From 9afd30dbc82a9dbea4101aba57beb2a2a7e1b8d5 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 28 Feb 2017 18:53:53 +0100 Subject: [PATCH 1/4] libceph: fix crush_decode() for older maps Older (shorter) CRUSH maps too need to be finalized. Fixes: 66a0e2d579db ("crush: remove mutable part of CRUSH map") Signed-off-by: Ilya Dryomov --- net/ceph/osdmap.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 6824c0ec8373..cc22dd282a3e 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; From b581a5854eee4b7851dedb0f8c2ceb54fb902c06 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 1 Mar 2017 17:33:27 +0100 Subject: [PATCH 2/4] libceph: don't set weight to IN when OSD is destroyed Since ceph.git commit 4e28f9e63644 ("osd/OSDMap: clear osd_info, osd_xinfo on osd deletion"), weight is set to IN when OSD is deleted. This changes the result of applying an incremental for clients, not just OSDs. Because CRUSH computations are obviously affected, pre-4e28f9e63644 servers disagree with post-4e28f9e63644 clients on object placement, resulting in misdirected requests. Mirrors ceph.git commit a6009d1039a55e2c77f431662b3d6cc5a8e8e63f. Fixes: 930c53286977 ("libceph: apply new_state before new_up_client on incrementals") Link: http://tracker.ceph.com/issues/19122 Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- net/ceph/osdmap.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index cc22dd282a3e..ffe9e904d4d1 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -1379,7 +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) From 8767b293a4ab6632f9288f34bcf2ab9ba20dca3a Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 2 Mar 2017 19:56:57 +0100 Subject: [PATCH 3/4] rbd: supported_features bus attribute ... so that userspace can generate meaningful error messages and spell out unsupported features that need to be disabled. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- drivers/block/rbd.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 4d6807723798..517838b65964 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -120,10 +120,11 @@ static int atomic_dec_return_safe(atomic_t *v) /* Feature bits */ -#define RBD_FEATURE_LAYERING (1<<0) -#define RBD_FEATURE_STRIPINGV2 (1<<1) -#define RBD_FEATURE_EXCLUSIVE_LOCK (1<<2) -#define RBD_FEATURE_DATA_POOL (1<<7) +#define RBD_FEATURE_LAYERING (1ULL<<0) +#define RBD_FEATURE_STRIPINGV2 (1ULL<<1) +#define RBD_FEATURE_EXCLUSIVE_LOCK (1ULL<<2) +#define RBD_FEATURE_DATA_POOL (1ULL<<7) + #define RBD_FEATURES_ALL (RBD_FEATURE_LAYERING | \ RBD_FEATURE_STRIPINGV2 | \ RBD_FEATURE_EXCLUSIVE_LOCK | \ @@ -499,16 +500,23 @@ static bool rbd_is_lock_owner(struct rbd_device *rbd_dev) return is_lock_owner; } +static ssize_t rbd_supported_features_show(struct bus_type *bus, char *buf) +{ + return sprintf(buf, "0x%llx\n", RBD_FEATURES_SUPPORTED); +} + static BUS_ATTR(add, S_IWUSR, NULL, rbd_add); static BUS_ATTR(remove, S_IWUSR, NULL, rbd_remove); static BUS_ATTR(add_single_major, S_IWUSR, NULL, rbd_add_single_major); static BUS_ATTR(remove_single_major, S_IWUSR, NULL, rbd_remove_single_major); +static BUS_ATTR(supported_features, S_IRUGO, rbd_supported_features_show, NULL); static struct attribute *rbd_bus_attrs[] = { &bus_attr_add.attr, &bus_attr_remove.attr, &bus_attr_add_single_major.attr, &bus_attr_remove_single_major.attr, + &bus_attr_supported_features.attr, NULL, }; From 7cc5e38f2f0b0b58a22a4c18a56348dd99a71270 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sun, 12 Feb 2017 17:11:07 +0100 Subject: [PATCH 4/4] libceph: osd_request_timeout option osd_request_timeout specifies how many seconds to wait for a response from OSDs before returning -ETIMEDOUT from an OSD request. 0 (default) means no limit. osd_request_timeout is osdkeepalive-precise -- in-flight requests are swept through every osdkeepalive seconds. With ack vs commit behaviour gone, abort_request() is really simple. This is based on a patch from Artur Molchanov . Tested-by: Artur Molchanov Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/libceph.h | 2 ++ include/linux/ceph/osd_client.h | 1 + net/ceph/ceph_common.c | 15 ++++++++++++++ net/ceph/osd_client.c | 36 ++++++++++++++++++++++++++++++++- 4 files changed, 53 insertions(+), 1 deletion(-) diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 1816c5e26581..88cd5dc8e238 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -48,6 +48,7 @@ struct ceph_options { unsigned long mount_timeout; /* jiffies */ unsigned long osd_idle_ttl; /* jiffies */ unsigned long osd_keepalive_timeout; /* jiffies */ + unsigned long osd_request_timeout; /* jiffies */ /* * any type that can't be simply compared or doesn't need need @@ -68,6 +69,7 @@ struct ceph_options { #define CEPH_MOUNT_TIMEOUT_DEFAULT msecs_to_jiffies(60 * 1000) #define CEPH_OSD_KEEPALIVE_DEFAULT msecs_to_jiffies(5 * 1000) #define CEPH_OSD_IDLE_TTL_DEFAULT msecs_to_jiffies(60 * 1000) +#define CEPH_OSD_REQUEST_TIMEOUT_DEFAULT 0 /* no timeout */ #define CEPH_MONC_HUNT_INTERVAL msecs_to_jiffies(3 * 1000) #define CEPH_MONC_PING_INTERVAL msecs_to_jiffies(10 * 1000) diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 2ea0c282f3dc..c125b5d9e13c 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -189,6 +189,7 @@ struct ceph_osd_request { /* internal */ unsigned long r_stamp; /* jiffies, send or check time */ + unsigned long r_start_stamp; /* jiffies */ int r_attempts; struct ceph_eversion r_replay_version; /* aka reassert_version */ u32 r_last_force_resend; 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/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);