head	1.7;
access;
symbols
	pkgsrc-2013Q2:1.7.0.4
	pkgsrc-2013Q2-base:1.7
	pkgsrc-2012Q4:1.7.0.2
	pkgsrc-2012Q4-base:1.7
	pkgsrc-2012Q3:1.6.0.8
	pkgsrc-2012Q3-base:1.6
	pkgsrc-2012Q2:1.6.0.6
	pkgsrc-2012Q2-base:1.6
	pkgsrc-2012Q1:1.6.0.4
	pkgsrc-2012Q1-base:1.6
	pkgsrc-2011Q4:1.6.0.2
	pkgsrc-2011Q4-base:1.6
	pkgsrc-2011Q3:1.5.0.2
	pkgsrc-2011Q3-base:1.5;
locks; strict;
comment	@# @;


1.7
date	2012.10.19.04.15.21;	author manu;	state dead;
branches;
next	1.6;

1.6
date	2011.10.06.02.19.06;	author manu;	state Exp;
branches;
next	1.5;

1.5
date	2011.09.18.01.36.06;	author manu;	state Exp;
branches;
next	1.4;

1.4
date	2011.08.09.07.15.42;	author manu;	state Exp;
branches;
next	1.3;

1.3
date	2011.07.23.01.14.44;	author manu;	state Exp;
branches;
next	1.2;

1.2
date	2011.07.19.07.54.31;	author manu;	state Exp;
branches;
next	1.1;

1.1
date	2011.07.08.08.02.57;	author manu;	state Exp;
branches;
next	;


desc
@@


1.7
log
@Bump to glusterfs-3.3.1, which brings
- unified file and object storage
- storage for Hadoop (not tested here)
- proactive self-healing
- much better performance
@
text
@$NetBSD: patch-bt,v 1.6 2011/10/06 02:19:06 manu Exp $

Initialize pthread_cond_t, it hurts otherwise.

--- xlators/performance/io-threads/src/io-threads.c.orig	2011-08-23 14:31:41.000000000 +0200
+++ xlators/performance/io-threads/src/io-threads.c	2011-09-17 15:45:30.000000000 +0200
@@@@ -2194,8 +2194,20 @@@@
                         "pthread_mutex_init failed (%d)", ret);
                 goto out;
         }
 
+	if ((ret = pthread_cond_init(&conf->cond, NULL)) != 0) {
+                gf_log (this->name, GF_LOG_ERROR,
+                        "pthread_cond_init failed (%d)", ret);
+                goto out;
+	}
+
+	if ((ret = pthread_mutex_init(&conf->mutex, NULL)) != 0) {
+                gf_log (this->name, GF_LOG_ERROR,
+                        "pthread_mutex_init failed (%d)", ret);
+                goto out;
+	}
+
         set_stack_size (conf);
 
         if (xlator_get_volopt_info (&this->volume_options, "thread-count",
                                     &def_val, NULL)) {
@


1.6
log
@Add missing comments and RCSId in 3.2.3 patches, fix patch-bb checksum
@
text
@d1 1
a1 1
$NetBSD$
@


1.5
log
@Update glusterfs to 3.2.3
This maintenance release with no new features. Majot bug fixes are:
 Bug 2464 Fixed all the issues caused by GFID mismatch during
	  distribute rename.
 Bug 2988 Fixed the issue of high CPU usage when Directory Quota
	  is enabled.
 Bug 3122 Enhanced the volume set interface to support io-threads
	  on the client.
 Bug 3210 Fixed the issue of modified mtime/atime of the files after
	  rebalance operation.
 Bug 3191 Fixed the issue with symlinks during rebalance operation.
@
text
@d1 4
@


1.4
log
@- Use linkat(2) if available. This fixes a EPERM error when using rename(2)
on a symlink within a glusterfs volume that uses DHT
- Consider gfid changes as nn fatal. Glustefs will fix instead of panic.
@
text
@d1 4
a4 9
$NetBSD$

Fix the io-threads xlator, which forgot to initialize its pthread
condition and mutex.

--- xlators/performance/io-threads/src/io-threads.c.orig	2011-07-14 14:21:10.000000000 +0200
+++ xlators/performance/io-threads/src/io-threads.c	2011-07-22 09:01:34.000000000 +0200
@@@@ -2181,8 +2181,20 @@@@
                         "out of memory");
d22 2
a23 2
         thread_count = IOT_DEFAULT_THREADS;
 
@


1.3
log
@Update to glusterfs 3.2.2 (maintenance release for bug fixes)
@
text
@@


1.2
log
@Enable georeplication
@
text
@d6 2
a7 2
--- xlators/performance/io-threads/src/io-threads.c.orig
+++ xlators/performance/io-threads/src/io-threads.c
@


1.1
log
@Upgrade to glusterfs-3.2.1
This release is mostly about bug fixes, and we also fix bugs in the NetBSD
port.
@
text
@@