[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2019-04-15 Thread Bug Watch Updater
** Changed in: debian Status: Unknown => New -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1790181 Title: /proc/diskstats shows weird values Status in linux package in Ubuntu:

[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2019-04-15 Thread Yuriy Vidineev
** Bug watch added: Debian Bug tracker #927184 https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=927184 ** Also affects: debian via https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=927184 Importance: Unknown Status: Unknown -- You received this bug notification because you are

[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2019-01-03 Thread nyet
After rebooting, the values are < 2^31 and utilization is reporting fine. I feel this is a 31/32 bit overflow issue. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1790181 Title:

[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2018-11-13 Thread nyet
https://forums.fedoraforum.org/showthread.php?318580-iostat-svctm-and- busy-numbers-are-wrong-for-NVME-drives I think summing wr_ticks and rd_ticks might actually be the right solution. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to

[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2018-11-12 Thread nyet
Here is my patch for munin diskstats: diff -u diskstats-dist diskstats --- diskstats-dist 2018-09-29 16:28:39.933727540 -0700 +++ diskstats 2018-11-12 09:54:56.850815309 -0800 @@ -234,6 +234,9 @@ # a given second, the device is nearly 100% saturated. my $utilization = $tot_ticks

[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2018-11-11 Thread nyet
iostat is showing the same thing btw. See also https://access.redhat.com/solutions/1462993 -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1790181 Title: /proc/diskstats shows weird

[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2018-11-11 Thread nyet
https://www.redhat.com/archives/dm-devel/2015-June/msg00042.html https://www.redhat.com/archives/dm-devel/2015-June/msg00057.html Something is really really screwy here. Some stats are in ns, some are in ms: Index: linux-4.1-rc7/Documentation/device-mapper/statistics.txt

[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2018-11-11 Thread nyet
drivers/md/dm-stats.c: static void dm_stat_round(struct dm_stat *s, struct dm_stat_shared *shared, struct dm_stat_percpu *p) { /* * This is racy, but so is part_round_stats_single. */ unsigned long long now, difference; unsigned

[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2018-11-11 Thread nyet
It looks like partitions are being reported correctly, just not the main device $ cat /proc/diskstats | awk '{print $3, $7, $11, $7+$11, $13, $14}' | grep nvme nvme0n1 22988 457568 480556 2440737408 2441207708 nvme0n1p1 22988 339624 362612 528884 978496 nvme0n1p2 0 0 0 0 0 nvme0n1p5 0 0 0 4 4

[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2018-09-18 Thread Jens Peter
On my laptop with a SATA ssd I also have higher reported times than process real time, albeit not by such a huge margin. Only a factor of 2-4 too high. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu.

[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2018-09-18 Thread Jens Peter
Testing with http://kernel.ubuntu.com/~kernel-ppa/mainline/v4.19-rc2/ shows: Writes on the sd card are still reported about a factor 1000 too high, e.g. 2700ms = 27000s where I expect around 27s. I tried on an nvme ssd with the same result, just smaller numbers and /dev/urandom was the

[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2018-09-18 Thread Jens Peter
** Tags added: kernel-bug-exists-upstream -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1790181 Title: /proc/diskstats shows weird values Status in linux package in Ubuntu:

[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2018-09-05 Thread Jens Peter
I noticed the bug only after I installed munin recently. I don't know how long it may have existed before. I will test the mainline kernel as soon as I can but since the machine is used in production and can't be rebooted at will so testing probably be 2 weeks out. Thanks for your reply. --

[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2018-09-05 Thread Joseph Salisbury
Did this issue start happening after an update/upgrade? Was there a prior kernel version where you were not having this particular problem? Would it be possible for you to test the latest upstream kernel? Refer to https://wiki.ubuntu.com/KernelMainlineBuilds . Please test the latest v4.19

[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2018-08-31 Thread Jens Peter
apport information ** Tags added: apport-collected ** Description changed: For one block device on one of my servers munin shows abnormally high latency. When querying /proc/diskstats manually, the device in question shows: 8 32 sdc 973668 361965 64248290 10224376 755130

[Kernel-packages] [Bug 1790181] Re: /proc/diskstats shows weird values

2018-08-31 Thread Jens Peter
** Package changed: munin (Ubuntu) => linux (Ubuntu) -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1790181 Title: /proc/diskstats shows weird values Status in linux package in Ubuntu: