diff options
Diffstat (limited to 'net/ceph')
-rw-r--r-- | net/ceph/ceph_common.c | 15 | ||||
-rw-r--r-- | net/ceph/crypto.c | 1 | ||||
-rw-r--r-- | net/ceph/messenger.c | 44 | ||||
-rw-r--r-- | net/ceph/osd_client.c | 36 | ||||
-rw-r--r-- | net/ceph/osdmap.c | 4 |
5 files changed, 81 insertions, 19 deletions
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 464e88599b9d..108533859a53 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -230,6 +230,7 @@ enum { Opt_osdkeepalivetimeout, Opt_mount_timeout, Opt_osd_idle_ttl, + Opt_osd_request_timeout, Opt_last_int, /* int args above */ Opt_fsid, @@ -256,6 +257,7 @@ static match_table_t opt_tokens = { {Opt_osdkeepalivetimeout, "osdkeepalive=%d"}, {Opt_mount_timeout, "mount_timeout=%d"}, {Opt_osd_idle_ttl, "osd_idle_ttl=%d"}, + {Opt_osd_request_timeout, "osd_request_timeout=%d"}, /* int args above */ {Opt_fsid, "fsid=%s"}, {Opt_name, "name=%s"}, @@ -361,6 +363,7 @@ ceph_parse_options(char *options, const char *dev_name, opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; + opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT; /* get mon ip(s) */ /* ip1[:port1][,ip2[:port2]...] */ @@ -473,6 +476,15 @@ ceph_parse_options(char *options, const char *dev_name, } opt->mount_timeout = msecs_to_jiffies(intval * 1000); break; + case Opt_osd_request_timeout: + /* 0 is "wait forever" (i.e. infinite timeout) */ + if (intval < 0 || intval > INT_MAX / 1000) { + pr_err("osd_request_timeout out of range\n"); + err = -EINVAL; + goto out; + } + opt->osd_request_timeout = msecs_to_jiffies(intval * 1000); + break; case Opt_share: opt->flags &= ~CEPH_OPT_NOSHARE; @@ -557,6 +569,9 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client) if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT) seq_printf(m, "osdkeepalivetimeout=%d,", jiffies_to_msecs(opt->osd_keepalive_timeout) / 1000); + if (opt->osd_request_timeout != CEPH_OSD_REQUEST_TIMEOUT_DEFAULT) + seq_printf(m, "osd_request_timeout=%d,", + jiffies_to_msecs(opt->osd_request_timeout) / 1000); /* drop redundant comma */ if (m->count != pos) diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index 85747b7f91a9..46008d5ac504 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -8,6 +8,7 @@ #include <crypto/aes.h> #include <crypto/skcipher.h> #include <linux/key-type.h> +#include <linux/sched/mm.h> #include <keys/ceph-type.h> #include <keys/user-type.h> diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index bad3d4ae43f6..38dcf1eb427d 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -520,7 +520,8 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len) struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL }; int r; - r = kernel_recvmsg(sock, &msg, &iov, 1, len, msg.msg_flags); + iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, len); + r = sock_recvmsg(sock, &msg, msg.msg_flags); if (r == -EAGAIN) r = 0; return r; @@ -529,17 +530,20 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len) static int ceph_tcp_recvpage(struct socket *sock, struct page *page, int page_offset, size_t length) { - void *kaddr; - int ret; + struct bio_vec bvec = { + .bv_page = page, + .bv_offset = page_offset, + .bv_len = length + }; + struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL }; + int r; BUG_ON(page_offset + length > PAGE_SIZE); - - kaddr = kmap(page); - BUG_ON(!kaddr); - ret = ceph_tcp_recvmsg(sock, kaddr + page_offset, length); - kunmap(page); - - return ret; + iov_iter_bvec(&msg.msg_iter, READ | ITER_BVEC, &bvec, 1, length); + r = sock_recvmsg(sock, &msg, msg.msg_flags); + if (r == -EAGAIN) + r = 0; + return r; } /* @@ -579,18 +583,28 @@ static int __ceph_tcp_sendpage(struct socket *sock, struct page *page, static int ceph_tcp_sendpage(struct socket *sock, struct page *page, int offset, size_t size, bool more) { + struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL }; + struct bio_vec bvec; int ret; - struct kvec iov; /* sendpage cannot properly handle pages with page_count == 0, * we need to fallback to sendmsg if that's the case */ if (page_count(page) >= 1) return __ceph_tcp_sendpage(sock, page, offset, size, more); - iov.iov_base = kmap(page) + offset; - iov.iov_len = size; - ret = ceph_tcp_sendmsg(sock, &iov, 1, size, more); - kunmap(page); + bvec.bv_page = page; + bvec.bv_offset = offset; + bvec.bv_len = size; + + if (more) + msg.msg_flags |= MSG_MORE; + else + msg.msg_flags |= MSG_EOR; /* superfluous, but what the hell */ + + iov_iter_bvec(&msg.msg_iter, WRITE | ITER_BVEC, &bvec, 1, size); + ret = sock_sendmsg(sock, &msg); + if (ret == -EAGAIN) + ret = 0; return ret; } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index b65bbf9f45eb..e15ea9e4c495 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1709,6 +1709,8 @@ static void account_request(struct ceph_osd_request *req) req->r_flags |= CEPH_OSD_FLAG_ONDISK; atomic_inc(&req->r_osdc->num_requests); + + req->r_start_stamp = jiffies; } static void submit_request(struct ceph_osd_request *req, bool wrlocked) @@ -1789,6 +1791,14 @@ static void cancel_request(struct ceph_osd_request *req) ceph_osdc_put_request(req); } +static void abort_request(struct ceph_osd_request *req, int err) +{ + dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err); + + cancel_map_check(req); + complete_request(req, err); +} + static void check_pool_dne(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; @@ -2487,6 +2497,7 @@ static void handle_timeout(struct work_struct *work) container_of(work, struct ceph_osd_client, timeout_work.work); struct ceph_options *opts = osdc->client->options; unsigned long cutoff = jiffies - opts->osd_keepalive_timeout; + unsigned long expiry_cutoff = jiffies - opts->osd_request_timeout; LIST_HEAD(slow_osds); struct rb_node *n, *p; @@ -2502,15 +2513,23 @@ static void handle_timeout(struct work_struct *work) struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); bool found = false; - for (p = rb_first(&osd->o_requests); p; p = rb_next(p)) { + for (p = rb_first(&osd->o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); + p = rb_next(p); /* abort_request() */ + if (time_before(req->r_stamp, cutoff)) { dout(" req %p tid %llu on osd%d is laggy\n", req, req->r_tid, osd->o_osd); found = true; } + if (opts->osd_request_timeout && + time_before(req->r_start_stamp, expiry_cutoff)) { + pr_err_ratelimited("tid %llu on osd%d timeout\n", + req->r_tid, osd->o_osd); + abort_request(req, -ETIMEDOUT); + } } for (p = rb_first(&osd->o_linger_requests); p; p = rb_next(p)) { struct ceph_osd_linger_request *lreq = @@ -2530,6 +2549,21 @@ static void handle_timeout(struct work_struct *work) list_move_tail(&osd->o_keepalive_item, &slow_osds); } + if (opts->osd_request_timeout) { + for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) { + struct ceph_osd_request *req = + rb_entry(p, struct ceph_osd_request, r_node); + + p = rb_next(p); /* abort_request() */ + + if (time_before(req->r_start_stamp, expiry_cutoff)) { + pr_err_ratelimited("tid %llu on osd%d timeout\n", + req->r_tid, osdc->homeless_osd.o_osd); + abort_request(req, -ETIMEDOUT); + } + } + } + if (atomic_read(&osdc->num_homeless) || !list_empty(&slow_osds)) maybe_request_map(osdc); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 6824c0ec8373..ffe9e904d4d1 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -390,9 +390,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end) dout("crush decode tunable chooseleaf_stable = %d\n", c->chooseleaf_stable); - crush_finalize(c); - done: + crush_finalize(c); dout("crush_decode success\n"); return c; @@ -1380,7 +1379,6 @@ static int decode_new_up_state_weight(void **p, void *end, if ((map->osd_state[osd] & CEPH_OSD_EXISTS) && (xorstate & CEPH_OSD_EXISTS)) { pr_info("osd%d does not exist\n", osd); - map->osd_weight[osd] = CEPH_OSD_IN; ret = set_primary_affinity(map, osd, CEPH_OSD_DEFAULT_PRIMARY_AFFINITY); if (ret) |