[Bug 898] New: Very HIGH File & VM system latencies and system stop responding while extracting big tar archive file.

[Bug 898] New: Very HIGH File & VM system latencies and system stop responding while extracting big tar archive file.

[Martin J. Bligh]

http://bugme.osdl.org/show_bug.cgi?id=898

           Summary: Very HIGH File & VM system latencies and system stop
                    responding while extracting big tar  archive file.
    Kernel Version: 2.5.75
            Status: NEW
          Severity: high
             Owner: bugme-janitors@lists.osdl.org
         Submitter: bakhtiar@softhome.net


Distribution:Slackware v7.1 : glibc v2.1.3
Hardware Environment: P!!! 550 MHz, 256 MB RAM. HP Brio BA600

Software Environment:# lspci
00:00.0 Host bridge: Intel Corporation 440BX/ZX - 82443BX/ZX Host bridge (rev 03)
00:01.0 PCI bridge: Intel Corporation 440BX/ZX - 82443BX/ZX AGP bridge (rev 03)
00:04.0 Multimedia audio controller: Cirrus Logic CS 4614/22/24 [CrystalClear
SoundFusion Audio Accelerator] (rev 01)
00:07.0 ISA bridge: Intel Corporation 82371AB PIIX4 ISA (rev 02)
00:07.1 IDE interface: Intel Corporation 82371AB PIIX4 IDE (rev 01)
00:07.2 USB Controller: Intel Corporation 82371AB PIIX4 USB (rev 01)
00:07.3 Bridge: Intel Corporation 82371AB PIIX4 ACPI (rev 02)
00:0f.0 Ethernet controller: Accton Technology Corporation SMC2-1211TX (rev 10)
00:12.0 Multimedia audio controller: Creative Labs SB Live! EMU10000 (rev 07)
00:12.1 Input device controller: Creative Labs SB Live! (rev 07)
01:00.0 VGA compatible controller: Matrox Graphics, Inc. MGA G200 AGP (rev 03)

Problem Description:
1) lmbench v3.0 indicates VERY slow file handling since v2.5.74. I am using
reiserfs as a default FS.

File & VM system latencies in microseconds - smaller is better
-------------------------------------------------------------------------------
Host                 OS   0K File      10K File     Mmap    Prot   Page   100fd
                        Create Delete Create Delete Latency Fault  Fault  selct
--------- ------------- ------ ------ ------ ------ ------- ----- ------- -----
vfr        Linux 2.5.72   92.9 6.2000  272.0 6.4290  1120.0 0.836 3.12030  13.6
vfr        Linux 2.5.73   94.8 4.1030  197.8 4.2720  1076.0 0.782 2.85340  11.1
*vfr       Linux 2.5.74  155.4  170.4  391.8  247.7  1111.0 0.781 2.95210  11.1
*vfr       Linux 2.5.75  153.1  163.0  381.4  225.6  1044.0 0.656 2.77480  11.0



2) System stop responding while extracting big tar.bz2 archive file; example;
MozillaFirebird.tar.bz2 (about 32MB). ps indicates that sistem stuck at tar
process (pid 3607)

# ps aux
root      3598  0.0  0.0     0    0 ?        SW   11:26   0:00 [rpciod]
root      3599  0.0  0.0     0    0 ?        SW   11:26   0:00 [lockd]
root      3608 13.4  1.5  4712 4000 vc/1     S    11:27   0:58 bzip2 -d
root      3607  4.4  0.7  3428 1848 vc/1     D    11:27   0:19 tar xvfy
/mnt/nfs/mozilla/MozillaFirebird-0.6-source.tar.bz2

# cat /proc/vmstat
nr_dirty 26052
nr_writeback 0
nr_unstable 0
nr_page_table_pages 92
nr_mapped 3224
nr_slab 4825
pgpgin 101596
pgpgout 392800
pswpin 0
pswpout 0
pgalloc 6592963
pgfree 6594126
pgactivate 53079
pgdeactivate 12278
pgfault 3215804
pgmajfault 420
pgscan 56954
pgrefill 13927
pgsteal 56118
pginodesteal 0
kswapd_steal 54230
kswapd_inodesteal 8706
pageoutrun 141
allocstall 59
pgrotated 0

Load average also VERY high ... more than 4.00.

Steps to reproduce:

CONFIG_X86=y
CONFIG_MMU=y
CONFIG_UID16=y
CONFIG_GENERIC_ISA_DMA=y
CONFIG_EXPERIMENTAL=y
CONFIG_SWAP=y
CONFIG_SYSVIPC=y
CONFIG_SYSCTL=y
CONFIG_LOG_BUF_SHIFT=14
CONFIG_FUTEX=y
CONFIG_EPOLL=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
CONFIG_OBSOLETE_MODPARM=y
CONFIG_KMOD=y
CONFIG_X86_PC=y
CONFIG_MPENTIUMIII=y
CONFIG_X86_CMPXCHG=y
CONFIG_X86_XADD=y
CONFIG_X86_L1_CACHE_SHIFT=5
CONFIG_RWSEM_XCHGADD_ALGORITHM=y
CONFIG_X86_WP_WORKS_OK=y
CONFIG_X86_INVLPG=y
CONFIG_X86_BSWAP=y
CONFIG_X86_POPAD_OK=y
CONFIG_X86_GOOD_APIC=y
CONFIG_X86_INTEL_USERCOPY=y
CONFIG_X86_USE_PPRO_CHECKSUM=y
CONFIG_PREEMPT=y
CONFIG_X86_TSC=y
CONFIG_NOHIGHMEM=y
CONFIG_MTRR=y
CONFIG_HAVE_DEC_LOCK=y
CONFIG_PCI=y
CONFIG_PCI_GOANY=y
CONFIG_PCI_BIOS=y
CONFIG_PCI_DIRECT=y
CONFIG_PCI_NAMES=y
CONFIG_ISA=y
CONFIG_HOTPLUG=y
CONFIG_PCMCIA_PROBE=y
CONFIG_KCORE_ELF=y
CONFIG_BINFMT_ELF=y
CONFIG_PARPORT=m
CONFIG_PARPORT_PC=m
CONFIG_PARPORT_PC_CML1=m
CONFIG_PARPORT_1284=y
CONFIG_BLK_DEV_FD=y
CONFIG_BLK_DEV_LOOP=m
CONFIG_IDE=y
CONFIG_BLK_DEV_IDE=y
CONFIG_BLK_DEV_IDEDISK=y
CONFIG_IDEDISK_MULTI_MODE=y
CONFIG_BLK_DEV_IDECD=y
CONFIG_IDE_TASKFILE_IO=y
CONFIG_BLK_DEV_IDEPCI=yCONFIG_IDEPCI_SHARE_IRQ=y
CONFIG_BLK_DEV_IDEDMA_PCI=y
CONFIG_IDEDMA_PCI_AUTO=y
CONFIG_BLK_DEV_IDEDMA=y
CONFIG_BLK_DEV_ADMA=y
CONFIG_BLK_DEV_PIIX=y
CONFIG_IDEDMA_AUTO=y
CONFIG_BLK_DEV_IDE_MODES=y
CONFIG_SCSI=m
CONFIG_BLK_DEV_SD=m
CONFIG_BLK_DEV_SR=m
CONFIG_BLK_DEV_SR_VENDOR=y
CONFIG_CHR_DEV_SG=m
CONFIG_SCSI_MULTI_LUN=y
CONFIG_SCSI_REPORT_LUNS=y
CONFIG_SCSI_CONSTANTS=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_NETFILTER=y
CONFIG_UNIX=y
CONFIG_INET=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_NF_CONNTRACK=m
CONFIG_IP_NF_FTP=m
CONFIG_IP_NF_IRC=m
CONFIG_IP_NF_TFTP=m
CONFIG_IP_NF_AMANDA=m
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_MATCH_LIMIT=m
CONFIG_IP_NF_MATCH_MAC=m
CONFIG_IP_NF_MATCH_PKTTYPE=m
CONFIG_IP_NF_MATCH_MARK=m
CONFIG_IP_NF_MATCH_MULTIPORT=m
CONFIG_IP_NF_MATCH_TOS=m
CONFIG_IP_NF_MATCH_ECN=m
CONFIG_IP_NF_MATCH_DSCP=m
CONFIG_IP_NF_MATCH_AH_ESP=m
CONFIG_IP_NF_MATCH_LENGTH=m
CONFIG_IP_NF_MATCH_TTL=m
CONFIG_IP_NF_MATCH_TCPMSS=m
CONFIG_IP_NF_MATCH_HELPER=m
CONFIG_IP_NF_MATCH_STATE=m
CONFIG_IP_NF_MATCH_CONNTRACK=m
CONFIG_IP_NF_MATCH_UNCLEAN=m
CONFIG_IP_NF_MATCH_OWNER=m
CONFIG_IP_NF_FILTER=m
CONFIG_IP_NF_TARGET_REJECT=m
CONFIG_IP_NF_TARGET_MIRROR=m
CONFIG_IP_NF_NAT=m
CONFIG_IP_NF_NAT_NEEDED=y
CONFIG_IP_NF_TARGET_MASQUERADE=m
CONFIG_IP_NF_TARGET_REDIRECT=m
CONFIG_IP_NF_NAT_IRC=m
CONFIG_IP_NF_NAT_FTP=m
CONFIG_IP_NF_NAT_TFTP=m
CONFIG_IP_NF_NAT_AMANDA=m
CONFIG_IP_NF_MANGLE=m
CONFIG_IP_NF_TARGET_TOS=m
CONFIG_IP_NF_TARGET_ECN=m
CONFIG_IP_NF_TARGET_DSCP=m
CONFIG_IP_NF_TARGET_MARK=m
CONFIG_IP_NF_TARGET_LOG=m
CONFIG_IP_NF_TARGET_TCPMSS=m
CONFIG_IP_NF_ARPTABLES=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IPV6_SCTP__=y
CONFIG_NETDEVICES=y
CONFIG_DUMMY=m
CONFIG_BONDING=m
CONFIG_TUN=m
CONFIG_NET_ETHERNET=y
CONFIG_NET_PCI=y
CONFIG_8139TOO=y
CONFIG_PLIP=m
CONFIG_PPP=m
CONFIG_PPP_MULTILINK=y
CONFIG_PPP_FILTER=y
CONFIG_PPP_ASYNC=m
CONFIG_PPP_SYNC_TTY=m
CONFIG_PPP_DEFLATE=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPPOE=m
CONFIG_INPUT=y
CONFIG_INPUT_MOUSEDEV=y
CONFIG_INPUT_MOUSEDEV_PSAUX=y
CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
CONFIG_SOUND_GAMEPORT=y
CONFIG_SERIO=y
CONFIG_SERIO_I8042=y
CONFIG_INPUT_KEYBOARD=y
CONFIG_KEYBOARD_ATKBD=y
CONFIG_INPUT_MOUSE=y
CONFIG_MOUSE_PS2=y
CONFIG_VT=y
CONFIG_VT_CONSOLE=y
CONFIG_HW_CONSOLE=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_CORE=y
CONFIG_UNIX98_PTYS=y
CONFIG_UNIX98_PTY_COUNT=256
CONFIG_PRINTER=m
CONFIG_RTC=y
CONFIG_AGP=y
CONFIG_AGP_INTEL=y
CONFIG_DRM=y
CONFIG_DRM_MGA=y
CONFIG_EXT2_FS=y
CONFIG_EXT2_FS_XATTR=y
CONFIG_FS_MBCACHE=y
CONFIG_REISERFS_FS=y
CONFIG_AUTOFS4_FS=m
CONFIG_ISO9660_FS=m
CONFIG_JOLIET=y
CONFIG_BLK_DEV_GENERIC=y
CONFIG_UDF_FS=y
CONFIG_FAT_FS=m
CONFIG_VFAT_FS=m
CONFIG_NTFS_FS=m
CONFIG_NTFS_RW=y
CONFIG_PROC_FS=y
CONFIG_DEVFS_FS=y
CONFIG_DEVFS_MOUNT=y
CONFIG_DEVPTS_FS=y
CONFIG_TMPFS=y
CONFIG_RAMFS=y
CONFIG_NFS_FS=m
CONFIG_NFS_V3=y
CONFIG_NFS_V4=y
CONFIG_NFSD=m
CONFIG_NFSD_V3=y
CONFIG_NFSD_V4=y
CONFIG_NFSD_TCP=y
CONFIG_LOCKD=m
CONFIG_LOCKD_V4=y
CONFIG_EXPORTFS=m
CONFIG_SUNRPC=m
CONFIG_SUNRPC_GSS=m
CONFIG_MSDOS_PARTITION=y
CONFIG_NLS=y
CONFIG_NLS_DEFAULT="iso8859-1"
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
CONFIG_VIDEO_SELECT=y
CONFIG_VGA_CONSOLE=y
CONFIG_DUMMY_CONSOLE=y
CONFIG_SOUND=y
CONFIG_SND=y
CONFIG_SND_SEQUENCER=m
CONFIG_SND_OSSEMUL=y
CONFIG_SND_MIXER_OSS=m
CONFIG_SND_PCM_OSS=m
CONFIG_SND_SEQUENCER_OSS=y
CONFIG_SND_RTCTIMER=y
CONFIG_SND_EMU10K1=m
CONFIG_USB=y
CONFIG_USB_DEVICEFS=y
CONFIG_USB_UHCI_HCD=y
CONFIG_USB_STORAGE=m
CONFIG_USB_MOUSE=y
CONFIG_ZLIB_INFLATE=m
CONFIG_ZLIB_DEFLATE=m
CONFIG_X86_BIOS_REBOOT=y

Extra configurations:
/usr/src/linux/Makefile modifcation
HOSTCFLAGS      = -Wall -Wstrict-prototypes -Os -s -fomit-frame-pointer

/usr/src/linux/i366/Makefile
cflags-$(CONFIG_MPENTIUMIII)    += $(call check_gcc,-march=pentium3 -mmmx -msse,
-march=i686)

I hope this report enough to solve the problem...

Best wish...

Yours,
Mohammad Bahathir Hashim
MALAYSIA.

Re: [Bug 898] New: Very HIGH File & VM system latencies and system stop responding while extracting big tar archive file.

[Sergey S. Kostyliov]

Hello all,

On Friday 11 July 2003 10:14, Martin J. Bligh wrote:
> http://bugme.osdl.org/show_bug.cgi?id=898
>
>            Summary: Very HIGH File & VM system latencies and system stop
>                     responding while extracting big tar  archive file.
>     Kernel Version: 2.5.75
>             Status: NEW
>           Severity: high
>              Owner: bugme-janitors@lists.osdl.org
>          Submitter: bakhtiar@softhome.net
>
>
> Distribution:Slackware v7.1 : glibc v2.1.3
> Hardware Environment: P!!! 550 MHz, 256 MB RAM. HP Brio BA600

The same issues here with 2.5.7{4,5}. IO-intencive task got stuck in 'D'
state (bk,rsync,tar - it really doesn't matter). I think a have to get decoded
Alt-SysRq-T for this tasks next time. 

-- 
                   Best regards,
                   Sergey S. Kostyliov <rathamahata@php4.ru>
                   Public PGP key: http://sysadminday.org.ru/rathamahata.asc

Re: [Bug 898] New: Very HIGH File & VM system latencies and system stop responding while extracting big tar archive file.

[Nick Piggin]

Sergey S. Kostyliov wrote:

>Hello all,
>
>On Friday 11 July 2003 10:14, Martin J. Bligh wrote:
>
>>http://bugme.osdl.org/show_bug.cgi?id=898
>>
>>           Summary: Very HIGH File & VM system latencies and system stop
>>                    responding while extracting big tar  archive file.
>>    Kernel Version: 2.5.75
>>            Status: NEW
>>          Severity: high
>>             Owner: bugme-janitors@lists.osdl.org
>>         Submitter: bakhtiar@softhome.net
>>
>>
>>Distribution:Slackware v7.1 : glibc v2.1.3
>>Hardware Environment: P!!! 550 MHz, 256 MB RAM. HP Brio BA600
>>
>
>The same issues here with 2.5.7{4,5}. IO-intencive task got stuck in 'D'
>state (bk,rsync,tar - it really doesn't matter). I think a have to get decoded
>Alt-SysRq-T for this tasks next time. 
>

You're sure 2.5.74 got processes stuck in D? That means its possibly
a driver bug. If you can get 2.5.75 to hang, please also try with
elevator=deadline. Thank you.

Nick

Re: [Bug 898] New: Very HIGH File & VM system latencies and system stop responding while extracting big tar archive file.

[Andrew Morton]

Nick Piggin <piggin@cyberone.com.au> wrote:
>
> You're sure 2.5.74 got processes stuck in D? That means its possibly
>  a driver bug. If you can get 2.5.75 to hang, please also try with
>  elevator=deadline. Thank you.

No, this will be the reiserfs bug.

--- 25/fs/reiserfs/tail_conversion.c~reiserfs-dirty-memory-fix	2003-07-10 22:22:54.000000000 -0700
+++ 25-akpm/fs/reiserfs/tail_conversion.c	2003-07-10 22:22:54.000000000 -0700
@@ -191,7 +191,7 @@ unmap_buffers(struct page *page, loff_t 
 	bh = next ;
       } while (bh != head) ;
       if ( PAGE_SIZE == bh->b_size ) {
-	ClearPageDirty(page);
+	clear_page_dirty(page);
       }
     }
   } 

_

Re: Very HIGH File & VM system latencies and system stop responding while extracting big tar archive file.

[Mike Fedyk]

On Fri, Jul 11, 2003 at 03:45:10AM -0700, Andrew Morton wrote:
> Nick Piggin <piggin@cyberone.com.au> wrote:
> >
> > You're sure 2.5.74 got processes stuck in D? That means its possibly
> >  a driver bug. If you can get 2.5.75 to hang, please also try with
> >  elevator=deadline. Thank you.
> 
> No, this will be the reiserfs bug.

Is this in 2.5.75, or -mm?

(I just compiled vanilla 2.5.75, and I have a reiserfs root partition, so
I'd like to know it I need to patch and recompile)

> 
> --- 25/fs/reiserfs/tail_conversion.c~reiserfs-dirty-memory-fix	2003-07-10 22:22:54.000000000 -0700
> +++ 25-akpm/fs/reiserfs/tail_conversion.c	2003-07-10 22:22:54.000000000 -0700
> @@ -191,7 +191,7 @@ unmap_buffers(struct page *page, loff_t 
>  	bh = next ;
>        } while (bh != head) ;
>        if ( PAGE_SIZE == bh->b_size ) {
> -	ClearPageDirty(page);
> +	clear_page_dirty(page);
>        }
>      }
>    } 
> 
> _
> 
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
> 

Re: Very HIGH File & VM system latencies and system stop responding while extracting big tar archive file.

[Andrew Morton]

Mike Fedyk <mfedyk@matchmail.com> wrote:
>
> > No, this will be the reiserfs bug.
> 
> Is this in 2.5.75, or -mm?

2.5.75 needs the patch.

You are, as always, better off using the latest kernel.  That's 2.5.75 plus
the "gzipped full patch" from
http://www.kernel.org/pub/linux/kernel/v2.5/testing/cset/

It has the reiserfs fix.

Re: Very HIGH File & VM system latencies and system stop responding while extracting big tar archive file.

[Shawn]

On Fri, 2003-07-11 at 13:39, Mike Fedyk wrote:
> > No, this will be the reiserfs bug.
> 
> Is this in 2.5.75, or -mm?
You really should read the patch header... It tells you everything you
need to know.

> > --- 25/fs/reiserfs/tail_conversion.c~reiserfs-dirty-memory-fix	2003-07-10 22:22:54.000000000 -0700
> > +++ 25-akpm/fs/reiserfs/tail_conversion.c	2003-07-10 22:22:54.000000000 -0700
> > @@ -191,7 +191,7 @@ unmap_buffers(struct page *page, loff_t 
> >  	bh = next ;
> >        } while (bh != head) ;
> >        if ( PAGE_SIZE == bh->b_size ) {
> > -	ClearPageDirty(page);
> > +	clear_page_dirty(page);
> >        }
> >      }
> >    } 
> > 
> > _
> > 
> > -
> > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> > the body of a message to majordomo@vger.kernel.org
> > More majordomo info at  http://vger.kernel.org/majordomo-info.html
> > Please read the FAQ at  http://www.tux.org/lkml/
> > 
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/