OIfLZqwBh35MDyQthLc8p9ECCypl1ugxucO3cgJ
YvRRrMgsxyBrSnS7iWV4/kukS+S4ATmpJmdAZMxHKd4xfckiZfIaLDSHngpSQuZW
8vk8OTf67JXHn0MQh9E=
=2NqR
-----END PGP SIGNATURE-----
--- End Message ---
