From dc6ae6d8e7726bad4f1c87244b49cac851746c65 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sun, 31 Jan 2016 14:36:07 +0100 Subject: crush: add chooseleaf_stable tunable Add a tunable to fix the bug that chooseleaf may cause unnecessary pg migrations when some device fails. Reflects ceph.git commit fdb3f664448e80d984470f32f04e2e6f03ab52ec. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/crush/crush.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 48b49305716b..be8f12b8f195 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -59,7 +59,8 @@ enum { CRUSH_RULE_SET_CHOOSELEAF_TRIES = 9, /* override chooseleaf_descend_once */ CRUSH_RULE_SET_CHOOSE_LOCAL_TRIES = 10, CRUSH_RULE_SET_CHOOSE_LOCAL_FALLBACK_TRIES = 11, - CRUSH_RULE_SET_CHOOSELEAF_VARY_R = 12 + CRUSH_RULE_SET_CHOOSELEAF_VARY_R = 12, + CRUSH_RULE_SET_CHOOSELEAF_STABLE = 13 }; /* @@ -205,6 +206,11 @@ struct crush_map { * mappings line up a bit better with previous mappings. */ __u8 chooseleaf_vary_r; + /* if true, it makes chooseleaf firstn to return stable results (if + * no local retry) so that data migrations would be optimal when some + * device fails. */ + __u8 chooseleaf_stable; + #ifndef __KERNEL__ /* * version 0 (original) of straw_calc has various flaws. version 1 -- cgit v1.2.3 From 97db9a88186e3a7d3a1942370c836bf221d3ab90 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 1 Feb 2016 17:08:33 +0100 Subject: libceph: advertise support for TUNABLES5 Add TUNABLES5 feature (chooseleaf_stable tunable) to a set of features supported by default. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/ceph_features.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index f89b31d45cc8..c3b211c9fe83 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -63,6 +63,16 @@ #define CEPH_FEATURE_OSD_MIN_SIZE_RECOVERY (1ULL<<49) // duplicated since it was introduced at the same time as MIN_SIZE_RECOVERY #define CEPH_FEATURE_OSD_PROXY_FEATURES (1ULL<<49) /* overlap w/ above */ +#define CEPH_FEATURE_MON_METADATA (1ULL<<50) +#define CEPH_FEATURE_OSD_BITWISE_HOBJ_SORT (1ULL<<51) /* can sort objs bitwise */ +#define CEPH_FEATURE_OSD_PROXY_WRITE_FEATURES (1ULL<<52) +#define CEPH_FEATURE_ERASURE_CODE_PLUGINS_V3 (1ULL<<53) +#define CEPH_FEATURE_OSD_HITSET_GMT (1ULL<<54) +#define CEPH_FEATURE_HAMMER_0_94_4 (1ULL<<55) +#define CEPH_FEATURE_NEW_OSDOP_ENCODING (1ULL<<56) /* New, v7 encoding */ +#define CEPH_FEATURE_MON_STATEFUL_SUB (1ULL<<57) /* stateful mon subscription */ +#define CEPH_FEATURE_MON_ROUTE_OSDMAP (1ULL<<57) /* peon sends osdmaps */ +#define CEPH_FEATURE_CRUSH_TUNABLES5 (1ULL<<58) /* chooseleaf stable mode */ /* * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature @@ -108,7 +118,8 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_CRUSH_TUNABLES3 | \ CEPH_FEATURE_OSD_PRIMARY_AFFINITY | \ CEPH_FEATURE_MSGR_KEEPALIVE2 | \ - CEPH_FEATURE_CRUSH_V4) + CEPH_FEATURE_CRUSH_V4 | \ + CEPH_FEATURE_CRUSH_TUNABLES5) #define CEPH_FEATURES_REQUIRED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ -- cgit v1.2.3 From b0b31a8ffe54abf0a455bcaee54dd92f08817164 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 3 Feb 2016 15:25:48 +0100 Subject: libceph: MOSDOpReply v7 encoding Empty request_redirect_t (struct ceph_request_redirect in the kernel client) is now encoded with a bool. NEW_OSDOPREPLY_ENCODING feature bit overlaps with already supported CRUSH_TUNABLES5. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/ceph_features.h | 5 ++++- net/ceph/osd_client.c | 10 ++++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index c3b211c9fe83..c1ef6f14e7be 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -73,6 +73,8 @@ #define CEPH_FEATURE_MON_STATEFUL_SUB (1ULL<<57) /* stateful mon subscription */ #define CEPH_FEATURE_MON_ROUTE_OSDMAP (1ULL<<57) /* peon sends osdmaps */ #define CEPH_FEATURE_CRUSH_TUNABLES5 (1ULL<<58) /* chooseleaf stable mode */ +// duplicated since it was introduced at the same time as CEPH_FEATURE_CRUSH_TUNABLES5 +#define CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING (1ULL<<58) /* New, v7 encoding */ /* * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature @@ -119,7 +121,8 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_OSD_PRIMARY_AFFINITY | \ CEPH_FEATURE_MSGR_KEEPALIVE2 | \ CEPH_FEATURE_CRUSH_V4 | \ - CEPH_FEATURE_CRUSH_TUNABLES5) + CEPH_FEATURE_CRUSH_TUNABLES5 | \ + CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING) #define CEPH_FEATURES_REQUIRED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index f8f235930d88..3534e12683d3 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1770,6 +1770,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg) u32 osdmap_epoch; int already_completed; u32 bytes; + u8 decode_redir; unsigned int i; tid = le64_to_cpu(msg->hdr.tid); @@ -1841,6 +1842,15 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg) p += 8 + 4; /* skip replay_version */ p += 8; /* skip user_version */ + if (le16_to_cpu(msg->hdr.version) >= 7) + ceph_decode_8_safe(&p, end, decode_redir, bad_put); + else + decode_redir = 1; + } else { + decode_redir = 0; + } + + if (decode_redir) { err = ceph_redirect_decode(&p, end, &redir); if (err) goto bad_put; -- cgit v1.2.3