X-Git-Url: https://git.kernel.dk/?p=fio.git;a=blobdiff_plain;f=client.c;h=130aeafc1a493efc8d3c92f63049200b9724a177;hp=d81f755a03a9276bf0cb51ec26d5fabeb80b0b0a;hb=89c1707cb512e562b55b56c268f7fad612be6f04;hpb=cf451d1ede3bbbd2fed3619eb43def054d5b5a5a

diff --git a/client.c b/client.c
index d81f755a..130aeafc 100644
--- a/client.c
+++ b/client.c
@@ -8,138 +8,395 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/wait.h>
-#include <sys/mman.h>
+#include <sys/socket.h>
+#include <sys/un.h>
 #include <netinet/in.h>
 #include <arpa/inet.h>
 #include <netdb.h>
+#include <signal.h>
 
 #include "fio.h"
 #include "server.h"
-#include "crc/crc32.h"
 #include "flist.h"
+#include "hash.h"
+
+struct client_eta {
+	struct jobs_eta eta;
+	unsigned int pending;
+};
 
 struct fio_client {
 	struct flist_head list;
+	struct flist_head hash_list;
+	struct flist_head arg_list;
 	struct sockaddr_in addr;
+	struct sockaddr_un addr_un;
 	char *hostname;
+	int port;
 	int fd;
+
+	char *name;
+
+	int state;
+
+	int skip_newline;
+	int is_sock;
+
+	struct flist_head eta_list;
+	struct client_eta *eta_in_flight;
+
+	struct flist_head cmd_list;
+
+	uint16_t argc;
+	char **argv;
+};
+
+static struct timeval eta_tv;
+
+enum {
+	Client_created		= 0,
+	Client_connected	= 1,
+	Client_started		= 2,
+	Client_stopped		= 3,
+	Client_exited		= 4,
 };
 
 static FLIST_HEAD(client_list);
+static FLIST_HEAD(eta_list);
 
-static struct fio_client *find_client_by_fd(int fd)
+static FLIST_HEAD(arg_list);
+
+#define FIO_CLIENT_HASH_BITS	7
+#define FIO_CLIENT_HASH_SZ	(1 << FIO_CLIENT_HASH_BITS)
+#define FIO_CLIENT_HASH_MASK	(FIO_CLIENT_HASH_SZ - 1)
+static struct flist_head client_hash[FIO_CLIENT_HASH_SZ];
+
+static int handle_client(struct fio_client *client);
+static void dec_jobs_eta(struct client_eta *eta);
+
+static void fio_client_add_hash(struct fio_client *client)
 {
-	struct fio_client *client;
-	struct flist_head *entry;
+	int bucket = hash_long(client->fd, FIO_CLIENT_HASH_BITS);
 
-	flist_for_each(entry, &client_list) {
-		client = flist_entry(entry, struct fio_client, list);
+	bucket &= FIO_CLIENT_HASH_MASK;
+	flist_add(&client->hash_list, &client_hash[bucket]);
+}
 
-		if (client->fd == fd)
-			return client;
-	}
+static void fio_client_remove_hash(struct fio_client *client)
+{
+	if (!flist_empty(&client->hash_list))
+		flist_del_init(&client->hash_list);
+}
 
-	return NULL;
+static void fio_init fio_client_hash_init(void)
+{
+	int i;
+
+	for (i = 0; i < FIO_CLIENT_HASH_SZ; i++)
+		INIT_FLIST_HEAD(&client_hash[i]);
 }
 
-#if 0
-static struct fio_client *find_client_by_name(const char *name)
+static struct fio_client *find_client_by_fd(int fd)
 {
+	int bucket = hash_long(fd, FIO_CLIENT_HASH_BITS) & FIO_CLIENT_HASH_MASK;
 	struct fio_client *client;
 	struct flist_head *entry;
 
-	flist_for_each(entry, &client_list) {
-		client = flist_entry(entry, struct fio_client, list);
+	flist_for_each(entry, &client_hash[bucket]) {
+		client = flist_entry(entry, struct fio_client, hash_list);
 
-		if (!strcmp(name, client->hostname))
+		if (client->fd == fd)
 			return client;
 	}
 
 	return NULL;
 }
-#endif
 
 static void remove_client(struct fio_client *client)
 {
-	dprint(FD_NET, "removed client <%s>\n", client->hostname);
+	dprint(FD_NET, "client: removed <%s>\n", client->hostname);
 	flist_del(&client->list);
-	nr_clients--;
+
+	fio_client_remove_hash(client);
+
+	if (!flist_empty(&client->eta_list)) {
+		flist_del_init(&client->eta_list);
+		dec_jobs_eta(client->eta_in_flight);
+	}
+
 	free(client->hostname);
+	if (client->argv)
+		free(client->argv);
+	if (client->name)
+		free(client->name);
+
 	free(client);
+	nr_clients--;
+}
+
+static void __fio_client_add_cmd_option(struct fio_client *client,
+					const char *opt)
+{
+	int index;
+
+	index = client->argc++;
+	client->argv = realloc(client->argv, sizeof(char *) * client->argc);
+	client->argv[index] = strdup(opt);
+	dprint(FD_NET, "client: add cmd %d: %s\n", index, opt);
 }
 
-void fio_client_add(const char *hostname)
+void fio_client_add_cmd_option(void *cookie, const char *opt)
 {
+	struct fio_client *client = cookie;
+	struct flist_head *entry;
+
+	if (!client || !opt)
+		return;
+
+	__fio_client_add_cmd_option(client, opt);
+
+	/*
+	 * Duplicate arguments to shared client group
+	 */
+	flist_for_each(entry, &arg_list) {
+		client = flist_entry(entry, struct fio_client, arg_list);
+
+		__fio_client_add_cmd_option(client, opt);
+	}
+}
+
+int fio_client_add(const char *hostname, void **cookie)
+{
+	struct fio_client *existing = *cookie;
 	struct fio_client *client;
 
-	dprint(FD_NET, "added client <%s>\n", hostname);
+	if (existing) {
+		/*
+		 * We always add our "exec" name as the option, hence 1
+		 * means empty.
+		 */
+		if (existing->argc == 1)
+			flist_add_tail(&existing->arg_list, &arg_list);
+		else {
+			while (!flist_empty(&arg_list))
+				flist_del_init(arg_list.next);
+		}
+	}
+
 	client = malloc(sizeof(*client));
 	memset(client, 0, sizeof(*client));
-	client->hostname = strdup(hostname);
+
+	INIT_FLIST_HEAD(&client->list);
+	INIT_FLIST_HEAD(&client->hash_list);
+	INIT_FLIST_HEAD(&client->arg_list);
+	INIT_FLIST_HEAD(&client->eta_list);
+	INIT_FLIST_HEAD(&client->cmd_list);
+
+	if (fio_server_parse_string(hostname, &client->hostname,
+					&client->is_sock, &client->port,
+					&client->addr.sin_addr))
+		return -1;
+
 	client->fd = -1;
+
+	__fio_client_add_cmd_option(client, "fio");
+
 	flist_add(&client->list, &client_list);
 	nr_clients++;
+	dprint(FD_NET, "client: added <%s>\n", client->hostname);
+	*cookie = client;
+	return 0;
 }
 
-static int fio_client_connect(struct fio_client *client)
+static int fio_client_connect_ip(struct fio_client *client)
 {
 	int fd;
 
-	dprint(FD_NET, "connect to host %s\n", client->hostname);
-
-	memset(&client->addr, 0, sizeof(client->addr));
 	client->addr.sin_family = AF_INET;
-	client->addr.sin_port = htons(fio_net_port);
-
-	if (inet_aton(client->hostname, &client->addr.sin_addr) != 1) {
-		struct hostent *hent;
-
-		hent = gethostbyname(client->hostname);
-		if (!hent) {
-			log_err("fio: gethostbyname: %s\n", strerror(errno));
-			return 1;
-		}
-
-		memcpy(&client->addr.sin_addr, hent->h_addr, 4);
-	}
+	client->addr.sin_port = htons(client->port);
 
 	fd = socket(AF_INET, SOCK_STREAM, 0);
 	if (fd < 0) {
 		log_err("fio: socket: %s\n", strerror(errno));
-		return 1;
+		return -1;
 	}
 
 	if (connect(fd, (struct sockaddr *) &client->addr, sizeof(client->addr)) < 0) {
 		log_err("fio: connect: %s\n", strerror(errno));
-		return 1;
+		log_err("fio: failed to connect to %s:%u\n", client->hostname,
+								client->port);
+		close(fd);
+		return -1;
 	}
 
+	return fd;
+}
+
+static int fio_client_connect_sock(struct fio_client *client)
+{
+	struct sockaddr_un *addr = &client->addr_un;
+	fio_socklen_t len;
+	int fd;
+
+	memset(addr, 0, sizeof(*addr));
+	addr->sun_family = AF_UNIX;
+	strcpy(addr->sun_path, client->hostname);
+
+	fd = socket(AF_UNIX, SOCK_STREAM, 0);
+	if (fd < 0) {
+		log_err("fio: socket: %s\n", strerror(errno));
+		return -1;
+	}
+
+	len = sizeof(addr->sun_family) + strlen(addr->sun_path) + 1;
+	if (connect(fd, (struct sockaddr *) addr, len) < 0) {
+		log_err("fio: connect; %s\n", strerror(errno));
+		close(fd);
+		return -1;
+	}
+
+	return fd;
+}
+
+static int fio_client_connect(struct fio_client *client)
+{
+	int fd;
+
+	dprint(FD_NET, "client: connect to host %s\n", client->hostname);
+
+	if (client->is_sock)
+		fd = fio_client_connect_sock(client);
+	else
+		fd = fio_client_connect_ip(client);
+
+	dprint(FD_NET, "client: %s connected %d\n", client->hostname, fd);
+
+	if (fd < 0)
+		return 1;
+
 	client->fd = fd;
+	fio_client_add_hash(client);
+	client->state = Client_connected;
 	return 0;
 }
 
+void fio_clients_terminate(void)
+{
+	struct flist_head *entry;
+	struct fio_client *client;
+
+	dprint(FD_NET, "client: terminate clients\n");
+
+	flist_for_each(entry, &client_list) {
+		client = flist_entry(entry, struct fio_client, list);
+
+		fio_net_send_simple_cmd(client->fd, FIO_NET_CMD_QUIT, 0, NULL);
+	}
+}
+
+static void sig_int(int sig)
+{
+	dprint(FD_NET, "client: got signal %d\n", sig);
+	fio_clients_terminate();
+}
+
+static void client_signal_handler(void)
+{
+	struct sigaction act;
+
+	memset(&act, 0, sizeof(act));
+	act.sa_handler = sig_int;
+	act.sa_flags = SA_RESTART;
+	sigaction(SIGINT, &act, NULL);
+
+	memset(&act, 0, sizeof(act));
+	act.sa_handler = sig_int;
+	act.sa_flags = SA_RESTART;
+	sigaction(SIGTERM, &act, NULL);
+}
+
+static void probe_client(struct fio_client *client)
+{
+	dprint(FD_NET, "client: send probe\n");
+
+	fio_net_send_simple_cmd(client->fd, FIO_NET_CMD_PROBE, 0, &client->cmd_list);
+}
+
+static int send_client_cmd_line(struct fio_client *client)
+{
+	struct cmd_single_line_pdu *cslp;
+	struct cmd_line_pdu *clp;
+	unsigned long offset;
+	unsigned int *lens;
+	void *pdu;
+	size_t mem;
+	int i, ret;
+
+	dprint(FD_NET, "client: send cmdline %d\n", client->argc);
+
+	lens = malloc(client->argc * sizeof(unsigned int));
+
+	/*
+	 * Find out how much mem we need
+	 */
+	for (i = 0, mem = 0; i < client->argc; i++) {
+		lens[i] = strlen(client->argv[i]) + 1;
+		mem += lens[i];
+	}
+
+	/*
+	 * We need one cmd_line_pdu, and argc number of cmd_single_line_pdu
+	 */
+	mem += sizeof(*clp) + (client->argc * sizeof(*cslp));
+
+	pdu = malloc(mem);
+	clp = pdu;
+	offset = sizeof(*clp);
+
+	for (i = 0; i < client->argc; i++) {
+		uint16_t arg_len = lens[i];
+
+		cslp = pdu + offset;
+		strcpy((char *) cslp->text, client->argv[i]);
+		cslp->len = cpu_to_le16(arg_len);
+		offset += sizeof(*cslp) + arg_len;
+	}
+
+	free(lens);
+	clp->lines = cpu_to_le16(client->argc);
+	ret = fio_net_send_cmd(client->fd, FIO_NET_CMD_JOBLINE, pdu, mem, 0);
+	free(pdu);
+	return ret;
+}
+
 int fio_clients_connect(void)
 {
 	struct fio_client *client;
 	struct flist_head *entry, *tmp;
 	int ret;
 
+	dprint(FD_NET, "client: connect all\n");
+
+	client_signal_handler();
+
 	flist_for_each_safe(entry, tmp, &client_list) {
 		client = flist_entry(entry, struct fio_client, list);
 
 		ret = fio_client_connect(client);
-		if (ret)
+		if (ret) {
 			remove_client(client);
+			continue;
+		}
+
+		probe_client(client);
+
+		if (client->argc > 1)
+			send_client_cmd_line(client);
 	}
 
 	return !nr_clients;
 }
 
-static int send_file_buf(struct fio_client *client, char *buf, off_t size)
-{
-	return fio_net_send_cmd(client->fd, FIO_NET_CMD_JOB, buf, size);
-}
-
 /*
  * Send file contents to server backend. We could use sendfile(), but to remain
  * more portable lets just read/write the darn thing.
@@ -155,12 +412,13 @@ static int fio_client_send_ini(struct fio_client *client, const char *filename)
 
 	fd = open(filename, O_RDONLY);
 	if (fd < 0) {
-		log_err("fio: job file open: %s\n", strerror(errno));
+		log_err("fio: job file <%s> open: %s\n", filename, strerror(errno));
 		return 1;
 	}
 
 	if (fstat(fd, &sb) < 0) {
 		log_err("fio: job file stat: %s\n", strerror(errno));
+		close(fd);
 		return 1;
 	}
 
@@ -182,8 +440,16 @@ static int fio_client_send_ini(struct fio_client *client, const char *filename)
 			continue;
 	} while (1);
 
-	ret = send_file_buf(client, buf, sb.st_size);
+	if (len) {
+		log_err("fio: failed reading job file %s\n", filename);
+		close(fd);
+		free(buf);
+		return 1;
+	}
+
+	ret = fio_net_send_cmd(client->fd, FIO_NET_CMD_JOB, buf, sb.st_size, 0);
 	free(buf);
+	close(fd);
 	return ret;
 }
 
@@ -207,9 +473,12 @@ static void convert_io_stat(struct io_stat *dst, struct io_stat *src)
 	dst->max_val	= le64_to_cpu(src->max_val);
 	dst->min_val	= le64_to_cpu(src->min_val);
 	dst->samples	= le64_to_cpu(src->samples);
-	/* FIXME */
-	dst->mean	= __le64_to_cpu(src->mean);
-	dst->S		= __le64_to_cpu(src->S);
+
+	/*
+	 * Floats arrive as IEEE 754 encoded uint64_t, convert back to double
+	 */
+	dst->mean.u.f	= fio_uint64_to_double(le64_to_cpu(dst->mean.u.i));
+	dst->S.u.f	= fio_uint64_to_double(le64_to_cpu(dst->S.u.i));
 }
 
 static void convert_ts(struct thread_stat *dst, struct thread_stat *src)
@@ -234,7 +503,13 @@ static void convert_ts(struct thread_stat *dst, struct thread_stat *src)
 	dst->minf		= le64_to_cpu(src->minf);
 	dst->majf		= le64_to_cpu(src->majf);
 	dst->clat_percentiles	= le64_to_cpu(src->clat_percentiles);
-	dst->percentile_list	= NULL;
+
+	for (i = 0; i < FIO_IO_U_LIST_MAX_LEN; i++) {
+		fio_fp64_t *fps = &src->percentile_list[i];
+		fio_fp64_t *fpd = &dst->percentile_list[i];
+
+		fpd->u.f = fio_uint64_to_double(le64_to_cpu(fps->u.i));
+	}
 
 	for (i = 0; i < FIO_IO_U_MAP_NR; i++) {
 		dst->io_u_map[i]	= le32_to_cpu(src->io_u_map[i]);
@@ -253,7 +528,7 @@ static void convert_ts(struct thread_stat *dst, struct thread_stat *src)
 
 	for (i = 0; i < 3; i++) {
 		dst->total_io_u[i]	= le64_to_cpu(src->total_io_u[i]);
-		dst->short_io_u[i]	= le64_to_cpu(src->total_io_u[i]);
+		dst->short_io_u[i]	= le64_to_cpu(src->short_io_u[i]);
 	}
 
 	dst->total_submit	= le64_to_cpu(src->total_submit);
@@ -306,9 +581,8 @@ static void handle_gs(struct fio_net_cmd *cmd)
 	show_group_stats(gs);
 }
 
-static void handle_eta(struct fio_net_cmd *cmd)
+static void convert_jobs_eta(struct jobs_eta *je)
 {
-	struct jobs_eta *je = (struct jobs_eta *) cmd->payload;
 	int i;
 
 	je->nr_running		= le32_to_cpu(je->nr_running);
@@ -325,58 +599,253 @@ static void handle_eta(struct fio_net_cmd *cmd)
 		je->iops[i]	= le32_to_cpu(je->iops[i]);
 	}
 
-	je->elapsed_sec		= le32_to_cpu(je->nr_running);
+	je->elapsed_sec		= le64_to_cpu(je->elapsed_sec);
 	je->eta_sec		= le64_to_cpu(je->eta_sec);
+}
+
+static void sum_jobs_eta(struct jobs_eta *dst, struct jobs_eta *je)
+{
+	int i;
+
+	dst->nr_running		+= je->nr_running;
+	dst->nr_ramp		+= je->nr_ramp;
+	dst->nr_pending		+= je->nr_pending;
+	dst->files_open		+= je->files_open;
+	dst->m_rate		+= je->m_rate;
+	dst->t_rate		+= je->t_rate;
+	dst->m_iops		+= je->m_iops;
+	dst->t_iops		+= je->t_iops;
+
+	for (i = 0; i < 2; i++) {
+		dst->rate[i]	+= je->rate[i];
+		dst->iops[i]	+= je->iops[i];
+	}
+
+	dst->elapsed_sec	+= je->elapsed_sec;
+
+	if (je->eta_sec > dst->eta_sec)
+		dst->eta_sec = je->eta_sec;
+}
+
+static void dec_jobs_eta(struct client_eta *eta)
+{
+	if (!--eta->pending) {
+		display_thread_status(&eta->eta);
+		free(eta);
+	}
+}
+
+static void remove_reply_cmd(struct fio_client *client, struct fio_net_cmd *cmd)
+{
+	struct fio_net_int_cmd *icmd = NULL;
+	struct flist_head *entry;
 
-	display_thread_status(je);
+	flist_for_each(entry, &client->cmd_list) {
+		icmd = flist_entry(entry, struct fio_net_int_cmd, list);
+
+		if (cmd->tag == (uint64_t) icmd)
+			break;
+
+		icmd = NULL;
+	}
+
+	if (!icmd) {
+		log_err("fio: client: unable to find matching tag\n");
+		return;
+	}
+
+	flist_del(&icmd->list);
+	cmd->tag = icmd->saved_tag;
+	free(icmd);
+}
+
+static void handle_eta(struct fio_client *client, struct fio_net_cmd *cmd)
+{
+	struct jobs_eta *je = (struct jobs_eta *) cmd->payload;
+	struct client_eta *eta = (struct client_eta *) cmd->tag;
+
+	dprint(FD_NET, "client: got eta tag %p, %d\n", eta, eta->pending);
+
+	assert(client->eta_in_flight == eta);
+
+	client->eta_in_flight = NULL;
+	flist_del_init(&client->eta_list);
+
+	convert_jobs_eta(je);
+	sum_jobs_eta(&eta->eta, je);
+	dec_jobs_eta(eta);
+}
+
+static void handle_probe(struct fio_client *client, struct fio_net_cmd *cmd)
+{
+	struct cmd_probe_pdu *probe = (struct cmd_probe_pdu *) cmd->payload;
+	const char *os, *arch;
+
+	os = fio_get_os_string(probe->os);
+	if (!os)
+		os = "unknown";
+
+	arch = fio_get_arch_string(probe->arch);
+	if (!arch)
+		os = "unknown";
+
+	log_info("hostname=%s, be=%u, os=%s, arch=%s, fio=%u.%u.%u\n",
+		probe->hostname, probe->bigendian, os, arch, probe->fio_major,
+		probe->fio_minor, probe->fio_patch);
+
+	if (!client->name)
+		client->name = strdup((char *) probe->hostname);
 }
 
 static int handle_client(struct fio_client *client)
 {
 	struct fio_net_cmd *cmd;
-	int done = 0;
 
-	while ((cmd = fio_net_recv_cmd(client->fd)) != NULL) {
-		dprint(FD_NET, "%s: got cmd op %d\n", client->hostname,
-							cmd->opcode);
+	dprint(FD_NET, "client: handle %s\n", client->hostname);
+
+	cmd = fio_net_recv_cmd(client->fd);
+	if (!cmd)
+		return 0;
+
+	dprint(FD_NET, "client: got cmd op %s from %s\n",
+				fio_server_op(cmd->opcode), client->hostname);
+
+	switch (cmd->opcode) {
+	case FIO_NET_CMD_QUIT:
+		remove_client(client);
+		free(cmd);
+		break;
+	case FIO_NET_CMD_TEXT: {
+		const char *buf = (const char *) cmd->payload;
+		const char *name;
+		int fio_unused ret;
+
+		name = client->name ? client->name : client->hostname;
+
+		if (!client->skip_newline)
+			fprintf(f_out, "<%s> ", name);
+		ret = fwrite(buf, cmd->pdu_len, 1, f_out);
+		fflush(f_out);
+		client->skip_newline = strchr(buf, '\n') == NULL;
+		free(cmd);
+		break;
+		}
+	case FIO_NET_CMD_TS:
+		handle_ts(cmd);
+		free(cmd);
+		break;
+	case FIO_NET_CMD_GS:
+		handle_gs(cmd);
+		free(cmd);
+		break;
+	case FIO_NET_CMD_ETA:
+		remove_reply_cmd(client, cmd);
+		handle_eta(client, cmd);
+		free(cmd);
+		break;
+	case FIO_NET_CMD_PROBE:
+		remove_reply_cmd(client, cmd);
+		handle_probe(client, cmd);
+		free(cmd);
+		break;
+	case FIO_NET_CMD_START:
+		client->state = Client_started;
+		free(cmd);
+		break;
+	case FIO_NET_CMD_STOP:
+		client->state = Client_stopped;
+		free(cmd);
+		break;
+	default:
+		log_err("fio: unknown client op: %s\n", fio_server_op(cmd->opcode));
+		free(cmd);
+		break;
+	}
 
-		switch (cmd->opcode) {
-		case FIO_NET_CMD_ACK:
-			free(cmd);
-			break;
-		case FIO_NET_CMD_QUIT:
-			remove_client(client);
-			free(cmd);
-			done = 1;
-			break;
-		case FIO_NET_CMD_TEXT:
-			fwrite(cmd->payload, cmd->pdu_len, 1, stdout);
-			fflush(stdout);
-			free(cmd);
-			break;
-		case FIO_NET_CMD_TS:
-			handle_ts(cmd);
-			free(cmd);
-			break;
-		case FIO_NET_CMD_GS:
-			handle_gs(cmd);
-			free(cmd);
-			break;
-		case FIO_NET_CMD_ETA:
-			handle_eta(cmd);
-			free(cmd);
-			break;
-		default:
-			log_err("fio: unknown client op: %d\n", cmd->opcode);
-			free(cmd);
-			break;
+	return 1;
+}
+
+static void request_client_etas(void)
+{
+	struct fio_client *client;
+	struct flist_head *entry;
+	struct client_eta *eta;
+	int skipped = 0;
+
+	dprint(FD_NET, "client: request eta (%d)\n", nr_clients);
+
+	eta = malloc(sizeof(*eta));
+	memset(&eta->eta, 0, sizeof(eta->eta));
+	eta->pending = nr_clients;
+
+	flist_for_each(entry, &client_list) {
+		client = flist_entry(entry, struct fio_client, list);
+
+		if (!flist_empty(&client->eta_list)) {
+			skipped++;
+			continue;
 		}
 
-		if (done)
-			break;
+		assert(!client->eta_in_flight);
+		flist_add_tail(&client->eta_list, &eta_list);
+		client->eta_in_flight = eta;
+		fio_net_send_simple_cmd(client->fd, FIO_NET_CMD_SEND_ETA,
+					(uint64_t) eta, &client->cmd_list);
 	}
 
-	return 0;
+	while (skipped--)
+		dec_jobs_eta(eta);
+
+	dprint(FD_NET, "client: requested eta tag %p\n", eta);
+}
+
+static int client_check_cmd_timeout(struct fio_client *client,
+				    struct timeval *now)
+{
+	struct fio_net_int_cmd *cmd;
+	struct flist_head *entry, *tmp;
+	int ret = 0;
+
+	flist_for_each_safe(entry, tmp, &client->cmd_list) {
+		cmd = flist_entry(entry, struct fio_net_int_cmd, list);
+
+		if (mtime_since(&cmd->tv, now) < FIO_NET_CLIENT_TIMEOUT)
+			continue;
+
+		log_err("fio: client %s, timeout on cmd %s\n", client->hostname,
+						fio_server_op(cmd->cmd.opcode));
+		flist_del(&cmd->list);
+		free(cmd);
+		ret = 1;
+	}
+
+	return flist_empty(&client->cmd_list) && ret;
+}
+
+static int fio_client_timed_out(void)
+{
+	struct fio_client *client;
+	struct flist_head *entry, *tmp;
+	struct timeval tv;
+	int ret = 0;
+
+	gettimeofday(&tv, NULL);
+
+	flist_for_each_safe(entry, tmp, &client_list) {
+		client = flist_entry(entry, struct fio_client, list);
+
+		if (flist_empty(&client->cmd_list))
+			continue;
+
+		if (!client_check_cmd_timeout(client, &tv))
+			continue;
+
+		log_err("fio: client %s timed out\n", client->hostname);
+		remove_client(client);
+		ret = 1;
+	}
+
+	return ret;
 }
 
 int fio_handle_clients(void)
@@ -386,6 +855,8 @@ int fio_handle_clients(void)
 	struct pollfd *pfds;
 	int i, ret = 0;
 
+	gettimeofday(&eta_tv, NULL);
+
 	pfds = malloc(nr_clients * sizeof(struct pollfd));
 
 	while (!exit_backend && nr_clients) {
@@ -400,14 +871,27 @@ int fio_handle_clients(void)
 
 		assert(i == nr_clients);
 
-		ret = poll(pfds, nr_clients, 100);
-		if (ret < 0) {
-			if (errno == EINTR)
+		do {
+			struct timeval tv;
+
+			gettimeofday(&tv, NULL);
+			if (mtime_since(&eta_tv, &tv) >= 900) {
+				request_client_etas();
+				memcpy(&eta_tv, &tv, sizeof(tv));
+
+				if (fio_client_timed_out())
+					break;
+			}
+
+			ret = poll(pfds, nr_clients, 100);
+			if (ret < 0) {
+				if (errno == EINTR)
+					continue;
+				log_err("fio: poll clients: %s\n", strerror(errno));
+				break;
+			} else if (!ret)
 				continue;
-			log_err("fio: poll clients: %s\n", strerror(errno));
-			break;
-		} else if (!ret)
-			continue;
+		} while (ret <= 0);
 
 		for (i = 0; i < nr_clients; i++) {
 			if (!(pfds[i].revents & POLLIN))
@@ -415,10 +899,14 @@ int fio_handle_clients(void)
 
 			client = find_client_by_fd(pfds[i].fd);
 			if (!client) {
-				log_err("fio: unknown client\n");
+				log_err("fio: unknown client fd %d\n", pfds[i].fd);
 				continue;
 			}
-			handle_client(client);
+			if (!handle_client(client)) {
+				log_info("client: host=%s disconnected\n",
+						client->hostname);
+				remove_client(client);
+			}
 		}
 	}