static int run_bpf_prog()

in bpf/hbm.c [163:422]


static int run_bpf_prog(char *prog, int cg_id)
{
	struct hbm_queue_stats qstats = {0};
	char cg_dir[100], cg_pin_path[100];
	struct bpf_link *link = NULL;
	int key = 0;
	int cg1 = 0;
	int rc = 0;

	sprintf(cg_dir, "/hbm%d", cg_id);
	rc = prog_load(prog);
	if (rc != 0)
		return rc;

	if (setup_cgroup_environment()) {
		printf("ERROR: setting cgroup environment\n");
		goto err;
	}
	cg1 = create_and_get_cgroup(cg_dir);
	if (!cg1) {
		printf("ERROR: create_and_get_cgroup\n");
		goto err;
	}
	if (join_cgroup(cg_dir)) {
		printf("ERROR: join_cgroup\n");
		goto err;
	}

	qstats.rate = rate;
	qstats.stats = stats_flag ? 1 : 0;
	qstats.loopback = loopback_flag ? 1 : 0;
	qstats.no_cn = no_cn_flag ? 1 : 0;
	if (bpf_map_update_elem(queue_stats_fd, &key, &qstats, BPF_ANY)) {
		printf("ERROR: Could not update map element\n");
		goto err;
	}

	if (!outFlag)
		bpf_program__set_expected_attach_type(bpf_prog, BPF_CGROUP_INET_INGRESS);

	link = bpf_program__attach_cgroup(bpf_prog, cg1);
	if (libbpf_get_error(link)) {
		fprintf(stderr, "ERROR: bpf_program__attach_cgroup failed\n");
		goto err;
	}

	sprintf(cg_pin_path, "/sys/fs/bpf/hbm%d", cg_id);
	rc = bpf_link__pin(link, cg_pin_path);
	if (rc < 0) {
		printf("ERROR: bpf_link__pin failed: %d\n", rc);
		goto err;
	}

	if (work_conserving_flag) {
		struct timeval t0, t_last, t_new;
		FILE *fin;
		unsigned long long last_eth_tx_bytes, new_eth_tx_bytes;
		signed long long last_cg_tx_bytes, new_cg_tx_bytes;
		signed long long delta_time, delta_bytes, delta_rate;
		int delta_ms;
#define DELTA_RATE_CHECK 10000		/* in us */
#define RATE_THRESHOLD 9500000000	/* 9.5 Gbps */

		bpf_map_lookup_elem(queue_stats_fd, &key, &qstats);
		if (gettimeofday(&t0, NULL) < 0)
			do_error("gettimeofday failed", true);
		t_last = t0;
		fin = fopen("/sys/class/net/eth0/statistics/tx_bytes", "r");
		if (fscanf(fin, "%llu", &last_eth_tx_bytes) != 1)
			do_error("fscanf fails", false);
		fclose(fin);
		last_cg_tx_bytes = qstats.bytes_total;
		while (true) {
			usleep(DELTA_RATE_CHECK);
			if (gettimeofday(&t_new, NULL) < 0)
				do_error("gettimeofday failed", true);
			delta_ms = (t_new.tv_sec - t0.tv_sec) * 1000 +
				(t_new.tv_usec - t0.tv_usec)/1000;
			if (delta_ms > dur * 1000)
				break;
			delta_time = (t_new.tv_sec - t_last.tv_sec) * 1000000 +
				(t_new.tv_usec - t_last.tv_usec);
			if (delta_time == 0)
				continue;
			t_last = t_new;
			fin = fopen("/sys/class/net/eth0/statistics/tx_bytes",
				    "r");
			if (fscanf(fin, "%llu", &new_eth_tx_bytes) != 1)
				do_error("fscanf fails", false);
			fclose(fin);
			printf("  new_eth_tx_bytes:%llu\n",
			       new_eth_tx_bytes);
			bpf_map_lookup_elem(queue_stats_fd, &key, &qstats);
			new_cg_tx_bytes = qstats.bytes_total;
			delta_bytes = new_eth_tx_bytes - last_eth_tx_bytes;
			last_eth_tx_bytes = new_eth_tx_bytes;
			delta_rate = (delta_bytes * 8000000) / delta_time;
			printf("%5d - eth_rate:%.1fGbps cg_rate:%.3fGbps",
			       delta_ms, delta_rate/1000000000.0,
			       rate/1000.0);
			if (delta_rate < RATE_THRESHOLD) {
				/* can increase cgroup rate limit, but first
				 * check if we are using the current limit.
				 * Currently increasing by 6.25%, unknown
				 * if that is the optimal rate.
				 */
				int rate_diff100;

				delta_bytes = new_cg_tx_bytes -
					last_cg_tx_bytes;
				last_cg_tx_bytes = new_cg_tx_bytes;
				delta_rate = (delta_bytes * 8000000) /
					delta_time;
				printf(" rate:%.3fGbps",
				       delta_rate/1000000000.0);
				rate_diff100 = (((long long)rate)*1000000 -
						     delta_rate) * 100 /
					(((long long) rate) * 1000000);
				printf("  rdiff:%d", rate_diff100);
				if (rate_diff100  <= 3) {
					rate += (rate >> 4);
					if (rate > RATE_THRESHOLD / 1000000)
						rate = RATE_THRESHOLD / 1000000;
					qstats.rate = rate;
					printf(" INC\n");
				} else {
					printf("\n");
				}
			} else {
				/* Need to decrease cgroup rate limit.
				 * Currently decreasing by 12.5%, unknown
				 * if that is optimal
				 */
				printf(" DEC\n");
				rate -= (rate >> 3);
				if (rate < minRate)
					rate = minRate;
				qstats.rate = rate;
			}
			if (bpf_map_update_elem(queue_stats_fd, &key, &qstats, BPF_ANY))
				do_error("update map element fails", false);
		}
	} else {
		sleep(dur);
	}
	// Get stats!
	if (stats_flag && bpf_map_lookup_elem(queue_stats_fd, &key, &qstats)) {
		char fname[100];
		FILE *fout;

		if (!outFlag)
			sprintf(fname, "hbm.%d.in", cg_id);
		else
			sprintf(fname, "hbm.%d.out", cg_id);
		fout = fopen(fname, "w");
		fprintf(fout, "id:%d\n", cg_id);
		fprintf(fout, "ERROR: Could not lookup queue_stats\n");
	} else if (stats_flag && qstats.lastPacketTime >
		   qstats.firstPacketTime) {
		long long delta_us = (qstats.lastPacketTime -
				      qstats.firstPacketTime)/1000;
		unsigned int rate_mbps = ((qstats.bytes_total -
					   qstats.bytes_dropped) * 8 /
					  delta_us);
		double percent_pkts, percent_bytes;
		char fname[100];
		FILE *fout;
		int k;
		static const char *returnValNames[] = {
			"DROP_PKT",
			"ALLOW_PKT",
			"DROP_PKT_CWR",
			"ALLOW_PKT_CWR"
		};
#define RET_VAL_COUNT 4

// Future support of ingress
//		if (!outFlag)
//			sprintf(fname, "hbm.%d.in", cg_id);
//		else
		sprintf(fname, "hbm.%d.out", cg_id);
		fout = fopen(fname, "w");
		fprintf(fout, "id:%d\n", cg_id);
		fprintf(fout, "rate_mbps:%d\n", rate_mbps);
		fprintf(fout, "duration:%.1f secs\n",
			(qstats.lastPacketTime - qstats.firstPacketTime) /
			1000000000.0);
		fprintf(fout, "packets:%d\n", (int)qstats.pkts_total);
		fprintf(fout, "bytes_MB:%d\n", (int)(qstats.bytes_total /
						     1000000));
		fprintf(fout, "pkts_dropped:%d\n", (int)qstats.pkts_dropped);
		fprintf(fout, "bytes_dropped_MB:%d\n",
			(int)(qstats.bytes_dropped /
						       1000000));
		// Marked Pkts and Bytes
		percent_pkts = (qstats.pkts_marked * 100.0) /
			(qstats.pkts_total + 1);
		percent_bytes = (qstats.bytes_marked * 100.0) /
			(qstats.bytes_total + 1);
		fprintf(fout, "pkts_marked_percent:%6.2f\n", percent_pkts);
		fprintf(fout, "bytes_marked_percent:%6.2f\n", percent_bytes);

		// Dropped Pkts and Bytes
		percent_pkts = (qstats.pkts_dropped * 100.0) /
			(qstats.pkts_total + 1);
		percent_bytes = (qstats.bytes_dropped * 100.0) /
			(qstats.bytes_total + 1);
		fprintf(fout, "pkts_dropped_percent:%6.2f\n", percent_pkts);
		fprintf(fout, "bytes_dropped_percent:%6.2f\n", percent_bytes);

		// ECN CE markings
		percent_pkts = (qstats.pkts_ecn_ce * 100.0) /
			(qstats.pkts_total + 1);
		fprintf(fout, "pkts_ecn_ce:%6.2f (%d)\n", percent_pkts,
			(int)qstats.pkts_ecn_ce);

		// Average cwnd
		fprintf(fout, "avg cwnd:%d\n",
			(int)(qstats.sum_cwnd / (qstats.sum_cwnd_cnt + 1)));
		// Average rtt
		fprintf(fout, "avg rtt:%d\n",
			(int)(qstats.sum_rtt / (qstats.pkts_total + 1)));
		// Average credit
		if (edt_flag)
			fprintf(fout, "avg credit_ms:%.03f\n",
				(qstats.sum_credit /
				 (qstats.pkts_total + 1.0)) / 1000000.0);
		else
			fprintf(fout, "avg credit:%d\n",
				(int)(qstats.sum_credit /
				      (1500 * ((int)qstats.pkts_total ) + 1)));

		// Return values stats
		for (k = 0; k < RET_VAL_COUNT; k++) {
			percent_pkts = (qstats.returnValCount[k] * 100.0) /
				(qstats.pkts_total + 1);
			fprintf(fout, "%s:%6.2f (%d)\n", returnValNames[k],
				percent_pkts, (int)qstats.returnValCount[k]);
		}
		fclose(fout);
	}

	if (debugFlag)
		read_trace_pipe2();
	goto cleanup;

err:
	rc = 1;

cleanup:
	bpf_link__destroy(link);
	bpf_object__close(obj);

	if (cg1 != -1)
		close(cg1);

	if (rc != 0)
		cleanup_cgroup_environment();
	return rc;
}