X-Recipient: archive-cygwin AT delorie DOT com
DomainKey-Signature: a=rsa-sha1; c=nofws; d=sourceware.org; h=list-id
	:list-unsubscribe:list-subscribe:list-archive:list-post
	:list-help:sender:date:from:to:subject:message-id:references
	:mime-version:content-type:in-reply-to; q=dns; s=default; b=Kv8E
	SkG9QMT4h197Pp5K3sJPvcIIE7i9b6CT5HEnPtyNcXoFPYpaMZ3lPtyzneLccAo7
	kPefOxbPcY1F0XFkdYxGFix7UF2ttPiWHGCau93oSECTZk1b2Z+4CAY93TxyHclV
	qvfC4a68dJzIyZtuZyDUEEJaiXCEiWOSBokXODs=
DKIM-Signature: v=1; a=rsa-sha1; c=relaxed; d=sourceware.org; h=list-id
	:list-unsubscribe:list-subscribe:list-archive:list-post
	:list-help:sender:date:from:to:subject:message-id:references
	:mime-version:content-type:in-reply-to; s=default; bh=ADp7GWYsM7
	n8r36FeJuYFLLe7LU=; b=KnLDQLeK3ETz+clkz/VWN+wAFrofcNr91RksWuKLB4
	jThnMkyqX8drWR8Bt/2ZOanrdgGTd2L8CRMpXnWarEUpkNKbjjQsjonyXa8o+w9+
	RAe8otTA7JlvCARDv35+LcLGzlhlNLctwfQ2o7mHUeQ7yvpDsspoGnWN1bab1nwT
	8=
Mailing-List: contact cygwin-help AT cygwin DOT com; run by ezmlm
List-Id: <cygwin.cygwin.com>
List-Subscribe: <mailto:cygwin-subscribe AT cygwin DOT com>
List-Archive: <http://sourceware.org/ml/cygwin/>
List-Post: <mailto:cygwin AT cygwin DOT com>
List-Help: <mailto:cygwin-help AT cygwin DOT com>, <http://sourceware.org/ml/#faqs>
Sender: cygwin-owner AT cygwin DOT com
Mail-Followup-To: cygwin AT cygwin DOT com
Delivered-To: mailing list cygwin AT cygwin DOT com
Authentication-Results: sourceware.org; auth=none
X-Virus-Found: No
X-Spam-SWARE-Status: No, score=-1.4 required=5.0 tests=AWL,BAYES_00,RCVD_IN_DNSWL_NONE,RCVD_IN_SORBS_SPAM autolearn=no version=3.3.2 spammy=awhile, Pick, cease, classic
X-HELO: mail-pg0-f47.google.com
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;        d=1e100.net; s=20161025;        h=x-gm-message-state:date:from:to:subject:message-id:references         :mime-version:content-disposition:in-reply-to:user-agent;        bh=CtKgNGWGYgT8te0R2OziqUX6eGJQOzC1rUja/LryavU=;        b=h9ITnWvj4uxN/BidU4aXnt2rUuT9zH1yfMfaqBuOgRxA4rmKNDVONlLqEGmxA+UZ98         N+zfFtZ/cKw05yPWTngHKLMLMel5KWffUvqgYxtlKONiozO1uN5b8yZseSIoRnbp5qYz         sxPuD8JHkjv95Yn9Uf+mEjGjFmbk+gEOiCL/eLch9aEWPl1hKTnew/MDpl/5bG6M7wac         AE4882SdtrSOtX2Ant8yNjpIlhX79FgdkUbZrG4F841VSDzf9fS2Qug3edOe8JzcWLtF         92T9QKYOmWej4CUmUrhDb2HrG+MRFA01Cf/HXInsmCvfuO7303fDws8Elma6VcCzEvnE         diQw==
X-Gm-Message-State: AFeK/H31VGpdamfuWpdVULBW3WHmZ5k8IcPyhl1FZ5yiasP6MnUXnVYHb4gSpZ11I4dzig==
X-Received: by 10.84.253.15 with SMTP id z15mr12597831pll.142.1491100588278;        Sat, 01 Apr 2017 19:36:28 -0700 (PDT)
Date: Sat, 1 Apr 2017 22:36:24 -0400
From: Noah Misch <noah AT leadboat DOT com>
To: cygwin AT cygwin DOT com
Subject: Re: cygserver - Postgres Multiple connection Load Testing - Inifinte Loop
Message-ID: <20170402023624.GA2561924@tornado.leadboat.com>
References: <200408030333 DOT i733XEXn023894 AT mx3 DOT redhat DOT com> <20040803100612 DOT GP31522 AT cygbert DOT vinschen DOT de> <20170321025614 DOT GA2100214 AT tornado DOT leadboat DOT com> <20170324171101 DOT GI29995 AT calimero DOT vinschen DOT de> <20170328052652 DOT GA2351961 AT tornado DOT leadboat DOT com>
MIME-Version: 1.0
Content-Type: multipart/mixed; boundary="Nq2Wo0NMKNjxTN9z"
Content-Disposition: inline
In-Reply-To: <20170328052652.GA2351961@tornado.leadboat.com>
User-Agent: Mutt/1.5.24 (2015-08-30)

--Nq2Wo0NMKNjxTN9z
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline

On Tue, Mar 28, 2017 at 01:26:52AM -0400, Noah Misch wrote:
> On Fri, Mar 24, 2017 at 06:11:01PM +0100, Corinna Vinschen wrote:
> > I pushed a patchset now, and uploaded new developer snapshots for
> > testing to https://cygwin.com/snapshots/
> 
> > Please give it a try

> I call the cygwin-20170324 freezes "limited" because the symptoms differ from
> the classic freeze I described upthread.  "strace /bin/true" and "cat
> /proc/sysvipc/sem" do not hang, but every PostgreSQL backend process is stuck
> waiting on a synchronization primitive.
> 
> I can distill another self-contained test case for the limited freeze seen in
> cygwin-20170324, but that make take awhile.  I'm sending this early report so
> you're aware of the possible regression in cygwin-20170324.

I'm attaching a new test program that demonstrates the regression.  My previous
test program created sixteen processes that each picked a random semaphore to
lock.  Now, each process picks two semaphores and locks them in order.  This
proceeds smoothly on GNU/Linux and on cygwin-20170321.tar.xz "cygserver -r 40".
It freezes within one second on cygwin-20170324.tar.xz "cygserver -r 40".

--Nq2Wo0NMKNjxTN9z
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment; filename="sema_two.c"

/*
 * Demonstrate cygserver bug introduced in cygwin-20170324.tar.xz snapshot.  Run
 * without arguments.  Test against "cygserver -r 40" to get enough threads.
 * This is otherwise compatible with default cygserver settings; it uses a
 * single semaphore set of eight semaphores.
 *
 * Output will cease within a few seconds.  On older cygserver and non-Cygwin
 * systems, it will run to completion.
 */

#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <sys/ipc.h>
#include <sys/sem.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <unistd.h>

#define SEM_KEY 0x631a2c3f
#define N_WORKER 16
#define N_SEMA (N_WORKER/2)
#define N_CYCLE 1000000

union semun
{
    int val;
    struct semid_ds *buf;
    unsigned short *array;
};

static int print_every = 1;


static int lock(int set, unsigned short sem_num)
{
    struct sembuf op;
    op.sem_num = sem_num;
    op.sem_op = -1;
    op.sem_flg = 0;
    if (0 > semop(set, &op, 1))
    {
	perror("semop");
	return 1;
    }
    return 0;
}

static int unlock(int set, unsigned short sem_num)
{
    struct sembuf op;
    op.sem_num = sem_num;
    op.sem_op = 1 ;		/* only difference vs. lock() */
    op.sem_flg = 0;
    if (0 > semop(set, &op, 1))
    {
	perror("semop");
	return 1;
    }
    return 0;
}

/* In parallel, N_WORKER processes run this function. */
static int do_worker(int ordinal, int set)
{
    int i;

    printf("start worker %d\n", ordinal);
    fflush(stdout);

    for (i = 1; i <= N_CYCLE; i++)
    {
	unsigned short s0, s1;

	/* Pick two non-identical semaphore numbers. */
	s0 = random() % N_SEMA;
	do { s1 = random() % N_SEMA; } while (s0 == s1);

	/* Lock the lower one first, thereby preventing deadlock. */
	if (lock(set, s0 < s1 ? s0 : s1) || lock(set, s0 < s1 ? s1 : s0)
	    || unlock(set, s0) || unlock(set, s1))
	    return 1;

	if (i % print_every == 0)
	{
	    printf("worker %d: %d cycles elapsed\n", ordinal, i);
	    fflush(stdout);
	}
    }

    return 0;
}

int main(int argc, char **argv)
{
    int status = 1, set, i, child_status;

    if (argc == 2)
	print_every = atoi(argv[1]);
    else if (argc != 1)
    {
	fprintf(stderr, "Usage: sema_two [print-every-N]\n");
	return status;
    }

    puts("semget");
    fflush(stdout);
    set = semget(SEM_KEY, N_SEMA, IPC_CREAT | 0600);
    if (set == -1)
    {
	perror("semget");
	return status;
    }

    puts("SETVAL");
    fflush(stdout);
    for (i = 0; i < N_SEMA; i++)
    {
	union semun s;
	s.val = 1;

	if (0 > semctl(set, i, SETVAL, s))
	{
	    perror("semctl(SETVAL)");
	    goto cleanup;
	}
    }

    for (i = 0; i < N_WORKER; i++)
    {
	pid_t pid;
	pid = fork();
	switch (pid)
	{
	    case -1:
		perror("fork");
		goto cleanup;
	    case 0:
		return do_worker(i, set);
	}
    }

    status = 0;

cleanup:
    while (wait(&child_status) != -1)
	;
    if (errno != ECHILD)
    {
	perror("wait");
	status = 1;
    }

    if (0 > semctl(set, 0, IPC_RMID))
    {
	perror("semtctl(IPC_RMID)");
	status = 1;
    }

    return status;
}


--Nq2Wo0NMKNjxTN9z
Content-Type: text/plain; charset=us-ascii


--
Problem reports:       http://cygwin.com/problems.html
FAQ:                   http://cygwin.com/faq/
Documentation:         http://cygwin.com/docs.html
Unsubscribe info:      http://cygwin.com/ml/#unsubscribe-simple
--Nq2Wo0NMKNjxTN9z--