Commit 969e5aa3 authored by Alex Elder's avatar Alex Elder

Merge branch 'testing' of github.com:ceph/ceph-client into v3.8-rc5-testing

parents 949db153 1ec3911d
This diff is collapsed.
......@@ -611,8 +611,16 @@ int ceph_add_cap(struct inode *inode,
if (flags & CEPH_CAP_FLAG_AUTH)
ci->i_auth_cap = cap;
else if (ci->i_auth_cap == cap)
else if (ci->i_auth_cap == cap) {
ci->i_auth_cap = NULL;
spin_lock(&mdsc->cap_dirty_lock);
if (!list_empty(&ci->i_dirty_item)) {
dout(" moving %p to cap_dirty_migrating\n", inode);
list_move(&ci->i_dirty_item,
&mdsc->cap_dirty_migrating);
}
spin_unlock(&mdsc->cap_dirty_lock);
}
dout("add_cap inode %p (%llx.%llx) cap %p %s now %s seq %d mds%d\n",
inode, ceph_vinop(inode), cap, ceph_cap_string(issued),
......@@ -1460,7 +1468,7 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
struct ceph_mds_client *mdsc = fsc->mdsc;
struct inode *inode = &ci->vfs_inode;
struct ceph_cap *cap;
int file_wanted, used;
int file_wanted, used, cap_used;
int took_snap_rwsem = 0; /* true if mdsc->snap_rwsem held */
int issued, implemented, want, retain, revoking, flushing = 0;
int mds = -1; /* keep track of how far we've gone through i_caps list
......@@ -1563,9 +1571,14 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
/* NOTE: no side-effects allowed, until we take s_mutex */
cap_used = used;
if (ci->i_auth_cap && cap != ci->i_auth_cap)
cap_used &= ~ci->i_auth_cap->issued;
revoking = cap->implemented & ~cap->issued;
dout(" mds%d cap %p issued %s implemented %s revoking %s\n",
dout(" mds%d cap %p used %s issued %s implemented %s revoking %s\n",
cap->mds, cap, ceph_cap_string(cap->issued),
ceph_cap_string(cap_used),
ceph_cap_string(cap->implemented),
ceph_cap_string(revoking));
......@@ -1593,7 +1606,7 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
}
/* completed revocation? going down and there are no caps? */
if (revoking && (revoking & used) == 0) {
if (revoking && (revoking & cap_used) == 0) {
dout("completed revocation of %s\n",
ceph_cap_string(cap->implemented & ~cap->issued));
goto ack;
......@@ -1670,8 +1683,8 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
sent++;
/* __send_cap drops i_ceph_lock */
delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, used, want,
retain, flushing, NULL);
delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, cap_used,
want, retain, flushing, NULL);
goto retry; /* retake i_ceph_lock and restart our cap scan. */
}
......@@ -2416,7 +2429,9 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
dout("mds wanted %s -> %s\n",
ceph_cap_string(le32_to_cpu(grant->wanted)),
ceph_cap_string(wanted));
grant->wanted = cpu_to_le32(wanted);
/* imported cap may not have correct mds_wanted */
if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT)
check_caps = 1;
}
cap->seq = seq;
......@@ -2820,6 +2835,9 @@ void ceph_handle_caps(struct ceph_mds_session *session,
dout(" mds%d seq %lld cap seq %u\n", session->s_mds, session->s_seq,
(unsigned)seq);
if (op == CEPH_CAP_OP_IMPORT)
ceph_add_cap_releases(mdsc, session);
/* lookup ino */
inode = ceph_find_inode(sb, vino);
ci = ceph_inode(inode);
......
......@@ -243,6 +243,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
err = ceph_mdsc_do_request(mdsc,
(flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
req);
if (err)
goto out_err;
err = ceph_handle_snapdir(req, dentry, err);
if (err == 0 && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
......@@ -263,6 +266,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
err = finish_no_open(file, dn);
} else {
dout("atomic_open finish_open on dn %p\n", dn);
if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
*opened |= FILE_CREATED;
}
err = finish_open(file, dentry, ceph_open, opened);
}
......
......@@ -194,7 +194,7 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
return -EFAULT;
down_read(&osdc->map_sem);
r = ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, &len,
r = ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, len,
&dl.object_no, &dl.object_offset,
&olen);
if (r < 0)
......
......@@ -232,6 +232,30 @@ static int parse_reply_info_filelock(void **p, void *end,
return -EIO;
}
/*
* parse create results
*/
static int parse_reply_info_create(void **p, void *end,
struct ceph_mds_reply_info_parsed *info,
int features)
{
if (features & CEPH_FEATURE_REPLY_CREATE_INODE) {
if (*p == end) {
info->has_create_ino = false;
} else {
info->has_create_ino = true;
info->ino = ceph_decode_64(p);
}
}
if (unlikely(*p != end))
goto bad;
return 0;
bad:
return -EIO;
}
/*
* parse extra results
*/
......@@ -241,8 +265,12 @@ static int parse_reply_info_extra(void **p, void *end,
{
if (info->head->op == CEPH_MDS_OP_GETFILELOCK)
return parse_reply_info_filelock(p, end, info, features);
else
else if (info->head->op == CEPH_MDS_OP_READDIR)
return parse_reply_info_dir(p, end, info, features);
else if (info->head->op == CEPH_MDS_OP_CREATE)
return parse_reply_info_create(p, end, info, features);
else
return -EIO;
}
/*
......@@ -2170,7 +2198,8 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
mutex_lock(&req->r_fill_mutex);
err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session);
if (err == 0) {
if (result == 0 && req->r_op != CEPH_MDS_OP_GETFILELOCK &&
if (result == 0 && (req->r_op == CEPH_MDS_OP_READDIR ||
req->r_op == CEPH_MDS_OP_LSSNAP) &&
rinfo->dir_nr)
ceph_readdir_prepopulate(req, req->r_session);
ceph_unreserve_caps(mdsc, &req->r_caps_reservation);
......
......@@ -74,6 +74,12 @@ struct ceph_mds_reply_info_parsed {
struct ceph_mds_reply_info_in *dir_in;
u8 dir_complete, dir_end;
};
/* for create results */
struct {
bool has_create_ino;
u64 ino;
};
};
/* encoded blob describing snapshot contexts for certain
......
......@@ -14,13 +14,19 @@
#define CEPH_FEATURE_DIRLAYOUTHASH (1<<7)
/* bits 8-17 defined by user-space; not supported yet here */
#define CEPH_FEATURE_CRUSH_TUNABLES (1<<18)
/* bits 19-24 defined by user-space; not supported yet here */
#define CEPH_FEATURE_CRUSH_TUNABLES2 (1<<25)
/* bit 26 defined by user-space; not supported yet here */
#define CEPH_FEATURE_REPLY_CREATE_INODE (1<<27)
/*
* Features supported.
*/
#define CEPH_FEATURES_SUPPORTED_DEFAULT \
(CEPH_FEATURE_NOSRCADDR | \
CEPH_FEATURE_CRUSH_TUNABLES)
CEPH_FEATURE_CRUSH_TUNABLES | \
CEPH_FEATURE_CRUSH_TUNABLES2 | \
CEPH_FEATURE_REPLY_CREATE_INODE)
#define CEPH_FEATURES_REQUIRED_DEFAULT \
(CEPH_FEATURE_NOSRCADDR)
......
......@@ -99,8 +99,8 @@ static inline int ceph_has_room(void **p, void *end, size_t n)
*
* There are two possible failures:
* - converting the string would require accessing memory at or
* beyond the "end" pointer provided (-E
* - memory could not be allocated for the result
* beyond the "end" pointer provided (-ERANGE)
* - memory could not be allocated for the result (-ENOMEM)
*/
static inline char *ceph_extract_encoded_string(void **p, void *end,
size_t *lenp, gfp_t gfp)
......@@ -238,6 +238,11 @@ static inline void ceph_encode_string(void **p, void *end,
ceph_encode_need(p, end, sizeof(u16), bad); \
ceph_encode_16(p, v); \
} while (0)
#define ceph_encode_8_safe(p, end, v, bad) \
do { \
ceph_encode_need(p, end, sizeof(u8), bad); \
ceph_encode_8(p, v); \
} while (0)
#define ceph_encode_copy_safe(p, end, pv, n, bad) \
do { \
......
......@@ -10,6 +10,7 @@
#include <linux/ceph/osdmap.h>
#include <linux/ceph/messenger.h>
#include <linux/ceph/auth.h>
#include <linux/ceph/pagelist.h>
/*
* Maximum object name size
......@@ -22,7 +23,6 @@ struct ceph_snap_context;
struct ceph_osd_request;
struct ceph_osd_client;
struct ceph_authorizer;
struct ceph_pagelist;
/*
* completion callback for async writepages
......@@ -95,7 +95,7 @@ struct ceph_osd_request {
struct bio *r_bio; /* instead of pages */
#endif
struct ceph_pagelist *r_trail; /* trailing part of the data */
struct ceph_pagelist r_trail; /* trailing part of the data */
};
struct ceph_osd_event {
......@@ -157,7 +157,6 @@ struct ceph_osd_client {
struct ceph_osd_req_op {
u16 op; /* CEPH_OSD_OP_* */
u32 flags; /* CEPH_OSD_FLAG_* */
union {
struct {
u64 offset, length;
......@@ -207,29 +206,24 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc,
extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
struct ceph_msg *msg);
extern int ceph_calc_raw_layout(struct ceph_osd_client *osdc,
struct ceph_file_layout *layout,
u64 snapid,
extern int ceph_calc_raw_layout(struct ceph_file_layout *layout,
u64 off, u64 *plen, u64 *bno,
struct ceph_osd_request *req,
struct ceph_osd_req_op *op);
extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
int flags,
struct ceph_snap_context *snapc,
struct ceph_osd_req_op *ops,
unsigned int num_op,
bool use_mempool,
gfp_t gfp_flags,
struct page **pages,
struct bio *bio);
gfp_t gfp_flags);
extern void ceph_osdc_build_request(struct ceph_osd_request *req,
u64 off, u64 *plen,
u64 off, u64 len,
unsigned int num_op,
struct ceph_osd_req_op *src_ops,
struct ceph_snap_context *snapc,
struct timespec *mtime,
const char *oid,
int oid_len);
u64 snap_id,
struct timespec *mtime);
extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
struct ceph_file_layout *layout,
......
......@@ -110,7 +110,7 @@ extern void ceph_osdmap_destroy(struct ceph_osdmap *map);
/* calculate mapping of a file extent to an object */
extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
u64 off, u64 *plen,
u64 off, u64 len,
u64 *bno, u64 *oxoff, u64 *oxlen);
/* calculate mapping of object to a placement group */
......
......@@ -162,6 +162,8 @@ struct crush_map {
__u32 choose_local_fallback_tries;
/* choose attempts before giving up */
__u32 choose_total_tries;
/* attempt chooseleaf inner descent once; on failure retry outer descent */
__u32 chooseleaf_descend_once;
};
......
......@@ -287,6 +287,7 @@ static int is_out(const struct crush_map *map, const __u32 *weight, int item, in
* @outpos: our position in that vector
* @firstn: true if choosing "first n" items, false if choosing "indep"
* @recurse_to_leaf: true if we want one device under each item of given type
* @descend_once: true if we should only try one descent before giving up
* @out2: second output vector for leaf items (if @recurse_to_leaf)
*/
static int crush_choose(const struct crush_map *map,
......@@ -295,7 +296,7 @@ static int crush_choose(const struct crush_map *map,
int x, int numrep, int type,
int *out, int outpos,
int firstn, int recurse_to_leaf,
int *out2)
int descend_once, int *out2)
{
int rep;
unsigned int ftotal, flocal;
......@@ -391,7 +392,7 @@ static int crush_choose(const struct crush_map *map,
}
reject = 0;
if (recurse_to_leaf) {
if (!collide && recurse_to_leaf) {
if (item < 0) {
if (crush_choose(map,
map->buckets[-1-item],
......@@ -399,6 +400,7 @@ static int crush_choose(const struct crush_map *map,
x, outpos+1, 0,
out2, outpos,
firstn, 0,
map->chooseleaf_descend_once,
NULL) <= outpos)
/* didn't get leaf */
reject = 1;
......@@ -422,7 +424,10 @@ static int crush_choose(const struct crush_map *map,
ftotal++;
flocal++;
if (collide && flocal <= map->choose_local_tries)
if (reject && descend_once)
/* let outer call try again */
skip_rep = 1;
else if (collide && flocal <= map->choose_local_tries)
/* retry locally a few times */
retry_bucket = 1;
else if (map->choose_local_fallback_tries > 0 &&
......@@ -485,6 +490,7 @@ int crush_do_rule(const struct crush_map *map,
int i, j;
int numrep;
int firstn;
const int descend_once = 0;
if ((__u32)ruleno >= map->max_rules) {
dprintk(" bad ruleno %d\n", ruleno);
......@@ -544,7 +550,8 @@ int crush_do_rule(const struct crush_map *map,
curstep->arg2,
o+osize, j,
firstn,
recurse_to_leaf, c+osize);
recurse_to_leaf,
descend_once, c+osize);
}
if (recurse_to_leaf)
......
This diff is collapsed.
......@@ -13,26 +13,18 @@
char *ceph_osdmap_state_str(char *str, int len, int state)
{
int flag = 0;
if (!len)
goto done;
return str;
*str = '\0';
if (state) {
if (state & CEPH_OSD_EXISTS) {
if ((state & CEPH_OSD_EXISTS) && (state & CEPH_OSD_UP))
snprintf(str, len, "exists, up");
else if (state & CEPH_OSD_EXISTS)
snprintf(str, len, "exists");
flag = 1;
}
if (state & CEPH_OSD_UP) {
snprintf(str, len, "%s%s%s", str, (flag ? ", " : ""),
"up");
flag = 1;
}
} else {
else if (state & CEPH_OSD_UP)
snprintf(str, len, "up");
else
snprintf(str, len, "doesn't exist");
}
done:
return str;
}
......@@ -170,6 +162,7 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
c->choose_local_tries = 2;
c->choose_local_fallback_tries = 5;
c->choose_total_tries = 19;
c->chooseleaf_descend_once = 0;
ceph_decode_need(p, end, 4*sizeof(u32), bad);
magic = ceph_decode_32(p);
......@@ -336,6 +329,11 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
dout("crush decode tunable choose_total_tries = %d",
c->choose_total_tries);
ceph_decode_need(p, end, sizeof(u32), done);
c->chooseleaf_descend_once = ceph_decode_32(p);
dout("crush decode tunable chooseleaf_descend_once = %d",
c->chooseleaf_descend_once);
done:
dout("crush_decode success\n");
return c;
......@@ -1010,7 +1008,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
* pass a stride back to the caller.
*/
int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
u64 off, u64 *plen,
u64 off, u64 len,
u64 *ono,
u64 *oxoff, u64 *oxlen)
{
......@@ -1021,7 +1019,7 @@ int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
u32 su_per_object;
u64 t, su_offset;
dout("mapping %llu~%llu osize %u fl_su %u\n", off, *plen,
dout("mapping %llu~%llu osize %u fl_su %u\n", off, len,
osize, su);
if (su == 0 || sc == 0)
goto invalid;
......@@ -1054,11 +1052,10 @@ int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
/*
* Calculate the length of the extent being written to the selected
* object. This is the minimum of the full length requested (plen) or
* object. This is the minimum of the full length requested (len) or
* the remainder of the current stripe being written to.
*/
*oxlen = min_t(u64, *plen, su - su_offset);
*plen = *oxlen;
*oxlen = min_t(u64, len, su - su_offset);
dout(" obj extent %llu~%llu\n", *oxoff, *oxlen);
return 0;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment