f: Add support for changing congestion control")
Signed-off-by: Eric Dumazet
Cc: Lawrence Brakmo
Reported-by: Neal Cardwell
---
Acked-by: Lawrence Brakmo
Thanks, Eric!
> Suggested-by: Eric Dumazet
> Cc: Eric Dumazet
> Cc: Priyaranjan Jha
> Cc: Yuchung Cheng
> Cc: Soheil Hassas Yeganeh
> Acked-by: Soheil Hassas Yeganeh
> Acked-by: Yuchung Cheng
Ack for the whole series.
Acked-by: Yonghong Song
Thanks,
4 4865 0.00 156 306 425 759 1520 10 16
dctcp 5G4 4936 0.00 128 485 221 409 148479
dctcp-edt 5G4 4924 0.00 148 390 392 623 1508 11 26
v1 -> v2: Incorporated Andrii's suggestions
v2 -> v3: Incorporated Yonghong's su
ggestions
v3 -> v4: Removed credit update that is not needed
Signed-off-by: Lawrence Brakmo
---
samples/bpf/Makefile | 2 +
samples/bpf/do_hbm_test.sh | 22 ++---
samples/bpf/hbm.c | 18 +++-
samples/bpf/hbm_edt_kern.c | 168 +
samples
Yonhhong, thank you for the feedbac. Repies inlined. I will submit a new
revision later today.
On 7/1/19, 2:04 PM, "Yonghong Song" wrote:
On 6/28/19 12:41 PM, brakmo wrote:
> Adds support for fq's Earliest Departure Time to HBM (Host Bandwidth
> Manager
4 4865 0.00 156 306 425 759 1520 10 16
dctcp 5G4 4936 0.00 128 485 221 409 148479
dctcp-edt 5G4 4924 0.00 148 390 392 623 1508 11 26
v1 -> v2: Incorporated Andrii's suggestions
Signed-off-by: Lawrence Brakmo
---
v.o 840731904 6801 7002
> bpf_overlay.o 542023569 4754 4858
> bpf_lxc_jit.o 39389 35944550925 69631
> Overall precision tracking is still very effective.
>
> Fixes: b5dc0163d8fd ("bpf: precise scalar_val
4 4865 0.00 156 306 425 759 1520 10 16
dctcp 5G4 4936 0.00 128 485 221 409 148479
dctcp-edt 5G4 4924 0.00 148 390 392 623 1508 11 26
Signed-off-by: Lawrence Brakmo
---
samples/bpf/Makefile | 2 +
samples/bpf/do_hbm_tes
return -EPERM if any attached
program was found and if it returned != 1 during execution. Otherwise 0
is returned.
Signed-off-by: Lawrence Brakmo
---
kernel/bpf/cgroup.c | 25 -
1 file changed, 20 insertions(+), 5 deletions(-)
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf
Adds more stats to HBM, including average cwnd and rtt of all TCP
flows, percents of packets that are ecn ce marked and distribution
of return values.
Signed-off-by: Lawrence Brakmo
---
samples/bpf/hbm.c | 33 +++
samples/bpf/hbm.h | 6
samples/bpf
Update BPF_CGROUP_RUN_PROG_INET_EGRESS() callers to support returning
congestion notifications from the BPF programs.
Signed-off-by: Lawrence Brakmo
Signed-off-by: Alexei Starovoitov
---
net/ipv4/ip_output.c | 34 +++---
net/ipv6/ip6_output.c | 26
Update hbm_out_kern.c to support returning cn notifications.
Also updates relevant files to allow disabling cn notifications.
Signed-off-by: Lawrence Brakmo
---
samples/bpf/do_hbm_test.sh | 10 +++---
samples/bpf/hbm.c | 18 +++---
samples/bpf/hbm.h | 3
will
break backward compatibility.
This patch adds a enforce_expected_attach_type bit to only
enforce the expected_attach_type when it uses the new
return value.
Signed-off-by: Lawrence Brakmo
Signed-off-by: Martin KaFai Lau
---
include/linux/filter.h | 3 ++-
kernel/bpf/syscall.c | 12
hanges
v3->v4: Replaced preempt_enable_no_resched() by preempt_enable()
in BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY() macro
brakmo (6):
bpf: Create BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY
bpf: cgroup inet skb programs can return 0 to 3
bpf: Update __cgroup_bpf_run_filter_skb with
skb should be dropped (no cn)
Note that when more than one BPF program is called, the packet is
dropped if at least one of programs requests it be dropped, and
there is cn if at least one program returns cn.
Signed-off-by: Lawrence Brakmo
---
include/linux/bpf.h | 50
On 5/28/19, 1:43 PM, "Eric Dumazet" wrote:
On 5/28/19 11:54 AM, Lawrence Brakmo wrote:
> On 5/28/19, 6:43 AM, "netdev-ow...@vger.kernel.org on behalf of Eric
Dumazet"
wrote:
>
> Why are you using preempt_enable_no_resched() here ?
On 5/28/19, 6:43 AM, "netdev-ow...@vger.kernel.org on behalf of Eric Dumazet"
wrote:
On 5/27/19 8:49 PM, brakmo wrote:
> Create new macro BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY() to be used by
> __cgroup_bpf_run_filter_skb for EGRESS BPF progs so
Update BPF_CGROUP_RUN_PROG_INET_EGRESS() callers to support returning
congestion notifications from the BPF programs.
Signed-off-by: Lawrence Brakmo
Signed-off-by: Alexei Starovoitov
---
net/ipv4/ip_output.c | 34 +++---
net/ipv6/ip6_output.c | 26
Update hbm_out_kern.c to support returning cn notifications.
Also updates relevant files to allow disabling cn notifications.
Signed-off-by: Lawrence Brakmo
---
samples/bpf/do_hbm_test.sh | 10 +++---
samples/bpf/hbm.c | 18 +++---
samples/bpf/hbm.h | 3
Adds more stats to HBM, including average cwnd and rtt of all TCP
flows, percents of packets that are ecn ce marked and distribution
of return values.
Signed-off-by: Lawrence Brakmo
---
samples/bpf/hbm.c | 33 +++
samples/bpf/hbm.h | 6
samples/bpf
return -EPERM if any attached
program was found and if it returned != 1 during execution. Otherwise 0
is returned.
Signed-off-by: Lawrence Brakmo
---
kernel/bpf/cgroup.c | 25 -
1 file changed, 20 insertions(+), 5 deletions(-)
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf
hanges
brakmo (6):
bpf: Create BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY
bpf: cgroup inet skb programs can return 0 to 3
bpf: Update __cgroup_bpf_run_filter_skb with cn
bpf: Update BPF_CGROUP_RUN_PROG_INET_EGRESS calls
bpf: Add cn support to hbm_out_kern.c
bpf: Add more stats to HBM
i
skb should be dropped (no cn)
Note that when more than one BPF program is called, the packet is
dropped if at least one of programs requests it be dropped, and
there is cn if at least one program returns cn.
Signed-off-by: Lawrence Brakmo
---
include/linux/bpf.h | 50
will
break backward compatibility.
This patch adds a enforce_expected_attach_type bit to only
enforce the expected_attach_type when it uses the new
return value.
Signed-off-by: Lawrence Brakmo
Signed-off-by: Martin KaFai Lau
---
include/linux/filter.h | 3 ++-
kernel/bpf/syscall.c | 12
On 4/8/19, 10:39 AM, "Yuchung Cheng" wrote:
On Mon, Apr 8, 2019 at 10:07 AM Eric Dumazet wrote:
>
>
>
> On 04/08/2019 09:16 AM, Neal Cardwell wrote:
> > On Wed, Apr 3, 2019 at 8:13 PM brakmo wrote:
> >>
> >> When
On 4/8/19, 10:07 AM, "Eric Dumazet" wrote:
On 04/08/2019 09:16 AM, Neal Cardwell wrote:
> On Wed, Apr 3, 2019 at 8:13 PM brakmo wrote:
>>
>> When a packet is dropped when calling queue_xmit in __tcp_transmit_skb
>> and packets_ou
at 8:13 PM brakmo wrote:
>
> When a packet is dropped when calling queue_xmit in __tcp_transmit_skb
> and packets_out is 0, it is beneficial to set a small probe timer.
> Otherwise, the throughput for the flow can suffer because it may need to
> depend on the probe tim
Update BPF_CGROUP_RUN_PROG_INET_EGRESS() callers to support returning
congestion notifications from the BPF programs.
Signed-off-by: Lawrence Brakmo
Signed-off-by: Alexei Starovoitov
---
net/ipv4/ip_output.c | 34 +++---
net/ipv6/ip6_output.c | 26
0 and TCP_RTO_MIN. A value of 0
disables setting the probe timer with a small value.
Signed-off-by: Lawrence Brakmo
---
include/net/netns/ipv4.h | 1 +
net/ipv4/sysctl_net_ipv4.c | 10 ++
net/ipv4/tcp_ipv4.c| 1 +
net/ipv4/tcp_output.c | 18 +++---
4 files
Adds more stats to HBM, including average cwnd and rtt of all TCP
flows, percents of packets that are ecn ce marked and distribution
of return values.
Signed-off-by: Lawrence Brakmo
---
samples/bpf/hbm.c | 33 +++
samples/bpf/hbm.h | 6
samples/bpf
return -EPERM if any attached
program was found and if it returned != 1 during execution. Otherwise 0
is returned.
Signed-off-by: Lawrence Brakmo
---
kernel/bpf/cgroup.c | 25 -
1 file changed, 20 insertions(+), 5 deletions(-)
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf
skb should be dropped (no cn)
Note that when more than one BPF program is called, the packet is
dropped if at least one of programs requests it be dropped, and
there is cn if at least one program returns cn.
Signed-off-by: Lawrence Brakmo
---
include/linux/bpf.h | 50
Update hbm_out_kern.c to support returning cn notifications.
Also updates relevant files to allow disabling cn notifications.
Signed-off-by: Lawrence Brakmo
---
samples/bpf/do_hbm_test.sh | 10 +++---
samples/bpf/hbm.c | 18 +++---
samples/bpf/hbm.h | 3
will
break backward compatibility.
This patch adds a enforce_expected_attach_type bit to only
enforce the expected_attach_type when it uses the new
return value.
Signed-off-by: Lawrence Brakmo
Signed-off-by: Martin KaFai Lau
---
include/linux/filter.h | 3 ++-
kernel/bpf/syscall.c | 12
-202 0.48333 -199 0.50
200M,20, 5,cn 1992 -209 0.38 1991 -214 0.30
Notes:
--no_cn has no effect with DCTCP
Lim = rate limit
Prob = Probe timer
DA = maximum delay ack timer
cred = credit in packets
drops = % packets dropped
brakmo (7):
bpf: Create
On 3/23/19, 10:12 AM, "Eric Dumazet" wrote:
On 03/23/2019 01:05 AM, brakmo wrote:
> This patchset adds support for propagating congestion notifications (cn)
> to TCP from cgroup inet skb egress BPF programs.
>
> Current cgroup skb BPF progr
1992 -209 0.38 1991 -214 0.30
Notes:
--no_cn has no effect with DCTCP
Lim = rate limit
Prob = Probe timer
DA = maximum delay ack timer
cred = credit in packets
drops = % packets dropped
brakmo (7):
bpf: Create BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY
bpf: cgroup inet skb pro
Adds more stats to HBM, including average cwnd and rtt of all TCP
flows, percents of packets that are ecn ce marked and distribution
of return values.
Signed-off-by: Lawrence Brakmo
---
samples/bpf/hbm.c | 33 +++
samples/bpf/hbm.h | 6
samples/bpf
is not NET_XMIT_SUCCESS,
return it, otherwise return the return value of the call to
BPF_CGROUP_RUN_PROG_INET_EGRESS().
Otherwise, return the return value of the output function.
Signed-off-by: Lawrence Brakmo
---
net/ipv4/ip_output.c | 39 ++-
net/ipv6
0 and TCP_RTO_MIN. A value of 0
disables setting the probe timer with a small value.
Signed-off-by: Lawrence Brakmo
---
include/net/netns/ipv4.h | 1 +
net/ipv4/sysctl_net_ipv4.c | 10 ++
net/ipv4/tcp_ipv4.c| 1 +
net/ipv4/tcp_output.c | 18 +++---
4 files
Update hbm_out_kern.c to support returning cn notifications.
Also updates relevant files to allow disabling cn notifications.
Signed-off-by: Lawrence Brakmo
---
samples/bpf/do_hbm_test.sh | 10 +++---
samples/bpf/hbm.c | 18 +++---
samples/bpf/hbm.h | 3
return -EPERM if any attached
program was found and if it returned != 1 during execution. Otherwise 0
is returned.
Signed-off-by: Lawrence Brakmo
---
kernel/bpf/cgroup.c | 25 -
1 file changed, 20 insertions(+), 5 deletions(-)
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf
will
break backward compatibility.
This patch adds a enforce_expected_attach_type bit to only
enforce the expected_attach_type when it uses the new
return value.
Signed-off-by: Lawrence Brakmo
Signed-off-by: Martin KaFai Lau
---
include/linux/filter.h | 3 ++-
kernel/bpf/syscall.c | 12
skb should be dropped (no cn)
Note that when more than one BPF program is called, the packet is
dropped if at least one of programs requests it be dropped, and
there is cn if at least one program returns cn.
Signed-off-by: Lawrence Brakmo
---
include/linux/bpf.h | 50
M (Network Resource Manager) to HBM (Host
Bandwdith Manager)
* The bpf helper to set ECN ce now checks that the header is writeable
* Removed helper bpf functions that modified TCP state due to a concern
about whether the socket is locked by the current thread.
brakmo (5):
bpf: add
Name defaults to hbm_out_kern.o
More information about HBM can be found in the paper "BPF Host Resource
Management" presented at the 2018 Linux Plumbers Conference, Networking Track
(http://vger.kernel.org/lpc_net2018_talks/LPC%20BPF%20Network%20Resource%20Paper.pdf)
Signed-off-by: Lawrenc
A latter patch provides such a program (hbm.c)
Signed-off-by: Lawrence Brakmo
---
samples/bpf/Makefile | 2 +
samples/bpf/hbm.h | 31
samples/bpf/hbm_kern.h | 137
samples/bpf/hbm_out_kern.c | 157 +
This works best when using DCTCP.
Signed-off-by: Lawrence Brakmo
Signed-off-by: Martin KaFai Lau
---
include/uapi/linux/bpf.h | 10 +-
net/core/filter.c| 28
2 files changed, 37 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/bpf.h b/in
This patch syncs the uapi bpf.h to tools/ and also updates
bpf_herlpers.h in tools/
Signed-off-by: Lawrence Brakmo
---
tools/include/uapi/linux/bpf.h| 10 +-
tools/testing/selftests/bpf/bpf_helpers.h | 2 ++
2 files changed, 11 insertions(+), 1 deletion(-)
diff --git a
st the
rate is 8Gbps vs. 1Gbps of the previous test.
Signed-off-by: Lawrence Brakmo
---
samples/bpf/do_hbm_test.sh | 436 +
1 file changed, 436 insertions(+)
create mode 100755 samples/bpf/do_hbm_test.sh
diff --git a/samples/bpf/do_hbm_test.sh b/samples/bpf
This test ensures the verifier has checked the arg1 of
BPF_FUNC_tcp_enter_cwr is of ARG_PTR_TO_TCP_SOCK type.
Signed-off-by: Martin KaFai Lau
Signed-off-by: Lawrence Brakmo
---
tools/testing/selftests/bpf/verifier/sock.c | 33 +
1 file changed, 33 insertions(+)
diff --git
This works best when using DCTCP.
Signed-off-by: Lawrence Brakmo
---
include/uapi/linux/bpf.h | 10 +-
net/core/filter.c| 14 ++
2 files changed, 23 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 95b5058fa945..fc646f3ea
enforced if this new helper
is used by the prog.
Signed-off-by: Lawrence Brakmo
Signed-off-by: Martin KaFai Lau
---
include/linux/bpf.h | 1 +
include/linux/filter.h | 3 ++-
include/uapi/linux/bpf.h | 9 -
kernel/bpf/syscall.c | 12
kernel/bpf/verifier.c
This patch syncs the uapi bpf.h to tools/ and also updates
bpf_herlpers.h in tools/
Signed-off-by: Lawrence Brakmo
---
tools/include/uapi/linux/bpf.h| 27 ++-
tools/testing/selftests/bpf/bpf_helpers.h | 6 +
2 files changed, 32 insertions(+), 1 deletion
proto implementations
to avoid compiler error.
Signed-off-by: Martin KaFai Lau
Signed-off-by: Lawrence Brakmo
---
drivers/media/rc/bpf-lirc.c | 2 +-
include/linux/bpf.h | 2 +-
kernel/bpf/cgroup.c | 2 +-
kernel/trace/bpf_trace.c| 10 +-
ne
unction allows for setting a smaller probe timer.
Signed-off-by: Lawrence Brakmo
---
include/uapi/linux/bpf.h | 12 +++-
net/core/filter.c| 32
2 files changed, 43 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/li
)
Signed-off-by: Lawrence Brakmo
---
samples/bpf/Makefile | 3 +
samples/bpf/nrm.c| 440 +++
2 files changed, 443 insertions(+)
create mode 100644 samples/bpf/nrm.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 897b467066fd..6186c9fc317
ides such a program (nrm.c)
Signed-off-by: Lawrence Brakmo
---
samples/bpf/Makefile | 2 +
samples/bpf/nrm.h | 31 ++
samples/bpf/nrm_kern.h | 137 ++
samples/bpf/nrm_out_kern.c | 190 +
4 files changed, 360 i
he program netserver manually on
the remote host. It will use 1 flow, a rate limit of 2Gbps and dctcp.
./do_nrm_test.sh -f=1 -r=2000 -t=5 -N -D --stats -w dctcp \
-s=
As previous, but allows use of extra bandwidth. For this test the
rate is 8Gbps vs. 1Gbps of the previous test.
ECN_ defines instead of integers.
* NRM script test program now uses bpftool instead of load_cg_skb
Martin KaFai Lau (2):
bpf: Remove const from get_func_proto
bpf: Add bpf helper bpf_tcp_enter_cwr
brakmo (7):
bpf: Test bpf_tcp_enter_cwr in test_verifier
bpf: add bpf helper bpf_skb_ecn_s
On 2/19/19, 10:30 AM, "Eric Dumazet" wrote:
On 02/18/2019 09:38 PM, brakmo wrote:
> This patch adds a new bpf helper BPF_FUNC_skb_set_ecn
> "int bpf_skb_set_Ecn(struct sk_buff *skb)". It is added to
> BPF_PROG_TYPE_CGROUP_SKB typed bpf_prog
On 2/19/19, 10:30 AM, "Eric Dumazet" wrote:
On 02/18/2019 09:38 PM, brakmo wrote:
> This patch adds a new bpf helper BPF_FUNC_tcp_enter_cwr
> "int bpf_tcp_enter_cwr(struct bpf_tcp_sock *tp)".
> It is added to BPF_PROG_TYPE_CGROUP_SKB typed b
On 2/19/19, 2:52 AM, "netdev-ow...@vger.kernel.org on behalf of Daniel
Borkmann"
wrote:
On 02/19/2019 06:38 AM, brakmo wrote:
> This patch adds a new bpf helper BPF_FUNC_skb_set_ecn
> "int bpf_skb_set_Ecn(struct sk_buff *skb)". It is added to
> B
On 2/19/19, 2:24 AM, "Daniel Borkmann" wrote:
On 02/19/2019 06:38 AM, brakmo wrote:
> This patch adds a new bpf helper BPF_FUNC_tcp_enter_cwr
> "int bpf_tcp_enter_cwr(struct bpf_tcp_sock *tp)".
> It is added to BPF_PROG_TYPE_CGROUP_SKB typed bpf_p
On 2/19/19, 10:29 AM, "netdev-ow...@vger.kernel.org on behalf of Eric Dumazet"
wrote:
On 02/18/2019 09:38 PM, brakmo wrote:
> +
> +static __always_inline void get_nrm_pkt_info(struct bpf_sock *sk,
> + struct
This test ensures the verifier has checked the arg1 of
BPF_FUNC_tcp_enter_cwr is of ARG_PTR_TO_TCP_SOCK type.
Signed-off-by: Martin KaFai Lau
Signed-off-by: Lawrence Brakmo
---
tools/testing/selftests/bpf/verifier/sock.c | 33 +
1 file changed, 33 insertions(+)
diff --git
ot;-i" is used, the program is attached as ingress (default is
egress).
load_cg_skb -r[i]
Detaches the currnetly attached egress (or ingress if -ri is used)
cg skb program from the specified cgroup.
Signed-off-by: Lawrence Brakmo
---
samples/bpf/Makefile | 2 +
s
This patch syncs the uapi bpf.h to tools/ and also updates
bpf_herlpers.h in tools/
Signed-off-by: Lawrence Brakmo
---
tools/include/uapi/linux/bpf.h| 27 ++-
tools/testing/selftests/bpf/bpf_helpers.h | 6 +
2 files changed, 32 insertions(+), 1 deletion
used
by a bpf_prog to manage egress network bandwidth limit per
cgroupv2. A later patch will have a sample program to
show how it can be used to limit bandwidth usage per cgroupv2.
Signed-off-by: Lawrence Brakmo
Signed-off-by: Martin KaFai Lau
---
include/linux/bpf.h | 1 +
include/uapi/linux/
he program netserver manually on
the remote host. It will use 1 flow, a rate limit of 2Gbps and dctcp.
./do_nrm_test.sh -f=1 -r=2000 -t=5 -N -D --stats -w dctcp \
-s=
As previous, but allows use of extra bandwidth. For this test the
rate is 8Gbps vs. 1Gbps of the previous test.
ides such a program (nrm.c)
Signed-off-by: Lawrence Brakmo
---
samples/bpf/Makefile | 2 +
samples/bpf/nrm.h | 31 ++
samples/bpf/nrm_kern.h | 109 +++
samples/bpf/nrm_out_kern.c | 213 +
4 files changed, 355 i
)
Signed-off-by: Lawrence Brakmo
---
samples/bpf/Makefile | 3 +
samples/bpf/nrm.c| 439 +++
2 files changed, 442 insertions(+)
create mode 100644 samples/bpf/nrm.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 86633af239d4..248a88355a6
Signed-off-by: Lawrence Brakmo
---
include/uapi/linux/bpf.h | 12 +++-
net/core/filter.c| 27 +++
2 files changed, 38 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 5daf404511f7..a78936acccae 100644
---
sed to set the ECN bits (2) of the IPv6 or IPv4
header in skb. It can be used by a bpf_prog to manage egress
network bandwdith limit per cgroupv2 by inducing an ECN
response in the TCP sender (when the packet is ECN enabled).
This works best when using DCTCP.
Signed-off-by: Lawrence Brakmo
---
in
vided in an
upcomming patchset.
brakmo (9):
bpf: Add bpf helper bpf_tcp_enter_cwr
bpf: Test bpf_tcp_enter_cwr in test_verifier
bpf: add bpf helper bpf_skb_set_ecn
bpf: Add bpf helper bpf_tcp_check_probe_timer
bpf: sync bpf.h to tools and update bpf_helpers.h
bpf: Sample program to lo
On 2/3/19, 12:15 AM, "Yafang Shao" wrote:
Then we can enable/disable socket debugging without modifying user code.
That is more convenient for debugging.
Signed-off-by: Yafang Shao
Acked-by: Lawrence Brakmo
---
include/net/sock.h | 8
net/cor
it will
make it more consistent with the bpf_setsockopt() above.
Acked-by: Martin KaFai Lau
Cc: Lawrence Brakmo
Acked-by: Lawrence Brakmo
>
> Signed-off-by: Yafang Shao
> ---
> net/core/filter.c | 2 +-
> 1 file chan
Yafang Shao
For bug fixes, please target the bpf branch instead of bpf-next
and please also add the Fixes tag:
Fixes: 8c4b4c7e9ff0 ("bpf: Add setsockopt helper function to bpf")
Patch LGTM,
Acked-by: Martin KaFai Lau
Cc: Lawrence Brakmo, thought?
t;= 0 || tp->data_segs_out >
tp->syn_data)
ret = -EINVAL;
else
tp->snd_cwnd = val;
--
2.20.1.97.g81188d93c3-goog
Looks good to me.
Acked-by: Lawrence Brakmo
Note that without this fix the 99% latencies when doing 10KB RPCs in a
congested network using DCTCP are 40ms vs. 190us with the patch. Also note that
these 40ms high tail latencies started after commit
3759824da87b30ce7a35b4873b62b0ba38905ef5 in Jul 2015, which triggered the
bugs/features we a
01(0) ack 4 win 257
Modified based on comments by Neal Cardwell
Signed-off-by: Lawrence Brakmo
---
net/ipv4/tcp_input.c | 9 -
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 91dbb9afb950..2370fd79c5c5 100644
--- a/net/ipv4/tcp_inp
LGTM. Thank you for adding the listen callback and cleaning up the test.
Acked-by: Lawrence Brakmo
On 7/11/18, 8:34 PM, "Andrey Ignatov" wrote:
This patchset adds TCP-BPF callback for listening sockets.
Patch 0001 provides more details and is the main patch
cknowledging the latest data until the
sender times out and retry in some cases.
Packetdrill script (provided by Larry Brakmo)
0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
0.000 setsockopt(3, SOL_TCP, TCP_CONGES
LGTM. Thanks for the patch.
Acked-by: Lawrence Brakmo
On 7/12/18, 9:05 AM, "Yuchung Cheng" wrote:
After fixing the way DCTCP tracking delayed ACKs, the delayed-ACK
related callbacks are no longer needed
Signed-off-by: Yuchung Cheng
Signed-off-by: Eric Dumazet
On 7/9/18, 12:32 PM, "Yuchung Cheng" wrote:
On Sat, Jul 7, 2018 at 7:07 AM, Neal Cardwell wrote:
> On Sat, Jul 7, 2018 at 7:15 AM David Miller wrote:
>>
>> From: Lawrence Brakmo
>> Date: Tue, 3 Jul 2018 09:26:13 -0700
>>
>&g
On 7/3/18, 6:15 AM, "Neal Cardwell" wrote:
On Mon, Jul 2, 2018 at 7:49 PM Yuchung Cheng wrote:
>
> On Mon, Jul 2, 2018 at 2:39 PM, Lawrence Brakmo wrote:
> >
> > DCTCP depends on the CA_EVENT_NON_DELAYED_ACK and CA_EVENT_DELAYED_ACK
> >
roved based on comments from Neal Cardwell .
Signed-off-by: Lawrence Brakmo
---
net/ipv4/tcp_output.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f8f6129160dd..acefb64e8280 100644
--- a/net/ipv4/tcp_output.c
+++ b/net
arrives, the ACK was sometimes delayed even though it
is CWR marked, adding up to 40ms to the RPC latency.
This patch insures that CWR makred data packets arriving will be acked
immediately.
Modified based on comments by Neal Cardwell
Signed-off-by: Lawrence Brakmo
---
net/ipv4/tcp_input.c | 9
When have observed high tail latencies when using DCTCP for RPCs as
compared to using Cubic. For example, in one setup there are 2 hosts
sending to a 3rd one, with each sender having 3 flows (1 stream,
1 1MB back-to-back RPCs and 1 10KB back-to-back RPCs). The following
table shows the 99% and 99.9
On 7/2/18, 4:50 PM, "Yuchung Cheng" wrote:
On Mon, Jul 2, 2018 at 2:39 PM, Lawrence Brakmo wrote:
>
> DCTCP depends on the CA_EVENT_NON_DELAYED_ACK and CA_EVENT_DELAYED_ACK
> notifications to keep track if it needs to send an ACK for packets that
>
On 7/2/18, 5:52 PM, "netdev-ow...@vger.kernel.org on behalf of Neal Cardwell"
wrote:
On Mon, Jul 2, 2018 at 5:39 PM Lawrence Brakmo wrote:
>
> When have observed high tail latencies when using DCTCP for RPCs as
> compared to using Cubic. For example, in on
When have observed high tail latencies when using DCTCP for RPCs as
compared to using Cubic. For example, in one setup there are 2 hosts
sending to a 3rd one, with each sender having 3 flows (1 stream,
1 1MB back-to-back RPCs and 1 10KB back-to-back RPCs). The following
table shows the 99% and 99.9
arrives, the ACK was sometimes delayed even though it
is CWR marked, adding up to 40ms to the RPC latency.
This patch insures that CWR makred data packets arriving will be acked
immediately.
Modified based on comments by Neal Cardwell
Signed-off-by: Lawrence Brakmo
---
net/ipv4/tcp_input.c
roved based on comments from Neal Cardwell .
Signed-off-by: Lawrence Brakmo
---
net/ipv4/tcp_output.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f8f6129160dd..acefb64e8280 100644
--- a/net/ipv4/tcp_output.c
+++ b/net
On 7/2/18, 7:57 AM, "Neal Cardwell" wrote:
On Sat, Jun 30, 2018 at 9:47 PM Lawrence Brakmo wrote:
> I see two issues, one is that entering quickack mode as you
> mentioned does not insure that it will still be on when the CWR
> arrives. The second issue
On 7/2/18, 8:18 AM, "netdev-ow...@vger.kernel.org on behalf of Neal Cardwell"
wrote:
On Fri, Jun 29, 2018 at 9:48 PM Lawrence Brakmo wrote:
>
> DCTCP depends on the CA_EVENT_NON_DELAYED_ACK and CA_EVENT_DELAYED_ACK
> notifications to keep track if it needs
On 6/30/18, 5:26 PM, "netdev-ow...@vger.kernel.org on behalf of Neal Cardwell"
wrote:
On Fri, Jun 29, 2018 at 9:48 PM Lawrence Brakmo wrote:
>
> When have observed high tail latencies when using DCTCP for RPCs as
> compared to using Cubic. For example, in on
On 6/30/18, 11:23 AM, "Neal Cardwell" wrote:
On Fri, Jun 29, 2018 at 9:48 PM Lawrence Brakmo wrote:
>
> We observed high 99 and 99.9% latencies when doing RPCs with DCTCP. The
> problem is triggered when the last packet of a request arrives CE
> marked
arrives it was sometimes delayed adding up to 40ms to
the latency.
This patch insures that CWR makred data packets arriving will be acked
immediately.
Signed-off-by: Lawrence Brakmo
---
net/ipv4/tcp_input.c | 25 +
1 file changed, 17 insertions(+), 8 deletions(-)
diff
igned-off-by: Lawrence Brakmo
---
net/ipv4/tcp_output.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f8f6129160dd..41f6ad7a21e4 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -172,6 +172,8 @@ static inline
1 - 100 of 467 matches
Mail list logo
