Re: (ITS#8875) [Patch] Performance problems in back-mdb with large DITs and many aliases

[hyc@symas.com]

This is a multi-part message in MIME format.
--------------AED2FFEE73F73B1613190B64
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit

hyc@symas.com wrote:
> The tool to generate the test LDIF is attached. It reads an LDIF containing 500,000 users on stdin, and outputs the same LDIF,
> with aliases interspersed, on stdout.
> 
Slightly tweaked, creates the alias after the target entry. In case the server does referential integrity on loading.

-- 
  -- Howard Chu
  CTO, Symas Corp.           http://www.symas.com
  Director, Highland Sun     http://highlandsun.com/hyc/
  Chief Architect, OpenLDAP  http://www.openldap.org/project/

--------------AED2FFEE73F73B1613190B64
Content-Type: text/x-csrc;
 name="mkalias.c"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="mkalias.c"

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>

#define NUMUSERS 500000
#define NUMALIASES	30000
#define NUMSUBALIASES	435
#define SUFFIX	"dc=example,dc=com"

static const char ou1[] = "\
dn: ou=alias1," SUFFIX "\n\
objectclass: top\n\
objectclass: organizationalUnit\n\
ou: alias1\n";

static const char ou2[] = "\
dn: ou=alias2," SUFFIX "\n\
objectclass: top\n\
objectclass: organizationalUnit\n\
ou: alias2\n";

int qcmp(const void *a, const void *b)
{
	const int *i = a, *j = b;
	return *i - *j;
}

int main() {
	char line[1024], dn[1024], *ou;
	int aliases[NUMALIASES];
	int subaliases[NUMSUBALIASES];
	int i;
	int nusers=0, naliases=0, nsubaliases=0, showalias=0;
	
	/* select a random subset of users to generate aliases */
	srand(time(0L));
	for (i=0; i<NUMALIASES; i++) {
		aliases[i] = rand() % NUMUSERS;
	}
uniq1:
	qsort(aliases, NUMALIASES, sizeof(int), qcmp);
	/* make sure they're unique */
	for (i=1; i<NUMALIASES; i++) {
		if (aliases[i-1] == aliases[i]) {
			aliases[i] = rand() % NUMUSERS;
			goto uniq1;
		}
	}
	/* select a random susbset of aliases for the target subtree */
	for (i=0; i<NUMSUBALIASES; i++) {
		subaliases[i] = rand() % NUMALIASES;
	}
uniq2:
	qsort(subaliases, NUMSUBALIASES, sizeof(int), qcmp);
	/* make sure they're unique */
	for (i=1; i<NUMSUBALIASES; i++) {
		if (subaliases[i-1] == subaliases[i]) {
			subaliases[i] = rand() % NUMALIASES;
			goto uniq2;
		}
	}
	for (i=0; i<NUMSUBALIASES; i++) {
		subaliases[i] = aliases[subaliases[i]];
	}

	/* read LDIF */
	while (fgets(line, sizeof(line), stdin) != NULL) {
		if (line[0] == '#')
			continue;
		if (!strncmp(line, "dn: ", 4)) {
			/* we assume all users' DNs use uid for RDN */
			if (!strncmp(line+4, "uid=", 4)) {
				if (!nusers) {
					puts(ou1);
					puts(ou2);
				}
				if (showalias) {
					printf("dn: uid=x.%d,ou=%s," SUFFIX "\n", nusers, ou);
					puts("objectclass: alias");
					puts("objectclass: extensibleObject");
					printf("aliasedObjectName: %s\n", dn);
					showalias = 0;
				}
				if (nusers == aliases[naliases] ||
					nusers == subaliases[nsubaliases]) {
					if (nusers == subaliases[nsubaliases]) {
						ou = "alias2";
						nsubaliases++;
					} else {
						ou = "alias1";
					}
					naliases++;
					strcpy(dn, line+4);
					showalias = 1;
				}
				nusers++;
			}
		}
		fputs(line, stdout);
	}
	return 0;
}

--------------AED2FFEE73F73B1613190B64--