1. Added F-Stack FreeBSD support. see 9f7a1423a0 .
2. Enable INET6 by default in helloworld. see 51c91ab0ad .
3. Added FDIR support. see 4854315d0d .
4. To avoid compiling errors when gcc version >= 10. see 6daadb0b5c .
5. Modify `struct linux_sockaddr` same to `struct sockaddr` in linux. see d96a9d10f4 .
6. Sync some modified of ff_config.c, inclue set dpdk log level, Avoid memory leaks, suppor vip_addr and vip_addr6, etc. see git log lib/ff_config.c in branch of dev.
7. Sync some modified of ff_syscall_wrapper.c, include ff_sendmsg, ff_recvmsg, ip6_opt_convert, etc. see git log lib/ff_syscall_wrapper.c in branch of dev.
8. The CPU usage of packet_dispatcher() is modified to usr. see 0508c8b8ec .
9. If process_dispatch_ring() has data packet to be processed and it is considered non-idle state. see 81dd6c7a24 .
10. Fix a plurality of packets may not statistics in ff_traffic.rx_packets and ff_traffic.rx_bytes. see 0b4a084c8a .
11. Added FF_IPSEC=1 in lib/Makefile, disable by default.
12. Some other modified.
`FF_ZC_SEND` is same as `FF_USE_PAGE_ARRAY`, it will improve performance slightly in some scenarios, need to be tested in combination with real applications.
You can enable both compilation options at the same time or separately.
Two kinds of mbuf are used in f-stack: freebsd mbuf and dpdk mbuf.
freebsd mbufs are metadata used in freebsd stack, and their data
pointers (m_data) point to dpdk mbuf's data (buf_addr). And they have
their own chain, like this:
bsd_mbuf1 -> bsd_mbuf2 -> bsd_mbuf3
\ \ \
dpdk_mbuf1 -> dpdk_mbuf2 -> dpdk_mbuf3
Considering the map relationship,
- m_freem() is corresponding to rte_pktmbuf_free(), is to free the whole
chain of mbufs.
- m_free() is corresponding to rte_pktmbuf_free_seg(), is to free the
specified mbuf segment.
The current implementation in f-stack uses rte_pktmbuf_free() for
m_free(). This leads to mbufs, which are still in use, be freed
unexpectedly. For example, if the bsd_mbuf1 is trimed into zero length,
bsd will invoke m_free() to free the specified segment, however, the
whole mbuf chain is freed by calling rte_pktmbuf_free().
#0 rte_pktmbuf_free (m=0x22006fb480)
#1 in ff_dpdk_pktmbuf_free (m=0x22006fb480)
#2 in ff_mbuf_ext_free (m=0x7ffff7f82800, arg1=0x22006fb480, arg2=0x0)
#3 in mb_free_ext (m=0x7ffff7f82800)
#4 in m_free (m=0x7ffff7f82800)
#5 in sbcompress (sb=, m=0x7ffff7f82800, n=)
#6 in sbappendstream_locked (sb=, m=0x7ffff7f82800, flags=0)
The fix is straightforward. Use the correct API for segment free.
Reported-by: Yong-Hao Zou <yonghaoz1994@gmail.com>
Signed-off-by: Jianfeng Tan <henry.tjf@antgroup.com>
1.Close #22.
2.Configure the HW indirection table when initializing port.
3.Use several LSBs of the rss hash result according to reta_size when
calculating queue index.
RX: VLAN strip, CRC strip, IP/TCP/UDP checksum.
TX: IP/TCP/UDP checksum, TSO.
Note that TSO has a problem: when enable TSO,
F-Stack is much slower(Temporarily not resolved).
So TSO is disabled by default.
Edit config.ini to enable it.
fengbojiang
zengyi1001
freak82
Jianfeng Tan
HongBo Long
10077240
yanya
logwang