dpdk_vfreset.patch:
diff -urN dpdk-16.07/doc/guides/nics/overview.rst
dpdk-16.07-new/doc/guides/nics/overview.rst
--- dpdk-16.07/doc/guides/nics/overview.rst 2016-07-28 11:48:41.0
-0700
+++ dpdk-16.07-new/doc/guides/nics/overview.rst 2016-12-15 17:32:27.436425563
-0800
@@ -89,6 +89,
interrupts_excerpts.patch:
drivers/net/ixgbe/ixgbe_ethdev.c
eth_ixgbevf_dev_init:
@@ -1462,8 +1467,9 @@
rte_intr_callback_register(&pci_dev->intr_handle,
ixgbevf_dev_interrupt_handler,
(void *)eth_dev);
- rte_int
Attached are 2 patches, and the discussion below is related to the slightly
modified version of the dpdk 16.07 library: interrupts_excerpt.patch and
dpdk_vfreset.patch
1. We use a single-shot interrupt mechanism for the RX queue (vector #1,
intr_handle.efds[0]file descriptor).
When we receive
ixgbevf_dev_stop at this point but we cannot safely run
ixgbevf_dev_start. Do you have any suggestion how to handle this case? Also, is
there any better (more recent) patch to handle this?
Thanks,
Ruslan Nikolaev
4 matches
Mail list logo
