similar to: Periodic lockup problem with ext3

I'm lacking some understanding of how to tune / when to tune /proc/sys/vm/bdflush Where can I read up on this? Our current problem: Load is low, but ever so often the system decides to do some serious disk I/O which causes all processes to wait for disk I/O -- load explodes (rises linear up into the 20-30ies) just to fall linearly (spelling?) right after that. We think there might be some

Hi! Today I switched over to devfs. I'm on Debian unstable, installed devfsd, installed a kernel with devfs support and "devfs mount on boot". Reboot, devfs is being used. All over a sudden, dmesg reports: Linux version 2.4.21-ac1 (root@hummus) (gcc version 3.3 (Debian)) #1 Sun Jun 15 19:06:13 CEST 2003 ... kjournald starting. Commit interval 5 seconds EXT3-fs: mounted

Hi! I keep getting errors like these: oplock_break failed for file Word/einaikoon/v-Locator/IBB-Beantragung/0_Antrag_AZK.doc (dev = 301, inode = 2469218, file_id = 7). [2003/07/31 15:43:22, 0] smbd/oplock.c:oplock_break(843) oplock_break: client failure in break - shutting down this smbd. [2003/07/31 15:47:12, 0] smbd/oplock.c:oplock_break(758) oplock_break: receive_smb error (Success)

Right now I'm building a 2.4.17 kernel on an HPPA Linux system. The kernel it ships with supports ext2 only. Has anybody tried ext3 on HPPA? -- Ralf Hildebrandt (Im Auftrag des Referat V A) Ralf.Hildebrandt@charite.de Charite Campus Virchow-Klinikum Tel. +49 (0)30-450 570-155 Referat V A - Kommunikationsnetze - Fax. +49 (0)30-450 570-916 "A man who

Just out of curiosity: Is htree in 2.6.0-test11 ? -- Ralf Hildebrandt (Im Auftrag des Referat V a) Ralf.Hildebrandt@charite.de Charite - Universitätsmedizin Berlin Tel. +49 (0)30-450 570-155 Gemeinsame Einrichtung von FU- und HU-Berlin Fax. +49 (0)30-450 570-916 Referat V a - Kommunikationsnetze - AIM. ralfpostfix

Since I ain't got a better place to report this, I do it here: Kernel 2.4.20-ac1 # uptime 16:31:00 up 2 days, 22:10, 7 users, load average: 1.89, 2.20, 2.99 This is our main mailbox server. We're running ext3: # cat /proc/mounts rootfs / rootfs rw 0 0 /dev/root / ext3 rw 0 0 /proc /proc proc rw 0 0 /dev/sdb5 /boot ext3 rw 0 0 /dev/sda6 /home ext3 rw,noatime,nosuid 0 0 /dev/sdb8 /tmp

We have been using ext3 for our Maildir message store for the better part of a year now. I saw Stephen mention fragmentation and wondered if we might be affected from this as well. How can I find out how fragmented our message store is? -- Ralf Hildebrandt (Im Auftrag des Referat V A) Ralf.Hildebrandt@charite.de Charite Campus Virchow-Klinikum Tel. +49 (0)30-450 570-155

On my Debian box: Package: lilo Version: 1:22.2-5 Severity: normal lilo seems to cause a kernel warning (see subject) when / is a ext3 partition. Maybe a kernel problem? Who knows. I'm running 2.4.19-rc1-ac7 -- System Information: Debian Release: testing/unstable Architecture: i386 Kernel: Linux hummus 2.4.19-rc1-ac7 #1 Wed Jul 17 22:14:20 CEST 2002 i686 Locale: LANG=C, LC_CTYPE=C Versions

Hi! I'm investigating the maximum DB size of mySQL on ext3 with a 2.4 kernel. * mysql is supposed to support tables up to 2^63 bytes * kernel-2.4.x supports files up to a size of 16 TB But what about the filesystem? What are the limits for the local filesystem (ext2, ext3, ReiserFS and XFS) ? -- Ralf Hildebrandt (Im Auftrag des Referat V A) Ralf.Hildebrandt@charite.de Charite Campus

The ext3-2.4-0.9.17-2418p3 patch applies with 0 fuzz against both 2.4.18 pre 4 and 2.4.18 pre3-ac2. Will it be included into 2.4.18 pre 5? -- Ralf Hildebrandt (Im Auftrag des Referat V A) Ralf.Hildebrandt@charite.de Charite Campus Virchow-Klinikum Tel. +49 (0)30-450 570-155 Referat V A - Kommunikationsnetze - Fax. +49 (0)30-450 570-916 "Debugging is

Hi! We're using 2.4.15-pre5 on our Postfix mailserver. /etc/fstab: LABEL=/var /var auto data=journal 1 2 LABEL=/home /home auto exec,dev,nosuid,rw 1 2 Recently, we got the following entries in our /var/log/messages: Dec 1 00:42:05 postamt1 kernel: invalidate: busy buffer Dec 1 00:42:05 postamt1 last message repeated 329 times

On a 2.4.15-pre5 system with a 3ware-Escalade-68000 IDE RAID (mode 1) we had the follwing "dmesg" output today: EXT3-fs error (device sd(8,38)): ext3_free_blocks: Freeing blocks in system zones - Block = 16, count = 1 EXT3-fs error (device sd(8,38)): ext3_free_blocks: bit already cleared for block 1052672 EXT3-fs error (device sd(8,38)): ext3_free_blocks: Freeing blocks not in datazone

How do I increase the journal size of a partition? -- Ralf Hildebrandt (Im Auftrag des Referat V A) Ralf.Hildebrandt@charite.de Charite Campus Virchow-Klinikum Tel. +49 (0)30-450 570-155 Referat V A - Kommunikationsnetze - Fax. +49 (0)30-450 570-916 The Imperial Vendor or Contractor probably told them that droid armies don't need redundant command centers, nor

Please have a look at this http://www.net.oregonstate.edu/~kveton/fs/ While I'm not doubting the numbers per se, I fail to see how the lines: ext3 w/ noatime and ext3 w/ noatime,data=ordered can actually be different. According to the docs, the default mode IS data=ordered! -- Ralf Hildebrandt (Im Auftrag des Referat V A) Ralf.Hildebrandt@charite.de Charite Campus Virchow-Klinikum

There's a big thread about filesystems on postfix-users@postfix.org Could you shed some light on that issue? ----- Forwarded message from Wietse Venema <wietse@porcupine.org> ----- From: wietse@porcupine.org (Wietse Venema) Date: Sun, 3 Feb 2002 07:53:26 -0500 (EST) To: Lawrence Greenfield <leg+@andrew.cmu.edu> Cc: Wietse Venema <wietse@porcupine.org>,

Hi! Is it possible to merge two ext3/ext2 partitions into ONE ext3/ext2 partition? -- Ralf Hildebrandt (Im Auftrag des Referat V a) Ralf.Hildebrandt at charite.de Charite - Universit?tsmedizin Berlin Tel. +49 (0)30-450 570-155 Gemeinsame Einrichtung von FU- und HU-Berlin Fax. +49 (0)30-450 570-916 IT-Zentrum Standort Campus Mitte AIM. ralfpostfix

Which disk is it? /dev/sda6 or /dev/sdb8 or /dev/sdc6? >From my log: Jun 10 21:25:39 postamt1 kernel: attempt to access beyond end of device Jun 10 21:25:39 postamt1 kernel: 08:06: rw=0, want=1680353324, limit=59954548 Jun 10 21:25:39 postamt1 kernel: EXT3-fs error (device sd(8,6)): ext3_readdir: directory #3473659 contains a hole at offset 1852399616 $ mount /dev/sdb6 on / type auto (rw)

Hello, I converted one of my servers to ext3 and load average numbers went up. Now they are ~2-3 while on ext2 LA was <0.4. And I'm constantly seeing processes and kjournald in D state. vmstat confirms that. But even in such LA CPUs are ~99% idle. What can be wrong? RedHat 7.1 kernel 2.4.18-18.7.xsmp. SCSI cards: Compaq RAID array controller (cciss) and Q Logic ISP1020 (isp_mod).

There's a new set of ext2/3 patches for 2.4.21-pre5 available at: http://thunk.org/tytso/linux/extfs-2.4-update/extfs-update-2.4.21pre5-2 and in broken out form at: http://thunk.org/tytso/linux/extfs-2.4-update/broken-out-2.4.21pre5-2 New to this patch set include: * A kludge to help htree work well with Linux's NFS implementation * Allow the orlov allocator to be disabled via a

Just looking through the 2.4.20pre changelogs, I see there's been a bunch of Ext3 patches since 2.4.19. I'm keen to take advantage of any bug fixes and performance improvements, but am nervous about using 2.4.20 until it's completed its release cycle. Is there any way to get a patch just containing the Ext3 changes? Are there any changes since 2.4.20 that are very important, either