From: Tao Cui <[email protected]> Add a second example cost model which replaces the builtin single-cursor sequentiality heuristic with a per-cgroup table of stream slots: an IO is sequential iff its sector matches the expected next sector of any tracked stream. Interleaved sequential readers in one cgroup keep their own slots instead of ping-ponging a single cursor, and random IO inside a hot window rarely matches a moving expectation. Merged bios skip the base cost but still advance the matched stream position, so a merge at the expected sector does not make the following new IO look random.
Stream state lives in a CGRP_STORAGE map keyed by the cgroup of the blkcg argument, following the cgroup lifetime; there is no fixed-size registry to exhaust. Measured (QEMU, virtio-blk with the HDD profile, 4k IOs, w=1000): two sequential readers in one cgroup are priced 1961us/op by the builtin model (judged random) and 23us/op by this model (judged sequential), the completed IO count rises from 4495 to 207505; random IO inside an 8M window is priced 24us/op by builtin (undercharge) and 2607us/op by this model; single-stream sequential and whole-disk random pricing are unchanged. Stream updates are lockless like the builtin cursor; a lost update misclassifies a single IO. Slots are only advanced for bios the builtin prices. The streams test lives here with the model it loads. The page count truncates like the builtin. Signed-off-by: Tao Cui <[email protected]> --- .../selftests/bpf/prog_tests/iocost_model.c | 34 ++++ tools/testing/selftests/bpf/progs/iocost_ms.c | 156 ++++++++++++++++++ 2 files changed, 190 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/iocost_ms.c diff --git a/tools/testing/selftests/bpf/prog_tests/iocost_model.c b/tools/testing/selftests/bpf/prog_tests/iocost_model.c index bf9f245e29a52..db0a74b1885be 100644 --- a/tools/testing/selftests/bpf/prog_tests/iocost_model.c +++ b/tools/testing/selftests/bpf/prog_tests/iocost_model.c @@ -4,6 +4,7 @@ #include <fcntl.h> #include <unistd.h> #include "iocost_model.skel.h" +#include "iocost_ms.skel.h" /* * Write a line to io.cost.model with write(2) and return the errno of @@ -164,3 +165,36 @@ void serial_test_iocost_model(void) iocost_model__destroy(skel); } + +/* + * Same check for the multi-stream example model. Only one model can + * be bound to a device at a time; both tests bind and restore, so + * they are serial and independent. + */ +void serial_test_iocost_model_streams(void) +{ + struct iocost_ms *skel; + char *dev; + int err; + + dev = getenv("IOCOST_TEST_DEV"); + if (!dev || geteuid() != 0) { + test__skip(); + return; + } + if (!dev_has_iocost(dev)) { + printf("skip: %s has no iocost enabled\n", dev); + test__skip(); + return; + } + + skel = iocost_ms__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_load")) + return; + + err = iocost_ms__attach(skel); + if (ASSERT_OK(err, "attach")) + ASSERT_OK(bind_model(dev, "iocost_ms"), "bind_and_readback"); + + iocost_ms__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/iocost_ms.c b/tools/testing/selftests/bpf/progs/iocost_ms.c new file mode 100644 index 0000000000000..2a3c1d6aae4df --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iocost_ms.c @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Example multi-stream sequentiality detection cost model. + * + * The builtin model keeps a single cursor per cgroup, so two + * interleaved sequential readers in one cgroup are all priced random + * (measured 89x overcharge, 12.9x throughput collapse), while random + * IO inside a hot window smaller than the 16MB seek threshold is + * priced sequential (measured 107x undercharge). This model replaces + * the single cursor with a per-cgroup table of stream slots: an IO is + * sequential iff its sector matches the expected next sector of any + * tracked stream. Interleaved streams keep their own slots, and + * windowed random IO rarely matches a moving expectation. + * + * Stream state lives in a CGRP_STORAGE map, so it is created and + * freed with the cgroup. The model implements the full builtin + * linear formula itself, including flush pricing. + */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +/* VTIME_PER_SEC comes from vmlinux.h (a BTF enum constant) */ +#define IOC_PAGE_SIZE 4096 +#define IOC_SECT_TO_PAGE_SHIFT 3 /* 512B sectors to 4kB pages */ +#define IOCOST_COST_F_MERGE (1ULL << 0) /* not in BTF: a plain macro */ +#define IOCOST_REQ_OP_MASK 0xff /* REQ_OP_MASK, not in BTF */ + +/* + * DIV64_U64_ROUND_UP / DIV_ROUND_UP_ULL equivalents, folded at + * compile time + */ +#define RU(x, y) ((x) / (y) + (((x) % (y)) ? 1 : 0)) + +#define RBPS 174019176ULL +#define RSEQIOPS 41708ULL +#define RRANDIOPS 370ULL +#define WBPS 178075866ULL +#define WSEQIOPS 42705ULL +#define WRANDIOPS 378ULL + +#define RPAGE (RU(VTIME_PER_SEC, RU(RBPS, IOC_PAGE_SIZE))) +#define RSEQIO (RU(VTIME_PER_SEC, RSEQIOPS) - RPAGE) +#define RRANDIO (RU(VTIME_PER_SEC, RRANDIOPS) - RPAGE) +#define WPAGE (RU(VTIME_PER_SEC, RU(WBPS, IOC_PAGE_SIZE))) +#define WSEQIO (RU(VTIME_PER_SEC, WSEQIOPS) - WPAGE) +#define WRANDIO (RU(VTIME_PER_SEC, WRANDIOPS) - WPAGE) + +#define NSLOTS 4 + +struct streams { + __u64 expected[NSLOTS]; /* next expected sector, per stream */ + __u64 stamp[NSLOTS]; /* LRU stamp, 0 = empty */ +}; + +/* + * per-cgroup stream table: keyed by the cgroup, freed with it + */ +struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct streams); +} stream_tab SEC(".maps"); + +SEC("struct_ops") +u64 BPF_PROG(iocost_ms_calc_cost, u64 opf, u64 nbytes, u64 sector, + struct blkcg *blkcg, u64 model_flags) +{ + struct streams *s; + u64 pages, base, coef_page, randio, advance, now; + u32 i, victim = 0, found = 0xFFFFFFFF; + + if ((opf & IOCOST_REQ_OP_MASK) == REQ_OP_READ) { + base = RSEQIO; coef_page = RPAGE; randio = RRANDIO; + } else if ((opf & IOCOST_REQ_OP_MASK) == REQ_OP_WRITE) { + base = WSEQIO; coef_page = WPAGE; randio = WRANDIO; + } else { + /* + * a fully owning model must price every op; unknown + * ops are priced as per-page writes + */ + base = 0; coef_page = WPAGE; randio = 0; + } + advance = nbytes >> 9; /* whole sectors, like bio_end_sector() */ + + /* only bios the builtin prices participate in stream tracking */ + if (!(((opf & IOCOST_REQ_OP_MASK) == REQ_OP_READ || + (opf & IOCOST_REQ_OP_MASK) == REQ_OP_WRITE) && nbytes)) { + pages = nbytes >> IOC_PAGE_SHIFT; + if (!pages) + pages = 1; + return base + pages * coef_page; + } + + s = bpf_cgrp_storage_get(&stream_tab, blkcg->css.cgroup, NULL, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!s) { + /* no storage: price per page, truncating like the builtin */ + pages = nbytes >> IOC_PAGE_SHIFT; + if (!pages) + pages = 1; + return base + pages * coef_page; + } + + /* + * Slot access is lockless, mirroring the builtin single-cursor + * update in ioc_rqos_throttle(): concurrent CPUs submitting for + * the same cgroup can race on slot updates; mispricing is + * bounded and acceptable for an example model. + */ + now = bpf_ktime_get_ns(); + for (i = 0; i < NSLOTS; i++) { + if (s->expected[i] == sector && s->stamp[i]) { + found = i; + break; + } + } + if (found != 0xFFFFFFFF) { + /* sequential: keep the seq base from the op branch */ + s->expected[found] = sector + advance; + s->stamp[found] = now; + } else { + base = randio; + for (i = 1; i < NSLOTS; i++) { + if (s->stamp[i] < s->stamp[victim]) + victim = i; + } + s->expected[victim] = sector + advance; + s->stamp[victim] = now; + } + + /* builtin truncates: max(sectors >> IOC_SECT_TO_PAGE_SHIFT, 1) */ + pages = nbytes >> IOC_PAGE_SHIFT; + if (!pages) + pages = 1; + if (model_flags & IOCOST_COST_F_MERGE) { + /* + * merged bios skip the base cost but still advance + * the stream position above, so a merge at the + * expected sector does not make the following new IO + * look random + */ + base = 0; + } + + return base + pages * coef_page; +} + +SEC(".struct_ops") +struct iocost_model_ops iocost_ms = { + .calc_cost = (void *)iocost_ms_calc_cost, + .name = "iocost_ms", +}; + +char LICENSE[] SEC("license") = "GPL"; -- 2.43.0
