X-Git-Url: https://git.kernel.dk/?p=fio.git;a=blobdiff_plain;f=client.c;h=e443dc3eeba3b502c097041a3553c04a3589ca04;hp=5a6fc39ff8dac6f984e5bdfa2603a210ec9973b4;hb=d2333358fb3729de6681ed5cc3ec45cd86b5cfb8;hpb=2b7d9d5bba54ea0252f36d851c90fa4679aa0392

diff --git a/client.c b/client.c
index 5a6fc39f..e443dc3e 100644
--- a/client.c
+++ b/client.c
@@ -9,6 +9,7 @@
 #include <sys/stat.h>
 #include <sys/wait.h>
 #include <sys/socket.h>
+#include <sys/un.h>
 #include <netinet/in.h>
 #include <arpa/inet.h>
 #include <netdb.h>
@@ -16,22 +17,42 @@
 
 #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,
@@ -41,33 +62,55 @@ enum {
 };
 
 static FLIST_HEAD(client_list);
+static FLIST_HEAD(eta_list);
 
-static int handle_client(struct fio_client *client, int one, int block);
+static FLIST_HEAD(arg_list);
 
-static struct fio_client *find_client_by_fd(int fd)
+static struct thread_stat client_ts;
+static struct group_run_stats client_gs;
+static int sum_stat_clients;
+static int sum_stat_nr;
+
+#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]);
 }
 
-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;
 	}
 
@@ -78,101 +121,167 @@ static void remove_client(struct fio_client *client)
 {
 	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--;
+	sum_stat_clients--;
 }
 
-static int __fio_client_add_cmd_option(struct fio_client *client,
-				       const char *opt)
+static void __fio_client_add_cmd_option(struct fio_client *client,
+					const char *opt)
 {
 	int index;
 
-	if (client->argc == FIO_NET_CMD_JOBLINE_ARGV) {
-		log_err("fio: max cmd line number reached.\n");
-		log_err("fio: cmd line <%s> has been ignored.\n", opt);
-		return 1;
-	}
-
 	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);
-	return 0;
 }
 
-int fio_client_add_cmd_option(const char *hostname, const char *opt)
+void fio_client_add_cmd_option(void *cookie, const char *opt)
 {
-	struct fio_client *client;
+	struct fio_client *client = cookie;
+	struct flist_head *entry;
 
-	if (!hostname || !opt)
-		return 0;
+	if (!client || !opt)
+		return;
 
-	client = find_client_by_name(hostname);
-	if (!client) {
-		log_err("fio: unknown client %s\n", hostname);
-		return 1;
-	}
+	__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);
 
-	return __fio_client_add_cmd_option(client, opt);
+		__fio_client_add_cmd_option(client, opt);
+	}
 }
 
-void fio_client_add(const char *hostname)
+int fio_client_add(const char *hostname, void **cookie)
 {
+	struct fio_client *existing = *cookie;
 	struct fio_client *client;
 
-	dprint(FD_NET, "client: added  <%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, "client: 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));
-		log_err("fio: failed to connect to %s\n", client->hostname);
-		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;
 }
@@ -187,13 +296,13 @@ void fio_clients_terminate(void)
 	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);
+		fio_net_send_simple_cmd(client->fd, FIO_NET_CMD_QUIT, 0, NULL);
 	}
 }
 
 static void sig_int(int sig)
 {
-	dprint(FD_NET, "client: got sign %d\n", sig);
+	dprint(FD_NET, "client: got signal %d\n", sig);
 	fio_clients_terminate();
 }
 
@@ -216,23 +325,52 @@ 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);
-	handle_client(client, 1, 1);
+	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_line_pdu *pdu;
+	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);
 
-	pdu = malloc(sizeof(*pdu));
-	for (i = 0; i < client->argc; i++)
-		strcpy((char *) pdu->argv[i], client->argv[i]);
+	lens = malloc(client->argc * sizeof(unsigned int));
 
-	pdu->argc = cpu_to_le16(client->argc);
-	ret = fio_net_send_cmd(client->fd, FIO_NET_CMD_JOBLINE, pdu, sizeof(*pdu));
+	/*
+	 * 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;
 }
@@ -280,12 +418,13 @@ 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;
 	}
 
@@ -309,11 +448,14 @@ static int fio_client_send_ini(struct fio_client *client, const char *filename)
 
 	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);
+	ret = fio_net_send_cmd(client->fd, FIO_NET_CMD_JOB, buf, sb.st_size, 0);
 	free(buf);
+	close(fd);
 	return ret;
 }
 
@@ -435,6 +577,20 @@ static void handle_ts(struct fio_net_cmd *cmd)
 	convert_gs(&p->rs, &p->rs);
 
 	show_thread_status(&p->ts, &p->rs);
+
+	if (sum_stat_clients == 1)
+		return;
+
+	sum_thread_stats(&client_ts, &p->ts, sum_stat_nr);
+	sum_group_stats(&client_gs, &p->rs);
+
+	client_ts.members++;
+	client_ts.groupid = p->ts.groupid;
+
+	if (++sum_stat_nr == sum_stat_clients) {
+		strcpy(client_ts.name, "All clients");
+		show_thread_status(&client_ts, &client_gs);
+	}
 }
 
 static void handle_gs(struct fio_net_cmd *cmd)
@@ -445,9 +601,8 @@ 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);
@@ -464,87 +619,256 @@ 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;
+}
 
-	display_thread_status(je);
+static void dec_jobs_eta(struct client_eta *eta)
+{
+	if (!--eta->pending) {
+		display_thread_status(&eta->eta);
+		free(eta);
+	}
 }
 
-static void handle_probe(struct fio_net_cmd *cmd)
+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;
+
+	flist_for_each(entry, &client->cmd_list) {
+		icmd = flist_entry(entry, struct fio_net_int_cmd, list);
+
+		if (cmd->tag == (uintptr_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 *) (uintptr_t) 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;
+	char bit[16];
+
+	os = fio_get_os_string(probe->os);
+	if (!os)
+		os = "unknown";
+
+	arch = fio_get_arch_string(probe->arch);
+	if (!arch)
+		os = "unknown";
+
+	sprintf(bit, "%d-bit", probe->bpp * 8);
 
-	log_info("Probe: hostname=%s, be=%u, fio ver %u.%u.%u\n",
-		probe->hostname, probe->bigendian, probe->fio_major,
-		probe->fio_minor, probe->fio_patch);
+	log_info("hostname=%s, be=%u, %s, os=%s, arch=%s, fio=%u.%u.%u\n",
+		probe->hostname, probe->bigendian, bit, 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, int one, int block)
+static int handle_client(struct fio_client *client)
 {
 	struct fio_net_cmd *cmd;
-	int done = 0, did_cmd = 0;
 
 	dprint(FD_NET, "client: handle %s\n", client->hostname);
 
-	while ((cmd = fio_net_recv_cmd(client->fd, block)) != NULL) {
-		did_cmd++;
+	cmd = fio_net_recv_cmd(client->fd);
+	if (!cmd)
+		return 0;
 
-		dprint(FD_NET, "client: got cmd op %d from %s\n",
-					cmd->opcode, client->hostname);
+	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_QUIT:
-			remove_client(client);
-			free(cmd);
-			done = 1;
-			break;
-		case FIO_NET_CMD_TEXT: {
-			const char *buf = (const char *) cmd->payload;
-			int fio_unused ret;
-
-			if (!client->skip_newline)
-				fprintf(f_out, "<%s> ", client->hostname);
-			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:
-			handle_eta(cmd);
-			free(cmd);
-			break;
-		case FIO_NET_CMD_PROBE:
-			handle_probe(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: %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 || one)
-			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,
+					(uintptr_t) eta, &client->cmd_list);
+	}
+
+	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 did_cmd;
+	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)
@@ -554,8 +878,14 @@ int fio_handle_clients(void)
 	struct pollfd *pfds;
 	int i, ret = 0;
 
+	gettimeofday(&eta_tv, NULL);
+
 	pfds = malloc(nr_clients * sizeof(struct pollfd));
 
+	sum_stat_clients = nr_clients;
+	init_thread_stat(&client_ts);
+	init_group_run_stat(&client_gs);
+
 	while (!exit_backend && nr_clients) {
 		i = 0;
 		flist_for_each(entry, &client_list) {
@@ -569,6 +899,17 @@ int fio_handle_clients(void)
 		assert(i == nr_clients);
 
 		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)
@@ -585,10 +926,10 @@ 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;
 			}
-			if (!handle_client(client, 0, 0)) {
+			if (!handle_client(client)) {
 				log_info("client: host=%s disconnected\n",
 						client->hostname);
 				remove_client(client);