Repository: incubator-hawq
Updated Branches:
refs/heads/master 2a1506604 -> d17806287
HAWQ-473. Implement adding a entry into gp_configuration_history and
add a description column to show the reason of this segment is down
Project: http://git-wip-us.apache.org/repos/asf/incubator-hawq/repo
Commit: http://git-wip-us.apache.org/repos/asf/incubator-hawq/commit/d1780628
Tree: http://git-wip-us.apache.org/repos/asf/incubator-hawq/tree/d1780628
Diff: http://git-wip-us.apache.org/repos/asf/incubator-hawq/diff/d1780628
Branch: refs/heads/master
Commit: d178062876f0c55db7b1ac74946bd2ba096b779f
Parents: 2a15066
Author: Wen Lin <w...@pivotal.io>
Authored: Tue Mar 15 10:00:16 2016 +0800
Committer: Wen Lin <w...@pivotal.io>
Committed: Tue Mar 15 10:00:16 2016 +0800
----------------------------------------------------------------------
.../communication/rmcomm_RM2RMSEG.c | 28 +-
.../resourcemanager/include/resourcepool.h | 43 +-
src/backend/resourcemanager/requesthandler.c | 109 ++-
.../resourcemanager/requesthandler_RMSEG.c | 1 -
.../resourcebroker/resourcebroker_LIBYARN.c | 82 +-
.../resourcebroker_LIBYARN_proc.c | 1 -
src/backend/resourcemanager/resourcemanager.c | 91 +-
src/backend/resourcemanager/resourcepool.c | 857 ++++++++++++-------
src/backend/resourcemanager/resqueuemanager.c | 3 +-
src/backend/utils/gp/segadmin.c | 3 +-
src/include/catalog/gp_configuration.h | 27 +-
src/include/catalog/gp_segment_config.h | 11 +-
src/include/catalog/pg_proc.h | 5 +-
src/include/utils/builtins.h | 1 +
tools/bin/gppylib/data/2.0.json | 32 +-
15 files changed, 823 insertions(+), 471 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/d1780628/src/backend/resourcemanager/communication/rmcomm_RM2RMSEG.c
----------------------------------------------------------------------
diff --git a/src/backend/resourcemanager/communication/rmcomm_RM2RMSEG.c
b/src/backend/resourcemanager/communication/rmcomm_RM2RMSEG.c
index fe4a595..ca332c9 100644
--- a/src/backend/resourcemanager/communication/rmcomm_RM2RMSEG.c
+++ b/src/backend/resourcemanager/communication/rmcomm_RM2RMSEG.c
@@ -231,11 +231,23 @@ void
receivedRUAliveResponse(AsyncCommMessageHandlerContext context,
* This call makes resource pool remove unused
containers.
*/
returnAllGRMResourceFromSegment(segres);
+
+ segres->Stat->StatusDesc |=
SEG_STATUS_FAILED_PROBING_SEGMENT;
/* Set the host down in gp_segment_configuration table
*/
if (Gp_role != GP_ROLE_UTILITY)
{
+ SimpStringPtr description =
build_segment_status_description(segres->Stat);
update_segment_status(segres->Stat->ID +
REGISTRATION_ORDER_OFFSET,
-
SEGMENT_STATUS_DOWN);
+
SEGMENT_STATUS_DOWN,
+
(description->Len > 0)?description->Str:"");
+ add_segment_history_row(segres->Stat->ID +
REGISTRATION_ORDER_OFFSET,
+
GET_SEGRESOURCE_HOSTNAME(segres),
+
description->Str);
+ if (description != NULL)
+ {
+ freeSimpleStringContent(description);
+ rm_pfree(PCONTEXT, description);
+ }
}
/* Set the host down. */
elog(WARNING, "Resource manager sets host %s from up to
down "
@@ -281,10 +293,22 @@ void sentRUAliveError(AsyncCommMessageHandlerContext
context)
* This call makes resource pool remove unused containers.
*/
returnAllGRMResourceFromSegment(segres);
+ segres->Stat->StatusDesc |= SEG_STATUS_COMMUNICATION_ERROR;
/* Set the host down in gp_segment_configuration table */
if (Gp_role != GP_ROLE_UTILITY)
{
- update_segment_status(segres->Stat->ID +
REGISTRATION_ORDER_OFFSET, SEGMENT_STATUS_DOWN);
+ SimpStringPtr description =
build_segment_status_description(segres->Stat);
+ update_segment_status(segres->Stat->ID +
REGISTRATION_ORDER_OFFSET,
+
SEGMENT_STATUS_DOWN,
+
(description->Len > 0)?description->Str:"");
+ add_segment_history_row(segres->Stat->ID +
REGISTRATION_ORDER_OFFSET,
+
GET_SEGRESOURCE_HOSTNAME(segres),
+
description->Str);
+ if (description != NULL)
+ {
+ freeSimpleStringContent(description);
+ rm_pfree(PCONTEXT, description);
+ }
}
/* Set the host down. */
elog(LOG, "Resource manager sets host %s from up to down "
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/d1780628/src/backend/resourcemanager/include/resourcepool.h
----------------------------------------------------------------------
diff --git a/src/backend/resourcemanager/include/resourcepool.h
b/src/backend/resourcemanager/include/resourcepool.h
index 6e1412c..5feedd3 100644
--- a/src/backend/resourcemanager/include/resourcepool.h
+++ b/src/backend/resourcemanager/include/resourcepool.h
@@ -145,13 +145,14 @@ struct SegStatData {
int32_t ID; /*
Internal ID. */
uint16_t FailedTmpDirNum; /* Failed temporary
directory number */
uint8_t FTSAvailable; /* If it is available
now. */
- uint8_t GRMAvailable; /* If it is global
resource available.*/
-
+ uint8_t GRMHandled; /* If its GRM
status is handled */
uint32_t FTSTotalMemoryMB; /* FTS reports
memory capacity. */
uint32_t FTSTotalCore; /* FTS reports
core capacity. */
uint32_t GRMTotalMemoryMB; /* GRM reports
memory capacity. */
uint32_t GRMTotalCore; /* GRM reports
core capacity. */
uint64_t RMStartTimestamp; /* RM process
reset timestamp */
+ uint32_t StatusDesc; /*
Description of status */
+ uint32_t Reserved;
SegInfoData Info; /*
64-bit aligned. */
};
@@ -168,12 +169,9 @@ enum SegAvailabilityStatus {
};
int setSegStatHAWQAvailability( SegStat machine, uint8_t newstatus);
-int setSegStatGLOBAvailability( SegStat machine, uint8_t newstatus);
#define IS_SEGSTAT_FTSAVAILABLE(seg) \
((seg)->FTSAvailable == RESOURCE_SEG_STATUS_AVAILABLE)
-#define IS_SEGSTAT_GRMAVAILABLE(seg) \
- ((seg)->GRMAvailable == RESOURCE_SEG_STATUS_AVAILABLE)
/* Generate SegStat instance's report as a string saved in self maintained
buffer. */
void generateSegStatReport(SegStat segstat, SelfMaintainBuffer buff);
@@ -610,7 +608,7 @@ int returnResourceToResourcePool(int memory,
void returnAllGRMResourceFromSegment(SegResource segres);
void dropAllGRMContainersFromSegment(SegResource segres);
-void returnAllGRMResourceFromGRMUnavailableSegments(void);
+void returnAllGRMResourceFromUnavailableSegments(void);
void generateSegResourceReport(int32_t nodeid, SelfMaintainBuffer buff);
@@ -632,7 +630,7 @@ int addOrderedResourceAvailTreeIndexByRatio(uint32_t ratio,
BBST *tree);
int getOrderedResourceAvailTreeIndexByRatio(uint32_t ratio, BBST *tree);
int getOrderedResourceAllocTreeIndexByRatio(uint32_t ratio, BBST *tree);
-void setAllSegResourceGRMUnavailable(void);
+void setAllSegResourceGRMUnhandled(void);
void resetAllSegmentsGRMContainerFailAllocCount(void);
@@ -671,13 +669,11 @@ void adjustMemoryCoreValue(uint32_t *memorymb, uint32_t
*core);
/* Clean up gp_segment_configuration */
void cleanup_segment_config(void);
+
+#define SEG_STATUS_DESCRIPTION_UP "segment is up"
/* update a segment's status in gp_segment_configuration table */
-void update_segment_status(int32_t id, char status);
-/* update a segment's status and failed temporary directory
- * in gp_segment_configuration table
- */
-void update_segment_failed_tmpdir
-(int32_t id, char status, int32_t failedNum, char* failedTmpDir);
+void update_segment_status(int32_t id, char status, char* description);
+
/* Add a new entry into gp_segment_configuration table*/
void add_segment_config_row(int32_t id,
char
*hostname,
@@ -685,8 +681,25 @@ void add_segment_config_row(int32_t id,
uint32_t port,
char role,
char status,
- uint32_t
failed_tmpdir_num,
- char*
failed_tmpdir);
+ char*
description);
+
+/*
+ * SegStatData's StatusDesc is a combination of below flags
+ */
+#define SEG_STATUS_HEARTBEAT_TIMEOUT 0x00000001
+#define SEG_STATUS_FAILED_PROBING_SEGMENT 0x00000002
+#define SEG_STATUS_COMMUNICATION_ERROR 0x00000004
+#define SEG_STATUS_FAILED_TMPDIR
0x00000008
+#define SEG_STATUS_RM_RESET
0x00000010
+#define SEG_STATUS_NO_GRM_NODE_REPORT 0x00000020
+
+/* Add a new entry into gp_configuration_history table */
+void add_segment_history_row(int32_t id,
+ char* hostname,
+ char* description);
+
+/* build a string of status description based on SegStat */
+SimpStringPtr build_segment_status_description(SegStat segstat);
/*
* In resource pool, segment's id starts from 0, however in
gp_segment_configuration table,
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/d1780628/src/backend/resourcemanager/requesthandler.c
----------------------------------------------------------------------
diff --git a/src/backend/resourcemanager/requesthandler.c
b/src/backend/resourcemanager/requesthandler.c
index ba35e2e..a06d169 100644
--- a/src/backend/resourcemanager/requesthandler.c
+++ b/src/backend/resourcemanager/requesthandler.c
@@ -746,29 +746,13 @@ bool handleRMSEGRequestIMAlive(void **arg)
destroySelfMaintainBuffer(&newseginfo);
newsegstat->ID = SEGSTAT_ID_INVALID;
- newsegstat->GRMAvailable = RESOURCE_SEG_STATUS_UNSET;
RPCRequestHeadIMAlive header = SMBUFF_HEAD(RPCRequestHeadIMAlive,
&(conntrack->MessageBuff));
newsegstat->FailedTmpDirNum = header->TmpDirBrokenCount;
newsegstat->RMStartTimestamp = header->RMStartTimestamp;
-
- /*
- * Check if the there is any failed temporary directory on this segment.
- * if has, master considers this segment as down, even it has
heart-beat report.
- */
- if (newsegstat->FailedTmpDirNum == 0)
- {
- newsegstat->FTSAvailable = RESOURCE_SEG_STATUS_AVAILABLE;
- }
- else
- {
- elog(RMLOG, "Resource manager finds there is %d failed
temporary directories "
- "on this segment, "
- "so mark this segment unavailable.",
- newsegstat->FailedTmpDirNum);
- newsegstat->FTSAvailable = RESOURCE_SEG_STATUS_UNAVAILABLE;
- }
+ newsegstat->StatusDesc = 0;
+ newsegstat->Reserved = 0;
bool capstatchanged = false;
if ( addHAWQSegWithSegStat(newsegstat, &capstatchanged) !=
FUNC_RETURN_OK )
@@ -977,13 +961,13 @@ bool handleRMRequestSegmentIsDown(void **arg)
while( (hostname - SMBUFF_CONTENT(&(conntrack->MessageBuff)) <
getSMBContentSize(&(conntrack->MessageBuff))) &&
- *hostname != '\0' )
+ *hostname != '\0' )
{
hostnamelen = strlen(hostname);
res = getSegIDByHostName(hostname, hostnamelen, &segid);
if ( res == FUNC_RETURN_OK )
{
- /* Get resourceinfo of the expected host. */
+ /* Get resource info of the expected host. */
SegResource segres = getSegResource(segid);
Assert( segres != NULL );
@@ -1002,45 +986,56 @@ bool handleRMRequestSegmentIsDown(void **arg)
else
{
elog(RMLOG, "Resource manager probes the status
of host %s by "
- "sending RUAlive
request.",
+ "sending RUAlive
request.",
hostname);
- res = sendRUAlive(hostname);
- /* IN THIS CASE, the segment is considered as down. */
- if (res != FUNC_RETURN_OK)
- {
-
/*----------------------------------------------------------
- * This call makes resource manager able to
adjust queue and
- * mem/core trackers' capacity.
-
*----------------------------------------------------------
- */
- setSegResHAWQAvailability(segres,
-
RESOURCE_SEG_STATUS_UNAVAILABLE);
-
- /* Make resource pool remove unused containers
*/
- returnAllGRMResourceFromSegment(segres);
- /* Set the host down in
gp_segment_configuration table */
- if (Gp_role != GP_ROLE_UTILITY)
- {
- update_segment_status(segres->Stat->ID
+ REGISTRATION_ORDER_OFFSET,
-
SEGMENT_STATUS_DOWN);
- }
-
- /* Set the host down. */
- elog(LOG, "Resource manager sets host %s from
up to down "
- "due to not reaching host.",
hostname);
- }
- else
- {
- elog(RMLOG, "Resource manager triggered RUAlive
request to "
- "host %s.",
+ res = sendRUAlive(hostname);
+ /* IN THIS CASE, the segment is considered as
down. */
+ if (res != FUNC_RETURN_OK)
+ {
+
/*----------------------------------------------------------
+ * This call makes resource manager
able to adjust queue and
+ * mem/core trackers' capacity.
+
*----------------------------------------------------------
+ */
+ setSegResHAWQAvailability(segres,
+
RESOURCE_SEG_STATUS_UNAVAILABLE);
+
+ /* Make resource pool remove unused
containers */
+ returnAllGRMResourceFromSegment(segres);
+ /* Set the host down in
gp_segment_configuration table */
+ segres->Stat->StatusDesc |=
SEG_STATUS_FAILED_PROBING_SEGMENT;
+ if (Gp_role != GP_ROLE_UTILITY)
+ {
+ SimpStringPtr description =
build_segment_status_description(segres->Stat);
+
update_segment_status(segres->Stat->ID + REGISTRATION_ORDER_OFFSET,
+
SEGMENT_STATUS_DOWN,
+
(description->Len > 0)?description->Str:"");
+
add_segment_history_row(segres->Stat->ID + REGISTRATION_ORDER_OFFSET,
+
hostname,
+
description->Str);
+ if (description != NULL)
+ {
+
freeSimpleStringContent(description);
+ rm_pfree(PCONTEXT,
description);
+ }
+ }
+
+ /* Set the host down. */
+ elog(LOG, "Resource manager sets host
%s from up to down "
+ "due to not reaching
host.", hostname);
+ }
+ else
+ {
+ elog(RMLOG, "Resource manager triggered
RUAlive request to "
+ "host %s.",
hostname);
- }
+ }
}
}
else {
elog(WARNING, "Resource manager cannot find host %s to
check status, "
- "skip it.",
+ "skip it.",
hostname);
}
@@ -1124,7 +1119,7 @@ bool handleRMRequestTmpDir(void **arg)
RESPONSE_QD_TMPDIR);
elog(LOG, "Resource manager assigned temporary directory %s",
- tmpdir->Str);
+ tmpdir->Str);
}
conntrack->ResponseSent = false;
@@ -1271,11 +1266,11 @@ bool handleRMRequestDummy(void **arg)
sizeof(response),
conntrack->MessageMark1,
conntrack->MessageMark2,
- RESPONSE_DUMMY);
+ RESPONSE_DUMMY);
conntrack->ResponseSent = false;
- MEMORY_CONTEXT_SWITCH_TO(PCONTEXT)
- PCONTRACK->ConnToSend = lappend(PCONTRACK->ConnToSend, conntrack);
- MEMORY_CONTEXT_SWITCH_BACK
+ MEMORY_CONTEXT_SWITCH_TO(PCONTEXT)
+ PCONTRACK->ConnToSend = lappend(PCONTRACK->ConnToSend, conntrack);
+ MEMORY_CONTEXT_SWITCH_BACK
return true;
}
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/d1780628/src/backend/resourcemanager/requesthandler_RMSEG.c
----------------------------------------------------------------------
diff --git a/src/backend/resourcemanager/requesthandler_RMSEG.c
b/src/backend/resourcemanager/requesthandler_RMSEG.c
index e667c1a..90946a0 100644
--- a/src/backend/resourcemanager/requesthandler_RMSEG.c
+++ b/src/backend/resourcemanager/requesthandler_RMSEG.c
@@ -182,7 +182,6 @@ int refreshLocalHostInstance(void)
RMSEG_INBUILDHOST->GRMTotalCore = 0.0;
RMSEG_INBUILDHOST->FTSTotalMemoryMB =
DRMGlobalInstance->SegmentMemoryMB;
RMSEG_INBUILDHOST->FTSTotalCore =
DRMGlobalInstance->SegmentCore;
- RMSEG_INBUILDHOST->GRMAvailable = RESOURCE_SEG_STATUS_UNSET;
RMSEG_INBUILDHOST->FTSAvailable =
RESOURCE_SEG_STATUS_AVAILABLE;
RMSEG_INBUILDHOST->ID =
SEGSTAT_ID_INVALID;
RMSEG_INBUILDHOST->FailedTmpDirNum = failedTmpDirNum;
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/d1780628/src/backend/resourcemanager/resourcebroker/resourcebroker_LIBYARN.c
----------------------------------------------------------------------
diff --git
a/src/backend/resourcemanager/resourcebroker/resourcebroker_LIBYARN.c
b/src/backend/resourcemanager/resourcebroker/resourcebroker_LIBYARN.c
index 1e8c7ac..d446a6d 100644
--- a/src/backend/resourcemanager/resourcebroker/resourcebroker_LIBYARN.c
+++ b/src/backend/resourcemanager/resourcebroker/resourcebroker_LIBYARN.c
@@ -536,7 +536,9 @@ int handleRB2RM_ClusterReport(void)
uint32_t segsize;
int fd = ResBrokerNotifyPipe[0];
int piperes = 0;
- List *segstats = NULL;
+ List *segstats = NULL;
+ List *allsegres = NULL;
+ ListCell *cell = NULL;
PRESPOOL->RBClusterReportCounter++;
@@ -642,11 +644,7 @@ int handleRB2RM_ClusterReport(void)
return res;
}
- /*
- * Set all current segments GRM unavailable, only the segments
identified by
- * one segment in segstats are available.
- */
- setAllSegResourceGRMUnavailable();
+ setAllSegResourceGRMUnhandled();
/*
* Start to update resource pool content. The YARN cluster total size is
@@ -683,6 +681,66 @@ int handleRB2RM_ClusterReport(void)
rm_pfree(PCONTEXT, segstat);
segstats = list_delete_first(segstats);
}
+
+ /*
+ * iterate all segments without GRM report,
+ * and update its status.
+ */
+ getAllPAIRRefIntoList(&(PRESPOOL->Segments), &allsegres);
+ foreach(cell, allsegres)
+ {
+ SegResource segres = (SegResource)(((PAIR)lfirst(cell))->Value);
+ bool statusDescChange = false;
+
+ /*
+ * skip segments handled in GRM report list
+ */
+ if (segres->Stat->GRMHandled)
+ continue;
+
+ /*
+ * Set no GRM node report flag for this segment.
+ */
+ if ((segres->Stat->StatusDesc & SEG_STATUS_NO_GRM_NODE_REPORT)
== 0)
+ {
+ segres->Stat->StatusDesc |=
SEG_STATUS_NO_GRM_NODE_REPORT;
+ statusDescChange = true;
+ }
+
+ if (IS_SEGSTAT_FTSAVAILABLE(segres->Stat))
+ {
+ /*
+ * This segment is FTS available, but master hasn't
+ * gotten its GRM node report, so set this segment to
DOWN.
+ */
+ setSegResHAWQAvailability(segres,
RESOURCE_SEG_STATUS_UNAVAILABLE);
+ }
+
+ Assert(!IS_SEGSTAT_FTSAVAILABLE(segres->Stat));
+ if (statusDescChange && Gp_role != GP_ROLE_UTILITY)
+ {
+ SimpStringPtr description =
build_segment_status_description(segres->Stat);
+ update_segment_status(segres->Stat->ID +
REGISTRATION_ORDER_OFFSET,
+
SEGMENT_STATUS_DOWN,
+
(description->Len > 0)?description->Str:"");
+ add_segment_history_row(segres->Stat->ID +
REGISTRATION_ORDER_OFFSET,
+
GET_SEGRESOURCE_HOSTNAME(segres),
+
description->Str);
+
+ elog(LOG, "Resource manager hasn't gotten GRM node
report for segment(%s),"
+ "updates its status:'%c',
description:%s",
+
GET_SEGRESOURCE_HOSTNAME(segres),
+ SEGMENT_STATUS_DOWN,
+ (description->Len >
0)?description->Str:"");
+ if (description != NULL)
+ {
+ freeSimpleStringContent(description);
+ rm_pfree(PCONTEXT, description);
+ }
+ }
+ }
+ freePAIRRefList(&(PRESPOOL->Segments), &allsegres);
+
MEMORY_CONTEXT_SWITCH_BACK
elog(LOG, "Resource manager YARN resource broker counted HAWQ cluster
now "
@@ -694,10 +752,10 @@ int handleRB2RM_ClusterReport(void)
PRESPOOL->GRMTotalHavingNoHAWQNode.Core);
/*
- * If the segment is not GRM available, RM should return all containers
- * located upon them.
+ * If the segment is GRM unavailable or FTS unavailable,
+ * RM should return all containers located upon them.
*/
- returnAllGRMResourceFromGRMUnavailableSegments();
+ returnAllGRMResourceFromUnavailableSegments();
/* Refresh available node count. */
refreshAvailableNodeCount();
@@ -706,7 +764,7 @@ int handleRB2RM_ClusterReport(void)
PQUEMGR->GRMQueueCapacity = response.QueueCapacity;
PQUEMGR->GRMQueueCurCapacity = response.QueueCurCapacity;
PQUEMGR->GRMQueueMaxCapacity = (response.QueueMaxCapacity > 0 &&
-
response.QueueMaxCapacity <= 1) ?
+
response.QueueMaxCapacity <= 1) ?
response.QueueMaxCapacity :
PQUEMGR->GRMQueueMaxCapacity;
PQUEMGR->GRMQueueResourceTight = response.ResourceTight > 0 ? true :
false;
@@ -714,9 +772,9 @@ int handleRB2RM_ClusterReport(void)
refreshResourceQueueCapacity(false);
refreshActualMinGRMContainerPerSeg();
- PRESPOOL->LastUpdateTime = gettime_microsec();
+ PRESPOOL->LastUpdateTime = gettime_microsec();
- return FUNC_RETURN_OK;
+ return FUNC_RETURN_OK;
}
/*
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/d1780628/src/backend/resourcemanager/resourcebroker/resourcebroker_LIBYARN_proc.c
----------------------------------------------------------------------
diff --git
a/src/backend/resourcemanager/resourcebroker/resourcebroker_LIBYARN_proc.c
b/src/backend/resourcemanager/resourcebroker/resourcebroker_LIBYARN_proc.c
index 3afae7b..f99ed48 100644
--- a/src/backend/resourcemanager/resourcebroker/resourcebroker_LIBYARN_proc.c
+++ b/src/backend/resourcemanager/resourcebroker/resourcebroker_LIBYARN_proc.c
@@ -1482,7 +1482,6 @@ int RB2YARN_getClusterReport(DQueue hosts)
segstat->ID =
SEGSTAT_ID_INVALID;
segstat->FTSAvailable =
RESOURCE_SEG_STATUS_UNSET;
- segstat->GRMAvailable =
RESOURCE_SEG_STATUS_AVAILABLE;
segstat->GRMTotalMemoryMB =
pnodereport->memoryCapability;
segstat->GRMTotalCore =
pnodereport->vcoresCapability;
segstat->FTSTotalMemoryMB = 0;
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/d1780628/src/backend/resourcemanager/resourcemanager.c
----------------------------------------------------------------------
diff --git a/src/backend/resourcemanager/resourcemanager.c
b/src/backend/resourcemanager/resourcemanager.c
index 9a4bb85..138c5a0 100644
--- a/src/backend/resourcemanager/resourcemanager.c
+++ b/src/backend/resourcemanager/resourcemanager.c
@@ -489,7 +489,6 @@ int ResManagerMainServer2ndPhase(void)
PostPortNumber,
SEGMENT_ROLE_MASTER_CONFIG,
SEGMENT_STATUS_UP,
- 0,
"");
/* Load queue and user definition as no DDL now. */
@@ -2096,12 +2095,9 @@ int generateAllocRequestToBroker(void)
/*
* Resource manager skips this segment if
* 1) Not FTS available;
- * 2) Not GRM available;
- * 3) Having resource decrease pending.
+ * 2) Having resource decrease pending.
*/
if (!IS_SEGSTAT_FTSAVAILABLE(segres->Stat) ||
- (DRMGlobalInstance->ImpType != NONE_HAWQ2 &&
- !IS_SEGSTAT_GRMAVAILABLE(segres->Stat)) ||
(segres->DecPending.MemoryMB > 0 &&
segres->DecPending.Core > 0))
{
continue;
@@ -2311,12 +2307,9 @@ void completeAllocRequestToBroker(int32_t
*reqmem,
/*
* Resource manager skips this segment if
* 1) Not FTS available;
- * 2) Not GRM available;
- * 3) Having resource decrease pending.
+ * 2) Having resource decrease pending.
*/
- if (!IS_SEGSTAT_FTSAVAILABLE(segres->Stat) ||
- (DRMGlobalInstance->ImpType != NONE_HAWQ2 &&
- !IS_SEGSTAT_GRMAVAILABLE(segres->Stat)) ||
+ if (!IS_SEGSTAT_FTSAVAILABLE(segres->Stat) ||
(segres->DecPending.MemoryMB > 0 &&
segres->DecPending.Core > 0))
{
index++;
@@ -2391,12 +2384,9 @@ void completeAllocRequestToBroker(int32_t
*reqmem,
/*
* Resource manager skips this segment if
* 1) Not FTS available;
- * 2) Not GRM available;
- * 3) Having resource decrease pending.
+ * 2) Having resource decrease pending.
*/
if (!IS_SEGSTAT_FTSAVAILABLE(segres->Stat) ||
- (DRMGlobalInstance->ImpType != NONE_HAWQ2 &&
- !IS_SEGSTAT_GRMAVAILABLE(segres->Stat)) ||
(segres->DecPending.MemoryMB > 0 &&
segres->DecPending.Core > 0))
{
index++;
@@ -2566,31 +2556,51 @@ void updateStatusOfAllNodes()
curtime = gettime_microsec();
for(uint32_t idx = 0; idx < PRESPOOL->SegmentIDCounter; idx++)
{
- node = getSegResource(idx);
- if (node != NULL &&
- (curtime - node->LastUpdateTime >
+ node = getSegResource(idx);
+ uint8_t oldStatus = node->Stat->FTSAvailable;
+ if (node != NULL &&
+ (curtime - node->LastUpdateTime >
1000000LL * rm_segment_heartbeat_timeout) &&
- IS_SEGSTAT_FTSAVAILABLE(node->Stat) )
- {
- /*
- * This call makes resource manager able to adjust queue and
mem/core
- * trackers' capacity.
- */
- setSegResHAWQAvailability(node,
RESOURCE_SEG_STATUS_UNAVAILABLE);
- /*
- * This call makes resource pool remove unused containers.
- */
- returnAllGRMResourceFromSegment(node);
- if (Gp_role != GP_ROLE_UTILITY)
- {
- update_segment_status(idx + REGISTRATION_ORDER_OFFSET,
SEGMENT_STATUS_DOWN);
- }
+ (node->Stat->StatusDesc &
SEG_STATUS_HEARTBEAT_TIMEOUT) == 0)
+ {
+ /*
+ * This segment is heartbeat timeout, update its
description
+ * and set it to unavailable if needed.
+ */
+ if (oldStatus == RESOURCE_SEG_STATUS_AVAILABLE)
+ {
+ /*
+ * This call makes resource manager able to
adjust queue and mem/core
+ * trackers' capacity.
+ */
+ setSegResHAWQAvailability(node,
RESOURCE_SEG_STATUS_UNAVAILABLE);
+ /*
+ * This call makes resource pool remove unused
containers.
+ */
+ returnAllGRMResourceFromSegment(node);
+ changedstatus = true;
+ }
- elog(WARNING, "Resource manager sets host %s from up to down.",
- GET_SEGRESOURCE_HOSTNAME(node));
+ node->Stat->StatusDesc |= SEG_STATUS_HEARTBEAT_TIMEOUT;
+ if (Gp_role != GP_ROLE_UTILITY)
+ {
+ SimpStringPtr description =
build_segment_status_description(node->Stat);
+ update_segment_status(idx +
REGISTRATION_ORDER_OFFSET,
+
SEGMENT_STATUS_DOWN,
+
(description->Len > 0)?description->Str:"");
+ add_segment_history_row(idx +
REGISTRATION_ORDER_OFFSET,
+
GET_SEGRESOURCE_HOSTNAME(node),
+
(description->Len > 0)?description->Str:"");
+ if (description != NULL)
+ {
+ freeSimpleStringContent(description);
+ rm_pfree(PCONTEXT, description);
+ }
+ }
- changedstatus = true;
- }
+ elog(WARNING, "Resource manager sets host %s heartbeat
timeout.",
+
GET_SEGRESOURCE_HOSTNAME(node));
+ }
}
if ( changedstatus )
@@ -2711,11 +2721,10 @@ int loadHostInformationIntoResourcePool(void)
/* Build machine info instance. */
SegStat segstat = (SegStat)rm_palloc0(PCONTEXT,
- offsetof(SegStatData,
Info) +
-
seginfobuff.Cursor + 1);
- segstat->ID = SEGSTAT_ID_INVALID;
- segstat->GRMAvailable = RESOURCE_SEG_STATUS_UNSET;
- segstat->FTSAvailable = RESOURCE_SEG_STATUS_AVAILABLE;
+ offsetof(SegStatData, Info) +
+ seginfobuff.Cursor + 1);
+ segstat->ID = SEGSTAT_ID_INVALID;
+ segstat->FTSAvailable = RESOURCE_SEG_STATUS_AVAILABLE;
segstat->FTSTotalMemoryMB = DRMGlobalInstance->SegmentMemoryMB;
segstat->FTSTotalCore = DRMGlobalInstance->SegmentCore;
segstat->GRMTotalMemoryMB = 0;
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/d1780628/src/backend/resourcemanager/resourcepool.c
----------------------------------------------------------------------
diff --git a/src/backend/resourcemanager/resourcepool.c
b/src/backend/resourcemanager/resourcepool.c
index 329a5c6..6a36801 100644
--- a/src/backend/resourcemanager/resourcepool.c
+++ b/src/backend/resourcemanager/resourcepool.c
@@ -26,6 +26,8 @@
#include "resourcepool.h"
#include "gp-libpq-fe.h"
#include "gp-libpq-int.h"
+#include "utils/builtins.h"
+#include "catalog/pg_proc.h"
void addSegResourceAvailIndex(SegResource segres);
void addSegResourceAllocIndex(SegResource segres);
@@ -467,12 +469,99 @@ cleanup:
PQclear(result);
PQfinish(conn);
}
+
+/*
+ * Remove all entries in gp_configuration_history.
+ *
+ * gp_remove_segment_history()
+ *
+ * Returns:
+ * true upon success, otherwise throws error.
+ */
+Datum
+gp_remove_segment_history(PG_FUNCTION_ARGS)
+{
+ int libpqres = CONNECTION_OK;
+ PGconn *conn = NULL;
+ char conninfo[512];
+ PQExpBuffer sql = NULL;
+ PGresult* result = NULL;
+ int ret = true;
+
+ if (!superuser())
+ elog(ERROR, "gp_remove_segment_history can only be run by a
superuser");
+
+ if (Gp_role != GP_ROLE_UTILITY)
+ elog(ERROR, "gp_remove_segment_history can only be run in
utility mode");
+
+ sprintf(conninfo, "options='-c gp_session_role=UTILITY -c
allow_system_table_mods=dml' "
+ "dbname=template1 port=%d connect_timeout=%d",
master_addr_port, CONNECT_TIMEOUT);
+ conn = PQconnectdb(conninfo);
+ if ((libpqres = PQstatus(conn)) != CONNECTION_OK)
+ {
+ elog(WARNING, "Fail to connect database when cleanup "
+ "segment configuration catalog table,
error code: %d, %s",
+ libpqres,
+ PQerrorMessage(conn));
+ PQfinish(conn);
+ PG_RETURN_BOOL(false);
+ }
+
+ result = PQexec(conn, "BEGIN");
+ if (!result || PQresultStatus(result) != PGRES_COMMAND_OK)
+ {
+ elog(WARNING, "Fail to run SQL: %s when cleanup "
+ "segment history catalog table,
reason : %s",
+ "BEGIN",
+ PQresultErrorMessage(result));
+ ret = false;
+ goto cleanup;
+ }
+ PQclear(result);
+
+ sql = createPQExpBuffer();
+ appendPQExpBuffer(sql,"DELETE FROM gp_configuration_history");
+ result = PQexec(conn, sql->data);
+ if (!result || PQresultStatus(result) != PGRES_COMMAND_OK)
+ {
+ elog(WARNING, "Fail to run SQL: %s when cleanup "
+ "segment history catalog table,
reason : %s",
+ sql->data,
+ PQresultErrorMessage(result));
+ ret = false;
+ goto cleanup;
+ }
+ PQclear(result);
+
+ result = PQexec(conn, "COMMIT");
+ if (!result || PQresultStatus(result) != PGRES_COMMAND_OK)
+ {
+ elog(WARNING, "Fail to run SQL: %s when cleanup "
+ "segment history catalog table,
reason : %s",
+ "COMMIT",
+ PQresultErrorMessage(result));
+ ret = false;
+ goto cleanup;
+ }
+
+ elog(LOG, "Cleanup segment history catalog table successfully!");
+
+cleanup:
+ if(sql)
+ destroyPQExpBuffer(sql);
+ if(result)
+ PQclear(result);
+ PQfinish(conn);
+
+ PG_RETURN_BOOL(ret);
+}
+
/*
* update a segment's status in gp_segment_configuration table.
* id : registration order of this segment
* status : new status of this segment
*/
-void update_segment_status(int32_t id, char status)
+void update_segment_status(int32_t id, char status, char* description)
{
int libpqres = CONNECTION_OK;
PGconn *conn = NULL;
@@ -480,15 +569,22 @@ void update_segment_status(int32_t id, char status)
PQExpBuffer sql = NULL;
PGresult* result = NULL;
+ if (status == SEGMENT_STATUS_UP)
+ Assert(strlen(description) == 0);
+ else if (status == SEGMENT_STATUS_DOWN)
+ Assert(strlen(description) != 0);
+ else
+ Assert(0);
+
sprintf(conninfo, "options='-c gp_session_role=UTILITY -c
allow_system_table_mods=dml' "
"dbname=template1 port=%d connect_timeout=%d",
master_addr_port, CONNECT_TIMEOUT);
conn = PQconnectdb(conninfo);
if ((libpqres = PQstatus(conn)) != CONNECTION_OK)
{
elog(WARNING, "Fail to connect database when update segment's
status "
- "in segment configuration catalog table,
error code: %d, %s",
- libpqres,
- PQerrorMessage(conn));
+ "in segment configuration catalog
table, error code: %d, %s",
+ libpqres,
+ PQerrorMessage(conn));
PQfinish(conn);
return;
}
@@ -497,23 +593,24 @@ void update_segment_status(int32_t id, char status)
if (!result || PQresultStatus(result) != PGRES_COMMAND_OK)
{
elog(WARNING, "Fail to run SQL: %s when update segment's status
"
- "in segment configuration catalog table,
reason : %s",
- "BEGIN",
- PQresultErrorMessage(result));
+ "in segment configuration catalog
table, reason : %s",
+ "BEGIN",
+ PQresultErrorMessage(result));
goto cleanup;
}
PQclear(result);
sql = createPQExpBuffer();
- appendPQExpBuffer(sql,"UPDATE gp_segment_configuration SET status='%c'
WHERE registration_order=%d",
- status, id);
+ appendPQExpBuffer(sql, "UPDATE gp_segment_configuration SET
status='%c', "
+ "description='%s' WHERE
registration_order=%d",
+ status, description, id);
result = PQexec(conn, sql->data);
if (!result || PQresultStatus(result) != PGRES_COMMAND_OK)
{
elog(WARNING, "Fail to run SQL: %s when update segment's status
"
- "in segment configuration catalog table,
reason : %s",
- sql->data,
- PQresultErrorMessage(result));
+ "in segment configuration catalog
table, reason : %s",
+ sql->data,
+ PQresultErrorMessage(result));
goto cleanup;
}
PQclear(result);
@@ -528,9 +625,10 @@ void update_segment_status(int32_t id, char status)
goto cleanup;
}
- elog(LOG, "Update a segment's status to '%c' in segment configuration
catalog table,"
- "registration_order : %d",
- status, id);
+ elog(LOG, "Update a segment(registration_order:%d)'s status to '%c',"
+ "description to '%s', "
+ "in segment configuration catalog table,",
+ id, status, description);
cleanup:
if(sql)
@@ -541,19 +639,17 @@ cleanup:
}
/*
- * update a segment's status and failed tmp dir
- * in gp_segment_configuration table.
+ * Insert a row into gp_configuration_history,
+ * to record the status change of a segment.
* id : registration order of this segment
- * status : new status of this segment
- * failedNum : number of failed temporary directory
- * failedTmpDir : failed temporary directory list, separated by comma
+ * hostname : hostname of this segment
+ * description : description of status change
*/
-void update_segment_failed_tmpdir
-(int32_t id, char status, int32_t failedNum, char* failedTmpDir)
+void add_segment_history_row(int32_t id, char* hostname, char* description)
{
int libpqres = CONNECTION_OK;
PGconn *conn = NULL;
- char conninfo[512];
+ char conninfo[1024];
PQExpBuffer sql = NULL;
PGresult* result = NULL;
@@ -562,8 +658,8 @@ void update_segment_failed_tmpdir
conn = PQconnectdb(conninfo);
if ((libpqres = PQstatus(conn)) != CONNECTION_OK)
{
- elog(WARNING, "Fail to connect database when update segment's
failed tmpdir "
- "in segment configuration catalog
table, error code: %d, %s",
+ elog(WARNING, "Fail to connect database when add a new row into
"
+ "segment configuration history
catalog table, error code: %d, %s",
libpqres,
PQerrorMessage(conn));
PQfinish(conn);
@@ -573,24 +669,28 @@ void update_segment_failed_tmpdir
result = PQexec(conn, "BEGIN");
if (!result || PQresultStatus(result) != PGRES_COMMAND_OK)
{
- elog(WARNING, "Fail to run SQL: %s when update segment's failed
tmpdir "
- "in segment configuration catalog
table, reason : %s",
+ elog(WARNING, "Fail to run SQL: %s when add a new row into "
+ "segment configuration history
catalog table, reason : %s",
"BEGIN",
PQresultErrorMessage(result));
goto cleanup;
}
PQclear(result);
+ TimestampTz curtime = GetCurrentTimestamp();
+ const char *curtimestr = timestamptz_to_str(curtime);
sql = createPQExpBuffer();
- appendPQExpBuffer(sql, "UPDATE gp_segment_configuration SET "
- "status='%c',
failed_tmpdir_num = '%d', failed_tmpdir = '%s' "
- "WHERE
registration_order=%d",
- status, failedNum,
failedTmpDir, id);
+ appendPQExpBuffer(sql,
+ "INSERT INTO gp_configuration_history"
+ "(time, registration_order, hostname,
description) "
+ "VALUES ('%s','%d','%s','%s')",
+ curtimestr, id, hostname,
description);
+
result = PQexec(conn, sql->data);
if (!result || PQresultStatus(result) != PGRES_COMMAND_OK)
{
- elog(WARNING, "Fail to run SQL: %s when update segment's failed
tmpdir "
- "in segment configuration catalog
table, reason : %s",
+ elog(WARNING, "Fail to run SQL: %s when add a new row into "
+ "segment configuration history catalog
table, reason : %s",
sql->data,
PQresultErrorMessage(result));
goto cleanup;
@@ -600,18 +700,16 @@ void update_segment_failed_tmpdir
result = PQexec(conn, "COMMIT");
if (!result || PQresultStatus(result) != PGRES_COMMAND_OK)
{
- elog(WARNING, "Fail to run SQL: %s when update segment's failed
tmpdir "
- "in segment configuration catalog
table, reason : %s",
+ elog(WARNING, "Fail to run SQL: %s when add a new row into "
+ "segment configuration history
catalog table, reason : %s",
"COMMIT",
PQresultErrorMessage(result));
goto cleanup;
}
- elog(LOG, "Update a segment's failed tmpdir:"
- "status to '%c', failed_tmpdir_num to '%d',
failed_tmpdir to '%s' "
- "in segment configuration catalog table,"
- "registration_order : %d",
- status, failedNum, failedTmpDir, id);
+ elog(LOG, "Add a new row into segment configuration history catalog
table,"
+ "time: %s, registration order:%d, hostname:%s,
description:%s",
+ curtimestr, id, hostname, description);
cleanup:
if(sql)
@@ -629,8 +727,7 @@ cleanup:
* port : port of this segment
* role : role of this segment
* status : up or down
- * failed_tmpdir_num : the number of failed temporary directory
- * failed_tmpdir : failed temporary directory, separated by comma
+ * description : the description of this segment's current status
*/
void add_segment_config_row(int32_t id,
char* hostname,
@@ -638,9 +735,7 @@ void add_segment_config_row(int32_t id,
uint32_t port,
char role,
char status,
- uint32_t
- failed_tmpdir_num,
- char* failed_tmpdir)
+ char* description)
{
int libpqres = CONNECTION_OK;
PGconn *conn = NULL;
@@ -677,10 +772,10 @@ void add_segment_config_row(int32_t id,
{
appendPQExpBuffer(sql,
"INSERT INTO
gp_segment_configuration"
-
"(registration_order,role,status,port,hostname,address,failed_tmpdir_num,failed_tmpdir)
"
+
"(registration_order,role,status,port,hostname,address,description) "
"VALUES "
-
"(%d,'%c','%c',%d,'%s','%s',%d,'%s')",
-
id,role,status,port,hostname,address,failed_tmpdir_num,failed_tmpdir);
+
"(%d,'%c','%c',%d,'%s','%s','%s')",
+
id,role,status,port,hostname,address,description);
}
else
{
@@ -713,8 +808,8 @@ void add_segment_config_row(int32_t id,
elog(LOG, "Add a new row into segment configuration catalog table,"
"registration order:%d, role:%c, status:%c, port:%d, "
- "hostname:%s, address:%s, failed_tmpdir_num:%d,
failed_tmpdir:%s",
- id, role, status, port, hostname, address,
failed_tmpdir_num, failed_tmpdir);
+ "hostname:%s, address:%s, description:%s",
+ id, role, status, port, hostname, address,
description);
cleanup:
if(sql)
@@ -758,41 +853,38 @@ int addHAWQSegWithSegStat(SegStat segstat, bool
*capstatchanged)
*/
hostname = GET_SEGINFO_HOSTNAME(&(segstat->Info));
hostnamelen = segstat->Info.HostNameLen;
- res = getSegIDByHostName(hostname, hostnamelen, &segid);
- if ( res != FUNC_RETURN_OK )
- {
- /* Try addresses of this machine. */
- for ( int i = 0 ; i < segstat->Info.HostAddrCount ; ++i )
- {
-
- elog(DEBUG5, "Resource manager checks host ip (%d)th to get
segment.", i);
- AddressString addr = NULL;
- getSegInfoHostAddrStr(&(segstat->Info), i, &addr);
- if ( strcmp(addr->Address, IPV4_DOT_ADDR_LO) == 0 &&
- segstat->Info.HostAddrCount > 1 )
- {
- /*
- * If the host has only one address as 127.0.0.1, we
have to
- * save it to track the only one segment, otherwise, we
skip
- * 127.0.0.1 address in resource pool. Because, each
node has
- * one entry of this address.
- */
- continue;
- }
+ res = getSegIDByHostName(hostname, hostnamelen, &segid);
+ if ( res != FUNC_RETURN_OK )
+ {
+ /* Try addresses of this machine. */
+ for ( int i = 0 ; i < segstat->Info.HostAddrCount ; ++i )
+ {
+ elog(DEBUG5, "Resource manager checks host ip (%d)th to
get segment.", i);
+ AddressString addr = NULL;
+ getSegInfoHostAddrStr(&(segstat->Info), i, &addr);
+ if ( strcmp(addr->Address, IPV4_DOT_ADDR_LO) == 0 &&
+ segstat->Info.HostAddrCount > 1 )
+ {
+ /*
+ * If the host has only one address as
127.0.0.1, we have to
+ * save it to track the only one segment,
otherwise, we skip
+ * 127.0.0.1 address in resource pool. Because,
each node has
+ * one entry of this address.
+ */
+ continue;
+ }
- res = getSegIDByHostAddr((uint8_t *)(addr->Address),
addr->Length, &segid);
- if ( res == FUNC_RETURN_OK )
- {
- break;
- }
- }
- }
+ res = getSegIDByHostAddr((uint8_t *)(addr->Address),
addr->Length, &segid);
+ if ( res == FUNC_RETURN_OK )
+ {
+ break;
+ }
+ }
+ }
- /* CASE 1. It is a new host. */
+ /* CASE 1. It is a new host. */
if ( res != FUNC_RETURN_OK )
{
- uint8_t reportStatus = segstat->FTSAvailable;
-
/* Create machine information and corresponding resource
information. */
segresource = createSegResource(segstat);
@@ -815,7 +907,7 @@ int addHAWQSegWithSegStat(SegStat segstat, bool
*capstatchanged)
setSimpleStringRef(&hostnamekey, hostname, hostnamelen);
oldval = setHASHTABLENode(&(PRESPOOL->SegmentHostNameIndexed),
-
TYPCONVERT(void *, &hostnamekey),
+
TYPCONVERT(void *, &hostnamekey),
TYPCONVERT(void *, segid),
false /*
There should be no old value. */);
if ( oldval != NULL )
@@ -844,22 +936,39 @@ int addHAWQSegWithSegStat(SegStat segstat, bool
*capstatchanged)
TYPCONVERT(void
*, &hostaddrkey)) == NULL )
{
setHASHTABLENode(
&(PRESPOOL->SegmentHostAddrIndexed),
-
TYPCONVERT(void *, &hostaddrkey),
+
TYPCONVERT(void *, &hostaddrkey),
TYPCONVERT(void *, segid),
false /*
There should be no old value. */);
elog(LOG, "Resource manager tracked ip address
'%.*s' for host '%s'",
hostaddrkey.Len,
hostaddrkey.Array,
- hostname);
+ hostname);
}
}
/*
- * This is a new host registration. Normally the status is
available,
- * But if the number of failed temporary directory exceeds guc,
+ * If in GRM mode, the new registered segment is marked
+ * as DOWN, since master hasn't get a cluster report for it
+ * from global Resource Manager.
+ */
+ if (DRMGlobalInstance->ImpType != NONE_HAWQ2)
+ {
+ segresource->Stat->StatusDesc |=
SEG_STATUS_NO_GRM_NODE_REPORT;
+ }
+
+ /*
+ * If there is any failed temporary directory,
* this segment is considered as unavailable.
*/
- setSegResHAWQAvailability(segresource, reportStatus);
+ if (segresource->Stat->FailedTmpDirNum != 0)
+ {
+ segresource->Stat->StatusDesc |=
SEG_STATUS_FAILED_TMPDIR;
+ }
+
+ if (segresource->Stat->StatusDesc == 0)
+ {
+ setSegResHAWQAvailability(segresource,
RESOURCE_SEG_STATUS_AVAILABLE);
+ }
/* Add this node into the table gp_segment_configuration */
AddressString straddr = NULL;
@@ -868,16 +977,26 @@ int addHAWQSegWithSegStat(SegStat segstat, bool
*capstatchanged)
if (Gp_role != GP_ROLE_UTILITY)
{
+ SimpStringPtr description =
build_segment_status_description(segresource->Stat);
add_segment_config_row (segid+REGISTRATION_ORDER_OFFSET,
hostname,
straddr->Address,
segresource->Stat->Info.port,
SEGMENT_ROLE_PRIMARY,
-
segresource->Stat->FTSAvailable == RESOURCE_SEG_STATUS_AVAILABLE ?
+
IS_SEGSTAT_FTSAVAILABLE(segresource->Stat) ?
SEGMENT_STATUS_UP:SEGMENT_STATUS_DOWN,
-
segresource->Stat->FailedTmpDirNum,
-
segresource->Stat->FailedTmpDirNum == 0 ?
-
"":GET_SEGINFO_FAILEDTMPDIR(&segresource->Stat->Info));
+
(description->Len > 0)?description->Str:"");
+
+ add_segment_history_row(segid+REGISTRATION_ORDER_OFFSET,
+
hostname,
+
IS_SEGSTAT_FTSAVAILABLE(segresource->Stat) ?
+
SEG_STATUS_DESCRIPTION_UP:description->Str);
+
+ if (description != NULL)
+ {
+ freeSimpleStringContent(description);
+ rm_pfree(PCONTEXT, description);
+ }
}
if (segresource->Stat->FTSAvailable ==
RESOURCE_SEG_STATUS_AVAILABLE)
@@ -901,37 +1020,78 @@ int addHAWQSegWithSegStat(SegStat segstat, bool
*capstatchanged)
else {
segresource = getSegResource(segid);
Assert(segresource != NULL);
+ uint32_t oldStatusDesc = segresource->Stat->StatusDesc;
uint8_t oldStatus = segresource->Stat->FTSAvailable;
- bool statusChanged = oldStatus != segstat->FTSAvailable;
/*
- * Check if RM process is restarted in this segment.
* If the latest reported RM process startup timestamp doesn't
* match the previous, master RM consider segment's RM process
* has restarted.
* In rare case, the system's time is reset and segment's RM
process
* happen to get a same timestamp with previous one.
*/
- if (segresource->Stat->RMStartTimestamp !=
segstat->RMStartTimestamp)
+ if (segresource->Stat->RMStartTimestamp !=
segstat->RMStartTimestamp &&
+ (segresource->Stat->StatusDesc &
SEG_STATUS_HEARTBEAT_TIMEOUT) == 0 &&
+ (segresource->Stat->StatusDesc &
SEG_STATUS_COMMUNICATION_ERROR) == 0 &&
+ (segresource->Stat->StatusDesc &
SEG_STATUS_FAILED_PROBING_SEGMENT) == 0)
{
/*
- * This segment's RM process has restarted,
- * we should clean up old status, so mark it down.
+ * This segment's RM process has restarted.
+ * if StatusDesc doesn't have heartbeat timeout flag,
or communication error,
+ * or failed probing segment flag, this segment is set
to DOWN.
+ * It will be set to UP when reports a new heartbeat.
*/
- if (oldStatus == RESOURCE_SEG_STATUS_AVAILABLE &&
!statusChanged)
- {
- segstat->FTSAvailable =
RESOURCE_SEG_STATUS_UNAVAILABLE;
- statusChanged = true;
- }
+ segresource->Stat->StatusDesc |= SEG_STATUS_RM_RESET;
segresource->Stat->RMStartTimestamp =
segstat->RMStartTimestamp;
elog(LOG, "Master RM finds segment:%s 's RM process has
restarted. "
- "old status:%d, new status:%d",
+ "old status:%d",
GET_SEGRESOURCE_HOSTNAME(segresource),
- oldStatus,
- segstat->FTSAvailable);
+ oldStatus);
+ }
+ else
+ {
+ if (segresource->Stat->RMStartTimestamp !=
segstat->RMStartTimestamp)
+ {
+ segresource->Stat->RMStartTimestamp =
segstat->RMStartTimestamp;
+ }
+ /*
+ * Now clear heartbeat timeout flag, RM reset flag,
+ * no response flag, communication error flag
+ * and RM reset flag in StatusDesc
+ */
+ if ((segresource->Stat->StatusDesc &
SEG_STATUS_HEARTBEAT_TIMEOUT) != 0)
+ {
+ segresource->Stat->StatusDesc &=
~SEG_STATUS_HEARTBEAT_TIMEOUT;
+ elog(RMLOG, "Master RM gets heartbeat report
from segment:%s, "
+ "clear its heartbeat
timeout flag",
+
GET_SEGRESOURCE_HOSTNAME(segresource));
+ }
+ if ((segresource->Stat->StatusDesc &
SEG_STATUS_FAILED_PROBING_SEGMENT) != 0)
+ {
+ segresource->Stat->StatusDesc &=
~SEG_STATUS_FAILED_PROBING_SEGMENT;
+ elog(RMLOG, "Master RM gets heartbeat report
from segment:%s, "
+ "clear its failed
probing segment flag",
+
GET_SEGRESOURCE_HOSTNAME(segresource));
+ }
+ if ((segresource->Stat->StatusDesc &
SEG_STATUS_COMMUNICATION_ERROR) != 0)
+ {
+ segresource->Stat->StatusDesc &=
~SEG_STATUS_COMMUNICATION_ERROR;
+ elog(RMLOG, "Master RM gets heartbeat report
from segment:%s, "
+ "clear its
communication error flag",
+
GET_SEGRESOURCE_HOSTNAME(segresource));
+ }
+ if ((segresource->Stat->StatusDesc &
SEG_STATUS_RM_RESET) != 0)
+ {
+ segresource->Stat->StatusDesc &=
~SEG_STATUS_RM_RESET;
+ elog(RMLOG, "Master RM gets heartbeat report
from segment:%s, "
+ "clear its RM reset
flag",
+
GET_SEGRESOURCE_HOSTNAME(segresource));
+ }
}
- /* Check if temporary directory path is changed */
+ /*
+ * If temporary directory path is changed, update SegStatData
+ */
bool tmpDirChanged = false;
if (segresource->Stat->FailedTmpDirNum !=
segstat->FailedTmpDirNum)
{
@@ -944,160 +1104,162 @@ int addHAWQSegWithSegStat(SegStat segstat, bool
*capstatchanged)
GET_SEGINFO_FAILEDTMPDIR(&segstat->Info)) != 0)
{
tmpDirChanged = true;
- elog(LOG, "Resource manager finds segment
%s(%d) 's "
- "failed temporary directory
is changed from "
- "'%s' to '%s'",
-
GET_SEGRESOURCE_HOSTNAME(segresource),
- segid,
-
GET_SEGINFO_FAILEDTMPDIR(&segresource->Stat->Info),
-
GET_SEGINFO_FAILEDTMPDIR(&segstat->Info));
}
}
- /*
- * Either the FTSAvailable or the failed temporary directory
- * of this segment is changed.
- */
- if (statusChanged || tmpDirChanged)
+ if (tmpDirChanged)
{
- if (statusChanged && !tmpDirChanged)
- {
- if (Gp_role != GP_ROLE_UTILITY)
- {
-
update_segment_status(segresource->Stat->ID + REGISTRATION_ORDER_OFFSET,
-
segstat->FTSAvailable == RESOURCE_SEG_STATUS_AVAILABLE ?
-
SEGMENT_STATUS_UP:SEGMENT_STATUS_DOWN);
- }
-
- setSegResHAWQAvailability(segresource,
segstat->FTSAvailable);
- /*
- * Segment is set from up to down, return
resource.
- */
- if (oldStatus == RESOURCE_SEG_STATUS_AVAILABLE)
- {
- *capstatchanged = true;
-
returnAllGRMResourceFromSegment(segresource);
- }
+ elog(RMLOG, "Resource manager is going to set segment
%s(%d) 's "
+ "failed temporary directory
from "
+ "'%s' to '%s'",
+
GET_SEGRESOURCE_HOSTNAME(segresource),
+ segid,
+
segresource->Stat->FailedTmpDirNum == 0 ?
+ "" :
GET_SEGINFO_FAILEDTMPDIR(&segresource->Stat->Info),
+ segstat->FailedTmpDirNum == 0 ?
+ "" :
GET_SEGINFO_FAILEDTMPDIR(&segstat->Info));
+
+ int old = segresource->Stat->Info.FailedTmpDirLen == 0 ?
+ 0
:__SIZE_ALIGN64(segresource->Stat->Info.FailedTmpDirLen+1);
+ int new = segstat->Info.FailedTmpDirLen == 0 ?
+ 0 :
__SIZE_ALIGN64(segstat->Info.FailedTmpDirLen+1);
+
+ int current = segresource->Stat->Info.Size -
+ (segresource->Stat->Info.HostNameOffset
+ __SIZE_ALIGN64(segresource->Stat->Info.HostNameLen+1));
+ if (segresource->Stat->Info.GRMHostNameLen != 0 &&
segresource->Stat->Info.GRMHostNameOffset != 0)
+ current -=
__SIZE_ALIGN64(segresource->Stat->Info.GRMHostNameLen+1);
+ if (segresource->Stat->Info.GRMRackNameLen != 0 &&
segresource->Stat->Info.GRMRackNameOffset != 0)
+ current -=
__SIZE_ALIGN64(segresource->Stat->Info.GRMRackNameLen+1);
- elog(LOG, "Master resource manager sets segment
%s(%d)'s status "
- "to %c",
-
GET_SEGRESOURCE_HOSTNAME(segresource),
- segid,
- segstat->FTSAvailable ==
RESOURCE_SEG_STATUS_AVAILABLE ?
-
SEGMENT_STATUS_UP:SEGMENT_STATUS_DOWN);
+ /*
+ * repalloc memory if new size exceeds the old one.
+ * we don't shrink memory size if new size is less than
the old one.
+ */
+ if (new > old && current < new)
+ {
+ SegStat newSegStat = rm_repalloc(PCONTEXT,
+
segresource->Stat,
+
offsetof(SegStatData, Info) +
+
segresource->Stat->Info.Size + (new - old));
+ segresource->Stat = newSegStat;
+ segresource->Stat->Info.Size += (new - old);
}
- else
+
+ if (segresource->Stat->Info.FailedTmpDirOffset == 0)
{
- /*
- * Failed temporary directory is changed,
- * if the length of new failed temporary
directory exceeds the old one,
- * we need to repalloc SegInfoData
- */
- elog(RMLOG, "Master resource manager is going
to set segment %s(%d)'s "
- "failed temporary
directory from '%s' to '%s'",
-
GET_SEGRESOURCE_HOSTNAME(segresource),
- segid,
-
segresource->Stat->FailedTmpDirNum == 0 ?
- "" :
GET_SEGINFO_FAILEDTMPDIR(&segresource->Stat->Info),
-
segstat->FailedTmpDirNum == 0 ?
- "" :
GET_SEGINFO_FAILEDTMPDIR(&segstat->Info));
-
- int old =
segresource->Stat->Info.FailedTmpDirLen == 0 ?
-
0 :__SIZE_ALIGN64(segresource->Stat->Info.FailedTmpDirLen+1);
- int new = segstat->Info.FailedTmpDirLen == 0 ?
-
0 : __SIZE_ALIGN64(segstat->Info.FailedTmpDirLen+1);
-
- int current = segresource->Stat->Info.Size -
-
(segresource->Stat->Info.HostNameOffset +
__SIZE_ALIGN64(segresource->Stat->Info.HostNameLen+1));
+ Assert(segresource->Stat->FailedTmpDirNum == 0);
+ segresource->Stat->Info.FailedTmpDirOffset =
segresource->Stat->Info.HostNameOffset +
+
__SIZE_ALIGN64(segresource->Stat->Info.HostNameLen+1);
if (segresource->Stat->Info.GRMHostNameLen != 0
&& segresource->Stat->Info.GRMHostNameOffset != 0)
- current -=
__SIZE_ALIGN64(segresource->Stat->Info.GRMHostNameLen+1);
+
segresource->Stat->Info.FailedTmpDirOffset +=
__SIZE_ALIGN64(segresource->Stat->Info.GRMHostNameLen+1);
if (segresource->Stat->Info.GRMRackNameLen != 0
&& segresource->Stat->Info.GRMRackNameOffset != 0)
- current -=
__SIZE_ALIGN64(segresource->Stat->Info.GRMRackNameLen+1);
+
segresource->Stat->Info.FailedTmpDirOffset +=
__SIZE_ALIGN64(segresource->Stat->Info.GRMRackNameLen+1);
+ }
- /*
- * repalloc memory if new size exceeds the old
one.
- * we don't shrink memory size if new size is
less than the old one.
- */
- if (new > old && current < new)
- {
- SegStat newSegStat =
rm_repalloc(PCONTEXT,
-
segresource->Stat,
-
offsetof(SegStatData, Info) +
-
segresource->Stat->Info.Size + (new - old));
- segresource->Stat = newSegStat;
- segresource->Stat->Info.Size += (new -
old);
- }
+ /* Clear old failed temporary directory string in
SegInfoData */
+ memset((char *)&segresource->Stat->Info +
+
segresource->Stat->Info.FailedTmpDirOffset,
+ 0,
+ segresource->Stat->Info.Size -
+
segresource->Stat->Info.FailedTmpDirOffset);
- if (segresource->Stat->Info.FailedTmpDirOffset
== 0)
- {
-
Assert(segresource->Stat->FailedTmpDirNum == 0);
-
segresource->Stat->Info.FailedTmpDirOffset =
segresource->Stat->Info.HostNameOffset +
-
__SIZE_ALIGN64(segresource->Stat->Info.HostNameLen+1);
- if
(segresource->Stat->Info.GRMHostNameLen != 0 &&
segresource->Stat->Info.GRMHostNameOffset != 0)
-
segresource->Stat->Info.FailedTmpDirOffset +=
__SIZE_ALIGN64(segresource->Stat->Info.GRMHostNameLen+1);
- if
(segresource->Stat->Info.GRMRackNameLen != 0 &&
segresource->Stat->Info.GRMRackNameOffset != 0)
-
segresource->Stat->Info.FailedTmpDirOffset +=
__SIZE_ALIGN64(segresource->Stat->Info.GRMRackNameLen+1);
- }
+ if (segstat->FailedTmpDirNum != 0)
+ {
+ /* Update failed temporary directory string in
SegInfoData */
+ memcpy((char *)&segresource->Stat->Info +
segresource->Stat->Info.FailedTmpDirOffset,
+
GET_SEGINFO_FAILEDTMPDIR(&segstat->Info),
+
strlen(GET_SEGINFO_FAILEDTMPDIR(&segstat->Info)));
+ }
+ else
+ {
+ segresource->Stat->Info.FailedTmpDirOffset = 0;
+ }
+ segresource->Stat->Info.FailedTmpDirLen =
segstat->Info.FailedTmpDirLen;
+ segresource->Stat->FailedTmpDirNum =
segstat->FailedTmpDirNum;
- /* clear old failed temporary directory string
in SegInfoData */
- memset((char *)&segresource->Stat->Info +
-
segresource->Stat->Info.FailedTmpDirOffset,
- 0,
- segresource->Stat->Info.Size -
-
segresource->Stat->Info.FailedTmpDirOffset);
+ elog(LOG, "Resource manager change segment %s(%d) 's "
+ "failed temporary directory is
changed to '%s'",
+ GET_SEGRESOURCE_HOSTNAME(segresource),
+ segid,
+ segresource->Stat->FailedTmpDirNum ==
0 ?
+ "" :
GET_SEGINFO_FAILEDTMPDIR(&segresource->Stat->Info));
+
+ elog(RMLOG, "After resource manager "
+ "updates segment failed
temporary directory, "
+ "GRM hostname:%s, GRM
rackname:%s",
+
segresource->Stat->Info.GRMHostNameLen == 0 ?
+
"":GET_SEGINFO_GRMHOSTNAME(&(segresource->Stat->Info)),
+
segresource->Stat->Info.GRMRackNameLen == 0 ?
+
"":GET_SEGINFO_GRMRACKNAME(&(segresource->Stat->Info)));
+ }
- if (segstat->FailedTmpDirNum != 0)
- {
- memcpy((char *)&segresource->Stat->Info
+ segresource->Stat->Info.FailedTmpDirOffset,
-
GET_SEGINFO_FAILEDTMPDIR(&segstat->Info),
-
strlen(GET_SEGINFO_FAILEDTMPDIR(&segstat->Info)));
- }
- else
- {
-
segresource->Stat->Info.FailedTmpDirOffset = 0;
- }
- segresource->Stat->Info.FailedTmpDirLen =
segstat->Info.FailedTmpDirLen;
- segresource->Stat->FailedTmpDirNum =
segstat->FailedTmpDirNum;
-
- elog(RMLOG, "After resource manager "
- "updates segment failed
temporary directory, "
- "GRM hostname:%s, GRM
rackname:%s",
-
segresource->Stat->Info.GRMHostNameLen == 0 ?
-
"":GET_SEGINFO_GRMHOSTNAME(&(segresource->Stat->Info)),
-
segresource->Stat->Info.GRMRackNameLen == 0 ?
-
"":GET_SEGINFO_GRMRACKNAME(&(segresource->Stat->Info)));
-
- setSegResHAWQAvailability(segresource,
segstat->FTSAvailable);
- if (Gp_role != GP_ROLE_UTILITY)
- {
-
update_segment_failed_tmpdir(segresource->Stat->ID + REGISTRATION_ORDER_OFFSET,
-
segresource->Stat->FTSAvailable ==
RESOURCE_SEG_STATUS_AVAILABLE ?
-
SEGMENT_STATUS_UP:SEGMENT_STATUS_DOWN,
-
segresource->Stat->FailedTmpDirNum,
-
segresource->Stat->FailedTmpDirNum == 0 ?
-
"" :
GET_SEGINFO_FAILEDTMPDIR(&segresource->Stat->Info));
- }
+ /* Set or clear failed temporary directory flag */
+ if (segresource->Stat->FailedTmpDirNum != 0)
+ {
+ segresource->Stat->StatusDesc |=
SEG_STATUS_FAILED_TMPDIR;
+ }
+ else
+ {
+ if ((segresource->Stat->StatusDesc &
SEG_STATUS_FAILED_TMPDIR) != 0)
+ segresource->Stat->StatusDesc &=
~SEG_STATUS_FAILED_TMPDIR;
+ }
+
+ if (segresource->Stat->StatusDesc == 0)
+ {
+ if (oldStatus == RESOURCE_SEG_STATUS_UNAVAILABLE ||
+ oldStatus == RESOURCE_SEG_STATUS_UNSET)
+ setSegResHAWQAvailability(segresource,
RESOURCE_SEG_STATUS_AVAILABLE);
+ }
+ else
+ {
+ if (oldStatus == RESOURCE_SEG_STATUS_AVAILABLE)
+ setSegResHAWQAvailability(segresource,
RESOURCE_SEG_STATUS_UNAVAILABLE);
+ }
- if (statusChanged)
+ if (oldStatusDesc != segresource->Stat->StatusDesc ||
+ tmpDirChanged)
+ {
+ /*
+ * StatusDesc or failed temporary directory path is
changed,
+ * update the gp_segment_configuration table and insert
a row
+ * into gp_configuration_history table
+ */
+ if (Gp_role != GP_ROLE_UTILITY)
+ {
+ SimpStringPtr description =
build_segment_status_description(segresource->Stat);
+ update_segment_status(segresource->Stat->ID +
REGISTRATION_ORDER_OFFSET,
+
IS_SEGSTAT_FTSAVAILABLE(segresource->Stat) ?
+
SEGMENT_STATUS_UP:SEGMENT_STATUS_DOWN,
+
(description->Len > 0)?description->Str:"");
+
+ elog(LOG, "Resource manager update node(%s)
information with heartbeat report,"
+ "status:'%c',
description:%s",
+
GET_SEGRESOURCE_HOSTNAME(segresource),
+
IS_SEGSTAT_FTSAVAILABLE(segresource->Stat) ?
+
SEGMENT_STATUS_UP:SEGMENT_STATUS_DOWN,
+ (description->Len >
0)?description->Str:"");
+
+ add_segment_history_row(segresource->Stat->ID +
REGISTRATION_ORDER_OFFSET,
+
GET_SEGRESOURCE_HOSTNAME(segresource),
+
IS_SEGSTAT_FTSAVAILABLE(segresource->Stat) ?
+
SEG_STATUS_DESCRIPTION_UP:description->Str);
+ if (description != NULL)
{
- *capstatchanged = true;
- /*
- * Segment is set from up to down,
return resource.
- */
- if (oldStatus ==
RESOURCE_SEG_STATUS_AVAILABLE)
- {
-
returnAllGRMResourceFromSegment(segresource);
- }
+ freeSimpleStringContent(description);
+ rm_pfree(PCONTEXT, description);
}
+ }
+ }
- elog(LOG, "Master resource manager sets segment
%s(%d)'s "
- "failed temporary
directory to '%s', status:%c",
-
GET_SEGRESOURCE_HOSTNAME(segresource),
- segid,
-
segresource->Stat->FailedTmpDirNum == 0 ?
- "" :
GET_SEGINFO_FAILEDTMPDIR(&segresource->Stat->Info),
-
segresource->Stat->FTSAvailable == RESOURCE_SEG_STATUS_AVAILABLE ?
-
SEGMENT_STATUS_UP : SEGMENT_STATUS_DOWN);
+ if (oldStatus != segresource->Stat->FTSAvailable)
+ {
+ *capstatchanged = true;
+ /*
+ * Segment is set from up to down, return resource.
+ */
+ if (oldStatus == RESOURCE_SEG_STATUS_AVAILABLE)
+ {
+ returnAllGRMResourceFromSegment(segresource);
}
}
@@ -1161,6 +1323,7 @@ int updateHAWQSegWithGRMSegStat( SegStat segstat)
SegResource segres = NULL;
SegStat newSegStat = NULL;
int32_t segid = SEGSTAT_ID_INVALID;
+ bool statusDescChange = false;
/* Anyway, the host GRM capacity is updated here if the cluster level
* capacity is fixed.
@@ -1305,10 +1468,8 @@ int updateHAWQSegWithGRMSegStat( SegStat segstat)
elog(RMLOG, "After resource manager "
"updates segment info's GRM host name and rack
name, "
"failed temporary directory: %s",
- segres->Stat->FailedTmpDirNum == 0 ?
"":GET_SEGINFO_FAILEDTMPDIR(&(segres->Stat->Info)));
-
- /* Always set segment global resource manager available. */
- setSegResGLOBAvailability(segres, RESOURCE_SEG_STATUS_AVAILABLE);
+ segres->Stat->FailedTmpDirNum == 0 ?
+
"":GET_SEGINFO_FAILEDTMPDIR(&(segres->Stat->Info)));
if ( segres->Stat->GRMTotalMemoryMB != segstat->GRMTotalMemoryMB ||
segres->Stat->GRMTotalCore != segstat->GRMTotalCore )
@@ -1320,14 +1481,20 @@ int updateHAWQSegWithGRMSegStat( SegStat segstat)
segres->Stat->GRMTotalMemoryMB = segstat->GRMTotalMemoryMB;
segres->Stat->GRMTotalCore = segstat->GRMTotalCore;
- /* Update overall cluster resource capacity. */
- minusResourceBundleData(&(PRESPOOL->GRMTotal), oldgrmmem,
oldgrmcore);
- addResourceBundleData(&(PRESPOOL->GRMTotal),
-
segres->Stat->GRMTotalMemoryMB,
-
segres->Stat->GRMTotalCore);
+ /*
+ * If this segment is FTS available, then
+ * update overall cluster resource capacity.
+ */
+ if (IS_SEGSTAT_FTSAVAILABLE(segres->Stat))
+ {
+ minusResourceBundleData(&(PRESPOOL->GRMTotal),
oldgrmmem, oldgrmcore);
+ addResourceBundleData(&(PRESPOOL->GRMTotal),
+
segres->Stat->GRMTotalMemoryMB,
+
segres->Stat->GRMTotalCore);
+ }
elog(LOG, "Resource manager finds host %s capacity changed from
"
- "GRM (%d MB, %d CORE) to GRM (%d MB, %d
CORE)",
+ "GRM (%d MB, %d CORE) to GRM (%d MB, %d
CORE)",
GET_SEGRESOURCE_HOSTNAME(segres),
oldgrmmem,
oldgrmcore,
@@ -1335,6 +1502,49 @@ int updateHAWQSegWithGRMSegStat( SegStat segstat)
segres->Stat->GRMTotalCore);
}
+ segres->Stat->GRMHandled = true;
+ /* Clear no GRM node report flag. */
+ if ((segres->Stat->StatusDesc & SEG_STATUS_NO_GRM_NODE_REPORT) != 0)
+ {
+ segres->Stat->StatusDesc &= ~SEG_STATUS_NO_GRM_NODE_REPORT;
+ statusDescChange = true;
+ }
+
+ /*
+ * If get GRM node report, and there is no other flag,
+ * mark this segment to UP
+ */
+ if (!IS_SEGSTAT_FTSAVAILABLE(segres->Stat) && segres->Stat->StatusDesc
== 0)
+ {
+ Assert(statusDescChange == true);
+ setSegResHAWQAvailability(segres,
RESOURCE_SEG_STATUS_AVAILABLE);
+ }
+
+ if (statusDescChange && Gp_role != GP_ROLE_UTILITY)
+ {
+ SimpStringPtr description =
build_segment_status_description(segres->Stat);
+ update_segment_status(segres->Stat->ID +
REGISTRATION_ORDER_OFFSET,
+
IS_SEGSTAT_FTSAVAILABLE(segres->Stat) ?
+
SEGMENT_STATUS_UP:SEGMENT_STATUS_DOWN,
+
(description->Len > 0)?description->Str:"");
+ add_segment_history_row(segres->Stat->ID +
REGISTRATION_ORDER_OFFSET,
+
GET_SEGRESOURCE_HOSTNAME(segres),
+
IS_SEGSTAT_FTSAVAILABLE(segres->Stat) ?
+
SEG_STATUS_DESCRIPTION_UP:description->Str);
+
+ elog(LOG, "Resource manager update node(%s) information with
yarn node report,"
+ "status:'%c', description:%s",
+ GET_SEGRESOURCE_HOSTNAME(segres),
+ IS_SEGSTAT_FTSAVAILABLE(segres->Stat) ?
+
SEGMENT_STATUS_UP:SEGMENT_STATUS_DOWN,
+ (description->Len >
0)?description->Str:"");
+ if (description != NULL)
+ {
+ freeSimpleStringContent(description);
+ rm_pfree(PCONTEXT, description);
+ }
+ }
+
int32_t curratio = 0;
if (DRMGlobalInstance->ImpType == YARN_LIBYARN &&
segres->Stat->GRMTotalMemoryMB > 0 &&
@@ -1347,7 +1557,7 @@ int updateHAWQSegWithGRMSegStat( SegStat segstat)
return FUNC_RETURN_OK;
}
-void setAllSegResourceGRMUnavailable(void)
+void setAllSegResourceGRMUnhandled(void)
{
List *allsegres = NULL;
ListCell *cell = NULL;
@@ -1356,7 +1566,7 @@ void setAllSegResourceGRMUnavailable(void)
foreach(cell, allsegres)
{
SegResource segres = (SegResource)(((PAIR)lfirst(cell))->Value);
- setSegResGLOBAvailability(segres,
RESOURCE_SEG_STATUS_UNAVAILABLE);
+ segres->Stat->GRMHandled = false;
}
freePAIRRefList(&(PRESPOOL->Segments), &allsegres);
}
@@ -1432,7 +1642,6 @@ SegResource createSegResource(SegStat segstat)
res->LastUpdateTime = gettime_microsec();
res->RUAlivePending = false;
res->Stat->FTSAvailable = RESOURCE_SEG_STATUS_UNSET;
- res->Stat->GRMAvailable = RESOURCE_SEG_STATUS_UNSET;
for ( int i = 0 ; i < RESOURCE_QUEUE_RATIO_SIZE ; ++i )
{
@@ -1455,13 +1664,6 @@ int setSegStatHAWQAvailability( SegStat segstat, uint8_t
newstatus)
return res;
}
-int setSegStatGLOBAvailability( SegStat segstat, uint8_t newstatus)
-{
- int res = segstat->GRMAvailable;
- segstat->GRMAvailable = newstatus;
- return res;
-}
-
/* Set hawq status of host, return the old status */
int setSegResHAWQAvailability( SegResource segres, uint8_t newstatus)
{
@@ -1499,12 +1701,7 @@ int setSegResHAWQAvailability( SegResource segres,
uint8_t newstatus)
segres->Stat->GRMTotalCore);
addNewResourceToResourceManagerByBundle(&(segres->Allocated));
- if ( (DRMGlobalInstance->ImpType == NONE_HAWQ2) ||
- (DRMGlobalInstance->ImpType != NONE_HAWQ2 &&
- IS_SEGSTAT_GRMAVAILABLE(segres->Stat)))
- {
- PRESPOOL->AvailNodeCount++;
- }
+ PRESPOOL->AvailNodeCount++;
}
else
{
@@ -1528,12 +1725,6 @@ int setSegResHAWQAvailability( SegResource segres,
uint8_t newstatus)
return res;
}
-int setSegResGLOBAvailability( SegResource segres, uint8_t newstatus)
-{
- int res = setSegStatGLOBAvailability(segres->Stat, newstatus);
- return res;
-}
-
/* Generate HAWQ host report. */
void generateSegResourceReport(int32_t segid, SelfMaintainBuffer buff)
{
@@ -1549,15 +1740,14 @@ void generateSegResourceReport(int32_t segid,
SelfMaintainBuffer buff)
static char reporthead[256];
int headsize = sprintf(reporthead,
- "SEGMENT:ID=%d, "
- "HAWQAVAIL=%d,GLOBAVAIL=%d. "
- "FTS( %d MB, %d CORE). "
+ "SEGMENT:ID=%d, "
+ "HAWQAVAIL=%d. "
+ "FTS( %d MB, %d
CORE). "
"GRM( %d MB, %d
CORE). "
"MEM=%d(%d) MB. "
"CORE=%lf(%lf).\n",
seg->Stat->ID,
seg->Stat->FTSAvailable,
-
seg->Stat->GRMAvailable,
seg->Stat->FTSTotalMemoryMB,
seg->Stat->FTSTotalCore,
seg->Stat->GRMTotalMemoryMB,
@@ -1565,7 +1755,7 @@ void generateSegResourceReport(int32_t segid,
SelfMaintainBuffer buff)
seg->Allocated.MemoryMB,
seg->Available.MemoryMB,
seg->Allocated.Core,
- seg->Available.Core);
+ seg->Available.Core);
appendSelfMaintainBuffer(buff, reporthead, headsize);
generateSegInfoReport(&(seg->Stat->Info), buff);
}
@@ -1655,13 +1845,12 @@ void generateSegStatReport(SegStat segstat,
SelfMaintainBuffer buff)
static char reporthead[256];
int reportheadlen = 0;
reportheadlen = sprintf(reporthead,
- "NODE:ID=%d,HAWQ %s, GRM %s, "
- "HAWQ CAP (%d MB, %lf CORE), "
+ "NODE:ID=%d,HAWQ %s, "
+ "HAWQ CAP (%d MB, %lf CORE), "
"GRM CAP(%d MB, %lf CORE),",
- segstat->ID,
+ segstat->ID,
segstat->FTSAvailable ? "AVAIL" : "UNAVAIL",
- segstat->GRMAvailable ? "AVAIL" : "UNAVAIL",
- segstat->FTSTotalMemoryMB,
+ segstat->FTSTotalMemoryMB,
segstat->FTSTotalCore * 1.0,
segstat->GRMTotalMemoryMB,
segstat->GRMTotalCore * 1.0);
@@ -3004,9 +3193,9 @@ void returnAllGRMResourceFromSegment(SegResource segres)
/*
* Go through each segment, and return the GRM containers in those segments
- * global resource manager unavailable.
+ * with GRM unavailable or FTS unavailable.
*/
-void returnAllGRMResourceFromGRMUnavailableSegments(void)
+void returnAllGRMResourceFromUnavailableSegments(void)
{
List *allsegres = NULL;
ListCell *cell = NULL;
@@ -3016,7 +3205,7 @@ void returnAllGRMResourceFromGRMUnavailableSegments(void)
foreach(cell, allsegres)
{
SegResource segres = (SegResource)(((PAIR)lfirst(cell))->Value);
- if ( IS_SEGSTAT_GRMAVAILABLE(segres->Stat) )
+ if (IS_SEGSTAT_FTSAVAILABLE(segres->Stat))
{
continue;
}
@@ -4208,8 +4397,7 @@ void refreshAvailableNodeCount(void)
SegResource segres = (SegResource)(pair->Value);
Assert( segres != NULL );
- if ( IS_SEGSTAT_FTSAVAILABLE(segres->Stat) &&
- IS_SEGSTAT_GRMAVAILABLE(segres->Stat) )
+ if ( IS_SEGSTAT_FTSAVAILABLE(segres->Stat) )
{
PRESPOOL->AvailNodeCount++;
}
@@ -4335,10 +4523,12 @@ void fixClusterMemoryCoreRatio(void)
}
else
{
- if ( !IS_SEGSTAT_GRMAVAILABLE(segres->Stat) )
- {
- continue;
- }
+ /*
+ * If this segment is FTS available,
+ * RM should get GRM report for it.
+ */
+ Assert((segres->Stat->StatusDesc &
SEG_STATUS_NO_GRM_NODE_REPORT)
+ == 0);
memorymb = segres->Stat->GRMTotalMemoryMB;
core = segres->Stat->GRMTotalCore;
}
@@ -4389,10 +4579,12 @@ void fixClusterMemoryCoreRatio(void)
}
else
{
- if ( !IS_SEGSTAT_GRMAVAILABLE(segres->Stat) )
- {
- continue;
- }
+ /*
+ * If this segment is FTS available,
+ * RM should get GRM report for it.
+ */
+ Assert((segres->Stat->StatusDesc &
SEG_STATUS_NO_GRM_NODE_REPORT)
+ == 0);
memorymb = segres->Stat->GRMTotalMemoryMB;
core = segres->Stat->GRMTotalCore;
}
@@ -4563,8 +4755,7 @@ void adjustSegmentCapacityForGRM(SegResource segres)
adjustMemoryCoreValue(&(segres->Stat->GRMTotalMemoryMB),
&(segres->Stat->GRMTotalCore));
- if ( !IS_SEGSTAT_FTSAVAILABLE(segres->Stat) ||
- !IS_SEGSTAT_GRMAVAILABLE(segres->Stat))
+ if (!IS_SEGSTAT_FTSAVAILABLE(segres->Stat))
{
return;
}
@@ -4628,9 +4819,8 @@ void dumpResourcePoolHosts(const char *filename)
segresource->Stat->FTSTotalCore,
segresource->Stat->GRMTotalMemoryMB,
segresource->Stat->GRMTotalCore);
- fprintf(fp,
"HOST_AVAILABLITY(HAWQAvailable=%s:GLOBAvailable=%s)\n",
- segresource->Stat->FTSAvailable == 0 ? "false" : "true",
- segresource->Stat->GRMAvailable == 0 ? "false" : "true");
+ fprintf(fp, "HOST_AVAILABLITY(HAWQAvailable=%s)\n",
+ segresource->Stat->FTSAvailable == 0 ? "false" : "true");
fprintf(fp, "HOST_RESOURCE(AllocatedMemory=%d:AllocatedCores=%f:"
"AvailableMemory=%d:AvailableCores=%f:"
"IOBytesWorkload="INT64_FORMAT":"
@@ -4686,3 +4876,66 @@ void dumpResourcePoolHosts(const char *filename)
fclose(fp);
}
+
+static const char* SegStatusDesc[] = {
+ "heartbeat timeout",
+ "failed probing segment",
+ "communication error",
+ "failed temporary directory",
+ "resource manager process was reset",
+ "no global node report"
+};
+
+/*
+ * Build a string of status description for SegStat.
+ * This string contains the reason why this segment is DOWN.
+ * e.g. the failed temporary directories, heartbeat timeout.
+ */
+SimpStringPtr build_segment_status_description(SegStat segstat)
+{
+ SimpStringPtr description = createSimpleString(PCONTEXT);
+ SelfMaintainBufferData buf;
+ initializeSelfMaintainBuffer(&buf, PCONTEXT);
+ uint32_t tmp,cnt;
+
+ if (segstat->StatusDesc == 0)
+ goto _exit;
+
+ /* Count the number of flags */
+ cnt = tmp = segstat->StatusDesc;
+ while (tmp != 0)
+ {
+ tmp = tmp >> 1;
+ cnt -= tmp;
+ }
+
+ for (int idx = 0, tmp = 0; idx < sizeof(SegStatusDesc)/sizeof(char*);
idx++)
+ {
+ if ((segstat->StatusDesc & 1<<idx) != 0)
+ {
+ tmp++;
+ appendSelfMaintainBuffer(&buf, SegStatusDesc[idx],
strlen(SegStatusDesc[idx]));
+ if (1<<idx == SEG_STATUS_FAILED_TMPDIR)
+ {
+ appendSelfMaintainBuffer(&buf, ":", 1);
+ appendSelfMaintainBuffer(&buf,
+
GET_SEGINFO_FAILEDTMPDIR(&segstat->Info),
+
strlen(GET_SEGINFO_FAILEDTMPDIR(&segstat->Info)));
+ }
+ if (tmp != cnt)
+ appendSelfMaintainBuffer(&buf, ";", 1);
+ }
+ }
+
+ if (buf.Size > 0)
+ {
+ static char zeropad = '\0';
+ appendSMBVar(&buf, zeropad);
+ setSimpleStringNoLen(description, buf.Buffer);
+ destroySelfMaintainBuffer(&buf);
+ }
+
+_exit:
+ return description;
+}
+
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/d1780628/src/backend/resourcemanager/resqueuemanager.c
----------------------------------------------------------------------
diff --git a/src/backend/resourcemanager/resqueuemanager.c
b/src/backend/resourcemanager/resqueuemanager.c
index 00de72d..9af0d7c 100644
--- a/src/backend/resourcemanager/resqueuemanager.c
+++ b/src/backend/resourcemanager/resqueuemanager.c
@@ -2631,8 +2631,7 @@ void refreshActualMinGRMContainerPerSeg(void)
foreach(cell, allsegres)
{
SegResource segres =
(SegResource)(((PAIR)lfirst(cell))->Value);
- if ( !IS_SEGSTAT_FTSAVAILABLE(segres->Stat) ||
- !IS_SEGSTAT_GRMAVAILABLE(segres->Stat) )
+ if (IS_SEGSTAT_FTSAVAILABLE(segres->Stat))
{
continue;
}
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/d1780628/src/backend/utils/gp/segadmin.c
----------------------------------------------------------------------
diff --git a/src/backend/utils/gp/segadmin.c b/src/backend/utils/gp/segadmin.c
index 6b49926..775cadb 100644
--- a/src/backend/utils/gp/segadmin.c
+++ b/src/backend/utils/gp/segadmin.c
@@ -277,8 +277,7 @@ gp_add_master_standby(PG_FUNCTION_ARGS)
values[Anum_gp_segment_configuration_port - 1] =
Int32GetDatum(master->port);
values[Anum_gp_segment_configuration_hostname - 1] = PG_GETARG_DATUM(0);
values[Anum_gp_segment_configuration_address - 1] = PG_GETARG_DATUM(1);
- nulls[Anum_gp_segment_configuration_failed_tmpdir_num - 1] = true;
- nulls[Anum_gp_segment_configuration_failed_tmpdir - 1] = true;
+ nulls[Anum_gp_segment_configuration_description - 1] = true;
tuple = caql_form_tuple(pcqCtx, values, nulls);
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/d1780628/src/include/catalog/gp_configuration.h
----------------------------------------------------------------------
diff --git a/src/include/catalog/gp_configuration.h
b/src/include/catalog/gp_configuration.h
index eaa0893..ee127e6 100644
--- a/src/include/catalog/gp_configuration.h
+++ b/src/include/catalog/gp_configuration.h
@@ -135,9 +135,10 @@ typedef FormData_gp_configuration *Form_gp_configuration;
CREATE TABLE gp_configuration_history
with (camelcase=GpConfigHistory, shared=true, oid=false, relid=5006,
reltype_oid=6434, content=MASTER_ONLY)
(
- time timestamp with time zone,
- dbid smallint,
- "desc" text
+ time timestamp with time zone,
+ registration_order integer,
+ hostname text,
+ description text
);
TIDYCAT_ENDDEF
@@ -146,8 +147,8 @@ typedef FormData_gp_configuration *Form_gp_configuration;
/* TIDYCAT_BEGIN_CODEGEN
WARNING: DO NOT MODIFY THE FOLLOWING SECTION:
- Generated by tidycat.pl version 21.
- on Wed Nov 24 14:13:16 2010
+ Generated by tidycat.pl version 34
+ on Fri Feb 26 10:43:15 2016
*/
@@ -182,9 +183,10 @@ typedef FormData_gp_configuration *Form_gp_configuration;
CATALOG(gp_configuration_history,5006) BKI_SHARED_RELATION BKI_WITHOUT_OIDS
{
- timestamptz time;
- int2 dbid;
- text desc;
+ timestamptz time;
+ int4 registration_order;
+ text hostname;
+ text description;
} FormData_gp_configuration_history;
#undef timestamptz
@@ -202,10 +204,11 @@ typedef FormData_gp_configuration_history
*Form_gp_configuration_history;
* compiler constants for gp_configuration_history
* ----------------
*/
-#define Natts_gp_configuration_history 3
-#define Anum_gp_configuration_history_time 1
-#define Anum_gp_configuration_history_dbid 2
-#define Anum_gp_configuration_history_desc 3
+#define Natts_gp_configuration_history
4
+#define Anum_gp_configuration_history_time
1
+#define Anum_gp_configuration_history_registration_order 2
+#define Anum_gp_configuration_history_hostname 3
+#define Anum_gp_configuration_history_description 4
/* TIDYCAT_END_CODEGEN */
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/d1780628/src/include/catalog/gp_segment_config.h
----------------------------------------------------------------------
diff --git a/src/include/catalog/gp_segment_config.h
b/src/include/catalog/gp_segment_config.h
index f9f2def..fa577f1 100644
--- a/src/include/catalog/gp_segment_config.h
+++ b/src/include/catalog/gp_segment_config.h
@@ -53,8 +53,7 @@
port integer ,
hostname text ,
address text ,
- failed_tmpdir_num integer ,
- failed_tmpdir text
+ description text
);
create unique index on gp_segment_configuration(registration_order) with
(indexid=6106, indexname=gp_segment_config_registration_order_index);
@@ -95,8 +94,7 @@ CATALOG(gp_segment_configuration,5036) BKI_SHARED_RELATION
BKI_WITHOUT_OIDS
int4 port;
text hostname;
text address;
- int4 failed_tmpdir_num;
- text failed_tmpdir;
+ text description;
} FormData_gp_segment_configuration;
@@ -112,15 +110,14 @@ typedef FormData_gp_segment_configuration
*Form_gp_segment_configuration;
* compiler constants for gp_segment_configuration
* ----------------
*/
-#define Natts_gp_segment_configuration
8
+#define Natts_gp_segment_configuration
7
#define Anum_gp_segment_configuration_registration_order 1
#define Anum_gp_segment_configuration_role
2
#define Anum_gp_segment_configuration_status 3
#define Anum_gp_segment_configuration_port
4
#define Anum_gp_segment_configuration_hostname 5
#define Anum_gp_segment_configuration_address 6
-#define Anum_gp_segment_configuration_failed_tmpdir_num 7
-#define Anum_gp_segment_configuration_failed_tmpdir 8
+#define Anum_gp_segment_configuration_description 7
/* TIDYCAT_END_CODEGEN */
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/d1780628/src/include/catalog/pg_proc.h
----------------------------------------------------------------------
diff --git a/src/include/catalog/pg_proc.h b/src/include/catalog/pg_proc.h
index caf22a9..a6f8970 100644
--- a/src/include/catalog/pg_proc.h
+++ b/src/include/catalog/pg_proc.h
@@ -10196,7 +10196,6 @@ DESCR("Convert a cloned master catalog for use as a
segment");
DATA(insert OID = 5053 ( gp_activate_standby PGNSP PGUID 12 f f f f v 0 16 f
"" _null_ _null_ _null_ gp_activate_standby - _null_ n ));
DESCR("Activate a standby");
-
/* We cheat in the following two functions: they are technically volatile but
*/
/* we can only dispatch them if they're immutable :(. */
/* gp_add_segment_persistent_entries(int2, int2, _text) => bool */
@@ -10285,6 +10284,10 @@ DESCR("Remove an entry from gp_relation_node");
DATA(insert OID = 5074 ( gp_persistent_relation_node_check PGNSP PGUID 12 f f
f t v 0 6990 f "" _null_ _null_ _null_ gp_persistent_relation_node_check -
_null_ n ));
DESCR("physical filesystem information");
+/* gp_remove_segment_history() => bool */
+DATA(insert OID = 5075 ( gp_remove_segment_history PGNSP PGUID 12 f f f f v 0
16 f "" _null_ _null_ _null_ gp_remove_segment_history - _null_ n ));
+DESCR("Remove all entries from the gp_configuration_history");
+
/* cosh(float8) => float8 */
DATA(insert OID = 3539 ( cosh PGNSP PGUID 12 f f f f i 1 701 f "701" _null_
_null_ _null_ dcosh - _null_ n ));
DESCR("Hyperbolic cosine function");
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/d1780628/src/include/utils/builtins.h
----------------------------------------------------------------------
diff --git a/src/include/utils/builtins.h b/src/include/utils/builtins.h
index 48de877..55ff100 100644
--- a/src/include/utils/builtins.h
+++ b/src/include/utils/builtins.h
@@ -1120,6 +1120,7 @@ extern Datum gp_remove_master_standby(PG_FUNCTION_ARGS);
extern Datum gp_activate_standby(PG_FUNCTION_ARGS);
extern Datum gp_add_segment_mirror(PG_FUNCTION_ARGS);
+extern Datum gp_remove_segment_history(PG_FUNCTION_ARGS);
extern Datum gp_remove_segment_mirror(PG_FUNCTION_ARGS);
extern Datum gp_add_segment(PG_FUNCTION_ARGS);
extern Datum gp_remove_segment(PG_FUNCTION_ARGS);
http://git-wip-us.apache.org/repos/asf/incubator-hawq/blob/d1780628/tools/bin/gppylib/data/2.0.json
----------------------------------------------------------------------
diff --git a/tools/bin/gppylib/data/2.0.json b/tools/bin/gppylib/data/2.0.json
index c65e12d..019c378 100644
--- a/tools/bin/gppylib/data/2.0.json
+++ b/tools/bin/gppylib/data/2.0.json
@@ -109,8 +109,9 @@
"CamelCaseRelationId" : "GpConfigHistoryRelationId",
"UppercaseReltypeOid" : "GP_CONFIGURATION_HISTORY_RELTYPE_OID",
"colh" : {
- "dbid" : "int2",
- "desc" : "text",
+ "description" : "text",
+ "hostname" : "text",
+ "registration_order" : "int4",
"time" : "timestamptz"
},
"cols" : [
@@ -121,19 +122,24 @@
"sqltype" : "timestamp_with_time_zone"
},
{
- "colname" : "dbid",
- "ctype" : "int2",
- "sqltype" : "smallint"
+ "colname" : "registration_order",
+ "ctype" : "int4",
+ "sqltype" : "integer"
+ },
+ {
+ "colname" : "hostname",
+ "ctype" : "text",
+ "sqltype" : "text"
},
{
- "colname" : "desc",
+ "colname" : "description",
"ctype" : "text",
"sqltype" : "text"
}
],
"filename" : "gp_configuration.h",
"relid_comment_tag" : "/* relation id: 5006 - gp_configuration_history
*/\n",
- "tabdef_text" : "\n CREATE TABLE gp_configuration_history\n with
(camelcase=GpConfigHistory, shared=true, oid=false, relid=5006,
reltype_oid=6434, content=MASTER_ONLY)\n (\n time timestamp with time
zone,\n dbid smallint,\n \"desc\" text\n )",
+ "tabdef_text" : "\n CREATE TABLE gp_configuration_history\n with
(camelcase=GpConfigHistory, shared=true, oid=false, relid=5006,
reltype_oid=6434, content=MASTER_ONLY)\n (\n time timestamp
with time zone,\n registration_order integer,\n hostname text,\n
description text\n )",
"tzhack" : "\"time\"",
"with" : {
"bootstrap" : 0,
@@ -868,8 +874,7 @@
"UppercaseToastReltypeOid" :
"GP_SEGMENT_CONFIGURATION_TOAST_RELTYPE_OID",
"colh" : {
"address" : "text",
- "failed_tmpdir" : "text",
- "failed_tmpdir_num" : "int4",
+ "description" : "text",
"hostname" : "text",
"port" : "int4",
"registration_order" : "int4",
@@ -909,12 +914,7 @@
"sqltype" : "text"
},
{
- "colname" : "failed_tmpdir_num",
- "ctype" : "int4",
- "sqltype" : "integer"
- },
- {
- "colname" : "failed_tmpdir",
+ "colname" : "description",
"ctype" : "text",
"sqltype" : "text"
}
@@ -955,7 +955,7 @@
}
],
"relid_comment_tag" : "/* relation id: 5036 - gp_segment_configuration
*/\n",
- "tabdef_text" : "\n CREATE TABLE gp_segment_configuration\n with
(camelcase=GpSegmentConfig, shared=true, oid=false, relid=5036,
reltype_oid=6442, toast_oid=2900, toast_index=2901, toast_reltype=2906,
content=MASTER_ONLY)\n (\n registration_order integer ,\n role
\"char\" ,\n status \"char\" ,\n port
integer ,\n hostname text ,\n address text
,\n failed_tmpdir_num integer ,\n failed_tmpdir text\n )",
+ "tabdef_text" : "\n CREATE TABLE gp_segment_configuration\n with
(camelcase=GpSegmentConfig, shared=true, oid=false, relid=5036,
reltype_oid=6442, toast_oid=2900, toast_index=2901, toast_reltype=2906,
content=MASTER_ONLY)\n (\n registration_order integer ,\n role
\"char\" ,\n status \"char\" ,\n port
integer ,\n hostname text ,\n address text
,\n description text\n )",
"with" : {
"bootstrap" : 0,
"camelcase" : "GpSegmentConfig",
