Re: Implement support for TCP_KEEPCNT, TCP_KEEPIDLE, TCP_KEEPINTVL

Is this the functionality we agreed we wanted?

---------------------------------------------------------------------------

Oliver Jowett wrote:
> Bruce Momjian wrote:
> > Is this patch being worked on?
>
> Here's an updated version. It compiles and appears to work as expected
> under Linux (supports TCP_KEEPIDLE etc) and Solaris 9 (no support).
>
> Main changes:
>
> - removed the tcp_keepalives GUC, SO_KEEPALIVE is now always on (as in
> current CVS)
> - {get,set}sockopt calls are only done when absolutely necessary (no
> extra syscalls during backend startup in a default configuration).
>
> I still haven't had a chance to glue in support for the TCP_KEEPALIVE
> (Solaris-style) option, but that should be fairly painless to add later.
>
> -O

> ? postgresql-8.1devel.tar.gz
> Index: doc/src/sgml/runtime.sgml
> ===================================================================
> RCS file: /projects/cvsroot/pgsql/doc/src/sgml/runtime.sgml,v
> retrieving revision 1.335
> diff -u -c -r1.335 runtime.sgml
> *** doc/src/sgml/runtime.sgml 2 Jul 2005 19:16:36 -0000 1.335
> --- doc/src/sgml/runtime.sgml 4 Jul 2005 10:41:33 -0000
> ***************
> *** 894,899 ****
> --- 894,946 ----
> </listitem>
> </varlistentry>
>
> + <varlistentry id="guc-tcp-keepalives-idle" xreflabel="tcp_keepalives_idle">
> + <term><varname>tcp_keepalives_idle</varname> (<type>integer</type>)</term>
> + <indexterm>
> + <primary><varname>tcp_keepalives_idle</> configuration parameter</primary>
> + </indexterm>
> + <listitem>
> + <para>
> + On systems that support the TCP_KEEPIDLE socket option, specifies the
> + number of seconds between sending keepalives on an otherwise idle
> + connection. A value of 0 uses the system default. If TCP_KEEPIDLE is
> + not supported, this parameter must be 0. This option is ignored for
> + connections made via a Unix-domain socket.
> + </para>
> + </listitem>
> + </varlistentry>
> +
> + <varlistentry id="guc-tcp-keepalives-interval" xreflabel="tcp_keepalives_interval">
> + <term><varname>tcp_keepalives_interval</varname> (<type>integer</type>)</term>
> + <indexterm>
> + <primary><varname>tcp_keepalives_interval</> configuration parameter</primary>
> + </indexterm>
> + <listitem>
> + <para>
> + On systems that support the TCP_KEEPINTVL socket option, specifies how
> + long, in seconds, to wait for a response to a keepalive before
> + retransmitting. A value of 0 uses the system default. If TCP_KEEPINTVL
> + is not supported, this parameter must be 0. This option is ignored
> + for connections made via a Unix-domain socket.
> + </para>
> + </listitem>
> + </varlistentry>
> +
> + <varlistentry id="guc-tcp-keepalives-count" xreflabel="tcp_keepalives_count">
> + <term><varname>tcp_keepalives_count</varname> (<type>integer</type>)</term>
> + <indexterm>
> + <primary><varname>tcp_keepalives_count</> configuration parameter</primary>
> + </indexterm>
> + <listitem>
> + <para>
> + On systems that support the TCP_KEEPCNT socket option, specifies how
> + many keepalives may be lost before the connection is considered dead.
> + A value of 0 uses the system default. If TCP_KEEPINTVL is not
> + supported, this parameter must be 0.
> + </para>
> + </listitem>
> + </varlistentry>
> +
> </variablelist>
> </sect3>
> <sect3 id="runtime-config-connection-security">
> Index: src/backend/libpq/pqcomm.c
> ===================================================================
> RCS file: /projects/cvsroot/pgsql/src/backend/libpq/pqcomm.c,v
> retrieving revision 1.176
> diff -u -c -r1.176 pqcomm.c
> *** src/backend/libpq/pqcomm.c 22 Feb 2005 04:35:57 -0000 1.176
> --- src/backend/libpq/pqcomm.c 4 Jul 2005 10:41:33 -0000
> ***************
> *** 87,93 ****
> #include "libpq/libpq.h"
> #include "miscadmin.h"
> #include "storage/ipc.h"
> !
>
> /*
> * Configuration options
> --- 87,93 ----
> #include "libpq/libpq.h"
> #include "miscadmin.h"
> #include "storage/ipc.h"
> ! #include "utils/guc.h"
>
> /*
> * Configuration options
> ***************
> *** 594,599 ****
> --- 594,612 ----
> elog(LOG, "setsockopt(SO_KEEPALIVE) failed: %m");
> return STATUS_ERROR;
> }
> +
> + /* Set default keepalive parameters. This should also catch
> + * misconfigurations (non-zero values when socket options aren't
> + * supported)
> + */
> + if (pq_setkeepalivesidle(tcp_keepalives_idle, port) != STATUS_OK)
> + return STATUS_ERROR;
> +
> + if (pq_setkeepalivesinterval(tcp_keepalives_interval, port) != STATUS_OK)
> + return STATUS_ERROR;
> +
> + if (pq_setkeepalivescount(tcp_keepalives_count, port) != STATUS_OK)
> + return STATUS_ERROR;
> }
>
> return STATUS_OK;
> ***************
> *** 1158,1160 ****
> --- 1171,1369 ----
> /* in non-error case, copy.c will have emitted the terminator line */
> DoingCopyOut = false;
> }
> +
> + int
> + pq_getkeepalivesidle(Port *port)
> + {
> + #ifdef TCP_KEEPIDLE
> + if (IS_AF_UNIX(port->laddr.addr.ss_family))
> + return 0;
> +
> + if (port->keepalives_idle != 0)
> + return port->keepalives_idle;
> +
> + if (port->default_keepalives_idle == 0)
> + {
> + socklen_t size = sizeof(port->default_keepalives_idle);
> + if (getsockopt(port->sock, SOL_TCP, TCP_KEEPIDLE,
> + (char *) &port->default_keepalives_idle,
> + &size) < 0)
> + {
> + elog(LOG, "getsockopt(TCP_KEEPIDLE) failed: %m");
> + return -1;
> + }
> + }
> +
> + return port->default_keepalives_idle;
> + #else
> + return 0;
> + #endif
> + }
> +
> + int
> + pq_setkeepalivesidle(int idle, Port *port)
> + {
> + if (IS_AF_UNIX(port->laddr.addr.ss_family))
> + return STATUS_OK;
> +
> + #ifdef TCP_KEEPIDLE
> + if (idle == port->keepalives_idle)
> + return STATUS_OK;
> +
> + if (port->default_keepalives_idle == 0)
> + {
> + if (pq_getkeepalivesidle(port) < 0)
> + return STATUS_ERROR;
> + }
> +
> + if (idle == 0)
> + idle = port->default_keepalives_idle;
> +
> + if (setsockopt(port->sock, SOL_TCP, TCP_KEEPIDLE,
> + (char *) &idle, sizeof(idle)) < 0)
> + {
> + elog(LOG, "setsockopt(TCP_KEEPIDLE) failed: %m");
> + return STATUS_ERROR;
> + }
> +
> + port->keepalives_idle = idle;
> + #else
> + if (idle != 0)
> + {
> + elog(LOG, "setsockopt(TCP_KEEPIDLE) not supported");
> + return STATUS_ERROR;
> + }
> + #endif
> +
> + return STATUS_OK;
> + }
> +
> + int
> + pq_getkeepalivesinterval(Port *port)
> + {
> + #ifdef TCP_KEEPINTVL
> + if (IS_AF_UNIX(port->laddr.addr.ss_family))
> + return 0;
> +
> + if (port->keepalives_interval != 0)
> + return port->keepalives_interval;
> +
> + if (port->default_keepalives_interval == 0)
> + {
> + socklen_t size = sizeof(port->default_keepalives_interval);
> + if (getsockopt(port->sock, SOL_TCP, TCP_KEEPINTVL,
> + (char *) &port->default_keepalives_interval,
> + &size) < 0)
> + {
> + elog(LOG, "getsockopt(TCP_KEEPINTVL) failed: %m");
> + return -1;
> + }
> + }
> +
> + return port->default_keepalives_interval;
> + #else
> + return 0;
> + #endif
> + }
> +
> + int
> + pq_setkeepalivesinterval(int interval, Port *port)
> + {
> + if (IS_AF_UNIX(port->laddr.addr.ss_family))
> + return STATUS_OK;
> +
> + #ifdef TCP_KEEPINTVL
> + if (interval == port->keepalives_interval)
> + return STATUS_OK;
> +
> + if (port->default_keepalives_interval == 0) {
> + if (pq_getkeepalivesinterval(port) < 0)
> + return STATUS_ERROR;
> + }
> +
> + if (interval == 0)
> + interval = port->default_keepalives_interval;
> +
> + if (setsockopt(port->sock, SOL_TCP, TCP_KEEPINTVL,
> + (char *) &interval, sizeof(interval)) < 0)
> + {
> + elog(LOG, "setsockopt(TCP_KEEPINTVL) failed: %m");
> + return STATUS_ERROR;
> + }
> +
> + port->keepalives_interval = interval;
> + #else
> + if (interval != 0)
> + {
> + elog(LOG, "setsockopt(TCP_KEEPINTVL) not supported");
> + return STATUS_ERROR;
> + }
> + #endif
> +
> + return STATUS_OK;
> + }
> +
> + int
> + pq_getkeepalivescount(Port *port)
> + {
> + #ifdef TCP_KEEPCNT
> + if (IS_AF_UNIX(port->laddr.addr.ss_family))
> + return 0;
> +
> + if (port->keepalives_count != 0)
> + return port->keepalives_count;
> +
> + if (port->default_keepalives_count == 0)
> + {
> + socklen_t size = sizeof(port->default_keepalives_count);
> + if (getsockopt(port->sock, SOL_TCP, TCP_KEEPCNT,
> + (char *) &port->default_keepalives_count,
> + &size) < 0)
> + {
> + elog(LOG, "getsockopt(TCP_KEEPCNT) failed: %m");
> + return -1;
> + }
> + }
> +
> + return port->default_keepalives_count;
> + #else
> + return 0;
> + #endif
> + }
> +
> + int
> + pq_setkeepalivescount(int count, Port *port)
> + {
> + if (IS_AF_UNIX(port->laddr.addr.ss_family))
> + return STATUS_OK;
> +
> + #ifdef TCP_KEEPCNT
> + if (count == port->keepalives_count)
> + return STATUS_OK;
> +
> + if (port->default_keepalives_count == 0) {
> + if (pq_getkeepalivescount(port) < 0)
> + return STATUS_ERROR;
> + }
> +
> + if (count == 0)
> + count = port->default_keepalives_count;
> +
> + if (setsockopt(port->sock, SOL_TCP, TCP_KEEPCNT,
> + (char *) &count, sizeof(count)) < 0)
> + {
> + elog(LOG, "setsockopt(TCP_KEEPCNT) failed: %m");
> + return STATUS_ERROR;
> + }
> +
> + port->keepalives_count = count;
> + #else
> + if (count != 0)
> + {
> + elog(LOG, "setsockopt(TCP_KEEPCNT) not supported");
> + return STATUS_ERROR;
> + }
> + #endif
> +
> + return STATUS_OK;
> + }
> Index: src/backend/utils/misc/guc.c
> ===================================================================
> RCS file: /projects/cvsroot/pgsql/src/backend/utils/misc/guc.c,v
> retrieving revision 1.271
> diff -u -c -r1.271 guc.c
> *** src/backend/utils/misc/guc.c 28 Jun 2005 05:09:02 -0000 1.271
> --- src/backend/utils/misc/guc.c 4 Jul 2005 10:41:33 -0000
> ***************
> *** 117,122 ****
> --- 117,128 ----
> static bool assign_transaction_read_only(bool newval, bool doit, GucSource source);
> static const char *assign_canonical_path(const char *newval, bool doit, GucSource source);
>
> + static bool assign_tcp_keepalives_idle(int newval, bool doit, GucSource source);
> + static bool assign_tcp_keepalives_interval(int newval, bool doit, GucSource source);
> + static bool assign_tcp_keepalives_count(int newval, bool doit, GucSource source);
> + static const char *show_tcp_keepalives_idle(void);
> + static const char *show_tcp_keepalives_interval(void);
> + static const char *show_tcp_keepalives_count(void);
>
> /*
> * GUC option variables that are exported from this module
> ***************
> *** 158,163 ****
> --- 164,172 ----
> char *IdentFileName;
> char *external_pid_file;
>
> + int tcp_keepalives_idle;
> + int tcp_keepalives_interval;
> + int tcp_keepalives_count;
>
> /*
> * These variables are all dummies that don't do anything, except in some
> ***************
> *** 1375,1380 ****
> --- 1384,1418 ----
> BLCKSZ, BLCKSZ, BLCKSZ, NULL, NULL
> },
>
> + {
> + {"tcp_keepalives_idle", PGC_USERSET, CLIENT_CONN_OTHER,
> + gettext_noop("Seconds between issuing TCP keepalives."),
> + gettext_noop("A value of 0 uses the system default."),
> + },
> + &tcp_keepalives_idle,
> + 0, 0, INT_MAX, assign_tcp_keepalives_idle, show_tcp_keepalives_idle
> + },
> +
> + {
> + {"tcp_keepalives_interval", PGC_USERSET, CLIENT_CONN_OTHER,
> + gettext_noop("Seconds between TCP keepalive retransmits."),
> + gettext_noop("A value of 0 uses the system default."),
> + },
> + &tcp_keepalives_interval,
> + 0, 0, INT_MAX, assign_tcp_keepalives_interval, show_tcp_keepalives_interval
> + },
> +
> + {
> + {"tcp_keepalives_count", PGC_USERSET, CLIENT_CONN_OTHER,
> + gettext_noop("Maximum number of TCP keepalive retransmits."),
> + gettext_noop("This controls the number of consecutive keepalive retransmits that can be "
> + "lost before a connection is considered dead. A value of 0 uses the "
> + "system default."),
> + },
> + &tcp_keepalives_count,
> + 0, 0, INT_MAX, assign_tcp_keepalives_count, show_tcp_keepalives_count
> + },
> +
> /* End-of-list marker */
> {
> {NULL, 0, 0, NULL, NULL}, NULL, 0, 0, 0, NULL, NULL
> ***************
> *** 5744,5748 ****
> --- 5782,5842 ----
> return newval;
> }
>
> + static bool
> + assign_tcp_keepalives_idle(int newval, bool doit, GucSource source)
> + {
> + if (doit && MyProcPort != NULL)
> + {
> + return (pq_setkeepalivesidle(newval, MyProcPort) == STATUS_OK);
> + }
> +
> + return true;
> + }
> +
> + static const char *
> + show_tcp_keepalives_idle(void)
> + {
> + static char nbuf[32];
> + snprintf(nbuf, sizeof(nbuf), "%d", MyProcPort == NULL ? 0 : pq_getkeepalivesidle(MyProcPort));
> + return nbuf;
> + }
> +
> + static bool
> + assign_tcp_keepalives_interval(int newval, bool doit, GucSource source)
> + {
> + if (doit && MyProcPort != NULL)
> + {
> + return (pq_setkeepalivesinterval(newval, MyProcPort) == STATUS_OK);
> + }
> +
> + return true;
> + }
> +
> + static const char *
> + show_tcp_keepalives_interval(void)
> + {
> + static char nbuf[32];
> + snprintf(nbuf, sizeof(nbuf), "%d", MyProcPort == NULL ? 0 : pq_getkeepalivesinterval(MyProcPort));
> + return nbuf;
> + }
> +
> + static bool
> + assign_tcp_keepalives_count(int newval, bool doit, GucSource source)
> + {
> + if (doit && MyProcPort != NULL)
> + {
> + return (pq_setkeepalivescount(newval, MyProcPort) == STATUS_OK);
> + }
> +
> + return true;
> + }
> +
> + static const char *
> + show_tcp_keepalives_count(void)
> + {
> + static char nbuf[32];
> + snprintf(nbuf, sizeof(nbuf), "%d", MyProcPort == NULL ? 0 : pq_getkeepalivescount(MyProcPort));
> + return nbuf;
> + }
>
> #include "guc-file.c"
> Index: src/backend/utils/misc/postgresql.conf.sample
> ===================================================================
> RCS file: /projects/cvsroot/pgsql/src/backend/utils/misc/postgresql.conf.sample,v
> retrieving revision 1.151
> diff -u -c -r1.151 postgresql.conf.sample
> *** src/backend/utils/misc/postgresql.conf.sample 2 Jul 2005 18:46:45 -0000 1.151
> --- src/backend/utils/misc/postgresql.conf.sample 4 Jul 2005 10:41:33 -0000
> ***************
> *** 70,75 ****
> --- 70,80 ----
> #krb_caseins_users = off
> #krb_srvname = 'postgres'
>
> + # - TCP Keepalives -
> + # see 'man 7 tcp' for details
> + #tcp_keepalives_idle = 0 # TCP_KEEPIDLE, in seconds; 0 uses the system default.
> + #tcp_keepalives_interval = 0 # TCP_KEEPINTVL, in seconds; 0 uses the system default.
> + #tcp_keepalives_count = 0 # TCP_KEEPCNT, in seconds; 0 uses the system default.
>
> #---------------------------------------------------------------------------
> # RESOURCE USAGE (except WAL)
> Index: src/bin/psql/tab-complete.c
> ===================================================================
> RCS file: /projects/cvsroot/pgsql/src/bin/psql/tab-complete.c,v
> retrieving revision 1.133
> diff -u -c -r1.133 tab-complete.c
> *** src/bin/psql/tab-complete.c 22 Jun 2005 21:14:30 -0000 1.133
> --- src/bin/psql/tab-complete.c 4 Jul 2005 10:41:33 -0000
> ***************
> *** 600,605 ****
> --- 600,608 ----
> "superuser_reserved_connections",
> "syslog_facility",
> "syslog_ident",
> + "tcp_keepalives_idle",
> + "tcp_keepalives_interval",
> + "tcp_keepalives_count",
> "temp_buffers",
> "TimeZone",
> "trace_notify",
> Index: src/include/libpq/libpq-be.h
> ===================================================================
> RCS file: /projects/cvsroot/pgsql/src/include/libpq/libpq-be.h,v
> retrieving revision 1.49
> diff -u -c -r1.49 libpq-be.h
> *** src/include/libpq/libpq-be.h 31 Dec 2004 22:03:32 -0000 1.49
> --- src/include/libpq/libpq-be.h 4 Jul 2005 10:41:33 -0000
> ***************
> *** 25,30 ****
> --- 25,33 ----
> #include <openssl/ssl.h>
> #include <openssl/err.h>
> #endif
> + #ifdef HAVE_NETINET_TCP_H
> + #include <netinet/tcp.h>
> + #endif
>
> #include "libpq/hba.h"
> #include "libpq/pqcomm.h"
> ***************
> *** 92,100 ****
> --- 95,131 ----
> char peer_cn[SM_USER + 1];
> unsigned long count;
> #endif
> +
> + /*
> + * TCP keepalive settings;
> + * default values are 0 if AF_UNIX or not yet known;
> + * current values are 0 if AF_UNIX or using the default.
> + */
> + #ifdef TCP_KEEPIDLE
> + int default_keepalives_idle;
> + int keepalives_idle;
> + #endif
> + #ifdef TCP_KEEPINTVL
> + int default_keepalives_interval;
> + int keepalives_interval;
> + #endif
> + #ifdef TCP_KEEPCNT
> + int default_keepalives_count;
> + int keepalives_count;
> + #endif
> } Port;
>
>
> extern ProtocolVersion FrontendProtocol;
>
> + /* TCP keepalives configuration. These are no-ops on an AF_UNIX socket. */
> +
> + extern int pq_getkeepalivesidle(Port *port);
> + extern int pq_getkeepalivesinterval(Port *port);
> + extern int pq_getkeepalivescount(Port *port);
> +
> + extern int pq_setkeepalivesidle(int idle, Port *port);
> + extern int pq_setkeepalivesinterval(int interval, Port *port);
> + extern int pq_setkeepalivescount(int count, Port *port);
> +
> #endif /* LIBPQ_BE_H */
> Index: src/include/utils/guc.h
> ===================================================================
> RCS file: /projects/cvsroot/pgsql/src/include/utils/guc.h,v
> retrieving revision 1.61
> diff -u -c -r1.61 guc.h
> *** src/include/utils/guc.h 26 Jun 2005 03:04:12 -0000 1.61
> --- src/include/utils/guc.h 4 Jul 2005 10:41:33 -0000
> ***************
> *** 134,139 ****
> --- 134,142 ----
> extern char *IdentFileName;
> extern char *external_pid_file;
>
> + extern int tcp_keepalives_idle;
> + extern int tcp_keepalives_interval;
> + extern int tcp_keepalives_count;
>
> extern void SetConfigOption(const char *name, const char *value,
> GucContext context, GucSource source);

>
> ---------------------------(end of broadcast)---------------------------
> TIP 4: Don't 'kill -9' the postmaster

--
Bruce Momjian | http://candle.pha.pa.us
pgman(at)candle(dot)pha(dot)pa(dot)us | (610) 359-1001
+ If your life is a hard drive, | 13 Roberts Road
+ Christ can be your backup. | Newtown Square, Pennsylvania 19073