On Wed, 2015-07-15 at 12:52 +0300, Konstantin Khlebnikov wrote:
These functions check should_resched() before unlocking spinlock/bh-enable:
preempt_count always non-zero = should_resched() always returns false.
cond_resched_lock() worked iff spin_needbreak is set.
Interesting, this definitely
On Sat, 2014-10-11 at 15:16 +0800, Jason Wang wrote:
We free transmitted packets in ndo_start_xmit() in the past to get better
performance in the past. One side effect is that skb_orphan() needs to be
called in ndo_start_xmit() which makes sk_wmem_alloc not accurate in
fact. For TCP protocol,
On Tue, 2014-06-03 at 14:48 +0200, Paolo Bonzini wrote:
Il 02/06/2014 23:58, Eric Dumazet ha scritto:
This looks dubious
What about using kfree_rcu() instead ?
It would lead to unbound allocation from userspace.
Look at how we did this in commit
c3059477fce2d956a0bb3e04357324780c5d8eeb
On Tue, 2014-06-03 at 00:30 +0300, Michael S. Tsirkin wrote:
All memory accesses are done under some VQ mutex.
So lock/unlock all VQs is a faster equivalent of synchronize_rcu()
for memory access changes.
Some guests cause a lot of these changes, so it's helpful
to make them faster.
On Wed, 2014-05-14 at 14:40 +0100, Zoltan Kiss wrote:
Hi,
Recently I've investigated issues around SKBTX_DEV_ZEROCOPY skbs where
the frags list were modified. I came across this function skb_shift(),
which moves frags between skbs. And there are a lot more of such kind,
skb_split or
On Wed, 2014-05-14 at 13:42 -0400, David Miller wrote:
From: Eric Dumazet eric.duma...@gmail.com
Date: Wed, 14 May 2014 07:23:52 -0700
On Wed, 2014-05-14 at 14:40 +0100, Zoltan Kiss wrote:
Hi,
Recently I've investigated issues around SKBTX_DEV_ZEROCOPY skbs where
the frags list
On Wed, 2014-05-14 at 20:41 +0100, Zoltan Kiss wrote:
On 14/05/14 15:23, Eric Dumazet wrote:
On Wed, 2014-05-14 at 14:40 +0100, Zoltan Kiss wrote:
Hi,
Recently I've investigated issues around SKBTX_DEV_ZEROCOPY skbs where
the frags list were modified. I came across this function
On Tue, 2014-02-11 at 22:25 +0800, Qin Chuanyu wrote:
we could xmit directly instead of going through softirq to gain
throughput and lantency improved.
test model: VM-Host-Host just do transmit. with vhost thread and nic
interrupt bind cpu1. netperf do throuhput test and qperf do lantency
On Wed, 2014-02-12 at 13:28 +0800, Jason Wang wrote:
A question: without NAPI weight, could this starve other net devices?
Not really, as net devices are serviced by softirq handler.
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to
On Wed, 2014-02-12 at 13:50 +0800, Jason Wang wrote:
On 02/12/2014 01:47 PM, Eric Dumazet wrote:
On Wed, 2014-02-12 at 13:28 +0800, Jason Wang wrote:
A question: without NAPI weight, could this starve other net devices?
Not really, as net devices are serviced by softirq handler
On Tue, 2014-01-28 at 16:14 +0800, Qin Chuanyu wrote:
according perf test result,I found that there are 5%-8% cpu cost on
softirq by use netif_rx_ni called in tun_get_user.
so I changed the function which cause skb transmitted more quickly.
from
tun_get_user-
On Fri, 2013-03-08 at 14:24 +0800, Jason Wang wrote:
Hello all:
I meet an issue when testing multiqueue virtio-net. When I testing guest
small packets stream sending performance with netperf. I find an
regression of multiqueue. When I run 2 sessions of TCP_STREAM test with
1024 byte from
On Fri, 2012-07-27 at 22:09 -0500, sheng qiu wrote:
Hi all,
i am comparing network throughput performance under bare-metal case
with that running VM with assigned-device (assigned NIC). i have two
physical machines (each has a 10Gbit NIC), one is used as remote
server (run netserver) and
On Mon, 2012-05-14 at 20:04 +0300, Michael S. Tsirkin wrote:
On Mon, May 14, 2012 at 09:54:46AM -0700, Stephen Hemminger wrote:
On Sun, 13 May 2012 18:52:06 +0300
Michael S. Tsirkin m...@redhat.com wrote:
+ /* Userspace may produce vectors with count greater than
+ *
On Mon, 2012-05-14 at 22:14 +0300, Michael S. Tsirkin wrote:
They seem to be in net-next, or did I miss something?
Yes, you re-introduce in this patch some bugs already fixed in macvtap
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to
()
Signed-off-by: Alex Shi alex@intel.com
---
net/netfilter/xt_TEE.c | 12 ++--
net/socket.c |4 ++--
2 files changed, 8 insertions(+), 8 deletions(-)
Acked-by: Eric Dumazet eric.duma...@gmail.com
Thanks !
--
To unsubscribe from this list: send the line
Le jeudi 20 octobre 2011 à 10:44 +0800, Alex,Shi a écrit :
Acked-by: Christoph Lameter c...@gentwo.org
Thanks, Christoph!
and resend for code style problem correction.
Sorry this huge patch brings too many potential bugs.
I ask you a separate patch for the networking part, because I
Le lundi 22 août 2011 à 09:36 +0300, Avi Kivity a écrit :
On 08/20/2011 04:16 PM, Brad Campbell wrote:
Author: Alexander Duyck alexander.h.du...@intel.com
Date: Thu Jul 1 13:28:27 2010 +
x86: Drop CONFIG_MCORE2 check around setting of NET_IP_ALIGN
This patch removes the
Le vendredi 12 août 2011 à 09:55 +0800, Jason Wang a écrit :
+ rxq = skb_get_rxhash(skb);
+ if (rxq) {
+ tfile = rcu_dereference(tun-tfiles[rxq % numqueues]);
+ if (tfile)
+ goto out;
+ }
You can avoid an expensive divide with
Le jeudi 09 juin 2011 à 01:02 +0800, Brad Campbell a écrit :
On 08/06/11 11:59, Eric Dumazet wrote:
Well, a bisection definitely should help, but needs a lot of time in
your case.
Yes. compile, test, crash, walk out to the other building to press
reset, lather, rinse, repeat.
I need
Le mardi 07 juin 2011 à 21:27 +0800, Brad Campbell a écrit :
On 07/06/11 04:22, Eric Dumazet wrote:
Could you please try latest linux-2.6 tree ?
We fixed many networking bugs that could explain your crash.
No good I'm afraid.
[ 543.040056
Le mardi 07 juin 2011 à 17:35 +0200, Patrick McHardy a écrit :
The main suspects would be NAT and TCPMSS. Did you also try whether
the crash occurs with only one of these these rules?
I've just compiled out CONFIG_BRIDGE_NETFILTER and can no longer access
the address the way I was doing
Le mercredi 08 juin 2011 à 08:18 +0800, Brad Campbell a écrit :
On 08/06/11 06:57, Patrick McHardy wrote:
On 07.06.2011 20:31, Eric Dumazet wrote:
Le mardi 07 juin 2011 à 17:35 +0200, Patrick McHardy a écrit :
The main suspects would be NAT and TCPMSS. Did you also try whether
the crash
Le dimanche 05 juin 2011 à 21:45 +0800, Brad Campbell a écrit :
On 05/06/11 16:14, Avi Kivity wrote:
On 06/03/2011 04:38 PM, Brad Campbell wrote:
Is there anyone who can point me at the appropriate cage to rattle? I
know it appears to be a netfilter issue, but I don't seem to be able
to
Le lundi 06 juin 2011 à 22:10 +0200, Bart De Schuymer a écrit :
Hi Brad,
This has probably nothing to do with ebtables, so please rmmod in case
it's loaded.
A few questions I didn't directly see an answer to in the threads I
scanned...
I'm assuming you actually use the bridging firewall
Le jeudi 26 mai 2011 à 12:36 -0700, Shirley Ma a écrit :
This patch adds userspace buffers support in skb shared info. A new
struct skb_ubuf_info is needed to maintain the userspace buffers
argument and index, a callback is used to notify userspace to release
the buffers once lower device has
Le jeudi 26 mai 2011 à 13:24 -0700, Shirley Ma a écrit :
I could reduce callback pointer by moving it to *arg, but not desc, this
indicates that which buffer DMA hasn't done yet in *arg.
I guess you dont need to use skb itself to hold all your states ?
I understand its convenient for you,
0m3.296s
user0m1.366s
sys 0m1.926s
Reported-by: Ben Nagy b...@iagu.net
Signed-off-by: Eric Dumazet eric.duma...@gmail.com
Cc: Avi Kivity a...@redhat.com
Cc: Thomas Gleixner t...@linutronix.de
Cc: John Stultz johns...@us.ibm.com
Cc: Richard Cochran richard.coch...@omicron.at
Cc: Paul E
Le lundi 21 mars 2011 à 22:01 +0545, Ben Nagy a écrit :
On Mon, Mar 21, 2011 at 7:38 PM, Avi Kivitya...@redhat.com wrote:
In the future, please post the binary perf.dat.
Hi Avi,
How do I do that?
'make nconfig' and go to the kernel hacking section.
Imprecise question sorry, I
Le lundi 21 mars 2011 à 19:02 +0200, Avi Kivity a écrit :
Any ideas on how to fix it? We could pre-allocate IDs and batch them in
per-cpu caches, but it seems like a lot of work.
Hmm, I dont know what syscalls kvm do, but even a timer_gettime() has to
lock this idr_lock.
Sounds crazy, and
Le lundi 21 mars 2011 à 23:57 +0545, Ben Nagy a écrit :
On Mon, Mar 21, 2011 at 10:57 PM, Eric Dumazet eric.duma...@gmail.com wrote:
Le lundi 21 mars 2011 à 19:02 +0200, Avi Kivity a écrit :
Any ideas on how to fix it? We could pre-allocate IDs and batch them in
per-cpu caches
Le dimanche 13 mars 2011 à 17:06 +0200, Michael S. Tsirkin a écrit :
On Mon, Jan 17, 2011 at 04:11:17PM +0800, Jason Wang wrote:
We can use lock_sock_fast() instead of lock_sock() in order to get
speedup in peek_head_len().
Signed-off-by: Jason Wang jasow...@redhat.com
---
Le dimanche 13 mars 2011 à 18:19 +0200, Michael S. Tsirkin a écrit :
Other side is in drivers/net/tun.c and net/packet/af_packet.c
At least wrt tun it seems clear socket is not locked.
Yes (assuming you refer to tun_net_xmit())
Besides queue, dequeue seems to be done without socket locked.
Le dimanche 13 mars 2011 à 18:43 +0200, Michael S. Tsirkin a écrit :
On Sun, Mar 13, 2011 at 05:32:07PM +0100, Eric Dumazet wrote:
Le dimanche 13 mars 2011 à 18:19 +0200, Michael S. Tsirkin a écrit :
Other side is in drivers/net/tun.c and net/packet/af_packet.c
At least wrt tun
Le vendredi 18 février 2011 à 19:37 +0100, Patrick McHardy a écrit :
Am 14.02.2011 17:52, schrieb Patrick McHardy:
Am 14.02.2011 17:48, schrieb Eric Dumazet:
I am not sure, but I guess nf_reinject() needs a fix too ;)
I agree. That one looks uglier though, I guess we'll have to
iterate
Le lundi 14 février 2011 à 16:58 +0200, Avi Kivity a écrit :
We see severe memory corruption in kvm while used in conjunction with
bridge/netfilter. Enabling slab debugging points the finger at a
netfilter chain invoked from the bridge code.
Can someone take a look?
Le lundi 14 février 2011 à 16:18 +0100, Jan Engelhardt a écrit :
On Monday 2011-02-14 16:11, Eric Dumazet wrote:
Le lundi 14 février 2011 à 16:58 +0200, Avi Kivity a écrit :
We see severe memory corruption in kvm while used in conjunction with
bridge/netfilter. Enabling slab debugging
Le lundi 14 février 2011 à 17:24 +0100, Patrick McHardy a écrit :
Am 14.02.2011 16:50, schrieb Eric Dumazet:
Le lundi 14 février 2011 à 16:18 +0100, Jan Engelhardt a écrit :
On Monday 2011-02-14 16:11, Eric Dumazet wrote:
Le lundi 14 février 2011 à 16:58 +0200, Avi Kivity a écrit :
We
Le lundi 14 février 2011 à 17:37 +0100, Patrick McHardy a écrit :
Am 14.02.2011 17:29, schrieb Eric Dumazet:
Le lundi 14 février 2011 à 17:24 +0100, Patrick McHardy a écrit :
Also, I wonder if RCU rules are respected in nf_iterate().
For example this line is really suspicious :
*i = (*i
);
- lock_sock(sk);
head = skb_peek(sk-sk_receive_queue);
if (head)
len = head-len;
- release_sock(sk);
+ unlock_sock_fast(sk, slow);
return len;
}
Acked-by: Eric Dumazet eric.duma...@gmail.com
--
To unsubscribe from this list: send the line
Le jeudi 06 janvier 2011 à 18:33 +0900, Simon Horman a écrit :
Hi,
Back in October I reported that I noticed a problem whereby flow control
breaks down when openvswitch is configured to mirror a port[1].
I have (finally) looked into this further and the problem appears to relate
to
Le jeudi 06 janvier 2011 à 21:44 +0900, Simon Horman a écrit :
Hi Eric !
Thanks for the advice. I had thought about the socket buffer but at some
point it slipped my mind.
In any case the following patch seems to implement the change that I had in
mind. However my discussions Michael
Le mardi 21 décembre 2010 à 13:53 +0800, Yueyu Lin a écrit :
Hello, everyone
I just encountered a very strange issue in Ubuntu 10.10 server
edition X86 64bits. I just start up my kvm like :
kvm -net nic,macaddr=B3:C0:64:AF:73:28,model=virtio -net
Le vendredi 10 décembre 2010 à 02:13 -0800, Shirley Ma a écrit :
+ while (len) {
+ f = skb_shinfo(skb)-frags[i];
+ f-page = page[i];
+ f-page_offset = base ~PAGE_MASK;
+ f-size = min_t(int, len,
Le vendredi 10 décembre 2010 à 08:25 -0800, Shirley Ma a écrit :
On Fri, 2010-12-10 at 11:27 +0100, Eric Dumazet wrote:
You could make one atomic_add() outside of the loop, and factorize
many
things...
atomic_add(len, skb-sk-sk_wmem_alloc);
skb-data_len += len;
skb-len += len
Le jeudi 18 novembre 2010 à 07:28 +0100, Nikola Ciprich a écrit :
Yep, this is a known problem, thanks !
fix is there :
http://patchwork.ozlabs.org/patch/71354/
Thanks Eric, this indeed fixes the problem..
I noticed the fix didn't make it to 2.6.37-rc2-git3 though,
maybe it just
Le mardi 16 novembre 2010 à 09:41 +0100, Nikola Ciprich a écrit :
Hello,
I just tried running KVM on 2.6.37-rc2 host, and when trying to shutdown
guest, it
got to unterruptible state (D) and I'm getting lots of following messages:
[ 1269.392009] unregister_netdevice: waiting for vmtst01eth0
Le lundi 08 novembre 2010 à 16:03 +0800, xiaohui@intel.com a écrit :
From: Xin Xiaohui xiaohui@intel.com
Hmm, I suggest you read the comment two lines above.
If destructor_arg is now cleared each time we allocate a new skb, then,
please move it before dataref in shinfo
Le jeudi 04 novembre 2010 à 17:05 +0800, xiaohui@intel.com a écrit :
From: Xin Xiaohui xiaohui@intel.com
If buffer is external, then use the callback to destruct
buffers.
Signed-off-by: Xin Xiaohui xiaohui@intel.com
Signed-off-by: Zhao Yu yzhao81...@gmail.com
Reviewed-by:
Le jeudi 04 novembre 2010 à 10:04 +0100, Eric Dumazet a écrit :
Hmm, I suggest you read the comment two lines above.
If destructor_arg is now cleared each time we allocate a new skb, then,
please move it before dataref in shinfo structure, so that the following
memset() does the job
Le lundi 11 octobre 2010 à 08:27 -0700, David Miller a écrit :
From: Xin, Xiaohui xiaohui@intel.com
Date: Mon, 11 Oct 2010 15:06:05 +0800
That's to avoid the new cache miss caused by using destructor_arg in data
path
like skb_release_data().
That's based on the comment from Eric
Le jeudi 30 septembre 2010 à 22:04 +0800, xiaohui@intel.com a
écrit :
From: Xin Xiaohui xiaohui@intel.com
The hook is called in netif_receive_skb().
Signed-off-by: Xin Xiaohui xiaohui@intel.com
Signed-off-by: Zhao Yu yzhao81...@gmail.com
Reviewed-by: Jeff Dike
Le samedi 05 juin 2010 à 18:14 +0800, xiaohui@intel.com a écrit :
From: Xin Xiaohui xiaohui@intel.com
Signed-off-by: Xin Xiaohui xiaohui@intel.com
Signed-off-by: Zhao Yu yzhao81...@gmail.com
Reviewed-by: Jeff Dike jd...@linux.intel.com
---
include/linux/netdevice.h |3 +++
Le samedi 05 juin 2010 à 18:14 +0800, xiaohui@intel.com a écrit :
From: Xin Xiaohui xiaohui@intel.com
child-fclone = SKB_FCLONE_UNAVAILABLE;
}
+ /* Record the external buffer info in this field. It's not so good,
+ * but we cannot find another place easily.
+
Le samedi 05 juin 2010 à 18:14 +0800, xiaohui@intel.com a écrit :
From: Xin Xiaohui xiaohui@intel.com
If buffer is external, then use the callback to destruct
buffers.
Signed-off-by: Xin Xiaohui xiaohui@intel.com
Signed-off-by: Zhao Yu yzhao81...@gmail.com
Reviewed-by: Jeff
Le mardi 01 juin 2010 à 19:52 +0300, Avi Kivity a écrit :
What I'd like to see eventually is a short-term-unfair, long-term-fair
spinlock. Might make sense for bare metal as well. But it won't be
easy to write.
This thread rings a bell here :)
Yes, ticket spinlocks are sometime slower,
Le mercredi 10 février 2010 à 19:48 +0800, Xin Xiaohui a écrit :
Add a device to utilize the vhost-net backend driver for
copy-less data transfer between guest FE and host NIC.
It pins the guest user space to the host memory and
provides proto_ops as sendmsg/recvmsg to vhost-net.
Le 09/12/2009 16:11, Avi Kivity a écrit :
On 12/09/2009 03:46 PM, Adam Huffman wrote:
I've been seeing lots of crashes on a new Dell Precision T7500,
running the KVM in Fedora 12. Finally managed to capture an Oops,
which is shown below (hand-transcribed):
BUG: unable to handle kernel
Shirley Ma a écrit :
This patch is generated against 2.6 git tree. I didn't break up this
patch since it has one functionality. Please review it.
Thanks
Shirley
Signed-off-by: Shirley Ma x...@us.ibm.com
--
+void virtio_free_pages(void *buf)
+{
+ struct page *page = (struct
Paul E. McKenney a écrit :
(Sorry, but, as always, I could not resist!)
Yes :)
Thanks Paul for this masterpiece of diplomatic Acked-by ;)
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to majord...@vger.kernel.org
More majordomo info at
Michael S. Tsirkin a écrit :
+static void handle_tx(struct vhost_net *net)
+{
+ struct vhost_virtqueue *vq = net-dev.vqs[VHOST_NET_VQ_TX];
+ unsigned head, out, in, s;
+ struct msghdr msg = {
+ .msg_name = NULL,
+ .msg_namelen = 0,
+
Gregory Haskins a écrit :
Gregory Haskins wrote:
Eric Dumazet wrote:
Michael S. Tsirkin a écrit :
+static void handle_tx(struct vhost_net *net)
+{
+ struct vhost_virtqueue *vq = net-dev.vqs[VHOST_NET_VQ_TX];
+ unsigned head, out, in, s;
+ struct msghdr msg = {
+ .msg_name
Michael S. Tsirkin a écrit :
Paul, you acked this previously. Should I add you acked-by line so
people calm down? If you would rather I replace
rcu_dereference/rcu_assign_pointer with rmb/wmb, I can do this.
Or maybe patch Documentation to explain this RCU usage?
So you believe I am
63 matches
Mail list logo