tools/glusterfind: GFID to Path conversion using Changelog

Records fop information collected from Changelogs in sqlite database.
This is only working database, not required after processing.

After post processing, output file is generated by reading these
database files.

This is applicable only in incremental run, when a changelog is
parsed, all the details are saved in DB. GFID to Path is converted
to those files for which information is available in Changelogs.

For all the failed cases, it tries to convert to Path using Pgfid,
if not found GFID to Path is done using find.

BUG: 1219475
Change-Id: Iaccc9d063b1187d973137e592f024979b724e85c
Reviewed-On: http://review.gluster.org/#/c/10463/
Original-Author: Aravinda VK <avishwan@redhat.com>
Signed-off-by: Kotresh HR <khiremat@redhat.com>
Reviewed-on: http://review.gluster.org/10640
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Aravinda VK <avishwan@redhat.com>

1 files changed, 28 insertions, 6 deletions

diff --git a/tools/glusterfind/src/main.py b/tools/glusterfind/src/main.py
index 089a3aec3c5..d9936eebde1 100644
--- a/tools/glusterfind/src/main.py
+++ b/tools/glusterfind/src/main.py
@@ -20,9 +20,9 @@ import shutil
 
 from utils import execute, is_host_local, mkdirp, fail
 from utils import setup_logger, human_time, handle_rm_error
-from utils import get_changelog_rollover_time, cache_output
+from utils import get_changelog_rollover_time, cache_output, create_file
 import conf
-
+from changelogdata import OutputMerger
 
 PROG_DESCRIPTION = """
 GlusterFS Incremental API
@@ -235,6 +235,9 @@ def _get_args():
                             help="Regenerate outfile, discard the outfile "
                             "generated from last pre command",
                             action="store_true")
+    parser_pre.add_argument("-N", "--only-namespace-changes",
+                            help="List only namespace changes",
+                            action="store_true")
 
     # post <SESSION> <VOLUME>
     parser_post = subparsers.add_parser('post')
@@ -377,10 +380,29 @@ def mode_pre(session_dir, args):
     run_cmd_nodes("pre", args, start=start)
 
     # Merger
-    cmd = ["sort", "-u"] + node_outfiles + ["-o", args.outfile]
-    execute(cmd,
-            exit_msg="Failed to merge output files "
-            "collected from nodes", logger=logger)
+    if args.full:
+        cmd = ["sort", "-u"] + node_outfiles + ["-o", args.outfile]
+        execute(cmd,
+                exit_msg="Failed to merge output files "
+                "collected from nodes", logger=logger)
+    else:
+        # Read each Changelogs db and generate finaldb
+        create_file(args.outfile, exit_on_err=True, logger=logger)
+        outfilemerger = OutputMerger(args.outfile + ".db", node_outfiles)
+
+        with open(args.outfile, "a") as f:
+            for row in outfilemerger.get():
+                # Multiple paths in case of Hardlinks
+                paths = row[1].split(",")
+                for p in paths:
+                    if p == "":
+                        continue
+                    f.write("%s %s %s\n" % (row[0], p, row[2]))
+
+    try:
+        os.remove(args.outfile + ".db")
+    except (IOError, OSError):
+        pass
 
     run_cmd_nodes("cleanup", args)