Merge tag 'ceph-for-5.8-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "The highlights are:

   - OSD/MDS latency and caps cache metrics infrastructure for the
     filesytem (Xiubo Li). Currently available through debugfs and will
     be periodically sent to the MDS in the future.

   - support for replica reads (balanced and localized reads) for rbd
     and the filesystem (myself). The default remains to always read
     from primary, users can opt-in with the new crush_location and
     read_from_replica options. Note that reading from replica is safe
     for general use only since Octopus.

   - support for RADOS allocation hint flags (myself). Currently used by
     rbd to propagate the compressible/incompressible hint given with
     the new compression_hint map option and ready for passing on more
     advanced hints, e.g. based on fadvise() from the filesystem.

   - support for efficient cross-quota-realm renames (Luis Henriques)

   - assorted cap handling improvements and cleanups, particularly
     untangling some of the locking (Jeff Layton)"

* tag 'ceph-for-5.8-rc1' of git://github.com/ceph/ceph-client: (29 commits)
  rbd: compression_hint option
  libceph: support for alloc hint flags
  libceph: read_from_replica option
  libceph: support for balanced and localized reads
  libceph: crush_location infrastructure
  libceph: decode CRUSH device/bucket types and names
  libceph: add non-asserting rbtree insertion helper
  ceph: skip checking caps when session reconnecting and releasing reqs
  ceph: make sure mdsc->mutex is nested in s->s_mutex to fix dead lock
  ceph: don't return -ESTALE if there's still an open file
  libceph, rbd: replace zero-length array with flexible-array
  ceph: allow rename operation under different quota realms
  ceph: normalize 'delta' parameter usage in check_quota_exceeded
  ceph: ceph_kick_flushing_caps needs the s_mutex
  ceph: request expedited service on session's last cap flush
  ceph: convert mdsc->cap_dirty to a per-session list
  ceph: reset i_requested_max_size if file write is not wanted
  ceph: throw a warning if we destroy session with mutex still locked
  ceph: fix potential race in ceph_check_caps
  ceph: document what protects i_dirty_item and i_flushing_item
  ...

drivers/block/rbd.c

@@ -836,6 +836,7 @@ enum {
 	Opt_lock_timeout,
 	/* int args above */
 	Opt_pool_ns,
+	Opt_compression_hint,
 	/* string args above */
 	Opt_read_only,
 	Opt_read_write,
@@ -844,8 +845,23 @@ enum {
 	Opt_notrim,
 };
 
+enum {
+	Opt_compression_hint_none,
+	Opt_compression_hint_compressible,
+	Opt_compression_hint_incompressible,
+};
+
+static const struct constant_table rbd_param_compression_hint[] = {
+	{"none",		Opt_compression_hint_none},
+	{"compressible",	Opt_compression_hint_compressible},
+	{"incompressible",	Opt_compression_hint_incompressible},
+	{}
+};
+
 static const struct fs_parameter_spec rbd_parameters[] = {
 	fsparam_u32	("alloc_size",			Opt_alloc_size),
+	fsparam_enum	("compression_hint",		Opt_compression_hint,
+			 rbd_param_compression_hint),
 	fsparam_flag	("exclusive",			Opt_exclusive),
 	fsparam_flag	("lock_on_read",		Opt_lock_on_read),
 	fsparam_u32	("lock_timeout",		Opt_lock_timeout),
@@ -867,6 +883,8 @@ struct rbd_options {
 	bool	lock_on_read;
 	bool	exclusive;
 	bool	trim;
+
+	u32 alloc_hint_flags;  /* CEPH_OSD_OP_ALLOC_HINT_FLAG_* */
 };
 
 #define RBD_QUEUE_DEPTH_DEFAULT	BLKDEV_MAX_RQ
@@ -2253,7 +2271,8 @@ static void __rbd_osd_setup_write_ops(struct ceph_osd_request *osd_req,
 	    !(obj_req->flags & RBD_OBJ_FLAG_MAY_EXIST)) {
 		osd_req_op_alloc_hint_init(osd_req, which++,
 					   rbd_dev->layout.object_size,
-					   rbd_dev->layout.object_size);
+					   rbd_dev->layout.object_size,
+					   rbd_dev->opts->alloc_hint_flags);
 	}
 
 	if (rbd_obj_is_entire(obj_req))
@@ -6331,6 +6350,29 @@ static int rbd_parse_param(struct fs_parameter *param,
 		pctx->spec->pool_ns = param->string;
 		param->string = NULL;
 		break;
+	case Opt_compression_hint:
+		switch (result.uint_32) {
+		case Opt_compression_hint_none:
+			opt->alloc_hint_flags &=
+			    ~(CEPH_OSD_ALLOC_HINT_FLAG_COMPRESSIBLE |
+			      CEPH_OSD_ALLOC_HINT_FLAG_INCOMPRESSIBLE);
+			break;
+		case Opt_compression_hint_compressible:
+			opt->alloc_hint_flags |=
+			    CEPH_OSD_ALLOC_HINT_FLAG_COMPRESSIBLE;
+			opt->alloc_hint_flags &=
+			    ~CEPH_OSD_ALLOC_HINT_FLAG_INCOMPRESSIBLE;
+			break;
+		case Opt_compression_hint_incompressible:
+			opt->alloc_hint_flags |=
+			    CEPH_OSD_ALLOC_HINT_FLAG_INCOMPRESSIBLE;
+			opt->alloc_hint_flags &=
+			    ~CEPH_OSD_ALLOC_HINT_FLAG_COMPRESSIBLE;
+			break;
+		default:
+			BUG();
+		}
+		break;
 	case Opt_read_only:
 		opt->read_only = true;
 		break;

drivers/block/rbd_types.h

@@ -93,7 +93,7 @@ struct rbd_image_header_ondisk {
 	__le32 snap_count;
 	__le32 reserved;
 	__le64 snap_names_len;
-	struct rbd_image_snap_ondisk snaps[0];
+	struct rbd_image_snap_ondisk snaps[];
 } __attribute__((packed));
 
 

fs/ceph/Makefile

@@ -8,7 +8,7 @@ obj-$(CONFIG_CEPH_FS) += ceph.o
 ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
 	export.o caps.o snap.o xattr.o quota.o io.o \
 	mds_client.o mdsmap.o strings.o ceph_frag.o \
-	debugfs.o util.o
+	debugfs.o util.o metric.o
 
 ceph-$(CONFIG_CEPH_FSCACHE) += cache.o
 ceph-$(CONFIG_CEPH_FS_POSIX_ACL) += acl.o

fs/ceph/acl.c

@@ -22,7 +22,7 @@ static inline void ceph_set_cached_acl(struct inode *inode,
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
 	spin_lock(&ci->i_ceph_lock);
-	if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 0))
+	if (__ceph_caps_issued_mask_metric(ci, CEPH_CAP_XATTR_SHARED, 0))
 		set_cached_acl(inode, type, acl);
 	else
 		forget_cached_acl(inode, type);

fs/ceph/addr.c

@@ -11,10 +11,12 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/signal.h>
 #include <linux/iversion.h>
+#include <linux/ktime.h>
 
 #include "super.h"
 #include "mds_client.h"
 #include "cache.h"
+#include "metric.h"
 #include <linux/ceph/osd_client.h>
 #include <linux/ceph/striper.h>
 
@@ -216,6 +218,9 @@ static int ceph_sync_readpages(struct ceph_fs_client *fsc,
 	if (!rc)
 		rc = ceph_osdc_wait_request(osdc, req);
 
+	ceph_update_read_latency(&fsc->mdsc->metric, req->r_start_latency,
+				 req->r_end_latency, rc);
+
 	ceph_osdc_put_request(req);
 	dout("readpages result %d\n", rc);
 	return rc;
@@ -299,6 +304,7 @@ static int ceph_readpage(struct file *filp, struct page *page)
 static void finish_read(struct ceph_osd_request *req)
 {
 	struct inode *inode = req->r_inode;
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_osd_data *osd_data;
 	int rc = req->r_result <= 0 ? req->r_result : 0;
 	int bytes = req->r_result >= 0 ? req->r_result : 0;
@@ -336,6 +342,10 @@ static void finish_read(struct ceph_osd_request *req)
 		put_page(page);
 		bytes -= PAGE_SIZE;
 	}
+
+	ceph_update_read_latency(&fsc->mdsc->metric, req->r_start_latency,
+				 req->r_end_latency, rc);
+
 	kfree(osd_data->pages);
 }
 
@@ -643,6 +653,9 @@ static int ceph_sync_writepages(struct ceph_fs_client *fsc,
 	if (!rc)
 		rc = ceph_osdc_wait_request(osdc, req);
 
+	ceph_update_write_latency(&fsc->mdsc->metric, req->r_start_latency,
+				  req->r_end_latency, rc);
+
 	ceph_osdc_put_request(req);
 	if (rc == 0)
 		rc = len;
@@ -794,6 +807,9 @@ static void writepages_finish(struct ceph_osd_request *req)
 		ceph_clear_error_write(ci);
 	}
 
+	ceph_update_write_latency(&fsc->mdsc->metric, req->r_start_latency,
+				  req->r_end_latency, rc);
+
 	/*
 	 * We lost the cache cap, need to truncate the page before
 	 * it is unlocked, otherwise we'd truncate it later in the
@@ -1852,6 +1868,10 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 	err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
 	if (!err)
 		err = ceph_osdc_wait_request(&fsc->client->osdc, req);
+
+	ceph_update_write_latency(&fsc->mdsc->metric, req->r_start_latency,
+				  req->r_end_latency, err);
+
 out_put:
 	ceph_osdc_put_request(req);
 	if (err == -ECANCELED)