[dpdk-dev] [PATCH] vhost: call write barrier before used index update

tween CPU cores (applicable for virtual NICs in our case). smp_*mb() for Intel architecture would be a simple compiler barrier, whereas for processors with weaker memory model they may use real barrier instructions. Maybe implementing barriers similar way would work in DPDK as well? -- Best regards,

[dpdk-dev] [PATCH] vhost: call write barrier before used index update

: Nikita Kalyazin --- lib/librte_vhost/vhost_rxtx.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/lib/librte_vhost/vhost_rxtx.c b/lib/librte_vhost/vhost_rxtx.c index 7026bfa..d955287 100644 --- a/lib/librte_vhost/vhost_rxtx.c +++ b/lib/librte_vhost/vhost_rxtx.c @@ -216,7

[dpdk-dev] [PATCH v5 resend 07/12] virtio: resolve for control queue

Yes, exactly. I observe it same way even after applying the patch. -- Best regards, Nikita Kalyazin, n.kalyazin at samsung.com Software Engineer Virtualization Group Samsung R&D Institute Russia Tel: +7 (495) 797-25-00 #3816 Tel: +7 (495) 797-25-03 Office #1501, 12-1, Dvintsev str., Moscow, 127

[dpdk-dev] [PATCH v5 resend 07/12] virtio: resolve for control queue

t regards, Nikita Kalyazin, n.kalyazin at samsung.com Software Engineer Virtualization Group Samsung R&D Institute Russia Tel: +7 (495) 797-25-00 #3816 Tel: +7 (495) 797-25-03 Office #1501, 12-1, Dvintsev str., Moscow, 127018, Russia On Mon, Sep 21, 2015 at 02:36:47PM +0800, Yuanhan Liu wrote: >

[dpdk-dev] [PATCH v2] vhost: flush used->idx update before reading avail->flags

Ah, sorry. I looked at it without the context. Thanks. -- Best regards, Nikita Kalyazin, n.kalyazin at samsung.com Software Engineer CE OS Group Samsung R&D Institute Russia Tel: +7 (495) 797-25-00 #3816 Tel: +7 (495) 797-25-03 Office #1501, 12-1, Dvintsev str., Moscow, 127018, Russia On

[dpdk-dev] [PATCH v2] vhost: flush used->idx update before reading avail->flags

Hi, Maybe I missed a part of the discussion, but is there any special purpose for using rte_mb (both read and write fence) here rather than rte_wmb (write fence only)? -- Best regards, Nikita Kalyazin, n.kalyazin at samsung.com Software Engineer CE OS Group Samsung R&D Institute Ru

[dpdk-dev] data copy in vhost-user

Zoltan, Huawei, Thank you for your replies. -- Best regards, Nikita Kalyazin, n.kalyazin at samsung.com CE OS Group Samsung R&D Institute Russia Tel: +7 (495) 797-25-00 #3816 Tel: +7 (495) 797-25-03 Office #1501, 12-1, Dvintsev str., Moscow, 127018, Russia On Tue, Apr 28, 2015 at 01:24:

[dpdk-dev] data copy in vhost-user

copies (e.g., rte_vhost_enqueue_burst() might set up a reference at vring descriptor to mbuf's data rather than copying the data)? -- Best regards, Nikita Kalyazin, n.kalyazin at samsung.com CE OS Group Samsung R&D Institute Russia Tel: +7 (495) 797-25-00 #3816 Tel: +7 (495) 797-25-