From 97e27aaa9a2cbd6238c66b3251d397e0eacc9968 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 19 Mar 2020 23:45:01 -0400 Subject: ceph: add read/write latency metric support Calculate the latency for OSD read requests. Add a new r_end_stamp field to struct ceph_osd_request that will hold the time of that the reply was received. Use that to calculate the RTT for each call, and divide the sum of those by number of calls to get averate RTT. Keep a tally of RTT for OSD writes and number of calls to track average latency of OSD writes. URL: https://tracker.ceph.com/issues/43215 Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 9d9f745b98a1..734f7c6a9f56 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -213,6 +214,8 @@ struct ceph_osd_request { /* internal */ unsigned long r_stamp; /* jiffies, send or check time */ unsigned long r_start_stamp; /* jiffies */ + ktime_t r_start_latency; /* ktime_t */ + ktime_t r_end_latency; /* ktime_t */ int r_attempts; u32 r_map_dne_bound; -- cgit v1.2.3 From 53ab8e7cd2d47594e68951994ac083d30f82fce4 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 7 May 2020 13:51:38 -0500 Subject: libceph, rbd: replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/mon_client.h | 2 +- include/linux/crush/crush.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h index dbb8a6959a73..ce4ffeb384d7 100644 --- a/include/linux/ceph/mon_client.h +++ b/include/linux/ceph/mon_client.h @@ -19,7 +19,7 @@ struct ceph_monmap { struct ceph_fsid fsid; u32 epoch; u32 num_mon; - struct ceph_entity_inst mon_inst[0]; + struct ceph_entity_inst mon_inst[]; }; struct ceph_mon_client; diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 54741295c70b..38b0e4d50ed9 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -87,7 +87,7 @@ struct crush_rule_mask { struct crush_rule { __u32 len; struct crush_rule_mask mask; - struct crush_rule_step steps[0]; + struct crush_rule_step steps[]; }; #define crush_rule_size(len) (sizeof(struct crush_rule) + \ -- cgit v1.2.3 From 8a4b863c876d9f135fa00cfe65774c3740970303 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 19 May 2020 16:46:47 +0200 Subject: libceph: add non-asserting rbtree insertion helper Needed for the next commit and useful for ceph_pg_pool_info tree as well. I'm leaving the asserting helper in for now, but we should look at getting rid of it in the future. Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/libceph.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 525b7c3f1c81..4b5a47bcaba4 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -188,7 +188,7 @@ static inline int calc_pages_for(u64 off, u64 len) #define RB_CMP3WAY(a, b) ((a) < (b) ? -1 : (a) > (b)) #define DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, cmpexp, keyexp, nodefld) \ -static void insert_##name(struct rb_root *root, type *t) \ +static bool __insert_##name(struct rb_root *root, type *t) \ { \ struct rb_node **n = &root->rb_node; \ struct rb_node *parent = NULL; \ @@ -206,11 +206,17 @@ static void insert_##name(struct rb_root *root, type *t) \ else if (cmp > 0) \ n = &(*n)->rb_right; \ else \ - BUG(); \ + return false; \ } \ \ rb_link_node(&t->nodefld, parent, n); \ rb_insert_color(&t->nodefld, root); \ + return true; \ +} \ +static void __maybe_unused insert_##name(struct rb_root *root, type *t) \ +{ \ + if (!__insert_##name(root, t)) \ + BUG(); \ } \ static void erase_##name(struct rb_root *root, type *t) \ { \ -- cgit v1.2.3 From 86403a92c3c5c6c395983fdbfc5e2f29dc39279b Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 19 May 2020 17:09:52 +0200 Subject: libceph: decode CRUSH device/bucket types and names These would be matched with the provided client location to calculate the locality value. Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/crush/crush.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 38b0e4d50ed9..33c16f2de7f6 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -301,6 +301,12 @@ struct crush_map { __u32 *choose_tries; #else + /* device/bucket type id -> type name (CrushWrapper::type_map) */ + struct rb_root type_names; + + /* device/bucket id -> name (CrushWrapper::name_map) */ + struct rb_root names; + /* CrushWrapper::choose_args */ struct rb_root choose_args; #endif @@ -342,4 +348,10 @@ struct crush_work { struct crush_work_bucket **work; /* Per-bucket working store */ }; +#ifdef __KERNEL__ +/* osdmap.c */ +void clear_crush_names(struct rb_root *root); +void clear_choose_args(struct crush_map *c); +#endif + #endif -- cgit v1.2.3 From 45e6aa9f5592cd127367074f4822039cd8a825c3 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 22 May 2020 15:24:53 +0200 Subject: libceph: crush_location infrastructure Allow expressing client's location in terms of CRUSH hierarchy as a set of (bucket type name, bucket name) pairs. The userspace syntax "crush_location = key1=value1 key2=value2" is incompatible with mount options and needed adaptation. Key-value pairs are separated by '|' and we use ':' instead of '=' to separate keys from values. So for: crush_location = host=foo rack=bar one would write: crush_location=host:foo|rack:bar As in userspace, "multipath" locations are supported, so indicating locality for parallel hierarchies is possible: crush_location=rack:foo1|rack:foo2|datacenter:bar Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/libceph.h | 1 + include/linux/ceph/osdmap.h | 16 +++++++++++++++- 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 4b5a47bcaba4..4733959f1ec7 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -64,6 +64,7 @@ struct ceph_options { int num_mon; char *name; struct ceph_crypto_key *key; + struct rb_root crush_locs; }; /* diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 5e601975745f..8c9d18cc9f45 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -302,9 +302,23 @@ bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap, int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap, const struct ceph_pg *raw_pgid); +struct crush_loc { + char *cl_type_name; + char *cl_name; +}; + +struct crush_loc_node { + struct rb_node cl_node; + struct crush_loc cl_loc; /* pointers into cl_data */ + char cl_data[]; +}; + +int ceph_parse_crush_location(char *crush_location, struct rb_root *locs); +int ceph_compare_crush_locs(struct rb_root *locs1, struct rb_root *locs2); +void ceph_clear_crush_locs(struct rb_root *locs); + extern struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, u64 id); - extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id); extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name); u64 ceph_pg_pool_flags(struct ceph_osdmap *map, u64 id); -- cgit v1.2.3 From 117d96a04f007ce8fc2e292369056c3bd09f6f63 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sat, 23 May 2020 11:45:48 +0200 Subject: libceph: support for balanced and localized reads OSD-side issues with reads from replica have been resolved in Octopus. Reading from replica should be safe wrt. unstable or uncommitted state now, so add support for balanced and localized reads. There are two cases when a read from replica can't be served: - OSD may silently drop the request, expecting the client to notice that the acting set has changed and resend via the usual means (handled with t->used_replica) - OSD may return EAGAIN, expecting the client to resend to the primary, ignoring replica read flags (see handle_reply()) Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/osd_client.h | 1 + include/linux/ceph/osdmap.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 734f7c6a9f56..671fb93e8c60 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -165,6 +165,7 @@ struct ceph_osd_request_target { bool recovery_deletes; unsigned int flags; /* CEPH_OSD_FLAG_* */ + bool used_replica; bool paused; u32 epoch; diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 8c9d18cc9f45..3f4498fef6ad 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -317,6 +317,9 @@ int ceph_parse_crush_location(char *crush_location, struct rb_root *locs); int ceph_compare_crush_locs(struct rb_root *locs1, struct rb_root *locs2); void ceph_clear_crush_locs(struct rb_root *locs); +int ceph_get_crush_locality(struct ceph_osdmap *osdmap, int id, + struct rb_root *locs); + extern struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, u64 id); extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id); -- cgit v1.2.3 From 8ad44d5e0d1eda7e4a0ed382174888476dc81789 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sat, 23 May 2020 11:47:33 +0200 Subject: libceph: read_from_replica option Expose replica reads through read_from_replica=balance and read_from_replica=localize. The default is to read from primary (read_from_replica=no). Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/libceph.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 4733959f1ec7..2247e71beb83 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -53,6 +53,8 @@ struct ceph_options { unsigned long osd_keepalive_timeout; /* jiffies */ unsigned long osd_request_timeout; /* jiffies */ + u32 osd_req_flags; /* CEPH_OSD_FLAG_*, applied to each OSD request */ + /* * any type that can't be simply compared or doesn't need * to be compared should go beyond this point, -- cgit v1.2.3 From d3798acc094c8ff2406e9acc7a9b2c09da994616 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 29 May 2020 20:31:37 +0200 Subject: libceph: support for alloc hint flags Allow indicating future I/O pattern via flags. This is supported since Kraken (and bluestore persists flags together with expected_object_size and expected_write_size). Signed-off-by: Ilya Dryomov Reviewed-by: Jason Dillaman --- include/linux/ceph/osd_client.h | 4 +++- include/linux/ceph/rados.h | 14 ++++++++++++++ 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 671fb93e8c60..c60b59e9291b 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -136,6 +136,7 @@ struct ceph_osd_req_op { struct { u64 expected_object_size; u64 expected_write_size; + u32 flags; /* CEPH_OSD_OP_ALLOC_HINT_FLAG_* */ } alloc_hint; struct { u64 snapid; @@ -472,7 +473,8 @@ extern int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int extern void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req, unsigned int which, u64 expected_object_size, - u64 expected_write_size); + u64 expected_write_size, + u32 flags); extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index 88ed3c5c04c5..3a518fd0eaad 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -464,6 +464,19 @@ enum { const char *ceph_osd_watch_op_name(int o); +enum { + CEPH_OSD_ALLOC_HINT_FLAG_SEQUENTIAL_WRITE = 1, + CEPH_OSD_ALLOC_HINT_FLAG_RANDOM_WRITE = 2, + CEPH_OSD_ALLOC_HINT_FLAG_SEQUENTIAL_READ = 4, + CEPH_OSD_ALLOC_HINT_FLAG_RANDOM_READ = 8, + CEPH_OSD_ALLOC_HINT_FLAG_APPEND_ONLY = 16, + CEPH_OSD_ALLOC_HINT_FLAG_IMMUTABLE = 32, + CEPH_OSD_ALLOC_HINT_FLAG_SHORTLIVED = 64, + CEPH_OSD_ALLOC_HINT_FLAG_LONGLIVED = 128, + CEPH_OSD_ALLOC_HINT_FLAG_COMPRESSIBLE = 256, + CEPH_OSD_ALLOC_HINT_FLAG_INCOMPRESSIBLE = 512, +}; + enum { CEPH_OSD_BACKOFF_OP_BLOCK = 1, CEPH_OSD_BACKOFF_OP_ACK_BLOCK = 2, @@ -517,6 +530,7 @@ struct ceph_osd_op { struct { __le64 expected_object_size; __le64 expected_write_size; + __le32 flags; /* CEPH_OSD_OP_ALLOC_HINT_FLAG_* */ } __attribute__ ((packed)) alloc_hint; struct { __le64 snapid; -- cgit v1.2.3