glusterd : Introduce reset brick

The command basically allows replace brick with src and
dst bricks as same.

Usage:
gluster v reset-brick <volname> <hostname:brick-path> start
This command kills the brick to be reset. Once this command is run,
admin can do other manual operations that they need to do,
like configuring some options for the brick. Once this is done,
resetting the brick can be continued with the following options.

gluster v reset-brick <vname> <hostname:brick> <hostname:brick> commit {force}

Does the job of resetting the brick. 'force' option should be used
when the brick already contains volinfo id.

Problem: On doing a disk-replacement of a brick in a replicate volume
the following 2 scenarios may occur :

a) there is a chance that reads are served from this replaced-disk brick,
which leads to empty reads. b) potential data loss if next writes succeed
only on replaced brick, and heal is done to other bricks from this one.

Solution: After disk-replacement, make sure that reset-brick command is
run for that brick so that pending markers are set for the brick and it
is not chosen as source for reads and heal. But, as of now replace-brick
for the same brick-path is not allowed. In order to fix the above
mentioned problem, same brick-path replace-brick is needed.
With this patch reset-brick commit {force} will be allowed even when
source and destination <hostname:brickpath> are identical as long as
1) destination brick is not alive
2) source and destination brick have the same brick uuid and path.
Also, the destination brick after replace-brick will use the same port
as the source brick.

Change-Id: I440b9e892ffb781ea4b8563688c3f85c7a7c89de
BUG: 1266876
Signed-off-by: Anuradha Talur <atalur@redhat.com>
Reviewed-on: http://review.gluster.org/12250
Smoke: Gluster Build System <jenkins@build.gluster.org>
NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
Reviewed-by: Ashish Pandey <aspandey@redhat.com>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>

1 files changed, 61 insertions, 0 deletions

diff --git a/cli/src/cli-cmd-volume.c b/cli/src/cli-cmd-volume.c
index 020697ff56b..2171d357aa5 100644
--- a/cli/src/cli-cmd-volume.c
+++ b/cli/src/cli-cmd-volume.c
@@ -1829,6 +1829,59 @@ out:
 }
 
 int
+cli_cmd_volume_reset_brick_cbk (struct cli_state *state,
+                                struct cli_cmd_word *word,
+                                const char **words,
+                                int wordcount)
+{
+        int                      ret          = -1;
+        rpc_clnt_procedure_t    *proc         = NULL;
+        call_frame_t            *frame        = NULL;
+        dict_t                  *options = NULL;
+        int                      sent = 0;
+        int                      parse_error = 0;
+        cli_local_t             *local = NULL;
+
+#ifdef GF_SOLARIS_HOST_OS
+        cli_out ("Command not supported on Solaris");
+        goto out;
+#endif
+        proc = &cli_rpc_prog->proctable[GLUSTER_CLI_RESET_BRICK];
+
+        frame = create_frame (THIS, THIS->ctx->pool);
+        if (!frame)
+                goto out;
+
+        ret = cli_cmd_volume_reset_brick_parse (words, wordcount, &options);
+
+        if (ret) {
+                cli_usage_out (word->pattern);
+                parse_error = 1;
+                goto out;
+        }
+
+        CLI_LOCAL_INIT (local, words, frame, options);
+
+        if (proc->fn) {
+                ret = proc->fn (frame, THIS, options);
+        }
+
+out:
+        if (ret) {
+                gf_event (EVENT_BRICK_RESET, "Volume reset-brick failed.");
+                cli_cmd_sent_status_get (&sent);
+                if ((sent == 0) && (parse_error == 0))
+                        cli_out ("Volume reset-brick failed");
+        } else {
+                gf_event (EVENT_BRICK_RESET, "Volume reset-brick succeeded.");
+        }
+
+        CLI_STACK_DESTROY (frame);
+
+        return ret;
+}
+
+int
 cli_cmd_volume_replace_brick_cbk (struct cli_state *state,
                                   struct cli_cmd_word *word,
                                   const char **words,
@@ -1868,9 +1921,12 @@ cli_cmd_volume_replace_brick_cbk (struct cli_state *state,
 
 out:
         if (ret) {
+                gf_event (EVENT_BRICK_REPLACE, "Volume replace-brick failed.");
                 cli_cmd_sent_status_get (&sent);
                 if ((sent == 0) && (parse_error == 0))
                         cli_out ("Volume replace-brick failed");
+        } else {
+                gf_event (EVENT_BRICK_RESET, "Volume replace-brick succeeded.");
         }
 
         CLI_STACK_DESTROY (frame);
@@ -3016,6 +3072,11 @@ struct cli_cmd volume_cmds[] = {
          "Bitrot translator specific operation. For more information about "
          "bitrot command type  'man gluster'"
         },
+        { "volume reset-brick <VOLNAME> <SOURCE-BRICK> {{start} |"
+          " {<NEW-BRICK> commit}}",
+          cli_cmd_volume_reset_brick_cbk,
+          "reset-brick operations"},
+
         { NULL, NULL, NULL }
 };