similar to: [PATCH] btrfs: fix write_dev_supers

Hello. I found bugs on error handlings in the functions arround the ext3 file system, which cause inadequate completions of synchronous write I/O operations when disk I/O failures occur. Both 2.4 and 2.6 have this problem. I carried out following experiment: 1. Mount a ext3 file system on a SCSI disk with ordered mode. 2. Open a file on the file system with O_SYNC|O_RDWR|O_TRUNC|O_CREAT

Hi Chris. I think it is needed to call mark_inode_dirty() when file size expands in order to flush metadata updates to HDD through sync() syscall or background_writeout(). Thanks. Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> diff -Nrup linux-2.6.29-rc3.org/fs/btrfs/file.c linux-2.6.29-rc3/fs/btrfs/file.c --- linux-2.6.29-rc3.org/fs/btrfs/file.c 2009-02-02

Hi. In ocfs2, fdatasync and fsync are identical. I think fdatasync should skip committing transaction when inode->i_state is set just I_DIRTY_SYNC and this indicates only atime or/and mtime updates. Following patch improves fdatasync throughput. #sysbench --num-threads=16 --max-requests=300000 --test=fileio --file-block-size=4K --file-total-size=16G --file-test-mode=rndwr

Hi. I introduced "is_partially_uptodate" aops for OCFS2. A page can have multiple buffers and even if a page is not uptodate, some buffers can be uptodate on pagesize != blocksize environment. This aops checks that all buffers which correspond to a part of a file that we want to read are uptodate. If so, we do not have to issue actual read IO to HDD even if a page is not uptodate

Hi. In btrfs, fdatasync and fsync are identical. I think fdatasync should skip committing transaction when inode->i_state is set just I_DIRTY_SYNC and this indicates only atime or/and mtime updates. Following patch improves fdatasync throughput. #sysbench --num-threads=16 --max-requests=10000 --test=fileio --file-block-size=4K --file-total-size=16G --file-test-mode=rndwr

All, Please review the patches backported to 1.4 from mainline. Sunil

Currently, some new storage devices have the ability to do performance optimizations according to the type of data payload - say, file system metadata, time-stamps, sequential write in some granularity, random write and so on. For example, the latest eMMC 4.5 device can support the so-called ''Context Management'' and ''Data Tag Mechanism'' features. By receiving

Linus, et al, Here are the ocfs2 updates for 2.6.31. It's a quiet cycle, almost completely composed of fixes. There is a nice performance improvement from Hisashi Hifumi for fdatasync. Please pull. Joel The following changes since commit b4348f32dae3cb6eb4bc21c7ed8f76c0b11e9d6a: Linus Torvalds (1): Merge branch 'for-linus' of git://oss.sgi.com/xfs/xfs are available in

Hello Get this on first write made ( by deliver sending mail to inform of the restart of services ) Home partition (the one receiving the mail) is based on ocfs2 created from drbd block device in primary/primary mode These drbd devices are based on lvm. system is running linux-3.5.0, identical symptom with linux 3.3 and 3.2 but working with linux 3.0 kernel reproduced on two machines ( so

John R Pierce wrote: > On 10/7/2015 1:30 PM, m.roth at 5-cent.us wrote: >> No. I'm the one who got the quote and set up the order for my managers, >> and I know what it's got: the ethernet connection is to the internal >> webserver to manage the RAID. the 712S I have is dual-path SAS for data. > > then yeah, you'll need a plain SAS2 external HBA card. If

Hi All, I inherited a 4-node ocfs2 cluster and recently 2 ocfs2 filesystems were added to be use as temp tablespace.?One of the four nodes rebooted during the ?creation of the tablespace and hanged at the message below...and it just sits there. If I put the server into rescue mode and comment out all the filesystems it boots up fine and than I can mount the ocfs2 filesystem manuelly but it cannot

Dear all... Currently I am having 5 RAC nodes with Configurations as below : 1. HW = DL580 32 Bit Processor 2. OS = RHAS 2.1 3. OCFS= Latest Version 4. RAC= Oracle9i 9.2.0.5 (32 Bit) Now I am planning to add 2 more Rac Nodes in the existing RAC: 1. HW=Itanium 64 bit processor 2. OS=RHAS 3.0 3. OCFS=Latest Version 4. RAC=Oracle9i 9.2.0.5 (32 bit) Can I

I setup a CentOS 6 server to use with KVM/QEMU, and I am getting the following error a good bit, granted it doesn't seem to be causing any trouble. I figured I would post and see if anyone has any ideas on the issue, or if I can just dismiss it. If I look at my logging/dmesg, I see: do_IRQ: 19.217 No irq handler for vector (irq -1) do_IRQ: 3.178 No irq handler for vector (irq -1) do_IRQ:

Hi, folks, Since I've gotten a total of one response in days on the HP forum, maybe the collective mind here has an answer.... As I've mentioned in other posts, we have an HP dl580 g5 that started throwing ECC errors. But wait, it's worse: memory is mirrored.... And the thing is fully populated with 32 DIMMs. I took my best guess, pulled the matching set of DIMMs, and took two

I''ve installed facter-1.6.0 and puppet-2.7.3 on a number of SLES 10 hardware nodes (HP DL580) running the Virtuozzo hosting software. Well, facter correctly identifies such a machine as a hardware node ("virtual => openvzhn") but somehow concludes that the hardware node is in fact virtual. ("is_virtual => true") This breaks some rather important logic. If

Running CentOS 6.7, on an older HP DL580 G5. We've got a Dell 12-bay RAID box plugged into a PERC H800 (aka LSI Liberator) that we put in the HP, and that works fine. We've got a new RAID (a JetStor), and are trying to plug it in. The layout is that the Dell RAID is dual-pathed DAS. Each PERC has two DAS ports. We've got the Dell RAID in the top port of each PERC. I *thought* I could

Hey, folks, I've got an HP Proliant DL580 G5 throwing ECC errors. This is annoying, since a) it's all new as of a few months ago, and b) it's *fully* populated. The two things I need to figure out are a) *which* DIMM it is, and b) is it mirrored; if so, which *other* DIMM needs to come out until we get replacements from the OEM. Here's one of many, all identical, from dmesg:

I am debating installing CentOS on a new HP DL580 with an MSA1000 SAN. HP offers drivers that are specific to RHEL and will not install on other RH distros i.e. RH 9. Has anyone gotten the HP SupportPack to install under CentOS? Thanks! -- This message has been scanned for viruses and dangerous content by MailScanner, and is believed to be clean.

Hi, I have setup an old Compaq Proliant DL580 with 2 xeon @700MHz 2Gb RAM two SmartArray 5300 controllers and 12 drives in an array enclosure. I am running the latest opensolaris update bfu''ed from binaries since I could not build from source. I am controlling the drives with the cpqary3 driver (Solaris 10) from HP. Initially the array had 7 drives and I created a raidz zfs pool

I have a brand new 2T external Samsung SSD disk. (two of them) for backup. I tried the first one and had an issue, I tried the second one and got the same issue. Am I doing something wrong ? I find it hard to believe the SSD (both) are bad. I plugged in the USB 3.1 adapter, I fdisk /dev/sdd, n, p, default, default, w. then mkfs.ext4 -j /dev/sdd1, then just mount and rsync. [ 1085.193710]