its own lock in order to not create contention
between PMD threads of different vrings and to prevent
performance degradation by scaling queue pair number.
See https://bugzilla.redhat.com/show_bug.cgi?id=1450680
Signed-off-by: Victor Kaplansky
---
v5:
o get rid of spinlock wrapping functions in
- Original Message -
> From: "Stephen Hemminger"
> To: "Victor Kaplansky"
> Cc: dev@dpdk.org, sta...@dpdk.org, "Jens Freimann" ,
> "Maxime Coquelin"
> , "Yuanhan Liu" , "Tiwei
> Bie" , "Jianfeng
> T
- Original Message -
> From: "Stephen Hemminger"
> To: "Victor Kaplansky"
> Cc: dev@dpdk.org, sta...@dpdk.org, "Jens Freimann" ,
> "Maxime Coquelin"
> , "Yuanhan Liu" , "Tiwei
> Bie" , "Jianfeng
>
its own lock in order to not create contention
between PMD threads of different vrings and to prevent
performance degradation by scaling queue pair number.
See https://bugzilla.redhat.com/show_bug.cgi?id=1450680
Signed-off-by: Victor Kaplansky
---
v4:
o moved access_unlock before accessing
- Original Message -
> From: "Maxime Coquelin"
> To: "Victor Kaplansky" , dev@dpdk.org
> Cc: sta...@dpdk.org, "Jens Freimann" , "Yuanhan Liu"
> , "Tiwei Bie"
> , "Jianfeng Tan"
> Sent: Thursday, December
its own lock in order to not create contention
between PMD threads of different vrings and to prevent
performance degradation by scaling queue pair number.
See https://bugzilla.redhat.com/show_bug.cgi?id=1450680
Signed-off-by: Victor Kaplansky
Tested-by: Maxime Coquelin
---
v3:
o Added locking
different vrings and to prevent
performance degradation by scaling queue pair number.
Signed-off-by: Victor Kaplansky
---
lib/librte_vhost/vhost.h | 1 +
lib/librte_vhost/vhost_user.c | 46 +++
lib/librte_vhost/virtio_net.c | 8
3 files changed, 55
When performing live migration or memory hot-plugging,
the changes to the device and vrings made by message handler
done independently from vring usage by PMD threads.
This causes for example segfauls during live-migration
with MQ enable, but in general virtually any request
sent by qemu changing
- Original Message -
> From: "Maxime Coquelin"
> To: "Victor Kaplansky"
> Cc: dev@dpdk.org, y...@fridaylinux.org, "tiwei bie" ,
> "jianfeng tan" ,
> sta...@dpdk.org, jfrei...@redhat.com
> Sent: Monday, November 27, 2017 10:2
Hi,
While I agree that taking full fledged lock by rte_rwlock_read_lock() solves
the race condition,
I'm afraid that it would be too expensive in case when logging is off, since it
introduces
acquiring and releasing lock into the main flow of ring updates.
It is OK for now, as it fixes the bug,
-
> From: "Thomas Monjalon"
> To: "Bruce Richardson" , "Victor Kaplansky"
>
> Cc: dev@dpdk.org, "jingjing wu" , "Amnon Ilan"
> , "Tim Irnich"
> , "Georg Kunz" , "Gabor
> Halász" ,
> "
This RFC patch propose enhancements to testpmd to simulate
more realistic behavior of a guest machine engaged in receiving
and sending packets performing Virtual Network Function (VNF).
The goal is to enable simple of measuring performance impact on cache and
memory footprint utilization from var
Looks OK to me. I didn't quite get why open_int() is called so.
What does it open?
--
Victor
- Original Message -
> From: "Yuanhan Liu"
> To: dev at dpdk.org
> Cc: "huawei xie" , "Yuanhan Liu" linux.intel.com>, "Tetsuya Mukawa"
>
> Sent: Saturday, May 7, 2016 9:40:24 AM
> Subject: [dpd
Again, it may be useful to add mixed --client-server option, when
backend tries to connect as client and if failed, comes up as a server...
Just a suggestion from user point of view...
- Original Message -
> From: "Yuanhan Liu"
> To: dev at dpdk.org
> Cc: "huawei xie" , "Yuanhan Liu" lin
- Original Message -
> From: "Yuanhan Liu"
> To: dev at dpdk.org
> Cc: "huawei xie" , "Yuanhan Liu" linux.intel.com>, "Michael S. Tsirkin"
>
> Sent: Saturday, May 7, 2016 9:40:22 AM
> Subject: [dpdk-dev] [PATCH 4/6] vhost: workaround stale vring base
>
> When DPDK app crashes (or quit
Adding a flag for a future extension seems fine to me.
Could we manage without adding a flag?
For example, could we always try a client mode for a while at first,
and if unsuccessful, then come up with server mode?
-- Victor
- Original Message -
> From: "Yuanhan Liu"
> To: dev at dpdk.or
Great!
Thanks a lot, the tree will allow me to focus on development, and not
waste the time on testing and maintenance.
--
Victor
- Original Message -
> From: "Yuanhan Liu"
> To: dev at dpdk.org
> Cc: "Thomas Monjalon" , "Bruce Richardson"
Hi!
Since I was maintaining an internal tree with patches related to
vhost/virtio, I decided to make this staging tree public. It is
useful to me and I hope it will be useful to others.
Collecting patches like this allows tracking dependencies between
patches, their improvement etc. I also rebase
On Wed, Dec 02, 2015 at 10:38:02PM +0800, Yuanhan Liu wrote:
> On Wed, Dec 02, 2015 at 04:07:02PM +0200, Victor Kaplansky wrote:
> > On Wed, Dec 02, 2015 at 11:43:12AM +0800, Yuanhan Liu wrote:
> > > Invoking vhost_log_write() to mark corresponding page as dirty while
> &g
On Wed, Dec 02, 2015 at 11:43:09AM +0800, Yuanhan Liu wrote:
> This patch set adds the initial vhost-user live migration support.
>
> The major task behind that is to log pages we touched during
> live migration. So, this patch is basically about adding vhost
> log support, and using it.
>
> Patc
On Wed, Dec 02, 2015 at 11:43:12AM +0800, Yuanhan Liu wrote:
> Invoking vhost_log_write() to mark corresponding page as dirty while
> updating used vring.
Looks good, thanks!
I didn't find where you log the dirty pages in result of data
written to the buffers pointed by the descriptors in RX vrin
On Wed, Dec 02, 2015 at 11:43:11AM +0800, Yuanhan Liu wrote:
> Introduce vhost_log_write() helper function to log the dirty pages we
> touched. Page size is harded code to 4096 (VHOST_LOG_PAGE), and each
> log is presented by 1 bit.
>
> Therefore, vhost_log_write() simply finds the right bit for r
Yuanhan, looks fine. Thanks for handling this.
-- Victor
On Tue, Nov 24, 2015 at 03:25:35PM +0800, Yuanhan Liu wrote:
> From: Victor Kaplansky
>
> The VHOST_USER_SET_VRING_ENABLE request was sent for each queue-pair.
> However, it's changed to be sent per queue in the q
On Fri, Nov 20, 2015 at 03:45:00PM +0200, Victor Kaplansky wrote:
> The VHOST_USER_SET_VRING_ENABLE request is sent for each queue in
> queue-pair separately. So, a queue-pair should be considered
> enabled only when both RX and TX queues are enabled.
>
> The old code caused segfau
The VHOST_USER_SET_VRING_ENABLE request is sent for each queue in
queue-pair separately. So, a queue-pair should be considered
enabled only when both RX and TX queues are enabled.
The old code caused segfault when last TX queue was enabled.
Signed-off-by: Victor Kaplansky
---
lib/librte_vhost
25 matches
Mail list logo
