Hi Luke,
I?m very glad that you?re interested in this work. ?
I never published any performance data, and haven?t run cachebench.
We use test_memcpy_perf.c in DPDK to do the test mainly, because it?s the
environment that DPDK runs. You can also find the performance comparison there
with glibc.
v2 changes:
make fdset num field reflect the current number of fds vhost server manages
allocate context for connected fd in vserver_new_vq_conn
enable multiple socket support
get_feature fix: apply Tetsuya's comment
set_feature fix
close received log fd, err fd: apply Haifeng's comment
CTR
vhost-cuse functionality will be divided into two parts:
cuse driver specific logic and common logic.
cuse driver specific logic will be in vhost_cuse logic.
vhost ioctl message is pre-processed there and then sent to virtio-net
module if necessary.
virtio-net provides common message hand
Signed-off-by: Huawei Xie
---
lib/librte_vhost/vhost_rxtx.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/lib/librte_vhost/vhost_rxtx.c b/lib/librte_vhost/vhost_rxtx.c
index c7c9550..be4f6a5 100644
--- a/lib/librte_vhost/vhost_rxtx.c
+++ b/lib/librte_vhost/vhost_rxtx.c
@@
In virtnet_send_command:
/* Caller should know better */
BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ) ||
(out + in > VIRTNET_SEND_COMMAND_SG_MAX));
Signed-off-by: Huawei Xie
---
lib/librte_vhost/virtio-net.c | 3 ++-
1 file changed, 2 insertions(+),
This file defines the common operation provided by virtio-net(.c).
Signed-off-by: Huawei Xie
---
lib/librte_vhost/vhost-net-cdev.h| 113 ---
lib/librte_vhost/vhost-net.h | 113 +++
lib/librte_vhost/vhost_cuse/vhost-net-c
Signed-off-by: Huawei Xie
---
lib/librte_vhost/vhost_cuse/vhost-net-cdev.c | 85
lib/librte_vhost/virtio-net.c| 57 +--
2 files changed, 77 insertions(+), 65 deletions(-)
diff --git a/lib/librte_vhost/vhost_cuse/vhost-net-cdev.c
b/li
Signed-off-by: Huawei Xie
---
lib/librte_vhost/vhost_cuse/virtio-net-cdev.c | 258 ++
1 file changed, 258 insertions(+)
create mode 100644 lib/librte_vhost/vhost_cuse/virtio-net-cdev.c
diff --git a/lib/librte_vhost/vhost_cuse/virtio-net-cdev.c
b/lib/librte_vhost/vhost_
Signed-off-by: Huawei Xie
---
lib/librte_vhost/vhost_cuse/virtio-net-cdev.c | 43 +--
1 file changed, 20 insertions(+), 23 deletions(-)
diff --git a/lib/librte_vhost/vhost_cuse/virtio-net-cdev.c
b/lib/librte_vhost/vhost_cuse/virtio-net-cdev.c
index fbfc403..58ac3dd 1006
Signed-off-by: Huawei Xie
---
lib/librte_vhost/Makefile | 2 +-
lib/librte_vhost/vhost-net.h | 5 +-
lib/librte_vhost/vhost_cuse/vhost-net-cdev.c | 7 +-
lib/librte_vhost/vhost_cuse/virtio-net-cdev.c | 85 +++
lib/librte_vhost/vhost_cuse/virtio-net
for generic event driver processing, refer to:
http://libevent.org/
Signed-off-by: Huawei Xie
---
lib/librte_vhost/vhost_user/fd_man.c | 207 +++
lib/librte_vhost/vhost_user/fd_man.h | 64 +++
2 files changed, 271 insertions(+)
create mode 100644
Signed-off-by: Huawei Xie
---
lib/librte_vhost/Makefile | 5 +-
lib/librte_vhost/vhost-net.h | 4 +
lib/librte_vhost/vhost_cuse/virtio-net-cdev.c | 12 +-
lib/librte_vhost/vhost_user/fd_man.c | 4 +-
lib/librte_vhost/vhost_user/vhost-net-user.
Signed-off-by: Huawei Xie
---
lib/librte_vhost/rte_virtio_net.h | 2 +
lib/librte_vhost/vhost-net.h | 2 -
lib/librte_vhost/vhost_user/vhost-net-user.h | 3 +-
lib/librte_vhost/vhost_user/virtio-net-user.c | 109 --
4 files changed, 104
Signed-off-by: Huawei Xie
---
lib/librte_vhost/vhost_user/vhost-net-user.c | 4 ++
lib/librte_vhost/vhost_user/virtio-net-user.c | 56 +++
lib/librte_vhost/vhost_user/virtio-net-user.h | 1 +
3 files changed, 45 insertions(+), 16 deletions(-)
diff --git a/lib/librte_v
Signed-off-by: Huawei Xie
---
lib/librte_vhost/vhost_user/vhost-net-user.c | 57 +++-
lib/librte_vhost/vhost_user/vhost-net-user.h | 1 -
2 files changed, 40 insertions(+), 18 deletions(-)
diff --git a/lib/librte_vhost/vhost_user/vhost-net-user.c
b/lib/librte_vhost/vho
Signed-off-by: Huawei Xie
---
lib/librte_vhost/Makefile | 2 +-
lib/librte_vhost/rte_virtio_net.h | 3 +-
lib/librte_vhost/vhost-net.h | 3 +
lib/librte_vhost/vhost_cuse/eventfd_copy.c| 89 +++
lib/librte_vhost/vhost
The patch set supports NVGRE on i40e.
It includes:
- Support RX filters for NVGRE packet. It uses MAC and VLAN to point
to a queue. The filter types supported are listed below:
1. Inner MAC and Inner VLAN ID
2. Inner MAC address, inner VLAN ID and tenant ID.
3. Inner MAC and tenant
Add NVGRE header and Transparent Ethernet Bridging Macro in rte_ether.h file.
Signed-off-by: Jijiang Liu
---
lib/librte_ether/rte_ether.h | 12
1 files changed, 12 insertions(+), 0 deletions(-)
diff --git a/lib/librte_ether/rte_ether.h b/lib/librte_ether/rte_ether.h
index 7e7d22c
The filter types supported are listed below for NVGRE packet:
1. Inner MAC and Inner VLAN ID.
2. Inner MAC address, inner VLAN ID and tenant ID.
3. Inner MAC and tenant ID.
4. Inner MAC address.
5. Outer MAC address, tenant ID and inner MAC address.
6. Inner IP address.
Sig
Extend the "tunnel_filter" command in testpmd to test the RX tunnel filter API
for NVGRE packet.
Signed-off-by Jijiang Liu
---
app/test-pmd/cmdline.c | 18 +++---
1 files changed, 11 insertions(+), 7 deletions(-)
diff --git a/app/test-pmd/cmdline.c b/app/test-pmd/cmdline.c
index
This flag is used to tell the NIC the TX packet is a GRE tunneled packet.
Signed-off-by: Jijiang Liu
---
lib/librte_mbuf/rte_mbuf.h |6 ++
1 files changed, 6 insertions(+), 0 deletions(-)
diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
index 16059c6..a672bd8 100644
Support NVGRE TX checksum offload, which includes
- outer L3(IP) checksum offload
- inner L3(IP) checksum offload
- inner L4(UDP, TCP and SCTP) checksum offload
In addition, for GRE packet, the L4 tunnel type should be
I40E_TXD_CTX_GRE_TUNNELING.
Signed-off-by: Jijiang Liu
---
lib/librt
Enhance csum fwd engine and command lines based on current TX checksum
framework in order to test TX Checksum offload for NVGRE packet.
It includes:
- IPv4 and IPv6 packet
- outer L3, inner L3 and L4 checksum offload for Tx side.
Note: The patch will need to be reworked after Olivier's patch s
Hi lads,
> -Original Message-
> From: Olivier MATZ [mailto:olivier.matz at 6wind.com]
> Sent: Wednesday, January 21, 2015 3:25 PM
> To: Liu, Jijiang; Ananyev, Konstantin
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v3 0/3] enhance TX checksum command and csum
> forwarding engine
Hi,
> -Original Message-
> From: Ananyev, Konstantin
> Sent: Monday, January 26, 2015 12:14 PM
> To: Olivier MATZ; Liu, Jijiang
> Cc: dev at dpdk.org
> Subject: RE: [dpdk-dev] [PATCH v3 0/3] enhance TX checksum command and
> csum forwarding engine
>
> Hi lads,
>
> > -Original Message
> -Original Message-
> From: Linhaifeng [mailto:haifeng.lin at huawei.com]
> Sent: Friday, January 23, 2015 4:17 PM
> To: Xie, Huawei; dev at dpdk.org
> Cc: haifeng.lin at intel.com
> Subject: Re: [dpdk-dev] [PATCH RFC v2 00/12] lib/librte_vhost: vhost-user
> support
>
> Hi, Xie
>
> could
On 26 January 2015 at 02:30, Wang, Zhihong wrote:
> Hi Luke,
>
>
>
> I?m very glad that you?re interested in this work. J
>
Great :).
I never published any performance data, and haven?t run cachebench.
>
> We use test_memcpy_perf.c in DPDK to do the test mainly, because it?s the
> environmen
Hello,
recently I have found a case of significant performance degradation for our
application (built on top of DPDK, of course). Surprisingly, similar issue
is easily reproduced with default testpmd.
To show the case we need simple IPv4 UDP flood with variable UDP payload
size. Saying "packet le
On Sun, Jan 25, 2015 at 10:40:23PM +, Ananyev, Konstantin wrote:
> Hi Neil,
>
> > -Original Message-
> > From: Neil Horman [mailto:nhorman at tuxdriver.com]
> > Sent: Sunday, January 25, 2015 5:35 PM
> > To: Ananyev, Konstantin
> > Cc: dev at dpdk.org
> > Subject: Re: [dpdk-dev] [PATCH
On Thu, 22 Jan 2015 16:16:32 +0800
Cunming Liang wrote:
> - return rte_socket_id();
> + unsigned socket_id = rte_socket_id();
> +
> + if (socket_id == (unsigned)SOCKET_ID_ANY)
I prefer not casting -1 to unsigned it will cause warnings.
It is better to make socket_id an integer and th
Hi,
On 01/26/2015 07:02 AM, Liu, Jijiang wrote:
>> I tried to repeat Olivier test-cases on my box.
>> Though, I didn't use test-pmd cusmonly and i40ePMD logic, but filled TCD and
>> TDD mostly from hardcoded values.
>> That's what I got:
>>
>> 4 input packets:
>> a) ETHER/IPv4/UDP/VXLAN/ETHER/IP
Hi Olivier,
> -Original Message-
> From: Olivier MATZ [mailto:olivier.matz at 6wind.com]
> Sent: Monday, January 26, 2015 2:07 PM
> To: Liu, Jijiang; Ananyev, Konstantin; Zhang, Helin
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v3 0/3] enhance TX checksum command and csum
> fo
Hi Alexander,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Alexander Belyakov
> Sent: Monday, January 26, 2015 10:18 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] DPDK testpmd forwarding performace degradation
>
> Hello,
>
> recently I have found a case
Hi,
I must say: greate work.
I have some small comments:
> +/**
> + * Macro for copying unaligned block from one location to another,
> + * 47 bytes leftover maximum,
> + * locations should not overlap.
> + * Requirements:
> + * - Store is aligned
> + * - Load offset is , which must be immediate
On Tue, 20 Jan 2015 17:53:55 +0800
Danny Zhou wrote:
> This patchset includes below features:
> 1) Enable one-shot rx queue interrupt in ixgbe PMD for PF as well as VF.
> 2) Build on top of the VFIO mechanism instead of UIO, so it could support
> up to 64 interrupt vectors for rx queue interrupts
On Mon, 26 Jan 2015 13:17:48 +0300
Alexander Belyakov wrote:
> Hello,
>
> recently I have found a case of significant performance degradation for our
> application (built on top of DPDK, of course). Surprisingly, similar issue
> is easily reproduced with default testpmd.
>
> To show the case we
Hi Zhihong,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Wang, Zhihong
> Sent: Friday, January 23, 2015 6:52 AM
> To: Richardson, Bruce; Marc Sune
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 0/4] DPDK memcpy optimization
>
>
>
> > -Origin
2015-01-20 15:49, Neil Horman:
> the vhost library relies on libfuse, and thats included when we do a normal
> shared object build, but when we specify combined libs, its gets left out.
> Add
> it back in
>
> Signed-off-by: Neil Horman
> ---
> mk/rte.app.mk | 4
> 1 file changed, 4 insert
Ping. What next for this patch?
2014-12-18 22:05, Thomas Monjalon:
> 2014-12-18 09:41, Daniel Mrzyglod:
> > In test_sched, we are missing NULL pointer checks after calls to create the
> > mempool and to allocate an mbuf. Add in these checks using VERIFY macros.
> >
> > Signed-off-by: Daniel Mrzy
On Tue, Jan 27, 2015 at 10:35:40AM +0800, Ouyang Changchun wrote:
> This is the patch set for single virtio implementation.
>
> Why we need single virtio?
>
> As we know currently there are at least 3 virtio PMD driver implementations:
> A) lib/librte_pmd_virtio(refer
40 matches
Mail list logo
