Basic usage statistics collection. (#1656)

Adds ```citus.enable_statistics_collection``` GUC variable, which ```true``` by default, unless built without libcurl. If statistics collection is enabled, sends basic usage data to Citus servers every 24 hours. The data that is collected consists of: - Citus version - OS name & release - Hardware Id - Number of tables, rounded to next power of 2 - Size of data, rounded to next power of 2 - Number of workers
2017-10-11 09:55:15 -04:00 · 2017-10-11 09:55:15 -04:00 · a1387f4aa8
parent e202c51fec
commit a1387f4aa8
13 changed files with 1340 additions and 16 deletions
--- a/Makefile.global.in
+++ b/Makefile.global.in
@ -70,7 +70,7 @@ endif
 # Add options passed to configure or computed therein, to CFLAGS/CPPFLAGS/...
 override CFLAGS += @CFLAGS@ @CITUS_CFLAGS@
 override CPPFLAGS := @CPPFLAGS@ -I '${citus_abs_top_srcdir}/src/include' -I'${citus_top_builddir}/src/include' $(CPPFLAGS)
-override LDFLAGS += @LDFLAGS@
+override LDFLAGS += @LDFLAGS@ @CITUS_LDFLAGS@

 # optional file with user defined, additional, rules
 -include ${citus_abs_srcdir}/src/Makefile.custom
--- a/aclocal.m4
+++ b/aclocal.m4
@ -0,0 +1,2 @@
+dnl aclocal.m4
+m4_include([config/general.m4])
--- a/config/general.m4
+++ b/config/general.m4
@ -0,0 +1,151 @@
+# config/general.m4
+# Portions Copyright (c) 1996-2017, PostgreSQL Global Development Group
+# Portions Copyright (c) 1994, The Regents of the University of California
+
+# This file defines new macros to process configure command line
+# arguments, to replace the brain-dead AC_ARG_WITH and AC_ARG_ENABLE.
+# The flaw in these is particularly that they only differentiate
+# between "given" and "not given" and do not provide enough help to
+# process arguments that only accept "yes/no", that require an
+# argument (other than "yes/no"), etc.
+#
+# The point of this implementation is to reduce code size and
+# redundancy in configure.in and to improve robustness and consistency
+# in the option evaluation code.
+
+
+# Convert type and name to shell variable name (e.g., "enable_long_strings")
+m4_define([pgac_arg_to_variable],
+          [$1[]_[]patsubst($2, -, _)])
+
+
+# PGAC_ARG(TYPE, NAME, HELP-STRING-LHS-EXTRA, HELP-STRING-RHS,
+#          [ACTION-IF-YES], [ACTION-IF-NO], [ACTION-IF-ARG],
+#          [ACTION-IF-OMITTED])
+# ------------------------------------------------------------
+# This is the base layer. TYPE is either "with" or "enable", depending
+# on what you like.  NAME is the rest of the option name.
+# HELP-STRING-LHS-EXTRA is a string to append to the option name on
+# the left-hand side of the help output, e.g., an argument name.  If
+# set to "-", append nothing, but let the option appear in the
+# negative form (disable/without).  HELP-STRING-RHS is the option
+# description, for the right-hand side of the help output.
+# ACTION-IF-YES is executed if the option is given without an argument
+# (or "yes", which is the same); similar for ACTION-IF-NO.
+
+AC_DEFUN([PGAC_ARG],
+[
+m4_case([$1],
+
+enable, [
+AC_ARG_ENABLE([$2], [AS_HELP_STRING([--]m4_if($3, -, disable, enable)[-$2]m4_if($3, -, , $3), [$4])], [
+  case [$]enableval in
+    yes)
+      m4_default([$5], :)
+      ;;
+    no)
+      m4_default([$6], :)
+      ;;
+    *)
+      $7
+      ;;
+  esac
+],
+[$8])[]dnl AC_ARG_ENABLE
+],
+
+with, [
+AC_ARG_WITH([$2], [AS_HELP_STRING([--]m4_if($3, -, without, with)[-$2]m4_if($3, -, , $3), [$4])], [
+  case [$]withval in
+    yes)
+      m4_default([$5], :)
+      ;;
+    no)
+      m4_default([$6], :)
+      ;;
+    *)
+      $7
+      ;;
+  esac
+],
+[$8])[]dnl AC_ARG_WITH
+],
+
+[m4_fatal([first argument of $0 must be 'enable' or 'with', not '$1'])]
+)
+])# PGAC_ARG
+
+
+# PGAC_ARG_BOOL(TYPE, NAME, DEFAULT, HELP-STRING-RHS,
+#               [ACTION-IF-YES], [ACTION-IF-NO])
+# ---------------------------------------------------
+# Accept a boolean option, that is, one that only takes yes or no.
+# ("no" is equivalent to "disable" or "without"). DEFAULT is what
+# should be done if the option is omitted; it should be "yes" or "no".
+# (Consequently, one of ACTION-IF-YES and ACTION-IF-NO will always
+# execute.)
+
+AC_DEFUN([PGAC_ARG_BOOL],
+[dnl The following hack is necessary because in a few instances this
+dnl macro is called twice for the same option with different default
+dnl values.  But we only want it to appear once in the help.  We achieve
+dnl that by making the help string look the same, which is why we need to
+dnl save the default that was passed in previously.
+m4_define([_pgac_helpdefault], m4_ifdef([pgac_defined_$1_$2_bool], [m4_defn([pgac_defined_$1_$2_bool])], [$3]))dnl
+PGAC_ARG([$1], [$2], [m4_if(_pgac_helpdefault, yes, -)], [$4], [$5], [$6],
+          [AC_MSG_ERROR([no argument expected for --$1-$2 option])],
+          [m4_case([$3],
+                   yes, [pgac_arg_to_variable([$1], [$2])=yes
+$5],
+                   no,  [pgac_arg_to_variable([$1], [$2])=no
+$6],
+                   [m4_fatal([third argument of $0 must be 'yes' or 'no', not '$3'])])])[]dnl
+m4_define([pgac_defined_$1_$2_bool], [$3])dnl
+])# PGAC_ARG_BOOL
+
+
+# PGAC_ARG_REQ(TYPE, NAME, HELP-ARGNAME, HELP-STRING-RHS,
+#              [ACTION-IF-GIVEN], [ACTION-IF-NOT-GIVEN])
+# -------------------------------------------------------
+# This option will require an argument; "yes" or "no" will not be
+# accepted.  HELP-ARGNAME is a name for the argument for the help output.
+
+AC_DEFUN([PGAC_ARG_REQ],
+[PGAC_ARG([$1], [$2], [=$3], [$4],
+          [AC_MSG_ERROR([argument required for --$1-$2 option])],
+          [AC_MSG_ERROR([argument required for --$1-$2 option])],
+          [$5],
+          [$6])])# PGAC_ARG_REQ
+
+
+# PGAC_ARG_OPTARG(TYPE, NAME, HELP-ARGNAME, HELP-STRING-RHS,
+#                 [DEFAULT-ACTION], [ARG-ACTION],
+#                 [ACTION-ENABLED], [ACTION-DISABLED])
+# ----------------------------------------------------------
+# This will create an option that behaves as follows: If omitted, or
+# called with "no", then set the enable_variable to "no" and do
+# nothing else. If called with "yes", then execute DEFAULT-ACTION. If
+# called with argument, set enable_variable to "yes" and execute
+# ARG-ACTION. Additionally, execute ACTION-ENABLED if we ended up with
+# "yes" either way, else ACTION-DISABLED.
+#
+# The intent is to allow enabling a feature, and optionally pass an
+# additional piece of information.
+
+AC_DEFUN([PGAC_ARG_OPTARG],
+[PGAC_ARG([$1], [$2], [@<:@=$3@:>@], [$4], [$5], [],
+          [pgac_arg_to_variable([$1], [$2])=yes
+$6],
+          [pgac_arg_to_variable([$1], [$2])=no])
+dnl Add this code only if there's a ACTION-ENABLED or ACTION-DISABLED.
+m4_ifval([$7[]$8],
+[
+if test "[$]pgac_arg_to_variable([$1], [$2])" = yes; then
+  m4_default([$7], :)
+m4_ifval([$8],
+[else
+  $8
+])[]dnl
+fi
+])[]dnl
+])# PGAC_ARG_OPTARG
--- a/801
+++ b/801
@ -584,11 +584,51 @@ PACKAGE_STRING='Citus 7.1devel'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''

+# Factoring default headers for most tests.
+ac_includes_default="\
+#include <stdio.h>
+#ifdef HAVE_SYS_TYPES_H
+# include <sys/types.h>
+#endif
+#ifdef HAVE_SYS_STAT_H
+# include <sys/stat.h>
+#endif
+#ifdef STDC_HEADERS
+# include <stdlib.h>
+# include <stddef.h>
+#else
+# ifdef HAVE_STDLIB_H
+#  include <stdlib.h>
+# endif
+#endif
+#ifdef HAVE_STRING_H
+# if !defined STDC_HEADERS && defined HAVE_MEMORY_H
+#  include <memory.h>
+# endif
+# include <string.h>
+#endif
+#ifdef HAVE_STRINGS_H
+# include <strings.h>
+#endif
+#ifdef HAVE_INTTYPES_H
+# include <inttypes.h>
+#endif
+#ifdef HAVE_STDINT_H
+# include <stdint.h>
+#endif
+#ifdef HAVE_UNISTD_H
+# include <unistd.h>
+#endif"
+
 ac_subst_vars='LTLIBOBJS
 LIBOBJS
 POSTGRES_BUILDDIR
 POSTGRES_SRCDIR
+CITUS_LDFLAGS
 CITUS_CFLAGS
+EGREP
+GREP
+CPP
 OBJEXT
 EXEEXT
 ac_ct_CC
@ -621,7 +661,6 @@ infodir
 docdir
 oldincludedir
 includedir
-runstatedir
 localstatedir
 sharedstatedir
 sysconfdir
@ -645,6 +684,7 @@ ac_subst_files=''
 ac_user_opts='
 enable_option_checking
 enable_coverage
+with_libcurl
 '
      ac_precious_vars='build_alias
 host_alias
@ -655,7 +695,8 @@ CC
 CFLAGS
 LDFLAGS
 LIBS
-CPPFLAGS'
+CPPFLAGS
+CPP'


 # Initialize some variables set by options.
@ -694,7 +735,6 @@ datadir='${datarootdir}'
 sysconfdir='${prefix}/etc'
 sharedstatedir='${prefix}/com'
 localstatedir='${prefix}/var'
-runstatedir='${localstatedir}/run'
 includedir='${prefix}/include'
 oldincludedir='/usr/include'
 docdir='${datarootdir}/doc/${PACKAGE_TARNAME}'
@ -947,15 +987,6 @@ do
  | -silent | --silent | --silen | --sile | --sil)
    silent=yes ;;

-  -runstatedir | --runstatedir | --runstatedi | --runstated \
-  | --runstate | --runstat | --runsta | --runst | --runs \
-  | --run | --ru | --r)
-    ac_prev=runstatedir ;;
-  -runstatedir=* | --runstatedir=* | --runstatedi=* | --runstated=* \
-  | --runstate=* | --runstat=* | --runsta=* | --runst=* | --runs=* \
-  | --run=* | --ru=* | --r=*)
-    runstatedir=$ac_optarg ;;
-
  -sbindir | --sbindir | --sbindi | --sbind | --sbin | --sbi | --sb)
    ac_prev=sbindir ;;
  -sbindir=* | --sbindir=* | --sbindi=* | --sbind=* | --sbin=* \
@ -1093,7 +1124,7 @@ fi
 for ac_var in	exec_prefix prefix bindir sbindir libexecdir datarootdir \
 		datadir sysconfdir sharedstatedir localstatedir includedir \
 		oldincludedir docdir infodir htmldir dvidir pdfdir psdir \
-		libdir localedir mandir runstatedir
+		libdir localedir mandir
 do
  eval ac_val=\$$ac_var
  # Remove trailing slashes.
@ -1246,7 +1277,6 @@ Fine tuning of the installation directories:
  --sysconfdir=DIR        read-only single-machine data [PREFIX/etc]
  --sharedstatedir=DIR    modifiable architecture-independent data [PREFIX/com]
  --localstatedir=DIR     modifiable single-machine data [PREFIX/var]
-  --runstatedir=DIR       modifiable per-process data [LOCALSTATEDIR/run]
  --libdir=DIR            object code libraries [EPREFIX/lib]
  --includedir=DIR        C header files [PREFIX/include]
  --oldincludedir=DIR     C header files for non-gcc [/usr/include]
@ -1278,6 +1308,12 @@ Optional Features:
  --enable-FEATURE[=ARG]  include FEATURE [ARG=yes]
  --enable-coverage       build with coverage testing instrumentation

+Optional Packages:
+  --with-PACKAGE[=ARG]    use PACKAGE [ARG=yes]
+  --without-PACKAGE       do not use PACKAGE (same as --with-PACKAGE=no)
+  --without-libcurl       do not use libcurl for anonymous statistics
+                          collection
+
 Some influential environment variables:
  PG_CONFIG   Location to find pg_config for target PostgreSQL instalation
              (default PATH)
@ -1289,6 +1325,7 @@ Some influential environment variables:
  LIBS        libraries to pass to the linker, e.g. -l<library>
  CPPFLAGS    (Objective) C/C++ preprocessor flags, e.g. -I<include dir> if
              you have headers in a nonstandard directory <include dir>
+  CPP         C preprocessor

 Use these variables to override the choices made by `configure' or to help
 it to find libraries and programs with nonstandard names/locations.
@ -1409,6 +1446,249 @@ fi
  as_fn_set_status $ac_retval

 } # ac_fn_c_try_compile
+
+# ac_fn_c_try_link LINENO
+# -----------------------
+# Try to link conftest.$ac_ext, and return whether this succeeded.
+ac_fn_c_try_link ()
+{
+  as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack
+  rm -f conftest.$ac_objext conftest$ac_exeext
+  if { { ac_try="$ac_link"
+case "(($ac_try" in
+  *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;;
+  *) ac_try_echo=$ac_try;;
+esac
+eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\""
+$as_echo "$ac_try_echo"; } >&5
+  (eval "$ac_link") 2>conftest.err
+  ac_status=$?
+  if test -s conftest.err; then
+    grep -v '^ *+' conftest.err >conftest.er1
+    cat conftest.er1 >&5
+    mv -f conftest.er1 conftest.err
+  fi
+  $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+  test $ac_status = 0; } && {
+	 test -z "$ac_c_werror_flag" ||
+	 test ! -s conftest.err
+       } && test -s conftest$ac_exeext && {
+	 test "$cross_compiling" = yes ||
+	 test -x conftest$ac_exeext
+       }; then :
+  ac_retval=0
+else
+  $as_echo "$as_me: failed program was:" >&5
+sed 's/^/| /' conftest.$ac_ext >&5
+
+	ac_retval=1
+fi
+  # Delete the IPA/IPO (Inter Procedural Analysis/Optimization) information
+  # created by the PGI compiler (conftest_ipa8_conftest.oo), as it would
+  # interfere with the next link command; also delete a directory that is
+  # left behind by Apple's compiler.  We do this before executing the actions.
+  rm -rf conftest.dSYM conftest_ipa8_conftest.oo
+  eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno
+  as_fn_set_status $ac_retval
+
+} # ac_fn_c_try_link
+
+# ac_fn_c_try_cpp LINENO
+# ----------------------
+# Try to preprocess conftest.$ac_ext, and return whether this succeeded.
+ac_fn_c_try_cpp ()
+{
+  as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack
+  if { { ac_try="$ac_cpp conftest.$ac_ext"
+case "(($ac_try" in
+  *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;;
+  *) ac_try_echo=$ac_try;;
+esac
+eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\""
+$as_echo "$ac_try_echo"; } >&5
+  (eval "$ac_cpp conftest.$ac_ext") 2>conftest.err
+  ac_status=$?
+  if test -s conftest.err; then
+    grep -v '^ *+' conftest.err >conftest.er1
+    cat conftest.er1 >&5
+    mv -f conftest.er1 conftest.err
+  fi
+  $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+  test $ac_status = 0; } > conftest.i && {
+	 test -z "$ac_c_preproc_warn_flag$ac_c_werror_flag" ||
+	 test ! -s conftest.err
+       }; then :
+  ac_retval=0
+else
+  $as_echo "$as_me: failed program was:" >&5
+sed 's/^/| /' conftest.$ac_ext >&5
+
+    ac_retval=1
+fi
+  eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno
+  as_fn_set_status $ac_retval
+
+} # ac_fn_c_try_cpp
+
+# ac_fn_c_check_header_mongrel LINENO HEADER VAR INCLUDES
+# -------------------------------------------------------
+# Tests whether HEADER exists, giving a warning if it cannot be compiled using
+# the include files in INCLUDES and setting the cache variable VAR
+# accordingly.
+ac_fn_c_check_header_mongrel ()
+{
+  as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack
+  if eval \${$3+:} false; then :
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for $2" >&5
+$as_echo_n "checking for $2... " >&6; }
+if eval \${$3+:} false; then :
+  $as_echo_n "(cached) " >&6
+fi
+eval ac_res=\$$3
+	       { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5
+$as_echo "$ac_res" >&6; }
+else
+  # Is the header compilable?
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking $2 usability" >&5
+$as_echo_n "checking $2 usability... " >&6; }
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+$4
+#include <$2>
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+  ac_header_compiler=yes
+else
+  ac_header_compiler=no
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_header_compiler" >&5
+$as_echo "$ac_header_compiler" >&6; }
+
+# Is the header present?
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking $2 presence" >&5
+$as_echo_n "checking $2 presence... " >&6; }
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <$2>
+_ACEOF
+if ac_fn_c_try_cpp "$LINENO"; then :
+  ac_header_preproc=yes
+else
+  ac_header_preproc=no
+fi
+rm -f conftest.err conftest.i conftest.$ac_ext
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_header_preproc" >&5
+$as_echo "$ac_header_preproc" >&6; }
+
+# So?  What about this header?
+case $ac_header_compiler:$ac_header_preproc:$ac_c_preproc_warn_flag in #((
+  yes:no: )
+    { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: accepted by the compiler, rejected by the preprocessor!" >&5
+$as_echo "$as_me: WARNING: $2: accepted by the compiler, rejected by the preprocessor!" >&2;}
+    { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: proceeding with the compiler's result" >&5
+$as_echo "$as_me: WARNING: $2: proceeding with the compiler's result" >&2;}
+    ;;
+  no:yes:* )
+    { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: present but cannot be compiled" >&5
+$as_echo "$as_me: WARNING: $2: present but cannot be compiled" >&2;}
+    { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2:     check for missing prerequisite headers?" >&5
+$as_echo "$as_me: WARNING: $2:     check for missing prerequisite headers?" >&2;}
+    { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: see the Autoconf documentation" >&5
+$as_echo "$as_me: WARNING: $2: see the Autoconf documentation" >&2;}
+    { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2:     section \"Present But Cannot Be Compiled\"" >&5
+$as_echo "$as_me: WARNING: $2:     section \"Present But Cannot Be Compiled\"" >&2;}
+    { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: $2: proceeding with the compiler's result" >&5
+$as_echo "$as_me: WARNING: $2: proceeding with the compiler's result" >&2;}
+    ;;
+esac
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for $2" >&5
+$as_echo_n "checking for $2... " >&6; }
+if eval \${$3+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  eval "$3=\$ac_header_compiler"
+fi
+eval ac_res=\$$3
+	       { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5
+$as_echo "$ac_res" >&6; }
+fi
+  eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno
+
+} # ac_fn_c_check_header_mongrel
+
+# ac_fn_c_try_run LINENO
+# ----------------------
+# Try to link conftest.$ac_ext, and return whether this succeeded. Assumes
+# that executables *can* be run.
+ac_fn_c_try_run ()
+{
+  as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack
+  if { { ac_try="$ac_link"
+case "(($ac_try" in
+  *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;;
+  *) ac_try_echo=$ac_try;;
+esac
+eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\""
+$as_echo "$ac_try_echo"; } >&5
+  (eval "$ac_link") 2>&5
+  ac_status=$?
+  $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+  test $ac_status = 0; } && { ac_try='./conftest$ac_exeext'
+  { { case "(($ac_try" in
+  *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;;
+  *) ac_try_echo=$ac_try;;
+esac
+eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\""
+$as_echo "$ac_try_echo"; } >&5
+  (eval "$ac_try") 2>&5
+  ac_status=$?
+  $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+  test $ac_status = 0; }; }; then :
+  ac_retval=0
+else
+  $as_echo "$as_me: program exited with status $ac_status" >&5
+       $as_echo "$as_me: failed program was:" >&5
+sed 's/^/| /' conftest.$ac_ext >&5
+
+       ac_retval=$ac_status
+fi
+  rm -rf conftest.dSYM conftest_ipa8_conftest.oo
+  eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno
+  as_fn_set_status $ac_retval
+
+} # ac_fn_c_try_run
+
+# ac_fn_c_check_header_compile LINENO HEADER VAR INCLUDES
+# -------------------------------------------------------
+# Tests whether HEADER exists and can be compiled using the include files in
+# INCLUDES, setting the cache variable VAR accordingly.
+ac_fn_c_check_header_compile ()
+{
+  as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack
+  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for $2" >&5
+$as_echo_n "checking for $2... " >&6; }
+if eval \${$3+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+$4
+#include <$2>
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+  eval "$3=yes"
+else
+  eval "$3=no"
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+fi
+eval ac_res=\$$3
+	       { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5
+$as_echo "$ac_res" >&6; }
+  eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno
+
+} # ac_fn_c_check_header_compile
 cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
@ -3058,8 +3338,501 @@ if test "$enable_coverage" = yes; then
    CITUS_CFLAGS="$CITUS_CFLAGS -fprofile-arcs -ftest-coverage"
 fi

+#
+# libcurl
+#
+
+
+
+# Check whether --with-libcurl was given.
+if test "${with_libcurl+set}" = set; then :
+  withval=$with_libcurl;
+  case $withval in
+    yes)
+      :
+      ;;
+    no)
+      :
+      ;;
+    *)
+      as_fn_error $? "no argument expected for --with-libcurl option" "$LINENO" 5
+      ;;
+  esac
+
+else
+  with_libcurl=yes
+
+fi
+
+
+
+if test "$with_libcurl" = yes; then
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for curl_global_init in -lcurl" >&5
+$as_echo_n "checking for curl_global_init in -lcurl... " >&6; }
+if ${ac_cv_lib_curl_curl_global_init+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  ac_check_lib_save_LIBS=$LIBS
+LIBS="-lcurl  $LIBS"
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+
+/* Override any GCC internal prototype to avoid an error.
+   Use char because int might match the return type of a GCC
+   builtin and then its argument prototype would still apply.  */
+#ifdef __cplusplus
+extern "C"
+#endif
+char curl_global_init ();
+int
+main ()
+{
+return curl_global_init ();
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+  ac_cv_lib_curl_curl_global_init=yes
+else
+  ac_cv_lib_curl_curl_global_init=no
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext conftest.$ac_ext
+LIBS=$ac_check_lib_save_LIBS
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_curl_curl_global_init" >&5
+$as_echo "$ac_cv_lib_curl_curl_global_init" >&6; }
+if test "x$ac_cv_lib_curl_curl_global_init" = xyes; then :
+  cat >>confdefs.h <<_ACEOF
+#define HAVE_LIBCURL 1
+_ACEOF
+
+  LIBS="-lcurl $LIBS"
+
+else
+  as_fn_error $? "libcurl not found
+If you have libcurl already installed, see config.log for details on the
+failure. It is possible the compiler isn't looking in the proper directory.
+Use --without-libcurl to disable anonymous statistics collection." "$LINENO" 5
+fi
+
+  ac_ext=c
+ac_cpp='$CPP $CPPFLAGS'
+ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5'
+ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5'
+ac_compiler_gnu=$ac_cv_c_compiler_gnu
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking how to run the C preprocessor" >&5
+$as_echo_n "checking how to run the C preprocessor... " >&6; }
+# On Suns, sometimes $CPP names a directory.
+if test -n "$CPP" && test -d "$CPP"; then
+  CPP=
+fi
+if test -z "$CPP"; then
+  if ${ac_cv_prog_CPP+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+      # Double quotes because CPP needs to be expanded
+    for CPP in "$CC -E" "$CC -E -traditional-cpp" "/lib/cpp"
+    do
+      ac_preproc_ok=false
+for ac_c_preproc_warn_flag in '' yes
+do
+  # Use a header file that comes with gcc, so configuring glibc
+  # with a fresh cross-compiler works.
+  # Prefer <limits.h> to <assert.h> if __STDC__ is defined, since
+  # <limits.h> exists even on freestanding compilers.
+  # On the NeXT, cc -E runs the code through the compiler's parser,
+  # not just through cpp. "Syntax error" is here to catch this case.
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#ifdef __STDC__
+# include <limits.h>
+#else
+# include <assert.h>
+#endif
+		     Syntax error
+_ACEOF
+if ac_fn_c_try_cpp "$LINENO"; then :
+
+else
+  # Broken: fails on valid input.
+continue
+fi
+rm -f conftest.err conftest.i conftest.$ac_ext
+
+  # OK, works on sane cases.  Now check whether nonexistent headers
+  # can be detected and how.
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <ac_nonexistent.h>
+_ACEOF
+if ac_fn_c_try_cpp "$LINENO"; then :
+  # Broken: success on invalid input.
+continue
+else
+  # Passes both tests.
+ac_preproc_ok=:
+break
+fi
+rm -f conftest.err conftest.i conftest.$ac_ext
+
+done
+# Because of `break', _AC_PREPROC_IFELSE's cleaning code was skipped.
+rm -f conftest.i conftest.err conftest.$ac_ext
+if $ac_preproc_ok; then :
+  break
+fi
+
+    done
+    ac_cv_prog_CPP=$CPP
+
+fi
+  CPP=$ac_cv_prog_CPP
+else
+  ac_cv_prog_CPP=$CPP
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $CPP" >&5
+$as_echo "$CPP" >&6; }
+ac_preproc_ok=false
+for ac_c_preproc_warn_flag in '' yes
+do
+  # Use a header file that comes with gcc, so configuring glibc
+  # with a fresh cross-compiler works.
+  # Prefer <limits.h> to <assert.h> if __STDC__ is defined, since
+  # <limits.h> exists even on freestanding compilers.
+  # On the NeXT, cc -E runs the code through the compiler's parser,
+  # not just through cpp. "Syntax error" is here to catch this case.
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#ifdef __STDC__
+# include <limits.h>
+#else
+# include <assert.h>
+#endif
+		     Syntax error
+_ACEOF
+if ac_fn_c_try_cpp "$LINENO"; then :
+
+else
+  # Broken: fails on valid input.
+continue
+fi
+rm -f conftest.err conftest.i conftest.$ac_ext
+
+  # OK, works on sane cases.  Now check whether nonexistent headers
+  # can be detected and how.
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <ac_nonexistent.h>
+_ACEOF
+if ac_fn_c_try_cpp "$LINENO"; then :
+  # Broken: success on invalid input.
+continue
+else
+  # Passes both tests.
+ac_preproc_ok=:
+break
+fi
+rm -f conftest.err conftest.i conftest.$ac_ext
+
+done
+# Because of `break', _AC_PREPROC_IFELSE's cleaning code was skipped.
+rm -f conftest.i conftest.err conftest.$ac_ext
+if $ac_preproc_ok; then :
+
+else
+  { { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5
+$as_echo "$as_me: error: in \`$ac_pwd':" >&2;}
+as_fn_error $? "C preprocessor \"$CPP\" fails sanity check
+See \`config.log' for more details" "$LINENO" 5; }
+fi
+
+ac_ext=c
+ac_cpp='$CPP $CPPFLAGS'
+ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5'
+ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5'
+ac_compiler_gnu=$ac_cv_c_compiler_gnu
+
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for grep that handles long lines and -e" >&5
+$as_echo_n "checking for grep that handles long lines and -e... " >&6; }
+if ${ac_cv_path_GREP+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  if test -z "$GREP"; then
+  ac_path_GREP_found=false
+  # Loop through the user's path and test for each of PROGNAME-LIST
+  as_save_IFS=$IFS; IFS=$PATH_SEPARATOR
+for as_dir in $PATH$PATH_SEPARATOR/usr/xpg4/bin
+do
+  IFS=$as_save_IFS
+  test -z "$as_dir" && as_dir=.
+    for ac_prog in grep ggrep; do
+    for ac_exec_ext in '' $ac_executable_extensions; do
+      ac_path_GREP="$as_dir/$ac_prog$ac_exec_ext"
+      as_fn_executable_p "$ac_path_GREP" || continue
+# Check for GNU ac_path_GREP and select it if it is found.
+  # Check for GNU $ac_path_GREP
+case `"$ac_path_GREP" --version 2>&1` in
+*GNU*)
+  ac_cv_path_GREP="$ac_path_GREP" ac_path_GREP_found=:;;
+*)
+  ac_count=0
+  $as_echo_n 0123456789 >"conftest.in"
+  while :
+  do
+    cat "conftest.in" "conftest.in" >"conftest.tmp"
+    mv "conftest.tmp" "conftest.in"
+    cp "conftest.in" "conftest.nl"
+    $as_echo 'GREP' >> "conftest.nl"
+    "$ac_path_GREP" -e 'GREP$' -e '-(cannot match)-' < "conftest.nl" >"conftest.out" 2>/dev/null || break
+    diff "conftest.out" "conftest.nl" >/dev/null 2>&1 || break
+    as_fn_arith $ac_count + 1 && ac_count=$as_val
+    if test $ac_count -gt ${ac_path_GREP_max-0}; then
+      # Best one so far, save it but keep looking for a better one
+      ac_cv_path_GREP="$ac_path_GREP"
+      ac_path_GREP_max=$ac_count
+    fi
+    # 10*(2^10) chars as input seems more than enough
+    test $ac_count -gt 10 && break
+  done
+  rm -f conftest.in conftest.tmp conftest.nl conftest.out;;
+esac
+
+      $ac_path_GREP_found && break 3
+    done
+  done
+  done
+IFS=$as_save_IFS
+  if test -z "$ac_cv_path_GREP"; then
+    as_fn_error $? "no acceptable grep could be found in $PATH$PATH_SEPARATOR/usr/xpg4/bin" "$LINENO" 5
+  fi
+else
+  ac_cv_path_GREP=$GREP
+fi
+
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_path_GREP" >&5
+$as_echo "$ac_cv_path_GREP" >&6; }
+ GREP="$ac_cv_path_GREP"
+
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for egrep" >&5
+$as_echo_n "checking for egrep... " >&6; }
+if ${ac_cv_path_EGREP+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  if echo a | $GREP -E '(a|b)' >/dev/null 2>&1
+   then ac_cv_path_EGREP="$GREP -E"
+   else
+     if test -z "$EGREP"; then
+  ac_path_EGREP_found=false
+  # Loop through the user's path and test for each of PROGNAME-LIST
+  as_save_IFS=$IFS; IFS=$PATH_SEPARATOR
+for as_dir in $PATH$PATH_SEPARATOR/usr/xpg4/bin
+do
+  IFS=$as_save_IFS
+  test -z "$as_dir" && as_dir=.
+    for ac_prog in egrep; do
+    for ac_exec_ext in '' $ac_executable_extensions; do
+      ac_path_EGREP="$as_dir/$ac_prog$ac_exec_ext"
+      as_fn_executable_p "$ac_path_EGREP" || continue
+# Check for GNU ac_path_EGREP and select it if it is found.
+  # Check for GNU $ac_path_EGREP
+case `"$ac_path_EGREP" --version 2>&1` in
+*GNU*)
+  ac_cv_path_EGREP="$ac_path_EGREP" ac_path_EGREP_found=:;;
+*)
+  ac_count=0
+  $as_echo_n 0123456789 >"conftest.in"
+  while :
+  do
+    cat "conftest.in" "conftest.in" >"conftest.tmp"
+    mv "conftest.tmp" "conftest.in"
+    cp "conftest.in" "conftest.nl"
+    $as_echo 'EGREP' >> "conftest.nl"
+    "$ac_path_EGREP" 'EGREP$' < "conftest.nl" >"conftest.out" 2>/dev/null || break
+    diff "conftest.out" "conftest.nl" >/dev/null 2>&1 || break
+    as_fn_arith $ac_count + 1 && ac_count=$as_val
+    if test $ac_count -gt ${ac_path_EGREP_max-0}; then
+      # Best one so far, save it but keep looking for a better one
+      ac_cv_path_EGREP="$ac_path_EGREP"
+      ac_path_EGREP_max=$ac_count
+    fi
+    # 10*(2^10) chars as input seems more than enough
+    test $ac_count -gt 10 && break
+  done
+  rm -f conftest.in conftest.tmp conftest.nl conftest.out;;
+esac
+
+      $ac_path_EGREP_found && break 3
+    done
+  done
+  done
+IFS=$as_save_IFS
+  if test -z "$ac_cv_path_EGREP"; then
+    as_fn_error $? "no acceptable egrep could be found in $PATH$PATH_SEPARATOR/usr/xpg4/bin" "$LINENO" 5
+  fi
+else
+  ac_cv_path_EGREP=$EGREP
+fi
+
+   fi
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_path_EGREP" >&5
+$as_echo "$ac_cv_path_EGREP" >&6; }
+ EGREP="$ac_cv_path_EGREP"
+
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for ANSI C header files" >&5
+$as_echo_n "checking for ANSI C header files... " >&6; }
+if ${ac_cv_header_stdc+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <stdlib.h>
+#include <stdarg.h>
+#include <string.h>
+#include <float.h>
+
+int
+main ()
+{
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+  ac_cv_header_stdc=yes
+else
+  ac_cv_header_stdc=no
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+
+if test $ac_cv_header_stdc = yes; then
+  # SunOS 4.x string.h does not declare mem*, contrary to ANSI.
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <string.h>
+
+_ACEOF
+if (eval "$ac_cpp conftest.$ac_ext") 2>&5 |
+  $EGREP "memchr" >/dev/null 2>&1; then :
+
+else
+  ac_cv_header_stdc=no
+fi
+rm -f conftest*
+
+fi
+
+if test $ac_cv_header_stdc = yes; then
+  # ISC 2.0.2 stdlib.h does not declare free, contrary to ANSI.
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <stdlib.h>
+
+_ACEOF
+if (eval "$ac_cpp conftest.$ac_ext") 2>&5 |
+  $EGREP "free" >/dev/null 2>&1; then :
+
+else
+  ac_cv_header_stdc=no
+fi
+rm -f conftest*
+
+fi
+
+if test $ac_cv_header_stdc = yes; then
+  # /bin/cc in Irix-4.0.5 gets non-ANSI ctype macros unless using -ansi.
+  if test "$cross_compiling" = yes; then :
+  :
+else
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <ctype.h>
+#include <stdlib.h>
+#if ((' ' & 0x0FF) == 0x020)
+# define ISLOWER(c) ('a' <= (c) && (c) <= 'z')
+# define TOUPPER(c) (ISLOWER(c) ? 'A' + ((c) - 'a') : (c))
+#else
+# define ISLOWER(c) \
+		   (('a' <= (c) && (c) <= 'i') \
+		     || ('j' <= (c) && (c) <= 'r') \
+		     || ('s' <= (c) && (c) <= 'z'))
+# define TOUPPER(c) (ISLOWER(c) ? ((c) | 0x40) : (c))
+#endif
+
+#define XOR(e, f) (((e) && !(f)) || (!(e) && (f)))
+int
+main ()
+{
+  int i;
+  for (i = 0; i < 256; i++)
+    if (XOR (islower (i), ISLOWER (i))
+	|| toupper (i) != TOUPPER (i))
+      return 2;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_run "$LINENO"; then :
+
+else
+  ac_cv_header_stdc=no
+fi
+rm -f core *.core core.conftest.* gmon.out bb.out conftest$ac_exeext \
+  conftest.$ac_objext conftest.beam conftest.$ac_ext
+fi
+
+fi
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_header_stdc" >&5
+$as_echo "$ac_cv_header_stdc" >&6; }
+if test $ac_cv_header_stdc = yes; then
+
+$as_echo "#define STDC_HEADERS 1" >>confdefs.h
+
+fi
+
+# On IRIX 5.3, sys/types and inttypes.h are conflicting.
+for ac_header in sys/types.h sys/stat.h stdlib.h string.h memory.h strings.h \
+		  inttypes.h stdint.h unistd.h
+do :
+  as_ac_Header=`$as_echo "ac_cv_header_$ac_header" | $as_tr_sh`
+ac_fn_c_check_header_compile "$LINENO" "$ac_header" "$as_ac_Header" "$ac_includes_default
+"
+if eval test \"x\$"$as_ac_Header"\" = x"yes"; then :
+  cat >>confdefs.h <<_ACEOF
+#define `$as_echo "HAVE_$ac_header" | $as_tr_cpp` 1
+_ACEOF
+
+fi
+
+done
+
+
+ac_fn_c_check_header_mongrel "$LINENO" "curl/curl.h" "ac_cv_header_curl_curl_h" "$ac_includes_default"
+if test "x$ac_cv_header_curl_curl_h" = xyes; then :
+
+else
+  as_fn_error $? "libcurl header not found
+If you have libcurl already installed, see config.log for details on the
+failure.  It is possible the compiler isn't looking in the proper directory.
+Use --without-libcurl to disable libcurl support." "$LINENO" 5
+fi
+
+
+  CITUS_CFLAGS="$CITUS_CFLAGS -DHAVE_LIBCURL"
+fi
+
 CITUS_CFLAGS="$CITUS_CFLAGS"

+CITUS_LDFLAGS="$LIBS"
+
 POSTGRES_SRCDIR="$POSTGRES_SRCDIR"

 POSTGRES_BUILDDIR="$POSTGRES_BUILDDIR"
--- a/configure.in
+++ b/configure.in
@ -140,7 +140,27 @@ if test "$enable_coverage" = yes; then
    CITUS_CFLAGS="$CITUS_CFLAGS -fprofile-arcs -ftest-coverage"
 fi

+#
+# libcurl
+#
+PGAC_ARG_BOOL(with, libcurl, yes,
+              [do not use libcurl for anonymous statistics collection])
+
+if test "$with_libcurl" = yes; then
+  AC_CHECK_LIB(curl, curl_global_init, [],
+              [AC_MSG_ERROR([libcurl not found
+If you have libcurl already installed, see config.log for details on the
+failure. It is possible the compiler isn't looking in the proper directory.
+Use --without-libcurl to disable anonymous statistics collection.])])
+  AC_CHECK_HEADER(curl/curl.h, [], [AC_MSG_ERROR([libcurl header not found
+If you have libcurl already installed, see config.log for details on the
+failure.  It is possible the compiler isn't looking in the proper directory.
+Use --without-libcurl to disable libcurl support.])])
+  CITUS_CFLAGS="$CITUS_CFLAGS -DHAVE_LIBCURL"
+fi
+
 AC_SUBST(CITUS_CFLAGS, "$CITUS_CFLAGS")
+AC_SUBST(CITUS_LDFLAGS, "$LIBS")
 AC_SUBST(POSTGRES_SRCDIR, "$POSTGRES_SRCDIR")
 AC_SUBST(POSTGRES_BUILDDIR, "$POSTGRES_BUILDDIR")

--- a/src/backend/distributed/shared_library_init.c
+++ b/src/backend/distributed/shared_library_init.c
@ -41,6 +41,7 @@
 #include "distributed/placement_connection.h"
 #include "distributed/remote_commands.h"
 #include "distributed/shared_library_init.h"
+#include "distributed/statistics_collection.h"
 #include "distributed/task_tracker.h"
 #include "distributed/transaction_management.h"
 #include "distributed/worker_manager.h"
@ -65,6 +66,8 @@ static void WarningForEnableDeadlockPrevention(bool newval, void *extra);
 static bool ErrorIfNotASuitableDeadlockFactor(double *newval, void **extra,
 											  GucSource source);
 static void NormalizeWorkerListPath(void);
+static bool StatisticsCollectionGucCheckHook(bool *newval, void **extra, GucSource
+											 source);


 /* *INDENT-OFF* */
@ -785,6 +788,24 @@ RegisterCitusConfigVariables(void)
 		0,
 		NULL, NULL, NULL);

+	DefineCustomBoolVariable(
+		"citus.enable_statistics_collection",
+		gettext_noop("Enables sending basic usage statistics to Citus."),
+		gettext_noop("Citus uploads daily anonymous usage reports containing "
+					 "rounded node count, shard size, distributed table count, "
+					 "and operating system name. This configuration value controls "
+					 "whether these reports are sent."),
+		&EnableStatisticsCollection,
+#if HAVE_LIBCURL
+		true,
+#else
+		false,
+#endif
+		PGC_SIGHUP,
+		GUC_SUPERUSER_ONLY | GUC_NO_SHOW_ALL,
+		&StatisticsCollectionGucCheckHook,
+		NULL, NULL);
+
 	/* warn about config items in the citus namespace that are not registered above */
 	EmitWarningsOnPlaceholders("citus");
 }
@ -866,3 +887,25 @@ NormalizeWorkerListPath(void)
 					PGC_S_OVERRIDE);
 	free(absoluteFileName);
 }
+
+
+static bool
+StatisticsCollectionGucCheckHook(bool *newval, void **extra, GucSource source)
+{
+#if HAVE_LIBCURL
+	return true;
+#else
+
+	/* if libcurl is not installed, only accept false */
+	if (*newval)
+	{
+		GUC_check_errcode(ERRCODE_FEATURE_NOT_SUPPORTED);
+		GUC_check_errdetail("Citus was compiled without libcurl support.");
+		return false;
+	}
+	else
+	{
+		return true;
+	}
+#endif
+}
--- a/src/backend/distributed/utils/maintenanced.c
+++ b/src/backend/distributed/utils/maintenanced.c
@ -16,6 +16,7 @@

 #include "postgres.h"

+#include <time.h>

 #include "miscadmin.h"
 #include "pgstat.h"
@ -27,7 +28,9 @@
 #include "catalog/namespace.h"
 #include "distributed/distributed_deadlock_detection.h"
 #include "distributed/maintenanced.h"
+#include "distributed/master_protocol.h"
 #include "distributed/metadata_cache.h"
+#include "distributed/statistics_collection.h"
 #include "nodes/makefuncs.h"
 #include "postmaster/bgworker.h"
 #include "storage/ipc.h"
@ -36,6 +39,7 @@
 #include "storage/lmgr.h"
 #include "storage/lwlock.h"
 #include "tcop/tcopprot.h"
+#include "utils/memutils.h"


 /*
@ -209,6 +213,8 @@ CitusMaintenanceDaemonMain(Datum main_arg)
 {
 	Oid databaseOid = DatumGetObjectId(main_arg);
 	MaintenanceDaemonDBData *myDbData = NULL;
+	time_t prevStatsCollection = 0;
+	bool prevStatsCollectionFailed = false;
 	ErrorContextCallback errorCallback;

 	/*
@ -271,9 +277,22 @@ CitusMaintenanceDaemonMain(Datum main_arg)
 		int latchFlags = WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH;
 		double timeout = 10000.0; /* use this if the deadlock detection is disabled */
 		bool foundDeadlock = false;
+		time_t currentTime = time(NULL);
+		double secondsSincePrevStatsCollection = difftime(currentTime,
+														  prevStatsCollection);
+		bool citusHasBeenLoaded = false;

 		CHECK_FOR_INTERRUPTS();

+		StartTransactionCommand();
+		citusHasBeenLoaded = CitusHasBeenLoaded();
+		CommitTransactionCommand();
+
+		if (!citusHasBeenLoaded)
+		{
+			continue;
+		}
+
 		/*
 		 * XXX: We clear the metadata cache before every iteration because otherwise
 		 * it might contain stale OIDs. It appears that in some cases invalidation
@ -289,6 +308,31 @@ CitusMaintenanceDaemonMain(Datum main_arg)
 		 * tasks should do their own time math about whether to re-run checks.
 		 */

+		if (secondsSincePrevStatsCollection >= STATISTICS_COLLECTION_INTERVAL ||
+			(prevStatsCollectionFailed &&
+			 secondsSincePrevStatsCollection >= STATISTICS_COLLECTION_RETRY_INTERVAL))
+		{
+#if HAVE_LIBCURL
+			if (EnableStatisticsCollection)
+			{
+				MemoryContext statsCollectionContext =
+					AllocSetContextCreate(CurrentMemoryContext,
+										  "StatsCollection",
+										  ALLOCSET_DEFAULT_MINSIZE,
+										  ALLOCSET_DEFAULT_INITSIZE,
+										  ALLOCSET_DEFAULT_MAXSIZE);
+				MemoryContext oldContext =
+					MemoryContextSwitchTo(statsCollectionContext);
+
+				WarnIfSyncDNS();
+				prevStatsCollectionFailed = !CollectBasicUsageStatistics();
+
+				MemoryContextSwitchTo(oldContext);
+				prevStatsCollection = currentTime;
+			}
+#endif
+		}
+
 		/* the config value -1 disables the distributed deadlock detection  */
 		if (DistributedDeadlockDetectionTimeoutFactor != -1.0)
 		{
--- a/src/backend/distributed/utils/statistics_collection.c
+++ b/src/backend/distributed/utils/statistics_collection.c
@ -0,0 +1,213 @@
+/*-------------------------------------------------------------------------
+ *
+ * statistics_collection.c
+ *	  Anonymous reports and statistics collection.
+ *
+ * Copyright (c) 2017, Citus Data, Inc.
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+
+#include <curl/curl.h>
+#include <sys/utsname.h>
+
+#include "access/xact.h"
+#include "citus_version.h"
+#include "distributed/metadata_cache.h"
+#include "distributed/statistics_collection.h"
+#include "distributed/worker_manager.h"
+#include "lib/stringinfo.h"
+#include "utils/json.h"
+
+bool EnableStatisticsCollection = true; /* send basic usage statistics to Citus */
+
+#if HAVE_LIBCURL
+
+static uint64 NextPow2(uint64 n);
+static uint64 ClusterSize(List *distributedTableList);
+static bool SendHttpPostJsonRequest(const char *url, const char *postFields, long
+									timeoutSeconds);
+
+/* WarnIfSyncDNS warns if libcurl is compiled with synchronous DNS. */
+void
+WarnIfSyncDNS(void)
+{
+	curl_version_info_data *versionInfo = curl_version_info(CURLVERSION_NOW);
+	if (!(versionInfo->features & CURL_VERSION_ASYNCHDNS))
+	{
+		ereport(WARNING, (errmsg("your current libcurl version doesn't support "
+								 "asynchronous DNS, which might cause unexpected "
+								 "delays in the operation of Citus"),
+						  errhint("Install a libcurl version with asynchronous DNS "
+								  "support.")));
+	}
+}
+
+
+/*
+ * CollectBasicUsageStatistics sends basic usage statistics to Citus servers.
+ * This includes Citus version, table count rounded to next power of 2, cluster
+ * size rounded to next power of 2, worker node count, and uname data. Returns
+ * true if we actually have sent statistics to the server.
+ */
+bool
+CollectBasicUsageStatistics(void)
+{
+	List *distributedTables = NIL;
+	uint64 roundedDistTableCount = 0;
+	uint64 roundedClusterSize = 0;
+	uint32 workerNodeCount = 0;
+	StringInfo fields = makeStringInfo();
+	struct utsname unameData;
+	memset(&unameData, 0, sizeof(unameData));
+
+	StartTransactionCommand();
+	distributedTables = DistributedTableList();
+	roundedDistTableCount = NextPow2(list_length(distributedTables));
+	roundedClusterSize = NextPow2(ClusterSize(distributedTables));
+	workerNodeCount = ActivePrimaryNodeCount();
+	CommitTransactionCommand();
+
+	uname(&unameData);
+
+	appendStringInfoString(fields, "{\"citus_version\": ");
+	escape_json(fields, CITUS_VERSION);
+	appendStringInfo(fields, ",\"table_count\": " UINT64_FORMAT, roundedDistTableCount);
+	appendStringInfo(fields, ",\"cluster_size\": " UINT64_FORMAT, roundedClusterSize);
+	appendStringInfo(fields, ",\"worker_node_count\": %u", workerNodeCount);
+	appendStringInfoString(fields, ",\"os_name\": ");
+	escape_json(fields, unameData.sysname);
+	appendStringInfoString(fields, ",\"os_release\": ");
+	escape_json(fields, unameData.release);
+	appendStringInfoString(fields, ",\"hwid\": ");
+	escape_json(fields, unameData.machine);
+	appendStringInfoString(fields, "}");
+
+	return SendHttpPostJsonRequest(STATS_COLLECTION_HOST "/v1/usage_reports",
+								   fields->data, HTTP_TIMEOUT_SECONDS);
+}
+
+
+/*
+ * ClusterSize returns total size of data store in the cluster consisting of
+ * given distributed tables. We ignore tables which we cannot get their size.
+ */
+static uint64
+ClusterSize(List *distributedTableList)
+{
+	uint64 clusterSize = 0;
+	ListCell *distTableCacheEntryCell = NULL;
+
+	foreach(distTableCacheEntryCell, distributedTableList)
+	{
+		DistTableCacheEntry *distTableCacheEntry = lfirst(distTableCacheEntryCell);
+		Oid relationId = distTableCacheEntry->relationId;
+		MemoryContext savedContext = CurrentMemoryContext;
+
+		PG_TRY();
+		{
+			Datum distTableSizeDatum = DirectFunctionCall1(citus_table_size,
+														   ObjectIdGetDatum(relationId));
+			clusterSize += DatumGetInt64(distTableSizeDatum);
+		}
+		PG_CATCH();
+		{
+			FlushErrorState();
+
+			/* citus_table_size() throws an error while the memory context is changed */
+			MemoryContextSwitchTo(savedContext);
+		}
+		PG_END_TRY();
+	}
+
+	return clusterSize;
+}
+
+
+/*
+ * NextPow2 returns smallest power of 2 less than or equal to n. If n is greater
+ * than 2^63, it returns 2^63. Returns 0 when n is 0.
+ */
+static uint64
+NextPow2(uint64 n)
+{
+	uint64 result = 1;
+
+	if (n == 0)
+	{
+		return 0;
+	}
+
+	/* if there is no 64-bit power of 2 greater than n, return 2^63 */
+	if (n > (1ull << 63))
+	{
+		return (1ull << 63);
+	}
+
+	while (result < n)
+	{
+		result *= 2;
+	}
+
+	return result;
+}
+
+
+/*
+ * SendHttpPostJsonRequest sends a HTTP/HTTPS POST request to the given URL with
+ * the given json object.
+ */
+static bool
+SendHttpPostJsonRequest(const char *url, const char *jsonObj, long timeoutSeconds)
+{
+	bool success = false;
+	CURLcode curlCode = false;
+	CURL *curl = NULL;
+
+	curl_global_init(CURL_GLOBAL_DEFAULT);
+	curl = curl_easy_init();
+	if (curl)
+	{
+		struct curl_slist *headers = NULL;
+		headers = curl_slist_append(headers, "Content-Type: application/json");
+		headers = curl_slist_append(headers, "charsets: utf-8");
+
+		curl_easy_setopt(curl, CURLOPT_URL, url);
+		curl_easy_setopt(curl, CURLOPT_POSTFIELDS, jsonObj);
+		curl_easy_setopt(curl, CURLOPT_TIMEOUT, timeoutSeconds);
+		curl_easy_setopt(curl, CURLOPT_HTTPHEADER, headers);
+
+		curlCode = curl_easy_perform(curl);
+		if (curlCode == CURLE_OK)
+		{
+			int httpCode = 0;
+			curl_easy_getinfo(curl, CURLINFO_RESPONSE_CODE, &httpCode);
+			if (httpCode == 200)
+			{
+				success = true;
+			}
+			else if (httpCode >= 400 && httpCode < 500)
+			{
+				ereport(WARNING, (errmsg("HTTP request failed."),
+								  errhint("HTTP response code: %d", httpCode)));
+			}
+		}
+		else
+		{
+			ereport(WARNING, (errmsg("Sending HTTP POST request failed."),
+							  errhint("Error code: %s.", curl_easy_strerror(curlCode))));
+		}
+
+		curl_slist_free_all(headers);
+		curl_easy_cleanup(curl);
+	}
+
+	curl_global_cleanup();
+
+	return success;
+}
+
+
+#endif /* HAVE_LIBCURL */
--- a/src/include/citus_config.h.in
+++ b/src/include/citus_config.h.in
@ -22,6 +22,36 @@
 /* Citus version as a number */
 #undef CITUS_VERSION_NUM

+/* Define to 1 if you have the <inttypes.h> header file. */
+#undef HAVE_INTTYPES_H
+
+/* Define to 1 if you have the `curl' library (-lcurl). */
+#undef HAVE_LIBCURL
+
+/* Define to 1 if you have the <memory.h> header file. */
+#undef HAVE_MEMORY_H
+
+/* Define to 1 if you have the <stdint.h> header file. */
+#undef HAVE_STDINT_H
+
+/* Define to 1 if you have the <stdlib.h> header file. */
+#undef HAVE_STDLIB_H
+
+/* Define to 1 if you have the <strings.h> header file. */
+#undef HAVE_STRINGS_H
+
+/* Define to 1 if you have the <string.h> header file. */
+#undef HAVE_STRING_H
+
+/* Define to 1 if you have the <sys/stat.h> header file. */
+#undef HAVE_SYS_STAT_H
+
+/* Define to 1 if you have the <sys/types.h> header file. */
+#undef HAVE_SYS_TYPES_H
+
+/* Define to 1 if you have the <unistd.h> header file. */
+#undef HAVE_UNISTD_H
+
 /* Define to the address where bug reports for this package should be sent. */
 #undef PACKAGE_BUGREPORT

@ -39,3 +69,6 @@

 /* Define to the version of this package. */
 #undef PACKAGE_VERSION
+
+/* Define to 1 if you have the ANSI C header files. */
+#undef STDC_HEADERS
--- a/src/include/distributed/maintenanced.h
+++ b/src/include/distributed/maintenanced.h
@ -12,6 +12,12 @@
 #ifndef MAINTENANCED_H
 #define MAINTENANCED_H

+/* collect statistics every 24 hours */
+#define STATISTICS_COLLECTION_INTERVAL 86400
+
+/* if statistics collection fails, retry in 1 minute */
+#define STATISTICS_COLLECTION_RETRY_INTERVAL 60
+
 /* config variable for */
 extern double DistributedDeadlockDetectionTimeoutFactor;

--- a/src/include/distributed/master_metadata_utility.h
+++ b/src/include/distributed/master_metadata_utility.h
@ -107,6 +107,11 @@ typedef struct ShardPlacement
 /* Config variable managed via guc.c */
 extern int ReplicationModel;

+/* Size functions */
+extern Datum citus_table_size(PG_FUNCTION_ARGS);
+extern Datum citus_total_relation_size(PG_FUNCTION_ARGS);
+extern Datum citus_relation_size(PG_FUNCTION_ARGS);
+
 /* Function declarations to read shard and shard placement data */
 extern uint32 TableShardReplicationFactor(Oid relationId);
 extern List * LoadShardIntervalList(Oid relationId);
--- a/src/include/distributed/statistics_collection.h
+++ b/src/include/distributed/statistics_collection.h
@ -0,0 +1,26 @@
+/*-------------------------------------------------------------------------
+ *
+ * statistics_collection.h
+ *
+ * Copyright (c) 2017, Citus Data, Inc.
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef STATISTICS_COLLECTION_H
+#define STATISTICS_COLLECTION_H
+
+/* Config variables managed via guc.c */
+extern bool EnableStatisticsCollection;
+
+#if HAVE_LIBCURL
+
+#define STATS_COLLECTION_HOST "https://citus-statistics.herokuapp.com"
+#define HTTP_TIMEOUT_SECONDS 5
+
+extern void WarnIfSyncDNS(void);
+extern bool CollectBasicUsageStatistics(void);
+
+#endif /* HAVE_LIBCURL */
+
+#endif /* STATISTICS_COLLECTION_H */
--- a/src/test/regress/Makefile
+++ b/src/test/regress/Makefile
@ -43,36 +43,44 @@ check-full: check-multi check-multi-mx check-multi-task-tracker-extra check-work
 # for check-worker. But that's harmless besides a few cycles.
 check-worker: all
 	$(pg_regress_multi_check) --load-extension=citus \
+	--server-option=citus.enable_statistics_collection=0 \
 	-- $(MULTI_REGRESS_OPTS) --schedule=$(citus_abs_srcdir)/worker_schedule $(EXTRA_TESTS)

 check-multi: all tempinstall-main
 	$(pg_regress_multi_check) --load-extension=citus \
+	--server-option=citus.enable_statistics_collection=0 \
 	-- $(MULTI_REGRESS_OPTS) --schedule=$(citus_abs_srcdir)/multi_schedule $(EXTRA_TESTS)

 check-multi-vg: all tempinstall-main
 	$(pg_regress_multi_check) --load-extension=citus --valgrind \
+	--server-option=citus.enable_statistics_collection=0 \
 	--pg_ctl-timeout=360 --connection-timeout=500000 --valgrind-path=valgrind --valgrind-log-file=$(VALGRIND_LOG_FILE) \
 	-- $(MULTI_REGRESS_OPTS) --schedule=$(citus_abs_srcdir)/multi_schedule $(EXTRA_TESTS)

 check-isolation: all tempinstall-main
 	$(pg_regress_multi_check) --load-extension=citus --isolationtester \
+	--server-option=citus.enable_statistics_collection=0 \
 	-- $(MULTI_REGRESS_OPTS) --schedule=$(citus_abs_srcdir)/isolation_schedule $(EXTRA_TESTS)

 check-vanilla: all tempinstall-main
-	$(pg_regress_multi_check) --load-extension=citus --vanillatest
+	$(pg_regress_multi_check) --load-extension=citus --vanillatest \
+	--server-option=citus.enable_statistics_collection=0

 check-multi-mx: all tempinstall-main
 	$(pg_regress_multi_check) --load-extension=citus \
+	--server-option=citus.enable_statistics_collection=0 \
 	-- $(MULTI_REGRESS_OPTS) --schedule=$(citus_abs_srcdir)/multi_mx_schedule $(EXTRA_TESTS)

 check-multi-task-tracker-extra: all tempinstall-main
 	$(pg_regress_multi_check) --load-extension=citus \
+	--server-option=citus.enable_statistics_collection=0 \
 	--server-option=citus.task_executor_type=task-tracker \
 	--server-option=citus.large_table_shard_count=1 \
 	-- $(MULTI_REGRESS_OPTS) --schedule=$(citus_abs_srcdir)/multi_task_tracker_extra_schedule $(EXTRA_TESTS)

 check-follower-cluster: all
 	$(pg_regress_multi_check) --load-extension=citus --follower-cluster \
+	--server-option=citus.enable_statistics_collection=0 \
 	-- $(MULTI_REGRESS_OPTS) --schedule=$(citus_abs_srcdir)/multi_follower_schedule $(EXTRA_TESTS)

 clean distclean maintainer-clean: