Monitor resource contention with Pressure Stall Information
Memory and I/O
The two other files, memory
and io
, each return two lines. The first line starts with some
; the second with full
. The some
values show the portion of time in which at least one process is stalled, and the full
values show the time in which all non-idle processes are stalled simultaneously. According to the documentation at the Kernel.org site, the full
state means that "…actual CPU cycles are going to waste, and the workload that spends extended time in this state is considered to be thrashing." Listing 3 shows an example of a 2-socket compute node with an AMD EPYC 7551 and a total of 128 threads.
Listing 3
Measuring with memory and io
$ grep -R . /proc/pressure/ /proc/pressure/io:some avg10=0.00 avg60=0.00 avg300=0.00 total=10587199096 /proc/pressure/io:full avg10=0.00 avg60=0.00 avg300=0.00 total=10072568253 /proc/pressure/cpu:some avg10=30.27 avg60=29.97 avg300=18.80 total=1620253162 /proc/pressure/memory:some avg10=0.00 avg60=0.00 avg300=0.00 total=15411 /proc/pressure/memory:full avg10=0.00 avg60=0.00 avg300=0.00 total=12389 $ uptime 07:24:59 up 2 days, 16:15, 1 user, load average: 150.58, 118.00, 76.42
A large full
value in memory
can mean that the system was unable to handle a single runnable process in this time and that the CPU was probably busy paging. The overloaded backup server in Listing 4 illustrates this nicely. In this example, logging onto the system with SSH took more than a minute.
Listing 4
Overloaded Backup Server
$ grep -R . /proc/pressure/ /proc/pressure/io:some avg10=15.60 avg60=11.13 avg300=7.98 total=94192093351 /proc/pressure/io:full avg10=15.60 avg60=11.13 avg300=7.97 total=93713900789 /proc/pressure/cpu:some avg10=0.00 avg60=0.00 avg300=0.00 total=1159442298 /proc/pressure/memory:some avg10=67.79 avg60=67.80 avg300=72.51 total=618948360599 /proc/pressure/memory:full avg10=67.60 avg60=67.58 avg300=72.18 total=613900281165
Polling
The Linux PSI interface lets admins generate triggers by writing them to the files and then reading them with poll()
. Listing 5 breaks down the syntax; the values for the stall amount and the time window are in microseconds.
Listing 5
Polling Syntax
some|full Stall_Amount Time_Window
Listing 6 shows an example of a monitoring program from the Linux documentation [4]. The program defines an event that sends notifications if a process fails to receive RAM resources for more than 150 milliseconds within a one-second time interval. If you name the file, say, psi_example.c
, you can build it easily by typing make psi_example
, assuming you have the build tools in place.
Listing 6
psi_example.c
01 #include <errno.h> 02 #include <fcntl.h> 03 #include <stdio.h> 04 #include <poll.h> 05 #include <string.h> 06 #include <unistd.h> 07 /* 08 * Monitor memory partial stall with 1s tracking 09 * window size and 150ms threshold. 10 */ 11 int main() { 12 const char trig[] = "some 150000 1000000"; 13 struct pollfd fds; 14 int n; 15 fds.fd = open("/proc/pressure/memory", 16 O_RDWR | O_NONBLOCK); 17 if (fds.fd < 0) { 18 printf("/proc/pressure/memory open error: %s\n", 19 strerror(errno)); 20 return 1; 21 } 22 fds.events = POLLPRI; 23 if (write(fds.fd, trig, strlen(trig) + 1) < 0) { 24 printf("/proc/pressure/memory write error: %s\n", 25 strerror(errno)); 26 return 1; 27 } 28 printf("waiting for events...\n"); 29 while (1) { 30 n = poll(&fds, 1, -1); 31 if (n < 0) { 32 printf("poll error: %s\n", strerror(errno)); 33 return 1; 34 } 35 if (fds.revents & POLLERR) { 36 printf("got POLLERR, event source is gone\n"); 37 return 0; 38 } 39 if (fds.revents & POLLPRI) { 40 printf("event triggered!\n"); 41 } else { 42 printf("unknown event received: 0x%x\n", 43 fds.revents); 44 return 1; 45 } 46 } 47 return 0; 48 }
Conclusions
PSIs compressed to only one or two lines inform the admin about resource bottlenecks [5]. The file-based interface makes it easy to integrate scripts and helps to build monitoring systems. Even external system monitoring tools such as Atop already integrate PSI (Figure 2).
Thanks to the integration of PSI in Cgroups, admins receive this information globally for the entire system and in a granular form. PSI provides admins with a powerful alternative to the load average for a better overview of resource bottlenecks.
Infos
- "Solving the Mystery": http://www.brendangregg.com/blog/2017-08-08/linux-load-averages.html
- PSI: https://facebookmicrosites.github.io/psi/
- Weiner's project presentation: https://lkml.org/lkml/2018/8/28/816
- PSI documentation: https://www.kernel.org/doc/html/latest/accounting/psi.html
- Examples of using PSI: https://unixism.net/2019/08/linux-pressure-stall-information-psi-by-example/
« Previous 1 2
Buy this article as PDF
(incl. VAT)
Buy Linux Magazine
Subscribe to our Linux Newsletters
Find Linux and Open Source Jobs
Subscribe to our ADMIN Newsletters
Support Our Work
Linux Magazine content is made possible with support from readers like you. Please consider contributing when you've found an article to be beneficial.
News
-
elementary OS 7.1 Now Available for Download
The team behind elementary OS has released the latest version of its operating system with a focus on personalization, inclusivity, accessibility, and privacy.
-
The GNU Project Celebrates Its 40th Birthday
September 27 marks the 40th anniversary of the GNU Project, and it was celebrated with a hacker meeting in Biel/Bienne, Switzerland.
-
Linux Kernel Reducing Long-Term Support
LTS support for the Linux kernel is about to undergo some serious changes that will have a considerable impact on the future.
-
Fedora 39 Beta Now Available for Testing
For fans and users of Fedora Linux, the first beta of release 39 is now available, which is a minor upgrade but does include GNOME 45.
-
Fedora Linux 40 to Drop X11 for KDE Plasma
When Fedora 40 arrives in 2024, there will be a few big changes coming, especially for the KDE Plasma option.
-
Real-Time Ubuntu Available in AWS Marketplace
Anyone looking for a Linux distribution for real-time processing could do a whole lot worse than Real-Time Ubuntu.
-
KSMBD Finally Reaches a Stable State
For those who've been looking forward to the first release of KSMBD, after two years it's no longer considered experimental.
-
Nitrux 3.0.0 Has Been Released
The latest version of Nitrux brings plenty of innovation and fresh apps to the table.
-
Linux From Scratch 12.0 Now Available
If you're looking to roll your own Linux distribution, the latest version of Linux From Scratch is now available with plenty of updates.
-
Linux Kernel 6.5 Has Been Released
The newest Linux kernel, version 6.5, now includes initial support for two very exciting features.