similar to: Linux performance bug: fsync() for files with zero links

Hello, We found that fsync and fdatasync syscalls sometimes don't sync data in an ext3 file system under the following conditions. 1. Kernel version is 2.6.6 or later (including 2.6.8.1 and 2.6.9-rc2). 2. Ext3's journalling mode is "data=journal". 3. Create a file (whose size is 1Mbytes) and execute umount/mount. 4. lseek to a random position within the file, write 8192 bytes

Well, also below in dmesg: [ 190.249219] usb 3-1.3: usbfs: USBDEVFS_CONTROL failed cmd blazer_usb rqt 33 rq 9 len 8 ret -110 26.11.2014, 03:05, "Victor Porton" <porton at narod.ru>: > A fragment of dmesg output (here idVendor=0665, idProduct=5161 is the UPS; the webcam is idVendor=17a1, idProduct=0128): > > [ ???1.317085] usb 4-1: new high-speed USB device number 2

On Nov 25, 2014, at 8:17 PM, Victor Porton <porton at narod.ru> wrote: > Well, also below in dmesg: > > [ 190.249219] usb 3-1.3: usbfs: USBDEVFS_CONTROL failed cmd blazer_usb rqt 33 rq 9 len 8 ret -110 -110 is -ETIMEDOUT. > 26.11.2014, 03:05, "Victor Porton" <porton at narod.ru>: >> A fragment of dmesg output (here idVendor=0665, idProduct=5161 is the

01.12.2014, 14:50, "Charles Lepple" <clepple at gmail.com>: > On Dec 1, 2014, at 4:11 AM, Victor Porton <porton at narod.ru> wrote: >> ?battery.voltage: 13.70 >> ?battery.voltage.high: 13.00 >> ?battery.voltage.low: 10.40 > > These are the voltage thresholds for the UPS, so theoretically the UPS will send the LB signal when the battery voltage goes

01.12.2014, 16:27, "Charles Lepple" <clepple at gmail.com>: > On Dec 1, 2014, at 9:19 AM, Victor Porton <porton at narod.ru> wrote: >> ?01.12.2014, 14:50, "Charles Lepple" <clepple at gmail.com>: >>> ?Does "upsrw -l advice" show anything? >> ?$ upsrw -l advice >> ?upsrw: invalid option -- 'l' > > I suppose

A fragment of dmesg output (here idVendor=0665, idProduct=5161 is the UPS; the webcam is idVendor=17a1, idProduct=0128): [ 1.317085] usb 4-1: new high-speed USB device number 2 using ehci-pci [ 1.405223] tsc: Refined TSC clocksource calibration: 3395.557 MHz [ 1.405228] Switching to clocksource tsc [ 1.449642] usb 4-1: New USB device found, idVendor=8087, idProduct=0024 [ 1.449648]

01.12.2014, 06:18, "Charles Lepple" <clepple at gmail.com>: > On Nov 29, 2014, at 7:32 AM, Victor Porton <porton at narod.ru> wrote: >> ?On Debian Linux jessie: >> >> ?After buying an UPS and installation of nut-server and nut-client at my PC and configuring the ports and the protocol, do I need to adjust time and/or percentage parameters, to be sure my

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

My application always needs to sync file data after writing. I don't want anything handing around in the kernel buffers. I am wondering what is the best method to accomplish this. 1. Do I use EXT2 and use fdatasync() or fsync()? 2. Do I use EXT2 and mount with the "sync" option? 3. Do I use EXT2 and use the O_DIRECT flag on open()? 4. Do I use EXT3 in full journaled mode,

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

On Dec 1, 2014, at 4:11 AM, Victor Porton <porton at narod.ru> wrote: > battery.voltage: 13.70 > battery.voltage.high: 13.00 > battery.voltage.low: 10.40 These are the voltage thresholds for the UPS, so theoretically the UPS will send the LB signal when the battery voltage goes lower than 10.40 Volts. Also, if battery.charge works, you can use "ignorelb" if you want to

On Dec 1, 2014, at 9:19 AM, Victor Porton <porton at narod.ru> wrote: > 01.12.2014, 14:50, "Charles Lepple" <clepple at gmail.com>: >> Does "upsrw -l advice" show anything? > > $ upsrw -l advice > upsrw: invalid option -- 'l' I suppose I should read the documentation every once in a while :-) "upsrw advice" I was thinking of

On Nov 29, 2014, at 7:32 AM, Victor Porton <porton at narod.ru> wrote: > On Debian Linux jessie: > > After buying an UPS and installation of nut-server and nut-client at my PC and configuring the ports and the protocol, do I need to adjust time and/or percentage parameters, to be sure my computer will be turned off automatically after a reasonable time after failing electricity?

On Debian Linux jessie: After buying an UPS and installation of nut-server and nut-client at my PC and configuring the ports and the protocol, do I need to adjust time and/or percentage parameters, to be sure my computer will be turned off automatically after a reasonable time after failing electricity? My UPS is Advice PRS850. If I need to adjust the parameters, please explain the details. --

I use Debian jessie with nut-server 2.7.2-1+b3. Yesterday I've configured it for my new Advice PRS850 (a UPS with USB interface). I also have an USB webcam (and also USB mouse and keyboard, but that doesn't matter). When I start the program Cheese (a program which uses the webcam), I receive the following broadcast message: "Communications with UPS advice at localhost lost"

I've just updated from 1.0.14 to 1.1.1 (Maildirs). According to <URL:http://wiki.dovecot.org/Upgrading/1.1>, "dovecot-uidlist file is in a new format. The old format is automatically converted to new one." When I try to delete a message (which moves it to the IMAP Trash folder), I get the following looping sequence of errors until I cancel the delete operation in the mail

Hi, I can't tell the reason and conditions to repeat this bug... "ls" and "ls $PWD" produce different directory listing (of different times, so a subdir is existing in one listing and missing in an other). ls . $PWD Linux 2.6.15.6 GNU bash, version 2.05b.0(1)-release (i386-pc-linux-gnu) Linux 2.6.15.6 PREEMPT i686 /dev/hda5 on / type ext3

Hi, I have a question on fsync() and ext3's journaling modes. Assume that I call fsync(fd) on a file. If that file is in 'data=journal' mode, would the fsync() return once the data gets safely into the journal ? On the other hand, if that file is in 'data=writeback' mode, would the fsync() return only when the data gets safely into its actual location ? Any help is

Hi all, I'm using dovecot since a few months and it works great. But a few days ago some coworkers mentioned that they got errormessages in their Mailapp. I searched in the logfiles and found this: Sep 14 12:07:35 Mailserv dovecot: IMAP(eckhard-ma-domain-com): fsync(/home/eckhard-ma-domain-com/mails/.INBOX.0002-Druckangebote von Druckereien.0002-schmerk

In order to improve the performance of fsync, we use the outstanding ordered extents to avoid looking up the checksum from the csum tree. But we didn''t filter out the ordered extents whose csum is still being calculated, when we got those ordered extents, we had to wait for the csum calculation. It made the performance dropped down suddenly. (On my box, it drop down from 56MB/s to