Needed by showmap and also android_s_Debug to classify each allocation
into multiple heaps.
The APIs added are:
ForEachVmaFromFile - Global API to parse a file expected to be in the
same format as /proc/<pid>/smaps and make a callback for each VMA found.
ProcMemInfo::ForEachVma - Same as 'ForEachVmaFromFile' but for a
ProcMemInfo object corresponding to a process(pid).
ProcMemInfo::Smaps - Wrapper to ProcMemInfo::ForEachVma, except the
function collects 'struct Vma' in a member vector and returns the
reference for the same.
Added showmap2 using the APIs and the corresponding tests the same time.
Bug: 111694435
Test: showmap_test.sh
Test: libmeminfo_test 1
Change-Id: I3065809cf94ecf3da88529809701035c47a8ce34
Signed-off-by: Sandeep Patil <sspatil@google.com>
This adds the tests and SmapsRollup() parsing function in
ProcMemInfo. Adds tests to check the return value as well as
the correctness.
Bug: 111694435
Test: libmeminfo_test 1 --gtest_filter=TestProcMemInfo.*
Test: libmeminfo_benchmark --benchmark_filter=BM_SmapsRollup_
Result:
----------------------------------------------------------
Benchmark Time CPU Iterations
----------------------------------------------------------
BM_SmapsRollup_old 4751 ns 4730 ns 149458
BM_SmapsRollup_new 4858 ns 4837 ns 144636
----------------------------------------------------------
Change-Id: Ia051fe53a7622e3091502ff7166efafae35e7935
Signed-off-by: Sandeep Patil <sspatil@google.com>
This is to replace occurrences of get_allocated_vmalloc_memory().
Splitting into libmeminfo already found a bug with current code which
failed to account for memory allocated by modules due to addition of
the extra [%module_name%] in __builtin_return_address().
See: https://elixir.bootlin.com/linux/latest/source/kernel/kallsyms.c#L373
Also improves the performance a bit in the process.
Bug: 119639955
Bug: 111694435
Test: libmeminfo_test 1 --gtest_filter=SysMemInfoParser.TestVmallocInfo
Test: libmeminfo_benchmark --benchmark_filter=BM_VmallocInfo_*
Result:
----------------------------------------------------------------
Benchmark Time CPU Iterations
----------------------------------------------------------------
BM_VmallocInfo_old_fixed 459239 ns 457268 ns 1532
BM_VmallocInfo_new 386032 ns 384353 ns 1821
----------------------------------------------------------------
Change-Id: I1b6606ac73b5cc2dac31d24487b462ec9abfb2ef
Signed-off-by: Sandeep Patil <sspatil@google.com>
The new variant is primarily used in framework. See: go/ag/5780400
for usage. Also add tests, benchmarks and fix several issues found in SysMemInfo
class.
New benchmark results are:
--------------------------------------------------------------
Benchmark Time CPU Iterations
--------------------------------------------------------------
BM_ReadMemInfo_old 7726 ns 7696 ns 90201
BM_ReadMemInfo_new 7554 ns 7525 ns 90358
BM_ZramTotal_old 6446 ns 6406 ns 108361
BM_ZramTotal_new 6529 ns 6488 ns 106545
BM_MemInfoWithZram_old 14485 ns 14412 ns 48492
BM_MemInfoWithZram_new 20572 ns 20459 ns 33438
--------------------------------------------------------------
The reason for BM_MemInfoWithZram_new shows worse numbers is because
the new API also tries to find more than 1 zram device (if it exists).
The old implementation hard coded everything to "/sys/block/zram0/"
Test: libmeminfo_test 1
Bug: 114325007
Bug: 111694435
Change-Id: I246d9e9a54986ee9b2542d1eaac79ecf7310b23a
Signed-off-by: Sandeep Patil <sspatil@google.com>
In the same time replace iomanipulators with
::android::base::StringPrintf which makes the output much more readable
and the overall program simpler.
Bug: 114325007
Bug: 111694435
Test: procmem 1
Test: procmem -W 1
Test: procmem -u 1
Test: procmem -p 1
Test: procmem -w 1
Test: procmem -w -u 1
Test: procmem -w -p 1
Change-Id: Ibf7ef59b24dfcb851c78a3b2fad672d96a708b98
Signed-off-by: Sandeep Patil <sspatil@google.com>
Implement procrank using new libmeminfo APIs. procrank2 is functionally
equivalent to procrank except for the part where the old procrank would
print processes under each oomadj level if called with 'procrank -c -o'.
The output format of 'procrank2' is identical to that of 'procrank'.
'procrank2' also gives significant performance boost over 'procrank' but
does cost a more memory as the library is written to 99% use case where
callers almost always want to read the memory usage of hte process.
Bug: 114325007
Bug: 111694435
Test:
# adb push /google/data/ro/users/ss/sspatil/test-memutils.sh /data/local/tmp/
# adb push procmem2 /data/local/tmp && adb push procrank2 /data/local/tmp
# adb root && adb shell
$ cd /data/local/tmp/
$ chmod +x test-memutils.sh
$ ./test-memutils.sh 2>&1 | tee test.log
Test:
procrank:
0m00.43s real 0m00.11s user 0m00.32s system
procrank2:
0m00.42s real 0m00.05s user 0m00.36s system
Change-Id: I37b71a4625248e333ba01801c0d8d7ef348e4cfa
Signed-off-by: Sandeep Patil <sspatil@google.com>
This restores the original behavior. The main reason it should be this
way is to make the class generic for all things memory under
/proc/<pid>/. For example, with the current behavior, a program that
only needs to read /proc/<pid>/smaps_rollup will end up wasting time and
memory by parsing /proc/<pid>/maps when the object is being constructed.
Same goes for a program that only wants to reset the working set.
The 'ProcMemInfo' object still retains the property that it can only be
used once to read maps and the object must be destroyed + recreated to
update the stats.
Bug: 114325007
Bug: 111694435
Test: libmeminfo_test 1
Test:
# adb push /google/data/ro/users/ss/sspatil/test-memutils.sh /data/local/tmp/
# adb push procmem2 /data/local/tmp && adb push procrank2 /data/local/tmp
# adb root && adb shell
$ cd /data/local/tmp/
$ chmod +x test-memutils.sh
$ ./test-memutils.sh 2>&1 | tee test.log
Change-Id: I856d3b78a0088cff02cbd010b29ffbe0e35f5ee2
Signed-off-by: Sandeep Patil <sspatil@google.com>
Adds procmeminfo API to get the vector of swap_offsets
if SWAP is enabled on the device.
Bug: 114325007
Bug: 111694435
Test: libmeminfo_test 1
Change-Id: If0b52d042749a5bcb2c87aa2cb1595190d4769b1
Signed-off-by: Sandeep Patil <sspatil@google.com>
The library is expected to be a unified place for all components to read
both global and per-process memory accounting form kernel including
getting the working set. This change adds the PageInfo, MemInfo and
ProcMemInfo classes and verifies the implementation against libpagemap
for correctness.
Adds a procmem2 tool show the usage.
TODO: Plumbing in os_debug, add vmastats, zoneinfo etc parsing.
Test: libmeminfo_test 1
Test: procmem2 1
Test: procmem2 -h -W 1
Test: procmem2 -h -w 1
Test: libmeminfo_benchmark
Bug: 111694435
Bug: 114325007
Change-Id: I280440b1dc26a498170686d10fcf63f953a0dcbd
Signed-off-by: Sandeep Patil <sspatil@google.com>
