similar to: [PATCH 1/1] fails ocfs2_get_block() immediately when hit -EIO

Hi everbody this is my first post, I have two test server .(Both of them is idle) db1 : RHEL4 OCFS2 db2 : RHEL3 OCFS I test the IO both of them The result is below. db1(Time Spend)db2(Time Spend)OS Test Command dd (1GB) (Yazma)0m0.796s0m18.420stime dd if=/dev/zero of=./sill.t bs=1M count=1000 dd (1GB) (Okuma)0m0.241s8m16.406stime dd of=/dev/zero if=./sill.t bs=1M count=1000 cp

Hi everbody this is my first post, I have two test server .(Both of them is idle) db1 : RHEL4 OCFS2 db2 : RHEL3 OCFS I test the IO both of them The result is below. db1(Time Spend)db2(Time Spend)OS Test Command dd (1GB) (Yazma)0m0.796s0m18.420stime dd if=/dev/zero of=./sill.t bs=1M count=1000 dd (1GB) (Okuma)0m0.241s8m16.406stime dd of=/dev/zero if=./sill.t bs=1M count=1000 cp

I created an account on the Forums this morning, but I got an error saying they were having a problem sending e-mail. I sent a message to the webmaster and no response either. So I can't post to the forum until my account is activated. Are the forums new? By the amount of traffic on the list, this must be where most people resolved their problems. I am thinkgng about installing CentOS 4 on my

/an ocfs2 bug: a truncate races with ocfs2_get_block(...,0). 1) 'dd' is doing a truncate, clearing the page cache and reset inode size./ /2) between clearing page cache and resizing inode, a read comes and create a / /new page and insert it to page cache./ /3) the read(from `cat`) set buffer head in the new page as mapped but doesn't increase / /ip_mmu_private in ocfs2_get_block()

use i_size_read() instead of accessing inode->i_size directly. Signed-off-by: Wengang Wang <wen.gang.wang at oracle.com> -- diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index b2c52b3..4491851 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -1920,7 +1920,7 @@ int ocfs2_write_end_nolock(struct address_space *mapping, out_write_size: pos += copied; - if (pos >

ocfs2 will become read-only if we try to read the bytes which pass the end of i_size. This can be easily reproduced by following steps: 1. mkfs a ocfs2 volume with bs=4k cs=4k and nosparse. 2. create a small file(say less than 100 bytes) and we will create the file which is allocated 1 cluster. 3. read 8196 bytes from the kernel using O_DIRECT which exceeds the limit. 4. The ocfs2 volume

Signed-off-by: Wengang Wang <wen.gang.wang at oracle.com> --- fs/ocfs2/aops.c | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index b730010..a10c989 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -1397,7 +1397,7 @@ static int ocfs2_write_cluster(struct address_space *mapping, if (tmpret) { mlog_errno(tmpret); if

>From c70adcaca99acf93bc00cf2edc4d549b83e2f95d Mon Sep 17 00:00:00 2001 From: Wengang Wang <wen.gang.wang at oracle.com> Date: Tue, 21 Jul 2009 10:52:52 +0800 Subject: [PATCH 1/1] ocfs2: adds mlogs to aops.c -V2 this patch adds some mlogs to apos.c helping tracing and narrowing down bugs. Signed-off-by: Wengang Wang <wen.gang.wang at oracle.com> --- fs/ocfs2/aops.c | 242

this patch adds mlogs to apos to help tracing. Signed-off-by: Wengang Wang <wen.gang.wang at oracle.com> --- fs/ocfs2/aops.c | 233 ++++++++++++++++++++++++++++++++++++++++++++----------- 1 files changed, 189 insertions(+), 44 deletions(-) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index b2c52b3..b730010 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -90,7 +90,7 @@ static int

Linus, et al, Here are all the outstanding ocfs2 fixes for 2.6.31. The major fixes are for aio write and for non-sparse file extending. There are also a couple of b-tree fixes as well as some for quotas. Please pull. Joel The following changes since commit 44b572809581d5a10dbe35aa6bf689f32b9c5ad6: Yinghai Lu (1): x86: don't clear nodes_states[N_NORMAL_MEMORY] when numa is not

this patch adds some mlogs to apos.c helping tracing and narrowing down bugs. Signed-off-by: Wengang Wang <wen.gang.wang at oracle.com> --- fs/ocfs2/aops.c | 242 +++++++++++++++++++++++++++++++++++++++++++++---------- 1 files changed, 198 insertions(+), 44 deletions(-) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index b2c52b3..4527f16 100644 --- a/fs/ocfs2/aops.c +++

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA512 hi, on OS X, when you try and use something which depends on X11, and you don't have XQuartz installed, you receive an error message, it directs you to download XQuartz, and then it euthanizes your process. (my guess is that there is a skeleton X11 dylib installed in OS X by default, and it is responsible for the error message and the

Hi, I did some more in-depth testing of OCFS2 quota code, especially with ECC feature enabled and spotted some problems. First four patches fix them. I need the fifth patch to be able to mount OCFS2 filesystem with 2.6.31-rc3. The sixth patch fixes a potential problem when quota syncing interval is updated while the cluster is running (which is not possible currently). Joel, could you please

This patch logs(ERROR) -EIO errors just when they are hitted. Signed-off-by: Wengang Wang <wen.gang.wang at oracle.com> -- diff -up ./linux-2.6.29.y.build/fs/ocfs2/buffer_head_io.c.orig ./linux-2.6.29.y.build/fs/ocfs2/buffer_head_io.c --- ./linux-2.6.29.y.build/fs/ocfs2/buffer_head_io.c.orig 2009-04-17 13:55:52.000000000 +0800 +++ ./linux-2.6.29.y.build/fs/ocfs2/buffer_head_io.c 2009-04-17

It''s come to our attention, that the time gets screwed up when set between EPOCH and EPOCH + uptime. This may not seem important (because we don''t live in the 70s anymore) but it makes LTP fail. LTP has a date test that checks what happens when set to EPOCH + 100 secs + 100 nsecs, and makes sure that it gets a proper result. The following patches helps xen handle the case

I've got a filesystem-based JBOD setup. During testing, I failed out one of the drives and tried to access the filesystem on it. Here are the results I got: stat /disk succeeds open /disk for reading succeeds readdir (getdents) for /disk fails EIO open /disk/noexist for reading fails ENOENT open /disk/noexist for writing

Enable cpufreq support in Xen for AMD Operton processors by: 1) Allowing the PowerNow! driver in dom0 to write to the PowerNow! MSRs. 2) Adding the cpufreq notifier chain to time-xen.c in dom0. On a frequency change, a platform hypercall is performed to scale the frequency multiplier in the hypervisor. 3) Adding a platform hypercall to the hypervisor the scale the frequency multiplier and reset

hi all, my appl works well but i get the following error suddenly for few pages. to resolve this, i had to restart the server everytime. then it works fine for some time, but after some time it appears again. this is happening contineously. i searched for solution on this, but didn''t get much. can anybody help in this plaese? any help will be greatly appreciated... i''ve pasted

Please pull from 'upstream-linus' branch of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2.git upstream-linus to receive the following updates: fs/ocfs2/aops.c | 20 ++++++++++---------- fs/ocfs2/cluster/masklog.c | 3 +-- 2 files changed, 11 insertions(+), 12 deletions(-) Mark Fasheh: ocfs2: Fix invalid assertion during write on 64k pages Tiger

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