Attached is a patch that fixes a long standing bug in pgbench: it won't
handle scale factors above ~4000 (around 60GB) because it uses 32-bit
integers for its computations related to the number of accounts, and it
just crashes badly when you exceed that. This month I've run into two
systems where that was barely enough to exceed physical RAM, so I'd
expect this to be a significant limiting factor during 9.0's lifetime.
A few people have complained about it already in 8.4.
The index size on the big accounts table has to increase for this to
work, it's a bigint now instead of an int. That's going to mean a drop
in results for some tests, just because less index will fit in RAM.
I'll quantify that better before submitting something final here. I
still have some other testing left to do as well: making sure I didn't
break the new \setshell feature (am suspicious of strtol()), confirming
the random numbers are still as random as they should be (there was a
little bug in the debugging code related to that, too).
Was looking for general feedback on whether the way I've converted this
to use 64 bit integers for the account numbers seems appropriate, and to
see if there's any objection to fixing this in general given the
potential downsides.
Here's the patch in action on previously unreachable sizes (this is a
system with 8GB of RAM, so I'm basically just testing seek speed here):
$ ./pgbench -j 4 -c 8 -T 30 -S pgbench
starting vacuum...end.
transaction type: SELECT only
scaling factor: 5000
query mode: simple
number of clients: 8
number of threads: 4
duration: 30 s
number of transactions actually processed: 2466
tps = 82.010509 (including connections establishing)
tps = 82.042946 (excluding connections establishing)
$ psql -x -c "select relname,reltuples from pg_class where
relname='pgbench_accounts'" -d pgbench
relname | pgbench_accounts
reltuples | 5e+08
$ psql -x -c "select pg_size_pretty(pg_table_size('pgbench_accounts'))"
-d pgbench
pg_size_pretty | 63 GB
$ psql -x -c "select aid from pgbench_accounts order by aid limit 1" -d
pgbench
aid | 1
$ psql -x -c "select aid from pgbench_accounts order by aid desc limit
1" -d pgbench
aid | 500000000
--
Greg Smith 2ndQuadrant Baltimore, MD
PostgreSQL Training, Services and Support
g...@2ndquadrant.com www.2ndQuadrant.com
diff --git a/contrib/pgbench/pgbench.c b/contrib/pgbench/pgbench.c
index 38086a5..8a7064a 100644
*** a/contrib/pgbench/pgbench.c
--- b/contrib/pgbench/pgbench.c
*************** usage(const char *progname)
*** 313,326 ****
}
/* random number generator: uniform distribution from min to max inclusive */
! static int
! getrand(int min, int max)
{
/*
* Odd coding is so that min and max have approximately the same chance of
* being selected as do numbers between them.
*/
! return min + (int) (((max - min + 1) * (double) random()) / (MAX_RANDOM_VALUE + 1.0));
}
/* call PQexec() and exit() on failure */
--- 313,326 ----
}
/* random number generator: uniform distribution from min to max inclusive */
! static int64
! getrand(int64 min, int64 max)
{
/*
* Odd coding is so that min and max have approximately the same chance of
* being selected as do numbers between them.
*/
! return min + (int64) (((max - min + 1) * (double) random()) / (MAX_RANDOM_VALUE + 1.0));
}
/* call PQexec() and exit() on failure */
*************** runShellCommand(CState *st, char *variab
*** 630,636 ****
FILE *fp;
char res[64];
char *endptr;
! int retval;
/*
* Join arguments with whilespace separaters. Arguments starting with
--- 630,636 ----
FILE *fp;
char res[64];
char *endptr;
! int64 retval;
/*
* Join arguments with whilespace separaters. Arguments starting with
*************** runShellCommand(CState *st, char *variab
*** 704,710 ****
}
/* Check whether the result is an integer and assign it to the variable */
! retval = (int) strtol(res, &endptr, 10);
while (*endptr != '\0' && isspace((unsigned char) *endptr))
endptr++;
if (*res == '\0' || *endptr != '\0')
--- 704,710 ----
}
/* Check whether the result is an integer and assign it to the variable */
! retval = (int64) strtol(res, &endptr, 19);
while (*endptr != '\0' && isspace((unsigned char) *endptr))
endptr++;
if (*res == '\0' || *endptr != '\0')
*************** runShellCommand(CState *st, char *variab
*** 712,718 ****
fprintf(stderr, "%s: must return an integer ('%s' returned)\n", argv[0], res);
return false;
}
! snprintf(res, sizeof(res), "%d", retval);
if (!putVariable(st, "setshell", variable, res))
return false;
--- 712,718 ----
fprintf(stderr, "%s: must return an integer ('%s' returned)\n", argv[0], res);
return false;
}
! snprintf(res, sizeof(res), INT64_FORMAT, retval);
if (!putVariable(st, "setshell", variable, res))
return false;
*************** top:
*** 959,966 ****
if (pg_strcasecmp(argv[0], "setrandom") == 0)
{
char *var;
! int min,
! max;
char res[64];
if (*argv[2] == ':')
--- 959,967 ----
if (pg_strcasecmp(argv[0], "setrandom") == 0)
{
char *var;
! int64 min,
! max,
! rand;
char res[64];
if (*argv[2] == ':')
*************** top:
*** 1000,1014 ****
if (max < min || max > MAX_RANDOM_VALUE)
{
! fprintf(stderr, "%s: invalid maximum number %d\n", argv[0], max);
st->ecnt++;
return true;
}
#ifdef DEBUG
! printf("min: %d max: %d random: %d\n", min, max, getrand(min, max));
#endif
! snprintf(res, sizeof(res), "%d", getrand(min, max));
if (!putVariable(st, argv[0], argv[1], res))
{
--- 1001,1016 ----
if (max < min || max > MAX_RANDOM_VALUE)
{
! fprintf(stderr, "%s: invalid maximum number " INT64_FORMAT "\n", argv[0], max);
st->ecnt++;
return true;
}
+ rand=getrand(min,max);
#ifdef DEBUG
! printf("min: " INT64_FORMAT " max: " INT64_FORMAT " random: " INT64_FORMAT "\n", min, max, rand);
#endif
! snprintf(res, sizeof(res), INT64_FORMAT, rand);
if (!putVariable(st, argv[0], argv[1], res))
{
*************** init(void)
*** 1191,1197 ****
"drop table if exists pgbench_tellers",
"create table pgbench_tellers(tid int not null,bid int,tbalance int,filler char(84)) with (fillfactor=%d)",
"drop table if exists pgbench_accounts",
! "create table pgbench_accounts(aid int not null,bid int,abalance int,filler char(84)) with (fillfactor=%d)",
"drop table if exists pgbench_history",
"create table pgbench_history(tid int,bid int,aid int,delta int,mtime timestamp,filler char(22))"
};
--- 1193,1199 ----
"drop table if exists pgbench_tellers",
"create table pgbench_tellers(tid int not null,bid int,tbalance int,filler char(84)) with (fillfactor=%d)",
"drop table if exists pgbench_accounts",
! "create table pgbench_accounts(aid bigint not null,bid int,abalance int,filler char(80)) with (fillfactor=%d)",
"drop table if exists pgbench_history",
"create table pgbench_history(tid int,bid int,aid int,delta int,mtime timestamp,filler char(22))"
};
*************** init(void)
*** 1204,1210 ****
PGconn *con;
PGresult *res;
char sql[256];
! int i;
if ((con = doConnect()) == NULL)
exit(1);
--- 1206,1212 ----
PGconn *con;
PGresult *res;
char sql[256];
! int64 i;
if ((con = doConnect()) == NULL)
exit(1);
*************** init(void)
*** 1232,1244 ****
for (i = 0; i < nbranches * scale; i++)
{
! snprintf(sql, 256, "insert into pgbench_branches(bid,bbalance) values(%d,0)", i + 1);
executeStatement(con, sql);
}
for (i = 0; i < ntellers * scale; i++)
{
! snprintf(sql, 256, "insert into pgbench_tellers(tid,bid,tbalance) values (%d,%d,0)",
i + 1, i / ntellers + 1);
executeStatement(con, sql);
}
--- 1234,1246 ----
for (i = 0; i < nbranches * scale; i++)
{
! snprintf(sql, 256, "insert into pgbench_branches(bid,bbalance) values(" INT64_FORMAT ",0)", i + 1);
executeStatement(con, sql);
}
for (i = 0; i < ntellers * scale; i++)
{
! snprintf(sql, 256, "insert into pgbench_tellers(tid,bid,tbalance) values (" INT64_FORMAT "," INT64_FORMAT ",0)",
i + 1, i / ntellers + 1);
executeStatement(con, sql);
}
*************** init(void)
*** 1263,1271 ****
for (i = 0; i < naccounts * scale; i++)
{
! int j = i + 1;
! snprintf(sql, 256, "%d\t%d\t%d\t\n", j, i / naccounts + 1, 0);
if (PQputline(con, sql))
{
fprintf(stderr, "PQputline failed\n");
--- 1265,1273 ----
for (i = 0; i < naccounts * scale; i++)
{
! int64 j = i + 1;
! snprintf(sql, 256, INT64_FORMAT "\t" INT64_FORMAT "\t%d\t\n", j, i / naccounts + 1, 0);
if (PQputline(con, sql))
{
fprintf(stderr, "PQputline failed\n");
*************** init(void)
*** 1273,1279 ****
}
if (j % 10000 == 0)
! fprintf(stderr, "%d tuples done.\n", j);
}
if (PQputline(con, "\\.\n"))
{
--- 1275,1281 ----
}
if (j % 10000 == 0)
! fprintf(stderr, INT64_FORMAT " tuples done.\n", j);
}
if (PQputline(con, "\\.\n"))
{
--
Sent via pgsql-hackers mailing list (pgsql-hackers@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-hackers
