summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorKevin Vigor <kvigor@fb.com>2017-03-21 08:23:25 -0700
committerKaushal M <kaushal@redhat.com>2017-05-08 05:37:07 +0000
commitb6cc5261d5809aa509eecd082aefb7a0a14ca74b (patch)
tree7ca30fc72b8a07ab7e7cf9172b01c17c32275137
parentd60d7c8939de76f99562a042bf8d42c5e64e63d1 (diff)
Halo Replication feature for AFR translator
Backport of https://review.gluster.org/16177 https://review.gluster.org/17174 Merged both these patches to make sure IPV6 changes don't make it to 3.11 at all. Summary: Halo Geo-replication is a feature which allows Gluster or NFS clients to write locally to their region (as defined by a latency "halo" or threshold if you like), and have their writes asynchronously propagate from their origin to the rest of the cluster. Clients can also write synchronously to the cluster simply by specifying a halo-latency which is very large (e.g. 10seconds) which will include all bricks. In other words, it allows clients to decide at mount time if they desire synchronous or asynchronous IO into a cluster and the cluster can support both of these modes to any number of clients simultaneously. There are a few new volume options due to this feature: halo-shd-latency: The threshold below which self-heal daemons will consider children (bricks) connected. halo-nfsd-latency: The threshold below which NFS daemons will consider children (bricks) connected. halo-latency: The threshold below which all other clients will consider children (bricks) connected. halo-min-replicas: The minimum number of replicas which are to be enforced regardless of latency specified in the above 3 options. If the number of children falls below this threshold the next best (chosen by latency) shall be swapped in. New FUSE mount options: halo-latency & halo-min-replicas: As descripted above. This feature combined with multi-threaded SHD support (D1271745) results in some pretty cool geo-replication possibilities. Operational Notes: - Global consistency is gaurenteed for synchronous clients, this is provided by the existing entry-locking mechanism. - Asynchronous clients on the other hand and merely consistent to their region. Writes & deletes will be protected via entry-locks as usual preventing concurrent writes into files which are undergoing replication. Read operations on the other hand should never block. - Writes are allowed from _any_ region and propagated from the origin to all other regions. The take away from this is care should be taken to ensure multiple writers do not write the same files resulting in a gfid split-brain which will require resolution via split-brain policies (majority, mtime & size). Recommended method for preventing this is using the nfs-auth feature to define which region for each share has RW permissions, tiers not in the origin region should have RO perms. TODO: - Synchronous clients (including the SHD) should choose clients from their own region as preferred sources for reads. Most of the plumbing is in place for this via the child_latency array. - Better GFID split brain handling & better dent type split brain handling (i.e. create a trash can and move the offending files into it). - Tagging in addition to latency as a means of defining which children you wish to synchronously write to Test Plan: - The usual suspects, clang, gcc w/ address sanitizer & valgrind - Prove tests Reviewers: jackl, dph, cjh, meyering Reviewed By: meyering Subscribers: ethanr Differential Revision: https://phabricator.fb.com/D1272053 Tasks: 4117827 >Change-Id: I694a9ab429722da538da171ec528406e77b5e6d1 >BUG: 1428061 >Signed-off-by: Kevin Vigor <kvigor@fb.com> >Reviewed-on: http://review.gluster.org/16099 >Reviewed-on: https://review.gluster.org/16177 >Tested-by: Pranith Kumar Karampuri <pkarampu@redhat.com> >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: Pranith Kumar Karampuri <pkarampu@redhat.com> BUG: 1448416 Change-Id: I694a9ab429722da538da171ec528406e77b5e6d1 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: https://review.gluster.org/17192 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: Kaushal M <kaushal@redhat.com>
-rw-r--r--cli/src/cli.c4
-rw-r--r--configure.ac2
-rw-r--r--libglusterfs/src/common-utils.c28
-rw-r--r--libglusterfs/src/defaults-tmpl.c12
-rw-r--r--libglusterfs/src/latency.c12
-rw-r--r--libglusterfs/src/mem-types.h1
-rw-r--r--libglusterfs/src/timespec.c12
-rw-r--r--libglusterfs/src/timespec.h3
-rw-r--r--libglusterfs/src/xlator.h1
-rw-r--r--rpc/rpc-lib/src/rpc-clnt-ping.c65
-rw-r--r--rpc/rpc-lib/src/rpc-clnt.h1
-rw-r--r--rpc/rpc-lib/src/rpc-transport.c8
-rw-r--r--rpc/rpc-lib/src/rpcsvc.c1
-rw-r--r--rpc/rpc-transport/socket/src/name.c7
-rw-r--r--rpc/rpc-transport/socket/src/socket.c1
-rw-r--r--rpc/xdr/src/glusterfs-fops.x1
-rw-r--r--tests/basic/exports_parsing.t15
-rwxr-xr-xtests/basic/mount-nfs-auth.t12
-rw-r--r--tests/configfiles/exports-v61
-rw-r--r--xlators/cluster/afr/src/afr-common.c364
-rw-r--r--xlators/cluster/afr/src/afr-mem-types.h3
-rw-r--r--xlators/cluster/afr/src/afr-self-heald.h1
-rw-r--r--xlators/cluster/afr/src/afr.c98
-rw-r--r--xlators/cluster/afr/src/afr.h14
-rw-r--r--xlators/features/changelog/lib/src/gf-changelog-rpc.c1
-rw-r--r--xlators/features/changelog/src/changelog-ev-handle.c2
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-volgen.c22
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-volume-ops.c6
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-volume-set.c33
-rwxr-xr-xxlators/mount/fuse/utils/mount.glusterfs.in24
-rw-r--r--xlators/nfs/server/src/exports.h2
-rw-r--r--xlators/nfs/server/src/mount3.c2
-rw-r--r--xlators/nfs/server/src/nfs.c1
-rw-r--r--xlators/protocol/client/src/client-handshake.c2
-rw-r--r--xlators/protocol/client/src/client.c98
35 files changed, 719 insertions, 141 deletions
diff --git a/cli/src/cli.c b/cli/src/cli.c
index 25fe58568a5..574ee0eea33 100644
--- a/cli/src/cli.c
+++ b/cli/src/cli.c
@@ -613,6 +613,7 @@ cli_rpc_init (struct cli_state *state)
int ret = -1;
int port = CLI_GLUSTERD_PORT;
xlator_t *this = NULL;
+ char *addr_family = "inet";
this = THIS;
cli_rpc_prog = &cli_prog;
@@ -648,7 +649,8 @@ cli_rpc_init (struct cli_state *state)
goto out;
ret = dict_set_str (options, "transport.address-family",
- "inet");
+ addr_family);
+
if (ret)
goto out;
}
diff --git a/configure.ac b/configure.ac
index fde410326de..7d5728f6445 100644
--- a/configure.ac
+++ b/configure.ac
@@ -287,7 +287,7 @@ if test "x$enable_debug" = "xyes"; then
CFLAGS="${CFLAGS} -g -O0 -DDEBUG"
else
BUILD_DEBUG=no
- CFLAGS="${CFLAGS} -g -O2"
+ CFLAGS="${CFLAGS} -g"
fi
AC_ARG_ENABLE([privport_tracking],
diff --git a/libglusterfs/src/common-utils.c b/libglusterfs/src/common-utils.c
index 56f545f28de..2acd83f36cf 100644
--- a/libglusterfs/src/common-utils.c
+++ b/libglusterfs/src/common-utils.c
@@ -194,26 +194,16 @@ gf_rev_dns_lookup (const char *ip)
{
char *fqdn = NULL;
int ret = 0;
- struct sockaddr_in sa = {0};
- char host_addr[256] = {0, };
GF_VALIDATE_OR_GOTO ("resolver", ip, out);
- sa.sin_family = AF_INET;
- inet_pton (AF_INET, ip, &sa.sin_addr);
- ret = getnameinfo ((struct sockaddr *)&sa, sizeof (sa), host_addr,
- sizeof (host_addr), NULL, 0, 0);
-
+ /* Get the FQDN */
+ ret = gf_get_hostname_from_ip ((char *)ip, &fqdn);
if (ret != 0) {
gf_msg ("resolver", GF_LOG_INFO, errno,
LG_MSG_RESOLVE_HOSTNAME_FAILED, "could not resolve "
"hostname for %s", ip);
- goto out;
}
-
- /* Get the FQDN */
- fqdn = gf_strdup (host_addr);
-
out:
return fqdn;
}
@@ -3127,11 +3117,13 @@ gf_get_hostname_from_ip (char *client_ip, char **hostname)
char *client_ip_copy = NULL;
char *tmp = NULL;
char *ip = NULL;
+ size_t addr_sz = 0;
/* if ipv4, reverse lookup the hostname to
* allow FQDN based rpc authentication
*/
- if (valid_ipv4_address (client_ip, strlen (client_ip), 0) == _gf_false) {
+ if (!valid_ipv6_address (client_ip, strlen (client_ip), 0) &&
+ !valid_ipv4_address (client_ip, strlen (client_ip), 0)) {
/* most times, we get a.b.c.d:port form, so check that */
client_ip_copy = gf_strdup (client_ip);
if (!client_ip_copy)
@@ -3144,12 +3136,14 @@ gf_get_hostname_from_ip (char *client_ip, char **hostname)
if (valid_ipv4_address (ip, strlen (ip), 0) == _gf_true) {
client_sockaddr = (struct sockaddr *)&client_sock_in;
+ addr_sz = sizeof (client_sock_in);
client_sock_in.sin_family = AF_INET;
ret = inet_pton (AF_INET, ip,
(void *)&client_sock_in.sin_addr.s_addr);
} else if (valid_ipv6_address (ip, strlen (ip), 0) == _gf_true) {
client_sockaddr = (struct sockaddr *) &client_sock_in6;
+ addr_sz = sizeof (client_sock_in6);
client_sock_in6.sin6_family = AF_INET6;
ret = inet_pton (AF_INET6, ip,
@@ -3163,8 +3157,14 @@ gf_get_hostname_from_ip (char *client_ip, char **hostname)
goto out;
}
+ /* You cannot just use sizeof (*client_sockaddr), as per the man page
+ * the (getnameinfo) size must be the size of the underlying sockaddr
+ * struct e.g. sockaddr_in6 or sockaddr_in. Failure to do so will
+ * break IPv6 hostname resolution (IPv4 will work only because
+ * the sockaddr_in struct happens to be of the correct size).
+ */
ret = getnameinfo (client_sockaddr,
- sizeof (*client_sockaddr),
+ addr_sz,
client_hostname, sizeof (client_hostname),
NULL, 0, 0);
if (ret) {
diff --git a/libglusterfs/src/defaults-tmpl.c b/libglusterfs/src/defaults-tmpl.c
index 5b7578b7c57..0889e07caa7 100644
--- a/libglusterfs/src/defaults-tmpl.c
+++ b/libglusterfs/src/defaults-tmpl.c
@@ -170,6 +170,18 @@ default_notify (xlator_t *this, int32_t event, void *data, ...)
}
}
break;
+ case GF_EVENT_CHILD_PING:
+ {
+ xlator_list_t *parent = this->parents;
+
+ while (parent) {
+ if (parent->xlator->init_succeeded)
+ xlator_notify (parent->xlator, event,
+ this, data);
+ parent = parent->next;
+ }
+ }
+ break;
default:
{
xlator_list_t *parent = this->parents;
diff --git a/libglusterfs/src/latency.c b/libglusterfs/src/latency.c
index 5025de6c8cf..1d75f5b98ce 100644
--- a/libglusterfs/src/latency.c
+++ b/libglusterfs/src/latency.c
@@ -21,6 +21,7 @@
#include "statedump.h"
#include "libglusterfs-messages.h"
+static int gf_set_fop_from_fn_pointer_warning;
void
gf_set_fop_from_fn_pointer (call_frame_t *frame, struct xlator_fops *fops, void *fn)
{
@@ -108,8 +109,15 @@ gf_set_fop_from_fn_pointer (call_frame_t *frame, struct xlator_fops *fops, void
fop = GF_FOP_READDIRP;
else if (fops->getspec == *(fop_getspec_t *)&fn)
fop = GF_FOP_GETSPEC;
- else
- fop = -1;
+ else if (fops->ipc == *(fop_ipc_t *)&fn)
+ fop = GF_FOP_IPC;
+ else {
+ fop = GF_FOP_NULL;
+ GF_LOG_OCCASIONALLY(gf_set_fop_from_fn_pointer_warning,
+ "latency",
+ GF_LOG_WARNING,
+ "Unknown FOP type");
+ }
frame->op = fop;
}
diff --git a/libglusterfs/src/mem-types.h b/libglusterfs/src/mem-types.h
index 6c0472f00b8..b41805e1f02 100644
--- a/libglusterfs/src/mem-types.h
+++ b/libglusterfs/src/mem-types.h
@@ -172,6 +172,7 @@ enum gf_common_mem_types_ {
gf_common_mt_tbf_bucket_t,
gf_common_mt_tbf_throttle_t,
gf_common_mt_pthread_t,
+ gf_common_ping_local_t,
gf_common_mt_end
};
#endif
diff --git a/libglusterfs/src/timespec.c b/libglusterfs/src/timespec.c
index f7b2bea2f30..903303d1380 100644
--- a/libglusterfs/src/timespec.c
+++ b/libglusterfs/src/timespec.c
@@ -60,3 +60,15 @@ void timespec_adjust_delta (struct timespec *ts, struct timespec delta)
ts->tv_sec += ((ts->tv_nsec + delta.tv_nsec) / 1000000000);
ts->tv_sec += delta.tv_sec;
}
+
+void timespec_sub (const struct timespec *begin, const struct timespec *end,
+ struct timespec *res)
+{
+ if (end->tv_nsec < begin->tv_nsec) {
+ res->tv_sec = end->tv_sec - begin->tv_sec - 1;
+ res->tv_nsec = end->tv_nsec + 1000000000 - begin->tv_nsec;
+ } else {
+ res->tv_sec = end->tv_sec - begin->tv_sec;
+ res->tv_nsec = end->tv_nsec - begin->tv_nsec;
+ }
+}
diff --git a/libglusterfs/src/timespec.h b/libglusterfs/src/timespec.h
index f37194b97cf..9c393ee7166 100644
--- a/libglusterfs/src/timespec.h
+++ b/libglusterfs/src/timespec.h
@@ -20,5 +20,8 @@
void timespec_now (struct timespec *ts);
void timespec_adjust_delta (struct timespec *ts, struct timespec delta);
+void timespec_sub (const struct timespec *begin,
+ const struct timespec *end,
+ struct timespec *res);
#endif /* __INCLUDE_TIMESPEC_H__ */
diff --git a/libglusterfs/src/xlator.h b/libglusterfs/src/xlator.h
index c2959efbd95..e0f82a70764 100644
--- a/libglusterfs/src/xlator.h
+++ b/libglusterfs/src/xlator.h
@@ -933,6 +933,7 @@ struct _xlator {
gf_loglevel_t loglevel; /* Log level for translator */
+ int64_t client_latency;
/* for latency measurement */
fop_latency_t latencies[GF_FOP_MAXVALUE];
diff --git a/rpc/rpc-lib/src/rpc-clnt-ping.c b/rpc/rpc-lib/src/rpc-clnt-ping.c
index e042121ad47..5a97f4bb9cf 100644
--- a/rpc/rpc-lib/src/rpc-clnt-ping.c
+++ b/rpc/rpc-lib/src/rpc-clnt-ping.c
@@ -18,6 +18,7 @@
#include "mem-pool.h"
#include "xdr-rpc.h"
#include "rpc-common-xdr.h"
+#include "timespec.h"
char *clnt_ping_procs[GF_DUMP_MAXVALUE] = {
@@ -30,6 +31,11 @@ struct rpc_clnt_program clnt_ping_prog = {
.procnames = clnt_ping_procs,
};
+struct ping_local {
+ struct rpc_clnt *rpc;
+ struct timespec submit_time;
+};
+
/* Must be called under conn->lock */
static int
__rpc_clnt_rearm_ping_timer (struct rpc_clnt *rpc, gf_timer_cbk_t cbk)
@@ -170,11 +176,17 @@ int
rpc_clnt_ping_cbk (struct rpc_req *req, struct iovec *iov, int count,
void *myframe)
{
- struct rpc_clnt *rpc = NULL;
+ struct ping_local *local = NULL;
xlator_t *this = NULL;
rpc_clnt_connection_t *conn = NULL;
call_frame_t *frame = NULL;
int unref = 0;
+ gf_boolean_t call_notify = _gf_false;
+
+ struct timespec now;
+ struct timespec delta;
+ int64_t latency_msec = 0;
+ int ret = 0;
if (!myframe) {
gf_log (THIS->name, GF_LOG_WARNING,
@@ -184,14 +196,23 @@ rpc_clnt_ping_cbk (struct rpc_req *req, struct iovec *iov, int count,
frame = myframe;
this = frame->this;
- rpc = frame->local;
- frame->local = NULL; /* Prevent STACK_DESTROY from segfaulting */
- conn = &rpc->conn;
+ local = frame->local;
+ conn = &local->rpc->conn;
+
+ timespec_now (&now);
+ timespec_sub (&local->submit_time, &now, &delta);
+ latency_msec = delta.tv_sec * 1000 + delta.tv_nsec / 1000000;
pthread_mutex_lock (&conn->lock);
{
+ this->client_latency = latency_msec;
+ gf_log (THIS->name, GF_LOG_DEBUG,
+ "Ping latency is %" PRIu64 "ms",
+ latency_msec);
+
+ call_notify = _gf_true;
if (req->rpc_status == -1) {
- unref = rpc_clnt_remove_ping_timer_locked (rpc);
+ unref = rpc_clnt_remove_ping_timer_locked (local->rpc);
if (unref) {
gf_log (this->name, GF_LOG_WARNING,
"socket or ib related error");
@@ -206,8 +227,8 @@ rpc_clnt_ping_cbk (struct rpc_req *req, struct iovec *iov, int count,
goto unlock;
}
- unref = rpc_clnt_remove_ping_timer_locked (rpc);
- if (__rpc_clnt_rearm_ping_timer (rpc,
+ unref = rpc_clnt_remove_ping_timer_locked (local->rpc);
+ if (__rpc_clnt_rearm_ping_timer (local->rpc,
rpc_clnt_start_ping) == -1) {
gf_log (this->name, GF_LOG_WARNING,
"failed to set the ping timer");
@@ -216,12 +237,24 @@ rpc_clnt_ping_cbk (struct rpc_req *req, struct iovec *iov, int count,
}
unlock:
pthread_mutex_unlock (&conn->lock);
+
+ if (call_notify) {
+ ret = local->rpc->notifyfn (local->rpc, this, RPC_CLNT_PING,
+ (void *)(uintptr_t)latency_msec);
+ if (ret) {
+ gf_log (this->name, GF_LOG_WARNING,
+ "RPC_CLNT_PING notify failed");
+ }
+ }
out:
if (unref)
- rpc_clnt_unref (rpc);
+ rpc_clnt_unref (local->rpc);
- if (frame)
+ if (frame) {
+ GF_FREE (frame->local);
+ frame->local = NULL;
STACK_DESTROY (frame->root);
+ }
return 0;
}
@@ -231,18 +264,28 @@ rpc_clnt_ping (struct rpc_clnt *rpc)
call_frame_t *frame = NULL;
int32_t ret = -1;
rpc_clnt_connection_t *conn = NULL;
+ struct ping_local *local = NULL;
conn = &rpc->conn;
+ local = GF_CALLOC (1, sizeof(struct ping_local),
+ gf_common_ping_local_t);
+ if (!local)
+ return ret;
frame = create_frame (THIS, THIS->ctx->pool);
- if (!frame)
+ if (!frame) {
+ GF_FREE (local);
return ret;
+ }
- frame->local = rpc;
+ local->rpc = rpc;
+ timespec_now (&local->submit_time);
+ frame->local = local;
ret = rpc_clnt_submit (rpc, &clnt_ping_prog,
GF_DUMP_PING, rpc_clnt_ping_cbk, NULL, 0,
NULL, 0, NULL, frame, NULL, 0, NULL, 0, NULL);
if (ret) {
+ /* FIXME: should we free the frame here? Methinks so! */
gf_log (THIS->name, GF_LOG_ERROR,
"failed to start ping timer");
}
diff --git a/rpc/rpc-lib/src/rpc-clnt.h b/rpc/rpc-lib/src/rpc-clnt.h
index b731ba2dfad..e5e493cd79e 100644
--- a/rpc/rpc-lib/src/rpc-clnt.h
+++ b/rpc/rpc-lib/src/rpc-clnt.h
@@ -19,6 +19,7 @@
typedef enum {
RPC_CLNT_CONNECT,
RPC_CLNT_DISCONNECT,
+ RPC_CLNT_PING,
RPC_CLNT_MSG,
RPC_CLNT_DESTROY
} rpc_clnt_event_t;
diff --git a/rpc/rpc-lib/src/rpc-transport.c b/rpc/rpc-lib/src/rpc-transport.c
index 4fbbc8cd7fc..fc26f462c31 100644
--- a/rpc/rpc-lib/src/rpc-transport.c
+++ b/rpc/rpc-lib/src/rpc-transport.c
@@ -656,6 +656,7 @@ rpc_transport_inet_options_build (dict_t **options, const char *hostname,
dict_t *dict = NULL;
char *host = NULL;
int ret = -1;
+ char *addr_family = "inet";
GF_ASSERT (options);
GF_ASSERT (hostname);
@@ -686,6 +687,13 @@ rpc_transport_inet_options_build (dict_t **options, const char *hostname,
goto out;
}
+ ret = dict_set_str (dict, "address-family", addr_family);
+ if (ret) {
+ gf_log (THIS->name, GF_LOG_WARNING,
+ "failed to set address-family to %s", addr_family);
+ goto out;
+ }
+
ret = dict_set_str (dict, "transport-type", "socket");
if (ret) {
gf_log (THIS->name, GF_LOG_WARNING,
diff --git a/rpc/rpc-lib/src/rpcsvc.c b/rpc/rpc-lib/src/rpcsvc.c
index 2be54a382f9..ce4e2bf0dc2 100644
--- a/rpc/rpc-lib/src/rpcsvc.c
+++ b/rpc/rpc-lib/src/rpcsvc.c
@@ -1550,7 +1550,6 @@ rpcsvc_program_unregister (rpcsvc_t *svc, rpcsvc_program_t *program)
" program failed");
goto out;
}
-
pthread_mutex_lock (&svc->rpclock);
{
list_for_each_entry (prog, &svc->programs, program) {
diff --git a/rpc/rpc-transport/socket/src/name.c b/rpc/rpc-transport/socket/src/name.c
index e9de1a78813..04dc2a989a7 100644
--- a/rpc/rpc-transport/socket/src/name.c
+++ b/rpc/rpc-transport/socket/src/name.c
@@ -561,6 +561,8 @@ server_fill_address_family (rpc_transport_t *this, sa_family_t *sa_family)
{
data_t *address_family_data = NULL;
int32_t ret = -1;
+ char *addr_family = "inet";
+ sa_family_t default_family = AF_INET;
GF_VALIDATE_OR_GOTO ("socket", sa_family, out);
@@ -586,8 +588,9 @@ server_fill_address_family (rpc_transport_t *this, sa_family_t *sa_family)
}
} else {
gf_log (this->name, GF_LOG_DEBUG,
- "option address-family not specified, defaulting to inet");
- *sa_family = AF_INET;
+ "option address-family not specified, "
+ "defaulting to %s", addr_family);
+ *sa_family = default_family;
}
ret = 0;
diff --git a/rpc/rpc-transport/socket/src/socket.c b/rpc/rpc-transport/socket/src/socket.c
index e6e73bf8f22..a4791437e6d 100644
--- a/rpc/rpc-transport/socket/src/socket.c
+++ b/rpc/rpc-transport/socket/src/socket.c
@@ -3101,6 +3101,7 @@ socket_connect (rpc_transport_t *this, int port)
}
}
+
if (priv->nodelay && (sa_family != AF_UNIX)) {
ret = __socket_nodelay (priv->sock);
diff --git a/rpc/xdr/src/glusterfs-fops.x b/rpc/xdr/src/glusterfs-fops.x
index 7b0bcb33213..5b7fe001f1c 100644
--- a/rpc/xdr/src/glusterfs-fops.x
+++ b/rpc/xdr/src/glusterfs-fops.x
@@ -103,6 +103,7 @@ enum glusterfs_event_t {
GF_EVENT_SOME_DESCENDENT_DOWN,
GF_EVENT_SCRUB_ONDEMAND,
GF_EVENT_SOME_DESCENDENT_UP,
+ GF_EVENT_CHILD_PING,
GF_EVENT_MAXVAL
};
diff --git a/tests/basic/exports_parsing.t b/tests/basic/exports_parsing.t
index fdaf9c2822e..da88bbcb2cc 100644
--- a/tests/basic/exports_parsing.t
+++ b/tests/basic/exports_parsing.t
@@ -32,7 +32,20 @@ function test_bad_opt ()
glusterfsd --print-exports $1 2>&1 | sed -n 1p
}
-EXPECT_KEYWORD "/test @test(rw,anonuid=0,sec=sys,) 10.35.11.31(rw,anonuid=0,sec=sys,)" test_good_file $EXP_FILES/exports
+function check_export_line() {
+ if [ "$1" == "$2" ]; then
+ echo "Y"
+ else
+ echo "N"
+ fi
+ return
+}
+
+export_result=$(test_good_file $EXP_FILES/exports)
+EXPECT "Y" check_export_line '/test @test(rw,anonuid=0,sec=sys,) 10.35.11.31(rw,anonuid=0,sec=sys,) ' "$export_result"
+
+export_result=$(test_good_file $EXP_FILES/exports-v6)
+EXPECT "Y" check_export_line '/test @test(rw,anonuid=0,sec=sys,) 2401:db00:11:1:face:0:3d:0(rw,anonuid=0,sec=sys,) ' "$export_result"
EXPECT_KEYWORD "Error parsing netgroups for:" test_bad_line $EXP_FILES/bad_exports
EXPECT_KEYWORD "Error parsing netgroups for:" test_long_netgroup $EXP_FILES/bad_exports
diff --git a/tests/basic/mount-nfs-auth.t b/tests/basic/mount-nfs-auth.t
index 9df5cb45c3b..cd0189788ba 100755
--- a/tests/basic/mount-nfs-auth.t
+++ b/tests/basic/mount-nfs-auth.t
@@ -15,6 +15,9 @@ TEST glusterd
TEST pidof glusterd
TEST $CLI volume info
+H0IP=$(ip addr show |grep -w inet |grep -v 127.0.0.1|awk '{ print $2 }'| cut -d "/" -f 1)
+H0IP6=$(host $HOSTNAME | grep IPv6 | awk '{print $NF}')
+
# Export variables for allow & deny
EXPORT_ALLOW="/$V0 $H0(sec=sys,rw,anonuid=0) @ngtop(sec=sys,rw,anonuid=0)"
EXPORT_ALLOW_SLASH="/$V0/ $H0(sec=sys,rw,anonuid=0) @ngtop(sec=sys,rw,anonuid=0)"
@@ -37,6 +40,10 @@ function build_dirs () {
mkdir -p $B0/b{0,1,2}/L1/L2/L3
}
+function export_allow_this_host_ipv6 () {
+ printf "$EXPORT_ALLOW6\n" > /var/lib/glusterd/nfs/exports
+}
+
function export_allow_this_host () {
printf "$EXPORT_ALLOW\n" > ${NFSDIR}/exports
}
@@ -186,6 +193,11 @@ EXPECT_WITHIN $NFS_EXPORT_TIMEOUT "1" is_nfs_export_available
## Mount NFS
EXPECT "Y" check_mount_success $V0
+EXPECT_WITHIN $UMOUNT_TIMEOUT "Y" umount_nfs $N0
+
+## Mount NFS using the IPv6 export
+export_allow_this_host_ipv6
+EXPECT "Y" check_mount_success $V0
## Disallow host
TEST export_deny_this_host
diff --git a/tests/configfiles/exports-v6 b/tests/configfiles/exports-v6
new file mode 100644
index 00000000000..426b1ef5705
--- /dev/null
+++ b/tests/configfiles/exports-v6
@@ -0,0 +1 @@
+/test @test(rw,anonuid=0,sec=sys,) 2401:db00:11:1:face:0:3d:0(rw,anonuid=0,sec=sys,)
diff --git a/xlators/cluster/afr/src/afr-common.c b/xlators/cluster/afr/src/afr-common.c
index ac834e90f4b..17943d7baae 100644
--- a/xlators/cluster/afr/src/afr-common.c
+++ b/xlators/cluster/afr/src/afr-common.c
@@ -2531,7 +2531,6 @@ unwind:
return 0;
}
-
int
afr_lookup_entry_heal (call_frame_t *frame, xlator_t *this)
{
@@ -3227,7 +3226,7 @@ afr_flush_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
}
UNLOCK (&frame->lock);
- call_count = afr_frame_return (frame);
+ call_count = afr_frame_return (frame);
if (call_count == 0)
AFR_STACK_UNWIND (flush, frame, local->op_ret,
@@ -4655,20 +4654,292 @@ __get_heard_from_all_status (xlator_t *this)
return heard_from_all;
}
+static int
+find_best_down_child (xlator_t *this)
+{
+ afr_private_t *priv = NULL;
+ int i = -1;
+ int32_t best_child = -1;
+ int64_t best_latency = INT64_MAX;
+
+ priv = this->private;
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (priv->child_up[i] &&
+ priv->child_latency[i] >= 0 &&
+ priv->child_latency[i] < best_latency) {
+ best_child = i;
+ best_latency = priv->child_latency[i];
+ }
+ }
+ if (best_child >= 0) {
+ gf_msg_debug (this->name, 0, "Found best down child (%d) "
+ "@ %ld ms latency", best_child, best_latency);
+ }
+ return best_child;
+}
+
+int
+find_worst_up_child (xlator_t *this)
+{
+ afr_private_t *priv = NULL;
+ int i = -1;
+ int32_t worst_child = -1;
+ int64_t worst_latency = INT64_MIN;
+
+ priv = this->private;
+
+ for (i = 0; i < priv->child_count; i++) {
+ if (priv->child_up[i] &&
+ priv->child_latency[i] >= 0 &&
+ priv->child_latency[i] > worst_latency) {
+ worst_child = i;
+ worst_latency = priv->child_latency[i];
+ }
+ }
+ if (worst_child >= 0) {
+ gf_msg_debug (this->name, 0, "Found worst up child (%d)"
+ " @ %ld ms latency", worst_child, worst_latency);
+ }
+ return worst_child;
+}
+
+void
+__afr_handle_ping_event (xlator_t *this, xlator_t *child_xlator,
+ const int idx, int64_t halo_max_latency_msec, int32_t *event,
+ int64_t child_latency_msec)
+{
+ afr_private_t *priv = NULL;
+ int up_children = 0;
+
+ priv = this->private;
+
+ priv->child_latency[idx] = child_latency_msec;
+ gf_msg_debug (child_xlator->name, 0, "Client ping @ %ld ms",
+ child_latency_msec);
+
+ up_children = __afr_get_up_children_count (priv);
+
+ if (child_latency_msec > halo_max_latency_msec &&
+ priv->child_up[idx] == 1 &&
+ up_children > priv->halo_min_replicas) {
+ if ((up_children - 1) <
+ priv->halo_min_replicas) {
+ gf_log (child_xlator->name, GF_LOG_INFO,
+ "Overriding halo threshold, "
+ "min replicas: %d",
+ priv->halo_min_replicas);
+ } else {
+ gf_log (child_xlator->name, GF_LOG_INFO,
+ "Child latency (%ld ms) "
+ "exceeds halo threshold (%ld), "
+ "marking child down.",
+ child_latency_msec,
+ halo_max_latency_msec);
+ *event = GF_EVENT_CHILD_DOWN;
+ }
+ } else if (child_latency_msec < halo_max_latency_msec &&
+ priv->child_up[idx] == 0) {
+ if (up_children < priv->halo_max_replicas) {
+ gf_log (child_xlator->name, GF_LOG_INFO,
+ "Child latency (%ld ms) "
+ "below halo threshold (%ld), "
+ "marking child up.",
+ child_latency_msec,
+ halo_max_latency_msec);
+ *event = GF_EVENT_CHILD_UP;
+ } else {
+ gf_log (child_xlator->name, GF_LOG_INFO,
+ "Not marking child %d up, "
+ "max replicas (%d) reached.", idx,
+ priv->halo_max_replicas);
+ }
+ }
+}
+
+void
+__afr_handle_child_up_event (xlator_t *this, xlator_t *child_xlator,
+ const int idx, int64_t halo_max_latency_msec,
+ int32_t *event, int32_t *call_psh, int32_t *up_child)
+{
+ afr_private_t *priv = NULL;
+ int up_children = 0;
+ int worst_up_child = -1;
+
+ priv = this->private;
+
+ /*
+ * This only really counts if the child was never up
+ * (value = -1) or had been down (value = 0). See
+ * comment at GF_EVENT_CHILD_DOWN for a more detailed
+ * explanation.
+ */
+ if (priv->child_up[idx] != 1) {
+ priv->event_generation++;
+ }
+ priv->child_up[idx] = 1;
+
+ *call_psh = 1;
+ *up_child = idx;
+ up_children = __afr_get_up_children_count (priv);
+
+ /*
+ * Handle the edge case where we exceed
+ * halo_min_replicas and we've got a child which is
+ * marked up as it was helping to satisfy the
+ * halo_min_replicas even though it's latency exceeds
+ * halo_max_latency_msec.
+ */
+ if (up_children > priv->halo_min_replicas) {
+ worst_up_child = find_worst_up_child (this);
+ if (worst_up_child >= 0 &&
+ priv->child_latency[worst_up_child] >
+ halo_max_latency_msec) {
+ gf_msg_debug (this->name, 0, "Marking child %d down, "
+ "doesn't meet halo threshold (%ld), and > "
+ "halo_min_replicas (%d)",
+ worst_up_child, halo_max_latency_msec,
+ priv->halo_min_replicas);
+ priv->child_up[worst_up_child] = 0;
+ up_children--;
+ }
+ }
+ if (up_children > priv->halo_max_replicas &&
+ !priv->shd.iamshd) {
+ worst_up_child = find_worst_up_child (this);
+ if (worst_up_child < 0) {
+ worst_up_child = idx;
+ }
+ priv->child_up[worst_up_child] = 0;
+ up_children--;
+ gf_msg_debug (this->name, 0, "Marking child %d down, "
+ "up_children (%d) > halo_max_replicas (%d)",
+ worst_up_child, up_children, priv->halo_max_replicas);
+ }
+
+ if (up_children == 1) {
+ gf_msg (this->name, GF_LOG_INFO, 0, AFR_MSG_SUBVOL_UP,
+ "Subvolume '%s' came back up; "
+ "going online.",
+ child_xlator->name);
+ } else {
+ *event = GF_EVENT_SOME_DESCENDENT_UP;
+ }
+
+ priv->last_event[idx] = *event;
+}
+
+void
+__afr_handle_child_down_event (xlator_t *this, xlator_t *child_xlator,
+ int idx, int64_t child_latency_msec, int32_t *event,
+ int32_t *call_psh, int32_t *up_child)
+{
+ afr_private_t *priv = NULL;
+ int i = 0;
+ int up_children = 0;
+ int down_children = 0;
+ int best_down_child = -1;
+
+ priv = this->private;
+
+ /*
+ * If a brick is down when we start, we'll get a
+ * CHILD_DOWN to indicate its initial state. There
+ * was never a CHILD_UP in this case, so if we
+ * increment "down_count" the difference between than
+ * and "up_count" will no longer be the number of
+ * children that are currently up. This has serious
+ * implications e.g. for quorum enforcement, so we
+ * don't increment these values unless the event
+ * represents an actual state transition between "up"
+ * (value = 1) and anything else.
+ */
+ if (priv->child_up[idx] == 1) {
+ priv->event_generation++;
+ }
+
+ /*
+ * If this is an _actual_ CHILD_DOWN event, we
+ * want to set the child_latency to < 0 to indicate
+ * the child is really disconnected.
+ */
+ if (child_latency_msec < 0) {
+ priv->child_latency[idx] = child_latency_msec;
+ }
+ priv->child_up[idx] = 0;
+
+ up_children = __afr_get_up_children_count (priv);
+ /*
+ * Handle the edge case where we need to find the
+ * next best child (to mark up) as marking this child
+ * down would cause us to fall below halo_min_replicas.
+ * We will also force the SHD to heal this child _now_
+ * as we want it to be up to date if we are going to
+ * begin using it synchronously.
+ */
+ if (up_children < priv->halo_min_replicas) {
+ best_down_child = find_best_down_child (this);
+ if (best_down_child >= 0) {
+ gf_msg_debug (this->name, 0,
+ "Swapping out child %d for "
+ "child %d to satisfy halo_min_replicas (%d).",
+ idx, best_down_child, priv->halo_min_replicas);
+ priv->child_up[best_down_child] = 1;
+ *call_psh = 1;
+ *up_child = best_down_child;
+ }
+ }
+
+ for (i = 0; i < priv->child_count; i++)
+ if (priv->child_up[i] == 0)
+ down_children++;
+ if (down_children == priv->child_count) {
+ gf_msg (this->name, GF_LOG_ERROR, 0, AFR_MSG_SUBVOLS_DOWN,
+ "All subvolumes are down. Going "
+ "offline until atleast one of them "
+ "comes back up.");
+ } else {
+ *event = GF_EVENT_SOME_DESCENDENT_DOWN;
+ }
+ priv->last_event[idx] = *event;
+}
+
+static int64_t
+afr_get_halo_latency (xlator_t *this)
+{
+ afr_private_t *priv = NULL;
+ int64_t halo_max_latency_msec = 0;
+
+ priv = this->private;
+
+ if (priv->shd.iamshd) {
+ halo_max_latency_msec = priv->shd.halo_max_latency_msec;
+ } else if (priv->nfsd.iamnfsd) {
+ halo_max_latency_msec =
+ priv->nfsd.halo_max_latency_msec;
+ } else {
+ halo_max_latency_msec = priv->halo_max_latency_msec;
+ }
+ gf_msg_debug (this->name, 0, "Using halo latency %ld",
+ halo_max_latency_msec);
+ return halo_max_latency_msec;
+}
+
+
int32_t
afr_notify (xlator_t *this, int32_t event,
void *data, void *data2)
{
afr_private_t *priv = NULL;
+ xlator_t *child_xlator = NULL;
int i = -1;
- int up_children = 0;
- int down_children = 0;
int propagate = 0;
int had_heard_from_all = 0;
int have_heard_from_all = 0;
int idx = -1;
int ret = -1;
int call_psh = 0;
+ int up_child = -1;
dict_t *input = NULL;
dict_t *output = NULL;
gf_boolean_t had_quorum = _gf_false;
@@ -4677,6 +4948,10 @@ afr_notify (xlator_t *this, int32_t event,
struct gf_upcall_cache_invalidation *up_ci = NULL;
inode_table_t *itable = NULL;
inode_t *inode = NULL;
+ int64_t halo_max_latency_msec = 0;
+ int64_t child_latency_msec = -1;
+
+ child_xlator = (xlator_t *)data;
priv = this->private;
@@ -4701,7 +4976,7 @@ afr_notify (xlator_t *this, int32_t event,
* subsequent revalidate lookup happens on all the dht's subvolumes
* which triggers afr self-heals if any.
*/
- idx = find_child_index (this, data);
+ idx = find_child_index (this, child_xlator);
if (idx < 0) {
gf_msg (this->name, GF_LOG_ERROR, 0, AFR_MSG_INVALID_CHILD_UP,
"Received child_up from invalid subvolume");
@@ -4710,6 +4985,30 @@ afr_notify (xlator_t *this, int32_t event,
had_quorum = priv->quorum_count && afr_has_quorum (priv->child_up,
this);
+ if (priv->halo_enabled) {
+ halo_max_latency_msec = afr_get_halo_latency (this);
+
+ if (event == GF_EVENT_CHILD_PING) {
+ /* Calculates the child latency and sets event
+ */
+ child_latency_msec = (int64_t)(uintptr_t)data2;
+ LOCK (&priv->lock);
+ {
+ __afr_handle_ping_event (this, child_xlator,
+ idx, halo_max_latency_msec, &event,
+ child_latency_msec);
+ }
+ UNLOCK (&priv->lock);
+ }
+ }
+
+ if (event == GF_EVENT_CHILD_PING) {
+ /* This is the only xlator that handles PING, no reason to
+ * propagate.
+ */
+ goto out;
+ }
+
if (event == GF_EVENT_TRANSLATOR_OP) {
LOCK (&priv->lock);
{
@@ -4736,57 +5035,15 @@ afr_notify (xlator_t *this, int32_t event,
propagate = 1;
break;
case GF_EVENT_CHILD_UP:
- /*
- * This only really counts if the child was never up
- * (value = -1) or had been down (value = 0). See
- * comment at GF_EVENT_CHILD_DOWN for a more detailed
- * explanation.
- */
- if (priv->child_up[idx] != 1) {
- priv->event_generation++;
- }
- priv->child_up[idx] = 1;
-
- call_psh = 1;
- up_children = __afr_get_up_children_count (priv);
- if (up_children == 1) {
- gf_msg (this->name, GF_LOG_INFO, 0,
- AFR_MSG_SUBVOL_UP,
- "Subvolume '%s' came back up; "
- "going online.", ((xlator_t *)data)->name);
- gf_event (EVENT_AFR_SUBVOL_UP,
- "subvol=%s", this->name);
-
- } else {
- event = GF_EVENT_SOME_DESCENDENT_UP;
- }
-
- priv->last_event[idx] = event;
-
+ __afr_handle_child_up_event (this, child_xlator,
+ idx, halo_max_latency_msec, &event, &call_psh,
+ &up_child);
break;
case GF_EVENT_CHILD_DOWN:
- if (priv->child_up[idx] == 1) {
- priv->event_generation++;
- }
- priv->child_up[idx] = 0;
-
- for (i = 0; i < priv->child_count; i++)
- if (priv->child_up[i] == 0)
- down_children++;
- if (down_children == priv->child_count) {
- gf_msg (this->name, GF_LOG_ERROR, 0,
- AFR_MSG_SUBVOLS_DOWN,
- "All subvolumes are down. Going offline "
- "until atleast one of them comes back up.");
- gf_event (EVENT_AFR_SUBVOLS_DOWN,
- "subvol=%s", this->name);
- } else {
- event = GF_EVENT_SOME_DESCENDENT_DOWN;
- }
-
- priv->last_event[idx] = event;
-
+ __afr_handle_child_down_event (this, child_xlator, idx,
+ child_latency_msec, &event, &call_psh,
+ &up_child);
break;
case GF_EVENT_CHILD_CONNECTING:
@@ -4839,7 +5096,6 @@ afr_notify (xlator_t *this, int32_t event,
had come up, propagate CHILD_UP, but only this time
*/
event = GF_EVENT_CHILD_DOWN;
- up_children = __afr_get_up_children_count (priv);
for (i = 0; i < priv->child_count; i++) {
if (priv->last_event[i] == GF_EVENT_CHILD_UP) {
event = GF_EVENT_CHILD_UP;
diff --git a/xlators/cluster/afr/src/afr-mem-types.h b/xlators/cluster/afr/src/afr-mem-types.h
index 7f7962013d7..c7d6261b110 100644
--- a/xlators/cluster/afr/src/afr-mem-types.h
+++ b/xlators/cluster/afr/src/afr-mem-types.h
@@ -46,7 +46,8 @@ enum gf_afr_mem_types_ {
gf_afr_mt_spbc_timeout_t,
gf_afr_mt_spb_status_t,
gf_afr_mt_empty_brick_t,
- gf_afr_mt_end
+ gf_afr_mt_child_latency_t,
+ gf_afr_mt_end
};
#endif
diff --git a/xlators/cluster/afr/src/afr-self-heald.h b/xlators/cluster/afr/src/afr-self-heald.h
index c6ac5ebfd1b..4ac1d32f58a 100644
--- a/xlators/cluster/afr/src/afr-self-heald.h
+++ b/xlators/cluster/afr/src/afr-self-heald.h
@@ -58,6 +58,7 @@ typedef struct {
eh_t **statistics;
uint32_t max_threads;
uint32_t wait_qlength;
+ uint32_t halo_max_latency_msec;
} afr_self_heald_t;
diff --git a/xlators/cluster/afr/src/afr.c b/xlators/cluster/afr/src/afr.c
index ceaa034dbbb..17b34822c17 100644
--- a/xlators/cluster/afr/src/afr.c
+++ b/xlators/cluster/afr/src/afr.c
@@ -184,6 +184,27 @@ reconfigure (xlator_t *this, dict_t *options)
GF_OPTION_RECONF ("data-self-heal-algorithm",
priv->data_self_heal_algorithm, options, str, out);
+ GF_OPTION_RECONF ("halo-enabled",
+ priv->halo_enabled, options, bool,
+ out);
+
+ GF_OPTION_RECONF ("halo-shd-max-latency",
+ priv->shd.halo_max_latency_msec, options, uint32,
+ out);
+
+ GF_OPTION_RECONF ("halo-nfsd-max-latency",
+ priv->nfsd.halo_max_latency_msec, options, uint32,
+ out);
+
+ GF_OPTION_RECONF ("halo-max-latency", priv->halo_max_latency_msec,
+ options, uint32, out);
+
+ GF_OPTION_RECONF ("halo-max-replicas", priv->halo_max_replicas, options,
+ uint32, out);
+
+ GF_OPTION_RECONF ("halo-min-replicas", priv->halo_min_replicas, options,
+ uint32, out);
+
GF_OPTION_RECONF ("read-subvolume", read_subvol, options, xlator, out);
GF_OPTION_RECONF ("read-hash-mode", priv->hash_mode,
@@ -473,6 +494,24 @@ init (xlator_t *this)
GF_OPTION_INIT ("entry-self-heal", priv->entry_self_heal, bool, out);
+ GF_OPTION_INIT ("halo-shd-max-latency", priv->shd.halo_max_latency_msec,
+ uint32, out);
+
+ GF_OPTION_INIT ("halo-max-latency", priv->halo_max_latency_msec,
+ uint32, out);
+ GF_OPTION_INIT ("halo-max-replicas", priv->halo_max_replicas, uint32,
+ out);
+ GF_OPTION_INIT ("halo-min-replicas", priv->halo_min_replicas, uint32,
+ out);
+
+ GF_OPTION_INIT ("halo-enabled",
+ priv->halo_enabled, bool, out);
+
+ GF_OPTION_INIT ("halo-nfsd-max-latency",
+ priv->nfsd.halo_max_latency_msec, uint32, out);
+
+ GF_OPTION_INIT ("iam-nfs-daemon", priv->nfsd.iamnfsd, bool, out);
+
GF_OPTION_INIT ("data-change-log", priv->data_change_log, bool, out);
GF_OPTION_INIT ("metadata-change-log", priv->metadata_change_log, bool,
@@ -528,7 +567,12 @@ init (xlator_t *this)
priv->child_up = GF_CALLOC (sizeof (unsigned char), child_count,
gf_afr_mt_char);
- if (!priv->child_up) {
+
+ priv->child_latency = GF_CALLOC (sizeof (*priv->child_latency),
+ child_count,
+ gf_afr_mt_child_latency_t);
+
+ if (!priv->child_up || !priv->child_latency) {
ret = -ENOMEM;
goto out;
}
@@ -736,7 +780,50 @@ struct volume_options options[] = {
"jobs that can perform parallel heals in the "
"background."
},
- { .key = {"heal-wait-queue-length"},
+ { .key = {"halo-shd-max-latency"},
+ .type = GF_OPTION_TYPE_INT,
+ .min = 1,
+ .max = 99999,
+ .default_value = "99999",
+ .description = "Maximum latency for shd halo replication in msec."
+ },
+ { .key = {"halo-enabled"},
+ .type = GF_OPTION_TYPE_BOOL,
+ .default_value = "False",
+ .description = "Enable Halo (geo) replication mode."
+ },
+ { .key = {"halo-nfsd-max-latency"},
+ .type = GF_OPTION_TYPE_INT,
+ .min = 1,
+ .max = 99999,
+ .default_value = "5",
+ .description = "Maximum latency for nfsd halo replication in msec."
+ },
+ { .key = {"halo-max-latency"},
+ .type = GF_OPTION_TYPE_INT,
+ .min = 1,
+ .max = 99999,
+ .default_value = "5",
+ .description = "Maximum latency for halo replication in msec."
+ },
+ { .key = {"halo-max-replicas"},
+ .type = GF_OPTION_TYPE_INT,
+ .min = 1,
+ .max = 99999,
+ .default_value = "99999",
+ .description = "The maximum number of halo replicas; replicas"
+ " beyond this value will be written asynchronously"
+ "via the SHD."
+ },
+ { .key = {"halo-min-replicas"},
+ .type = GF_OPTION_TYPE_INT,
+ .min = 1,
+ .max = 99999,
+ .default_value = "2",
+ .description = "The minimmum number of halo replicas, before adding "
+ "out of region replicas."
+ },
+ { .key = {"heal-wait-queue-length"},
.type = GF_OPTION_TYPE_INT,
.min = 0,
.max = 10000, /*Around 100MB with sizeof(afr_local_t)= 10496 bytes*/
@@ -876,6 +963,13 @@ struct volume_options options[] = {
"translator is running as part of self-heal-daemon "
"or not."
},
+ { .key = {"iam-nfs-daemon"},
+ .type = GF_OPTION_TYPE_BOOL,
+ .default_value = "off",
+ .description = "This option differentiates if the replicate "
+ "translator is running as part of an NFS daemon "
+ "or not."
+ },
{ .key = {"quorum-type"},
.type = GF_OPTION_TYPE_STR,
.value = { "none", "auto", "fixed"},
diff --git a/xlators/cluster/afr/src/afr.h b/xlators/cluster/afr/src/afr.h
index 0535e7c7271..3be15175dc7 100644
--- a/xlators/cluster/afr/src/afr.h
+++ b/xlators/cluster/afr/src/afr.h
@@ -74,6 +74,11 @@ typedef enum {
AFR_FAV_CHILD_POLICY_MAX,
} afr_favorite_child_policy;
+struct afr_nfsd {
+ gf_boolean_t iamnfsd;
+ uint32_t halo_max_latency_msec;
+};
+
typedef struct _afr_private {
gf_lock_t lock; /* to guard access to child_count, etc */
unsigned int child_count; /* total number of children */
@@ -85,6 +90,7 @@ typedef struct _afr_private {
inode_t *root_inode;
unsigned char *child_up;
+ int64_t *child_latency;
unsigned char *local;
char **pending_key;
@@ -155,8 +161,14 @@ typedef struct _afr_private {
gf_boolean_t ensure_durability;
char *sh_domain;
char *afr_dirty;
+ gf_boolean_t halo_enabled;
+
+ uint32_t halo_max_latency_msec;
+ uint32_t halo_max_replicas;
+ uint32_t halo_min_replicas;
- afr_self_heald_t shd;
+ afr_self_heald_t shd;
+ struct afr_nfsd nfsd;
gf_boolean_t consistent_metadata;
uint64_t spb_choice_timeout;
diff --git a/xlators/features/changelog/lib/src/gf-changelog-rpc.c b/xlators/features/changelog/lib/src/gf-changelog-rpc.c
index b9339a770d1..c1139423d6d 100644
--- a/xlators/features/changelog/lib/src/gf-changelog-rpc.c
+++ b/xlators/features/changelog/lib/src/gf-changelog-rpc.c
@@ -26,6 +26,7 @@ gf_changelog_rpc_notify (struct rpc_clnt *rpc,
case RPC_CLNT_DISCONNECT:
case RPC_CLNT_MSG:
case RPC_CLNT_DESTROY:
+ case RPC_CLNT_PING:
break;
}
diff --git a/xlators/features/changelog/src/changelog-ev-handle.c b/xlators/features/changelog/src/changelog-ev-handle.c
index cada369ba0f..caa5bbbadcd 100644
--- a/xlators/features/changelog/src/changelog-ev-handle.c
+++ b/xlators/features/changelog/src/changelog-ev-handle.c
@@ -179,6 +179,8 @@ changelog_rpc_notify (struct rpc_clnt *rpc,
/* Free up mydata */
changelog_rpc_clnt_unref (crpc);
break;
+ case RPC_CLNT_PING:
+ break;
}
return 0;
diff --git a/xlators/mgmt/glusterd/src/glusterd-volgen.c b/xlators/mgmt/glusterd/src/glusterd-volgen.c
index 30f690bb379..02c8ed2ade2 100644
--- a/xlators/mgmt/glusterd/src/glusterd-volgen.c
+++ b/xlators/mgmt/glusterd/src/glusterd-volgen.c
@@ -5058,6 +5058,24 @@ out:
return ret;
}
+static int
+volgen_graph_set_iam_nfsd (const volgen_graph_t *graph)
+{
+ xlator_t *trav;
+ int ret = 0;
+
+ for (trav = first_of ((volgen_graph_t *)graph); trav;
+ trav = trav->next) {
+ if (strcmp (trav->type, "cluster/replicate") != 0)
+ continue;
+
+ ret = xlator_set_option (trav, "iam-nfs-daemon", "yes");
+ if (ret)
+ break;
+ }
+ return ret;
+}
+
/* builds a graph for nfs server role, with option overrides in mod_dict */
int
build_nfs_graph (volgen_graph_t *graph, dict_t *mod_dict)
@@ -5196,6 +5214,10 @@ build_nfs_graph (volgen_graph_t *graph, dict_t *mod_dict)
if (ret)
goto out;
+ ret = volgen_graph_set_iam_nfsd (&cgraph);
+ if (ret)
+ goto out;
+
ret = volgen_graph_merge_sub (graph, &cgraph, 1);
if (ret)
goto out;
diff --git a/xlators/mgmt/glusterd/src/glusterd-volume-ops.c b/xlators/mgmt/glusterd/src/glusterd-volume-ops.c
index 5d164fd8df3..6bb81c14d89 100644
--- a/xlators/mgmt/glusterd/src/glusterd-volume-ops.c
+++ b/xlators/mgmt/glusterd/src/glusterd-volume-ops.c
@@ -287,6 +287,7 @@ __glusterd_handle_create_volume (rpcsvc_request_t *req)
int32_t type = 0;
char *username = NULL;
char *password = NULL;
+ char *addr_family = "inet";
GF_ASSERT (req);
@@ -395,11 +396,12 @@ __glusterd_handle_create_volume (rpcsvc_request_t *req)
if (conf->op_version >= GD_OP_VERSION_3_8_0) {
ret = dict_set_dynstr_with_alloc (dict,
"transport.address-family",
- "inet");
+ addr_family);
if (ret) {
gf_log (this->name, GF_LOG_ERROR,
"failed to set "
- "transport.address-family");
+ "transport.address-family "
+ "to %s", addr_family);
goto out;
}
}
diff --git a/xlators/mgmt/glusterd/src/glusterd-volume-set.c b/xlators/mgmt/glusterd/src/glusterd-volume-set.c
index fe291f1d845..9e84d248090 100644
--- a/xlators/mgmt/glusterd/src/glusterd-volume-set.c
+++ b/xlators/mgmt/glusterd/src/glusterd-volume-set.c
@@ -3312,6 +3312,39 @@ struct volopt_map_entry glusterd_volopt_map[] = {
.op_version = GD_OP_VERSION_3_10_1,
.flags = OPT_FLAG_CLIENT_OPT
},
+
+ /* Halo replication options */
+ { .key = "cluster.halo-enabled",
+ .voltype = "cluster/replicate",
+ .op_version = GD_OP_VERSION_3_11_0,
+ .flags = OPT_FLAG_CLIENT_OPT
+ },
+ { .key = "cluster.halo-shd-max-latency",
+ .voltype = "cluster/replicate",
+ .op_version = GD_OP_VERSION_3_11_0,
+ .flags = OPT_FLAG_CLIENT_OPT
+ },
+ { .key = "cluster.halo-nfsd-max-latency",
+ .voltype = "cluster/replicate",
+ .op_version = GD_OP_VERSION_3_11_0,
+ .flags = OPT_FLAG_CLIENT_OPT
+ },
+ { .key = "cluster.halo-max-latency",
+ .voltype = "cluster/replicate",
+ .op_version = GD_OP_VERSION_3_11_0,
+ .flags = OPT_FLAG_CLIENT_OPT
+ },
+ { .key = "cluster.halo-max-replicas",
+ .voltype = "cluster/replicate",
+ .op_version = GD_OP_VERSION_3_11_0,
+ .flags = OPT_FLAG_CLIENT_OPT
+ },
+ { .key = "cluster.halo-min-replicas",
+ .voltype = "cluster/replicate",
+ .op_version = GD_OP_VERSION_3_11_0,
+ .flags = OPT_FLAG_CLIENT_OPT
+ },
+
{ .key = NULL
}
};
diff --git a/xlators/mount/fuse/utils/mount.glusterfs.in b/xlators/mount/fuse/utils/mount.glusterfs.in
index 6c4cdfed062..b5c90ba1dff 100755
--- a/xlators/mount/fuse/utils/mount.glusterfs.in
+++ b/xlators/mount/fuse/utils/mount.glusterfs.in
@@ -186,6 +186,21 @@ start_glusterfs ()
fi
#options with values start here
+ if [ -n "$halo_max_latency" ]; then
+ cmd_line=$(echo "$cmd_line --xlator-option \
+ *replicate*.halo-max-latency=$halo_max_latency");
+ fi
+
+ if [ -n "$halo_max_replicas" ]; then
+ cmd_line=$(echo "$cmd_line --xlator-option \
+ *replicate*.halo-max-replicas=$halo_max_replicas");
+ fi
+
+ if [ -n "$halo_min_replicas" ]; then
+ cmd_line=$(echo "$cmd_line --xlator-option \
+ *replicate*.halo-min-replicas=$halo_min_replicas");
+ fi
+
if [ -n "$log_level" ]; then
cmd_line=$(echo "$cmd_line --log-level=$log_level");
fi
@@ -479,6 +494,15 @@ with_options()
[ -z "$fuse_mountopts" ] || fuse_mountopts="$fuse_mountopts,"
fuse_mountopts="${fuse_mountopts}$key=\"$value\""
;;
+ "halo-max-latency")
+ halo_max_latency=$value
+ ;;
+ "halo-max-replicas")
+ halo_max_replicas=$value
+ ;;
+ "halo-min-replicas")
+ halo_min_replicas=$value
+ ;;
x-*)
# comments or userspace application-specific options, drop them
;;
diff --git a/xlators/nfs/server/src/exports.h b/xlators/nfs/server/src/exports.h
index bc9af2f0b8b..0079b9a3deb 100644
--- a/xlators/nfs/server/src/exports.h
+++ b/xlators/nfs/server/src/exports.h
@@ -22,7 +22,7 @@
#define GF_EXP GF_NFS"-exports"
#define NETGROUP_REGEX_PATTERN "(@([a-zA-Z0-9\\(=, .])+)())"
-#define HOSTNAME_REGEX_PATTERN "[[:space:]]([a-zA-Z0-9.\\(=,*/)-]+)"
+#define HOSTNAME_REGEX_PATTERN "[[:space:]]([a-zA-Z0-9.\\(=,*/:)-]+)"
#define OPTIONS_REGEX_PATTERN "([a-zA-Z0-9=\\.]+)"
#define NETGROUP_MAX_LEN 128
diff --git a/xlators/nfs/server/src/mount3.c b/xlators/nfs/server/src/mount3.c
index 3f6415dba85..12f52e4f5d0 100644
--- a/xlators/nfs/server/src/mount3.c
+++ b/xlators/nfs/server/src/mount3.c
@@ -1907,7 +1907,7 @@ _mnt3_get_host_from_peer (const char *peer_addr)
size_t host_len = 0;
char *colon = NULL;
- colon = strchr (peer_addr, ':');
+ colon = strrchr (peer_addr, ':');
if (!colon) {
gf_msg (GF_MNT, GF_LOG_ERROR, 0, NFS_MSG_BAD_PEER,
"Bad peer %s", peer_addr);
diff --git a/xlators/nfs/server/src/nfs.c b/xlators/nfs/server/src/nfs.c
index 3e7199c036d..c2c3c863b05 100644
--- a/xlators/nfs/server/src/nfs.c
+++ b/xlators/nfs/server/src/nfs.c
@@ -901,6 +901,7 @@ nfs_init_state (xlator_t *this)
}
}
+
/* Right only socket support exists between nfs client and
* gluster nfs, so we can set default value as socket
*/
diff --git a/xlators/protocol/client/src/client-handshake.c b/xlators/protocol/client/src/client-handshake.c
index 447366c0deb..a36f6e435a7 100644
--- a/xlators/protocol/client/src/client-handshake.c
+++ b/xlators/protocol/client/src/client-handshake.c
@@ -1553,7 +1553,7 @@ client_query_portmap_cbk (struct rpc_req *req, struct iovec *iov, int count, voi
rpc_clnt_reconfig (conf->rpc, &config);
conf->skip_notify = 1;
- conf->quick_reconnect = 1;
+ conf->quick_reconnect = 1;
out:
if (frame)
diff --git a/xlators/protocol/client/src/client.c b/xlators/protocol/client/src/client.c
index e8db8eed166..6cb5b6b38ca 100644
--- a/xlators/protocol/client/src/client.c
+++ b/xlators/protocol/client/src/client.c
@@ -464,7 +464,7 @@ int32_t
client_forget (xlator_t *this, inode_t *inode)
{
/* Nothing here */
- return 0;
+ return 0;
}
int32_t
@@ -542,7 +542,7 @@ out:
STACK_UNWIND_STRICT (lookup, frame, -1, ENOTCONN,
NULL, NULL, NULL, NULL);
- return 0;
+ return 0;
}
@@ -568,7 +568,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (stat, frame, -1, ENOTCONN, NULL, NULL);
- return 0;
+ return 0;
}
@@ -597,7 +597,7 @@ out:
STACK_UNWIND_STRICT (truncate, frame, -1, ENOTCONN, NULL, NULL, NULL);
- return 0;
+ return 0;
}
@@ -625,7 +625,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (ftruncate, frame, -1, ENOTCONN, NULL, NULL, NULL);
- return 0;
+ return 0;
}
@@ -654,7 +654,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (access, frame, -1, ENOTCONN, NULL);
- return 0;
+ return 0;
}
@@ -684,7 +684,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (readlink, frame, -1, ENOTCONN, NULL, NULL, NULL);
- return 0;
+ return 0;
}
@@ -715,7 +715,7 @@ out:
STACK_UNWIND_STRICT (mknod, frame, -1, ENOTCONN,
NULL, NULL, NULL, NULL, NULL);
- return 0;
+ return 0;
}
@@ -745,7 +745,7 @@ out:
STACK_UNWIND_STRICT (mkdir, frame, -1, ENOTCONN,
NULL, NULL, NULL, NULL, NULL);
- return 0;
+ return 0;
}
@@ -775,7 +775,7 @@ out:
STACK_UNWIND_STRICT (unlink, frame, -1, ENOTCONN,
NULL, NULL, NULL);
- return 0;
+ return 0;
}
int32_t
@@ -804,7 +804,7 @@ out:
STACK_UNWIND_STRICT (rmdir, frame, -1, ENOTCONN,
NULL, NULL, NULL);
- return 0;
+ return 0;
}
@@ -834,7 +834,7 @@ out:
STACK_UNWIND_STRICT (symlink, frame, -1, ENOTCONN,
NULL, NULL, NULL, NULL, NULL);
- return 0;
+ return 0;
}
@@ -864,7 +864,7 @@ out:
STACK_UNWIND_STRICT (rename, frame, -1, ENOTCONN,
NULL, NULL, NULL, NULL, NULL, NULL);
- return 0;
+ return 0;
}
@@ -894,7 +894,7 @@ out:
STACK_UNWIND_STRICT (link, frame, -1, ENOTCONN,
NULL, NULL, NULL, NULL, NULL);
- return 0;
+ return 0;
}
@@ -929,7 +929,7 @@ out:
STACK_UNWIND_STRICT (create, frame, -1, ENOTCONN,
NULL, NULL, NULL, NULL, NULL, NULL);
- return 0;
+ return 0;
}
@@ -962,7 +962,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (open, frame, -1, ENOTCONN, NULL, NULL);
- return 0;
+ return 0;
}
@@ -997,7 +997,7 @@ out:
STACK_UNWIND_STRICT (readv, frame, -1, ENOTCONN,
NULL, 0, NULL, NULL, NULL);
- return 0;
+ return 0;
}
@@ -1035,7 +1035,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (writev, frame, -1, ENOTCONN, NULL, NULL, NULL);
- return 0;
+ return 0;
}
@@ -1061,7 +1061,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (flush, frame, -1, ENOTCONN, NULL);
- return 0;
+ return 0;
}
@@ -1090,7 +1090,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (fsync, frame, -1, ENOTCONN, NULL, NULL, NULL);
- return 0;
+ return 0;
}
@@ -1117,7 +1117,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (fstat, frame, -1, ENOTCONN, NULL, NULL);
- return 0;
+ return 0;
}
@@ -1146,7 +1146,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (opendir, frame, -1, ENOTCONN, NULL, NULL);
- return 0;
+ return 0;
}
@@ -1174,7 +1174,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (fsyncdir, frame, -1, ENOTCONN, NULL);
- return 0;
+ return 0;
}
@@ -1201,7 +1201,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (statfs, frame, -1, ENOTCONN, NULL, NULL);
- return 0;
+ return 0;
}
static gf_boolean_t
@@ -1390,7 +1390,7 @@ out:
if (need_unwind)
STACK_UNWIND_STRICT (setxattr, frame, op_ret, op_errno, NULL);
- return 0;
+ return 0;
}
@@ -1420,7 +1420,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (fsetxattr, frame, -1, ENOTCONN, NULL);
- return 0;
+ return 0;
}
@@ -1450,7 +1450,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (fgetxattr, frame, -1, ENOTCONN, NULL, NULL);
- return 0;
+ return 0;
}
@@ -1479,7 +1479,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (getxattr, frame, -1, ENOTCONN, NULL, NULL);
- return 0;
+ return 0;
}
@@ -1509,7 +1509,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (xattrop, frame, -1, ENOTCONN, NULL, NULL);
- return 0;
+ return 0;
}
@@ -1539,7 +1539,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (fxattrop, frame, -1, ENOTCONN, NULL, NULL);
- return 0;
+ return 0;
}
@@ -1568,7 +1568,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (removexattr, frame, -1, ENOTCONN, NULL);
- return 0;
+ return 0;
}
int32_t
@@ -1595,7 +1595,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (fremovexattr, frame, -1, ENOTCONN, NULL);
- return 0;
+ return 0;
}
int32_t
@@ -1651,7 +1651,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (lk, frame, -1, ENOTCONN, NULL, NULL);
- return 0;
+ return 0;
}
@@ -1681,7 +1681,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (inodelk, frame, -1, ENOTCONN, NULL);
- return 0;
+ return 0;
}
@@ -1712,7 +1712,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (finodelk, frame, -1, ENOTCONN, NULL);
- return 0;
+ return 0;
}
@@ -1744,7 +1744,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (entrylk, frame, -1, ENOTCONN, NULL);
- return 0;
+ return 0;
}
@@ -1777,7 +1777,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (fentrylk, frame, -1, ENOTCONN, NULL);
- return 0;
+ return 0;
}
@@ -1806,7 +1806,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (rchecksum, frame, -1, ENOTCONN, 0, NULL, NULL);
- return 0;
+ return 0;
}
int32_t
@@ -1837,7 +1837,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (readdir, frame, -1, ENOTCONN, NULL, NULL);
- return 0;
+ return 0;
}
@@ -1869,7 +1869,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (readdirp, frame, -1, ENOTCONN, NULL, NULL);
- return 0;
+ return 0;
}
@@ -1898,7 +1898,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (setattr, frame, -1, ENOTCONN, NULL, NULL, NULL);
- return 0;
+ return 0;
}
int32_t
@@ -1926,7 +1926,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (fsetattr, frame, -1, ENOTCONN, NULL, NULL, NULL);
- return 0;
+ return 0;
}
int32_t
@@ -2152,7 +2152,7 @@ out:
if (ret)
STACK_UNWIND_STRICT (getspec, frame, -1, EINVAL, NULL);
- return 0;
+ return 0;
}
@@ -2223,6 +2223,15 @@ client_rpc_notify (struct rpc_clnt *rpc, void *mydata, rpc_clnt_event_t event,
conf = this->private;
switch (event) {
+ case RPC_CLNT_PING:
+ {
+ ret = default_notify (this, GF_EVENT_CHILD_PING, data);
+ if (ret)
+ gf_log (this->name, GF_LOG_INFO,
+ "CHILD_PING notify failed");
+ conf->last_sent_event = GF_EVENT_CHILD_PING;
+ break;
+ }
case RPC_CLNT_CONNECT:
{
conf->connected = 1;
@@ -2314,7 +2323,6 @@ client_rpc_notify (struct rpc_clnt *rpc, void *mydata, rpc_clnt_event_t event,
} else {
rpc->conn.config.remote_port = 0;
-
}
break;
@@ -2666,7 +2674,7 @@ reconfigure (xlator_t *this, dict_t *options)
ret = 0;
out:
- return ret;
+ return ret;
}