- bullseye 0.18.0+ds-2
- bullseye-backports 0.22.0+ds-2~bpo11+1
- testing 0.25.0+ds-2
- unstable 0.26.0+ds-1
- experimental 0.26.0+ds-2~experimental1
|slabratetop(8)||System Manager's Manual||slabratetop(8)|
slabratetop - Kernel SLAB/SLUB memory cache allocation rate top. Uses Linux BPF/bcc.
slabratetop [-h] [-C] [-r MAXROWS] [interval] [count]
This is top for the the rate of kernel SLAB/SLUB memory allocations. It works by tracing kmem_cache_alloc() calls, a commonly used interface for kernel memory allocation (SLAB or SLUB). It summarizes the rate and total bytes allocated of these calls per interval: the activity. Compare this to slabtop(1), which shows the current static volume of the caches.
This tool uses kernel dynamic tracing of the kmem_cache_alloc() function.
Since this uses BPF, only the root user can use this tool.
CONFIG_BPF and bcc.
- Don't clear the screen.
- -r MAXROWS
- Maximum number of rows to print. Default is 20.
- Interval between updates, seconds.
- Number of interval summaries.
- Summarize active kernel SLAB/SLUB calls (kmem_cache_alloc()), showing the top 20 caches every second:
- # slabratetop
- Don't clear the screen, and top 8 rows only:
- # slabratetop -Cr 8
- 5 second summaries, 10 times only:
- # slabratetop 5 10
If kmem_cache_alloc() is called at a high rate (eg, >100k/second) the overhead of this tool might begin to be measurable. The rate can be seen in the ALLOCS column of the output.
This is from bcc.
Also look in the bcc distribution for a companion _examples.txt file containing example usage, output, and commentary for this tool.
Unstable - in development.