search for: intermezzo

Hi Stephen, We had some starvation/locks happening to us under very heavy load in two cases: - InterMezzo asked ext3 to do a journaled file write (for 1 block) essentially using ext3_write - similarly for truncate. These lockups went away when we started the transaction in InterMezzo and reserved somewhat more space than ext3 does. Any clues as to what this might be? Are the ext3 reservations bi...

Hi, We have encountered another funny with ext3 on 2.4. Like the kernel NFS server, we have a routine in InterMezzo that does something like looking up an inode by inode number. (compare intermezzo's presto_ilookup or knfsd's nfsfh_iget) Effectively both of these routines do ilookup() { inode = iget(sb, ino) if (inode->i_nlink==0) iput(inode); .... } We find that this oopses if the...

Hi Alan, Would you be opposed to including an InterMezzo patch for the ac series soon? It doesn't touch anything outside of its fs directory. It would probably help us get a few more users and fits nicely with ext3 being in ac now. We are also quite far along Reiser support for InterMezzo. Please let me know your thoughts on this. Thanks! - Pe...

...used it for quite a while. Then I learned about CentOS...and switched to it for my server needs. I have switched to CentOS4 and it is an awsome stable operating system. I just wanted to add my praise before I asked my question. I need a network based distributed operating system, something like Intermezzo or Coda to keep two servers in sync on one partition. I have a server at work and at home that I want to keep a MyDocuments partition in sync. NFS will not work because I need a offline or online solution. RSYNC will not work, who many inconsistancies from files being created and removed. Will...

Hi, While doing some stress testing with presto module from the intermezzo project layered over ext3, I got the following assertion failure: Jan 17 23:09:55 planck kernel: Assertion failure in jfs_prelock_buffer_check() at journal.c line 410: "bh->b_jlist == 0 || bh->b_jlist == BJ_LogCtl || bh->b_jlist == BJ_IO || bh->b_jlist == BJ_Data" Jan 17 23:0...

...ect " Instruction > Scheduler for Nouveau" caught my eye. I'm learning about Operating Systems > for 8 months in academics course and udacity linux and operating system > courses, and thus the idea seems interesting. Also, I’ve been working on a > Rust based file-system in intermezzOS project and applied to GSoC under > intermezzOS, which is an OS built using rust. Since it wasn’t completely a > Mozilla project proposal but was using rust as a programming language, > Mozilla took the proposal but didn’t have sufficient slots for a non-Mozilla > project during GSoC....

I need to maintain a log that contains information on files that are read / modified . I was suggested losf, but using lsof does not solve the problem as files opened/closed between two successive runs will always be missed. With reference to the stated need I have 2 Questions. 1) can data in the journal file be of any help to me ? if yes how, ? 2) can kjournald be used in some way ?

Hi, I have a detailed question about ordered data writes. Suppose we (i.e. intermezzo) does a transaction, which is closed and then followed by an ordered write. Let's assume the ordered write doesn't require new allocation metadata. Is the write still postponed until the first transaction has committed? As far as I can see, prepare_write always starts a transaction, b...

Lo, Actualy i'm looking for documents about journalised file system, in order to be able to compare them self. I need accurate information if i want to make a good study. Thoses informations have to permit me to get answer about table like this : Features \ fs | xfs | ext3 | jfs | reiserfs | ------------------------------------------------- chattr | ? | Y | ? | ?

Im intending use Ext3 file system in my web farm. Im using RedHat 6.2 (kernel 2.2.16-3) and Turbo Linux Cluster Server 6.0. I have NO SUCCESS in path my own kernel. I downloaded the following ext3 packages: ext3-0.0.2f.tar.gz (linux-2.2.16-3.kdb.diff , linux-2.2.16-3.ext3.diff ) e2fsprogs-1.20-0.WIP.i386.rpm e2fsprogs-1.20-0.WIP.src.rpm e2fsprogs-1.20-0ext3.i386.rpm

...issues: No ACLs, When NFS server goes down, everything fails. What method would you recommend for replicating folders, keeping existing ACLs (ability of manipulating that ACLs from Windows is not important) between Samba PDC-BDCs: - -Rsync+FAM based scripts or - -Distributed filesystems: -Coda -Intermezzo etc. Thank you for ANY answer. Geza -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.3 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org iD8DBQFALiLR/PxuIn+i1pIRAiYpAJ48q99ChLiScSte4VSYFT02BvWuMQCgi2mz DsD5cBSfPG+PFHLxS0pw8/s= =NcB6 -----END PGP SIGNATURE-----

...ync support to BackupPC. I am implementing the server-side in perl, and the client will run vanilla rsync. (BTW, is there the protocol documented? I've answered all my questions by looking at the source, but it would be great to check against any docs.) I started with librsync 0.9.3 and the Intermezzo perl interface to librsync written by Shirish Phatak. However, as I'm sure is well-known, the Adler crc32 and MD4 computed by librsync don't match those in rsync 2.5.5. After swapping the crc32 endianess, changing RS_CHAR_OFFSET from 31 to 0, and adding rsync's checksum_seed to librsy...

Hi, A system running ext3 crashed this afternoon (nothing to do with ext3, bad network driver). Is was saving a file from emacs when it happened. The file system is 0.06b and had ordered data as the mount option. Let me emphasize this was running ext3 pure, not with SnapFS or InterMezzo layered on top of it. strace reveals that Emacs does open("existing file name", O_TRUNC | O_CREAT | O_RDWR) and then writes the data out. When coming back up the file had a 4k block of zeroes in the middle. This seems somewhat suspicious, but it's likely that I'm not understan...

While investigating erratic performance on one our our servers, I'm getting some very odd performance stats coming from vmstat. What initially appeared to be happening is the machine goes into a hard loop in some mod_perl webserver code. Now there still may be an issue with the code, but my code examinations show no possible way this could be happening, but what I'm writing to you

Hi list, I recently came up with the need for the storage, shared between two nodes; one would do all the r/w to it and the other would mount it r/o and serve it to the client boxen. I want to use ext3 in this setup, since i trust it the most. My question is: is this possible? How would the r/o node handle the metadata updates that the r/w node would be doing? If there is some fundamental

Hi Jason, > Are there any Linux users out there using the likes of > RAID'ed-NBD, CODA or > Intermezzo for a similar effect? > The NBD (network block device) looks interesting, it allows > you to mount a remote raw partition - so you can effectively > RAID over the network. I'd recomend drbd over a nbd + raid solution: * drbd knows to read from local device only so performance is g...

hi all. just wondering if anyone has setup a samba cluster for speed/failover/redundency ? i'd love to hear from you... thanks -ipguy

On 24 Apr 2002, "Shirish H. Phatak" <shirish@tacitnetworks.com> wrote: > Since there appears to be a dedicated group of users and lots of > activity, maybe we can convince Martin to roll in these patches and make > a new release? I have been really lax in supporting librsync for the last few months, because of a new job and taking over maintenance of rsync

I've lurked on this list for a long time, and have learned many details on installing and using Ext3. Thanks! I'm finally posting to solicit feedback on my recently-published book on "Linux Filesystems". This book discusses the use, theory, and installation/integration of journaling and distributed filesystems on Linux, and also discusses what I call 'filesystem adapters'

...If anyone can reproduce this, please send me your .config, details of mountpoints, filesystem sizes, system config, shoe size, Mother's maiden name, etc. Thanks. - Two reports of an assertion failure in journal_revoke() - where the block was already revoked. One report was from the intermezzo developers who were using `chattr +J' to enable data journalling on just part of a filesystem (I really haven't been testing this feature at all). The other reporter had never used `chattr +J'. We can make this go away by clearing the revoke bits when refiling buffers for ch...