From 7a1c7d3ed705637aa8d1aaab3e04c547d1269106 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Wed, 17 Jun 2020 14:12:01 +0200
Subject: [PATCH] rbd: recognize crush_location and read_from_replica map
 options

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
(cherry picked from commit e3874a25f0e828e2a6bd8735dbeb14197008896c)
---
 doc/man/8/rbd.rst              | 41 ++++++++++++++++++++++++++++++++++
 src/tools/rbd/action/Kernel.cc | 22 ++++++++++++++++++
 2 files changed, 63 insertions(+)

diff --git a/doc/man/8/rbd.rst b/doc/man/8/rbd.rst
index b5a373584a213..ffc651546e944 100644
--- a/doc/man/8/rbd.rst
+++ b/doc/man/8/rbd.rst
@@ -792,6 +792,47 @@ Per mapping (block device) `rbd device map` options:
   solid-state drives).  For filestore with filestore_punch_hole = false, the
   recommended setting is image object size (typically 4M).
 
+* crush_location=x - Specify the location of the client in terms of CRUSH
+  hierarchy (since 5.8).  This is a set of key-value pairs separated from
+  each other by '|', with keys separated from values by ':'.  Note that '|'
+  may need to be quoted or escaped to avoid it being interpreted as a pipe
+  by the shell.  The key is the bucket type name (e.g. rack, datacenter or
+  region with default bucket types) and the value is the bucket name.  For
+  example, to indicate that the client is local to rack "myrack", data center
+  "mydc" and region "myregion"::
+
+    crush_location=rack:myrack|datacenter:mydc|region:myregion
+
+  Each key-value pair stands on its own: "myrack" doesn't need to reside in
+  "mydc", which in turn doesn't need to reside in "myregion".  The location
+  is not a path to the root of the hierarchy but rather a set of nodes that
+  are matched independently, owning to the fact that bucket names are unique
+  within a CRUSH map.  "Multipath" locations are supported, so it is possible
+  to indicate locality for multiple parallel hierarchies::
+
+    crush_location=rack:myrack1|rack:myrack2|datacenter:mydc
+
+* read_from_replica=no - Disable replica reads, always pick the primary OSD
+  (since 5.8, default).
+
+* read_from_replica=balance - When issued a read on a replicated pool, pick
+  a random OSD for serving it (since 5.8).
+
+  This mode is safe for general use only since Octopus (i.e. after "ceph osd
+  require-osd-release octopus").  Otherwise it should be limited to read-only
+  workloads such as images mapped read-only everywhere or snapshots.
+
+* read_from_replica=localize - When issued a read on a replicated pool, pick
+  the most local OSD for serving it (since 5.8).  The locality metric is
+  calculated against the location of the client given with crush_location;
+  a match with the lowest-valued bucket type wins.  For example, with default
+  bucket types, an OSD in a matching rack is closer than an OSD in a matching
+  data center, which in turn is closer than an OSD in a matching region.
+
+  This mode is safe for general use only since Octopus (i.e. after "ceph osd
+  require-osd-release octopus").  Otherwise it should be limited to read-only
+  workloads such as images mapped read-only everywhere or snapshots.
+
 `rbd device unmap` options:
 
 * force - Force the unmapping of a block device that is open (since 4.9).  The
diff --git a/src/tools/rbd/action/Kernel.cc b/src/tools/rbd/action/Kernel.cc
index 3ebb5bc1de40b..6013067ac9af2 100644
--- a/src/tools/rbd/action/Kernel.cc
+++ b/src/tools/rbd/action/Kernel.cc
@@ -64,6 +64,20 @@ static std::string map_option_int_cb(const char *value_char)
   return stringify(d);
 }
 
+static std::string map_option_string_cb(const char *value_char)
+{
+  return value_char;
+}
+
+static std::string map_option_read_from_replica_cb(const char *value_char)
+{
+  if (!strcmp(value_char, "no") || !strcmp(value_char, "balance") ||
+      !strcmp(value_char, "localize")) {
+    return value_char;
+  }
+  return "";
+}
+
 static void put_map_option(const std::string &key, const std::string &val)
 {
   map_options[key] = val;
@@ -153,6 +167,14 @@ static int parse_map_options(const std::string &options_string)
     } else if (!strcmp(this_char, "alloc_size")) {
       if (put_map_option_value("alloc_size", value_char, map_option_int_cb))
         return -EINVAL;
+    } else if (!strcmp(this_char, "crush_location")) {
+      if (put_map_option_value("crush_location", value_char,
+                               map_option_string_cb))
+        return -EINVAL;
+    } else if (!strcmp(this_char, "read_from_replica")) {
+      if (put_map_option_value("read_from_replica", value_char,
+                               map_option_read_from_replica_cb))
+        return -EINVAL;
     } else {
       std::cerr << "rbd: unknown map option '" << this_char << "'" << std::endl;
       return -EINVAL;
-- 
2.39.5