mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-25 11:30:54 +07:00
0fb1170ee6
BPF offers another way to generate latency histograms. We attach
kprobes at trace_preempt_off and trace_preempt_on and calculate the
time it takes to from seeing the off/on transition.
The first array is used to store the start time stamp. The key is the
CPU id. The second array stores the log2(time diff). We need to use
static allocation here (array and not hash tables). The kprobes
hooking into trace_preempt_on|off should not calling any dynamic
memory allocation or free path. We need to avoid recursivly
getting called. Besides that, it reduces jitter in the measurement.
CPU 0
latency : count distribution
1 -> 1 : 0 | |
2 -> 3 : 0 | |
4 -> 7 : 0 | |
8 -> 15 : 0 | |
16 -> 31 : 0 | |
32 -> 63 : 0 | |
64 -> 127 : 0 | |
128 -> 255 : 0 | |
256 -> 511 : 0 | |
512 -> 1023 : 0 | |
1024 -> 2047 : 0 | |
2048 -> 4095 : 166723 |*************************************** |
4096 -> 8191 : 19870 |*** |
8192 -> 16383 : 6324 | |
16384 -> 32767 : 1098 | |
32768 -> 65535 : 190 | |
65536 -> 131071 : 179 | |
131072 -> 262143 : 18 | |
262144 -> 524287 : 4 | |
524288 -> 1048575 : 1363 | |
CPU 1
latency : count distribution
1 -> 1 : 0 | |
2 -> 3 : 0 | |
4 -> 7 : 0 | |
8 -> 15 : 0 | |
16 -> 31 : 0 | |
32 -> 63 : 0 | |
64 -> 127 : 0 | |
128 -> 255 : 0 | |
256 -> 511 : 0 | |
512 -> 1023 : 0 | |
1024 -> 2047 : 0 | |
2048 -> 4095 : 114042 |*************************************** |
4096 -> 8191 : 9587 |** |
8192 -> 16383 : 4140 | |
16384 -> 32767 : 673 | |
32768 -> 65535 : 179 | |
65536 -> 131071 : 29 | |
131072 -> 262143 : 4 | |
262144 -> 524287 : 1 | |
524288 -> 1048575 : 364 | |
CPU 2
latency : count distribution
1 -> 1 : 0 | |
2 -> 3 : 0 | |
4 -> 7 : 0 | |
8 -> 15 : 0 | |
16 -> 31 : 0 | |
32 -> 63 : 0 | |
64 -> 127 : 0 | |
128 -> 255 : 0 | |
256 -> 511 : 0 | |
512 -> 1023 : 0 | |
1024 -> 2047 : 0 | |
2048 -> 4095 : 40147 |*************************************** |
4096 -> 8191 : 2300 |* |
8192 -> 16383 : 828 | |
16384 -> 32767 : 178 | |
32768 -> 65535 : 59 | |
65536 -> 131071 : 2 | |
131072 -> 262143 : 0 | |
262144 -> 524287 : 1 | |
524288 -> 1048575 : 174 | |
CPU 3
latency : count distribution
1 -> 1 : 0 | |
2 -> 3 : 0 | |
4 -> 7 : 0 | |
8 -> 15 : 0 | |
16 -> 31 : 0 | |
32 -> 63 : 0 | |
64 -> 127 : 0 | |
128 -> 255 : 0 | |
256 -> 511 : 0 | |
512 -> 1023 : 0 | |
1024 -> 2047 : 0 | |
2048 -> 4095 : 29626 |*************************************** |
4096 -> 8191 : 2704 |** |
8192 -> 16383 : 1090 | |
16384 -> 32767 : 160 | |
32768 -> 65535 : 72 | |
65536 -> 131071 : 32 | |
131072 -> 262143 : 26 | |
262144 -> 524287 : 12 | |
524288 -> 1048575 : 298 | |
All this is based on the trace3 examples written by
Alexei Starovoitov <ast@plumgrid.com>.
Signed-off-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: linux-kernel@vger.kernel.org
Cc: netdev@vger.kernel.org
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
63 lines
2.0 KiB
Makefile
63 lines
2.0 KiB
Makefile
# kbuild trick to avoid linker error. Can be omitted if a module is built.
|
|
obj- := dummy.o
|
|
|
|
# List of programs to build
|
|
hostprogs-y := test_verifier test_maps
|
|
hostprogs-y += sock_example
|
|
hostprogs-y += sockex1
|
|
hostprogs-y += sockex2
|
|
hostprogs-y += sockex3
|
|
hostprogs-y += tracex1
|
|
hostprogs-y += tracex2
|
|
hostprogs-y += tracex3
|
|
hostprogs-y += tracex4
|
|
hostprogs-y += tracex5
|
|
hostprogs-y += lathist
|
|
|
|
test_verifier-objs := test_verifier.o libbpf.o
|
|
test_maps-objs := test_maps.o libbpf.o
|
|
sock_example-objs := sock_example.o libbpf.o
|
|
sockex1-objs := bpf_load.o libbpf.o sockex1_user.o
|
|
sockex2-objs := bpf_load.o libbpf.o sockex2_user.o
|
|
sockex3-objs := bpf_load.o libbpf.o sockex3_user.o
|
|
tracex1-objs := bpf_load.o libbpf.o tracex1_user.o
|
|
tracex2-objs := bpf_load.o libbpf.o tracex2_user.o
|
|
tracex3-objs := bpf_load.o libbpf.o tracex3_user.o
|
|
tracex4-objs := bpf_load.o libbpf.o tracex4_user.o
|
|
tracex5-objs := bpf_load.o libbpf.o tracex5_user.o
|
|
lathist-objs := bpf_load.o libbpf.o lathist_user.o
|
|
|
|
# Tell kbuild to always build the programs
|
|
always := $(hostprogs-y)
|
|
always += sockex1_kern.o
|
|
always += sockex2_kern.o
|
|
always += sockex3_kern.o
|
|
always += tracex1_kern.o
|
|
always += tracex2_kern.o
|
|
always += tracex3_kern.o
|
|
always += tracex4_kern.o
|
|
always += tracex5_kern.o
|
|
always += tcbpf1_kern.o
|
|
always += lathist_kern.o
|
|
|
|
HOSTCFLAGS += -I$(objtree)/usr/include
|
|
|
|
HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
|
|
HOSTLOADLIBES_sockex1 += -lelf
|
|
HOSTLOADLIBES_sockex2 += -lelf
|
|
HOSTLOADLIBES_sockex3 += -lelf
|
|
HOSTLOADLIBES_tracex1 += -lelf
|
|
HOSTLOADLIBES_tracex2 += -lelf
|
|
HOSTLOADLIBES_tracex3 += -lelf
|
|
HOSTLOADLIBES_tracex4 += -lelf -lrt
|
|
HOSTLOADLIBES_tracex5 += -lelf
|
|
HOSTLOADLIBES_lathist += -lelf
|
|
|
|
# point this to your LLVM backend with bpf support
|
|
LLC=$(srctree)/tools/bpf/llvm/bld/Debug+Asserts/bin/llc
|
|
|
|
$(obj)/%.o: $(src)/%.c
|
|
clang $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \
|
|
-D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \
|
|
-O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
|