Fix error handling of vacuumdb and reindexdb when running out of fds

When trying to use a high number of jobs, vacuumdb (and more recently
reindexdb) has only checked for a maximum number of jobs used, causing
confusing failures when running out of file descriptors when the jobs
open connections to Postgres.  This commit changes the error handling so
as we do not check anymore for a maximum number of allowed jobs when
parsing the option value with FD_SETSIZE, but check instead if a file
descriptor is within the supported range when opening the connections
for the jobs so as this is detected at the earliest time possible.

Also, improve the error message to give a hint about the number of jobs
recommended, using a wording given by the reviewers of the patch.

Reported-by: Andres Freund
Author: Michael Paquier
Reviewed-by: Andres Freund, Álvaro Herrera, Tom Lane
Discussion: https://postgr.es/m/20190818001858.ho3ev4z57fqhs7a5@alap3.anarazel.de
Backpatch-through: 9.5

diff --git a/src/bin/scripts/reindexdb.c b/src/bin/scripts/reindexdb.c
index f93f7dd5fec76b80c131a2021b0cfff49d9a42d8..f00aec15de35e0c5d920fd7302c9a498b27dd37d 100644 (file)
--- a/src/bin/scripts/reindexdb.c
+++ b/src/bin/scripts/reindexdb.c
@@ -153,12 +153,6 @@ main(int argc, char *argv[])
                    pg_log_error("number of parallel jobs must be at least 1");
                    exit(1);
                }
-               if (concurrentCons > ParallelSlotsMax())
-               {
-                   pg_log_error("too many parallel jobs requested (maximum: %d)",
-                                ParallelSlotsMax());
-                   exit(1);
-               }
                break;
            case 'v':
                verbose = true;

diff --git a/src/bin/scripts/scripts_parallel.c b/src/bin/scripts/scripts_parallel.c
index 10379a1f99bd279959ff90c5dcadb7ca7c3df0d0..55bda9044b4df0911c2442b9fc1959037e06dcfb 100644 (file)
--- a/src/bin/scripts/scripts_parallel.c
+++ b/src/bin/scripts/scripts_parallel.c
@@ -94,20 +94,6 @@ select_loop(int maxFd, fd_set *workerset, bool *aborting)
    return i;
 }
 
-/*
- * ParallelSlotsMax
- *     Returns the maximum number of parallel slots supported.
- *
- * Note that this is included here as FD_SETSIZE is declared in sys/select.h
- * per POSIX.
- */
-int
-ParallelSlotsMax(void)
-{
-   /* leave some room for pre-existing fds */
-   return FD_SETSIZE - 10;
-}
-
 /*
  * ParallelSlotsGetIdle
  *     Return a connection slot that is ready to execute a command.
@@ -246,6 +232,18 @@ ParallelSlotsSetup(const char *dbname, const char *host, const char *port,
        {
            conn = connectDatabase(dbname, host, port, username, prompt_password,
                                   progname, echo, false, true);
+
+           /*
+            * Fail and exit immediately if trying to use a socket in an
+            * unsupported range.  POSIX requires open(2) to use the lowest
+            * unused file descriptor and the hint given relies on that.
+            */
+           if (PQsocket(conn) >= FD_SETSIZE)
+           {
+               pg_log_fatal("too many jobs for this platform -- try %d", i);
+               exit(1);
+           }
+
            init_slot(slots + i, conn);
        }
    }

diff --git a/src/bin/scripts/scripts_parallel.h b/src/bin/scripts/scripts_parallel.h
index 8042345072a5e3760c68956fedc13ba17a929fe1..ab82c5e6a962fb8e0521035abeb0a968fc3748c9 100644 (file)
--- a/src/bin/scripts/scripts_parallel.h
+++ b/src/bin/scripts/scripts_parallel.h
@@ -21,8 +21,6 @@ typedef struct ParallelSlot
    bool        isFree;         /* Is it known to be idle? */
 } ParallelSlot;
 
-extern int ParallelSlotsMax(void);
-
 extern ParallelSlot *ParallelSlotsGetIdle(ParallelSlot *slots, int numslots);
 
 extern ParallelSlot *ParallelSlotsSetup(const char *dbname, const char *host,

diff --git a/src/bin/scripts/vacuumdb.c b/src/bin/scripts/vacuumdb.c
index c5c38692edeaa1f40885b10ab571564155003d40..2c7219239f98396aaa1835d23b60159a5606c75f 100644 (file)
--- a/src/bin/scripts/vacuumdb.c
+++ b/src/bin/scripts/vacuumdb.c
@@ -181,12 +181,6 @@ main(int argc, char *argv[])
                    pg_log_error("number of parallel jobs must be at least 1");
                    exit(1);
                }
-               if (concurrentCons > ParallelSlotsMax())
-               {
-                   pg_log_error("too many parallel jobs requested (maximum: %d)",
-                                ParallelSlotsMax());
-                   exit(1);
-               }
                break;
            case 2:
                maintenance_db = pg_strdup(optarg);