Currently, sysctl kernel.bpf_stats_enabled controls BPF runtime stats. Typical userspace tools use kernel.bpf_stats_enabled as follows: 1. Enable kernel.bpf_stats_enabled; 2. Check program run_time_ns; 3. Sleep for the monitoring period; 4. Check program run_time_ns again, calculate the difference; 5. Disable kernel.bpf_stats_enabled. The problem with this approach is that only one userspace tool can toggle this sysctl. If multiple tools toggle the sysctl at the same time, the measurement may be inaccurate. To fix this problem while keep backward compatibility, introduce a new bpf command BPF_ENABLE_STATS. On success, this command enables stats and returns a valid fd. BPF_ENABLE_STATS takes argument "type". Currently, only one type, BPF_STATS_RUN_TIME, is supported. We can extend the command to support other types of stats in the future. With BPF_ENABLE_STATS, user space tool would have the following flow: 1. Get a fd with BPF_ENABLE_STATS, and make sure it is valid; 2. Check program run_time_ns; 3. Sleep for the monitoring period; 4. Check program run_time_ns again, calculate the difference; 5. Close the fd.
Showing the changes to include/uapi/linux (1 of 5 files). Show all
Unified · Split
| @@ -115,6 +115,7 @@ enum bpf_cmd { · 114 unmodified lines | |||
| 115 | BPF_LINK_UPDATE, | 115 | BPF_LINK_UPDATE, |
| 116 | BPF_LINK_GET_FD_BY_ID, | 116 | BPF_LINK_GET_FD_BY_ID, |
| 117 | BPF_LINK_GET_NEXT_ID, | 117 | BPF_LINK_GET_NEXT_ID, |
| 118 | BPF_ENABLE_STATS, | ||
| 118 | }; | 119 | }; |
| 119 | 120 | ||
| 120 | enum bpf_map_type { | 121 | enum bpf_map_type { |
| @@ -390,6 +391,12 @@ enum { · 269 unmodified lines | |||
| 390 | */ | 391 | */ |
| 391 | #define BPF_F_QUERY_EFFECTIVE (1U << 0) | 392 | #define BPF_F_QUERY_EFFECTIVE (1U << 0) |
| 392 | 393 | ||
| 394 | /* type for BPF_ENABLE_STATS */ | ||
| 395 | enum bpf_stats_type { | ||
| 396 | /* enabled run_time_ns and run_cnt */ | ||
| 397 | BPF_STATS_RUN_TIME = 0, | ||
| 398 | }; | ||
| 399 | |||
| 393 | enum bpf_stack_build_id_status { | 400 | enum bpf_stack_build_id_status { |
| 394 | /* user space need an empty entry to identify end of a trace */ | 401 | /* user space need an empty entry to identify end of a trace */ |
| 395 | BPF_STACK_BUILD_ID_EMPTY = 0, | 402 | BPF_STACK_BUILD_ID_EMPTY = 0, |
| @@ -601,6 +608,10 @@ union bpf_attr { · 205 unmodified lines | |||
| 601 | __u32 old_prog_fd; | 608 | __u32 old_prog_fd; |
| 602 | } link_update; | 609 | } link_update; |
| 603 | 610 | ||
| 611 | struct { /* struct used by BPF_ENABLE_STATS command */ | ||
| 612 | __u32 type; | ||
| 613 | } enable_stats; | ||
| 614 | |||
| 604 | } __attribute__((aligned(8))); | 615 | } __attribute__((aligned(8))); |
| 605 | 616 | ||
| 606 | /* The description below is an attempt at providing documentation to eBPF | 617 | /* The description below is an attempt at providing documentation to eBPF |