From 06eb3d0b8488d12a92ea21b92727497c585bae4b Mon Sep 17 00:00:00 2001 From: Harpreet Kaur Date: Mon, 7 Jan 2019 16:38:25 +0530 Subject: geo-rep: Fix for "Transport End Point not connected" issue problem: Geo-rep gsyncd process mounts the master and slave volume on master nodes and slave nodes respectively and starts the sync. But it doesn't wait for the mount to be in ready state to accept I/O. The gluster mount is considered to be ready when all the distribute sub-volumes is up. If the all the distribute subvolumes are not up, it can cause ENOTCONN error, when lookup on file comes and file is on the subvol that is down. solution: Added a Virtual Xattr "dht.subvol.status" which returns "1" if all subvols are up and "0" if all subvols are not up. Geo-rep then uses this virtual xattr after a fresh mount, to check whether all subvols are up or not and then starts the I/O. fixes: bz#1664335 Change-Id: If3ad01d728b1372da7c08ccbe75a45bdc1ab2a91 Signed-off-by: Harpreet Kaur Signed-off-by: Kotresh HR --- geo-replication/syncdaemon/resource.py | 11 +++++++++++ geo-replication/syncdaemon/syncdutils.py | 20 +++++++++++++++++--- 2 files changed, 28 insertions(+), 3 deletions(-) (limited to 'geo-replication') diff --git a/geo-replication/syncdaemon/resource.py b/geo-replication/syncdaemon/resource.py index ae5600d1d9a..c0ed408cf49 100644 --- a/geo-replication/syncdaemon/resource.py +++ b/geo-replication/syncdaemon/resource.py @@ -37,6 +37,7 @@ from syncdutils import NoStimeAvailable, PartialHistoryAvailable from syncdutils import ChangelogException, ChangelogHistoryNotAvailable from syncdutils import get_changelog_log_level, get_rsync_version from syncdutils import GX_GFID_CANONICAL_LEN +from syncdutils import gf_mount_ready from gsyncdstatus import GeorepStatus from syncdutils import lf, Popen, sup from syncdutils import Xattr, matching_disk_gfid, get_gfid_from_mnt @@ -950,6 +951,16 @@ class Mounter(object): logging.exception('mount cleanup failure:') rv = 200 os._exit(rv) + + #Polling the dht.subvol.status value. + RETRIES = 10 + while not gf_mount_ready(): + if RETRIES < 0: + logging.error('Subvols are not up') + break + RETRIES -= 1 + time.sleep(0.2) + logging.debug('auxiliary glusterfs mount prepared') diff --git a/geo-replication/syncdaemon/syncdutils.py b/geo-replication/syncdaemon/syncdutils.py index 4b6f4a265f6..dc0366266b9 100644 --- a/geo-replication/syncdaemon/syncdutils.py +++ b/geo-replication/syncdaemon/syncdutils.py @@ -21,8 +21,8 @@ import subprocess import socket from subprocess import PIPE from threading import Lock, Thread as baseThread -from errno import EACCES, EAGAIN, EPIPE, ENOTCONN, ECONNABORTED -from errno import EINTR, ENOENT, ESTALE, EBUSY, errorcode +from errno import EACCES, EAGAIN, EPIPE, ENOTCONN, ENOMEM, ECONNABORTED +from errno import EINTR, ENOENT, ESTALE, EBUSY, ENODATA, errorcode from signal import signal, SIGTERM import select as oselect from os import waitpid as owaitpid @@ -55,6 +55,8 @@ from rconf import rconf from hashlib import sha256 as sha256 +ENOTSUP = getattr(errno, 'ENOTSUP', 'EOPNOTSUPP') + # auxiliary gfid based access prefix _CL_AUX_GFID_PFX = ".gfid/" ROOT_GFID = "00000000-0000-0000-0000-000000000001" @@ -98,6 +100,19 @@ def unescape_space_newline(s): .replace(NEWLINE_ESCAPE_CHAR, "\n")\ .replace(PERCENTAGE_ESCAPE_CHAR, "%") +# gf_mount_ready() returns 1 if all subvols are up, else 0 +def gf_mount_ready(): + ret = errno_wrap(Xattr.lgetxattr, + ['.', 'dht.subvol.status', 16], + [ENOENT, ENOTSUP, ENODATA], [ENOMEM]) + + if isinstance(ret, int): + logging.error("failed to get the xattr value") + return 1 + ret = ret.rstrip('\x00') + if ret == "1": + return 1 + return 0 def norm(s): if s: @@ -562,7 +577,6 @@ def errno_wrap(call, arg=[], errnos=[], retry_errnos=[]): def lstat(e): return errno_wrap(os.lstat, [e], [ENOENT], [ESTALE, EBUSY]) - def get_gfid_from_mnt(gfidpath): return errno_wrap(Xattr.lgetxattr, [gfidpath, 'glusterfs.gfid.string', -- cgit