Windows
Some of the above values are easily available from the appropriate Win32 API, I just list them here for completeness. Others, however, need to be obtained from the Performance Data Helper library (PDH), which is a bit "unintuitive" and takes a lot of painful trial and error to get to work. (At least it took me quite a while, perhaps I've been only a bit stupid...)
Note: for clarity all error checking has been omitted from the following code. Do check the return codes...!
Total Virtual Memory:
#include "windows.h"
MEMORYSTATUSEX memInfo;
memInfo.dwLength = sizeof(MEMORYSTATUSEX);
GlobalMemoryStatusEx(&memInfo);
DWORDLONG totalVirtualMem = memInfo.ullTotalPageFile;
Note: The name "TotalPageFile" is a bit misleading here. In reality this parameter gives the "Virtual Memory Size", which is size of swap file plus installed RAM.
Virtual Memory currently used:
Same code as in "Total Virtual Memory" and then
DWORDLONG virtualMemUsed = memInfo.ullTotalPageFile - memInfo.ullAvailPageFile;
Virtual Memory currently used by current process:
#include "windows.h"
#include "psapi.h"
PROCESS_MEMORY_COUNTERS_EX pmc;
GetProcessMemoryInfo(GetCurrentProcess(), (PROCESS_MEMORY_COUNTERS*)&pmc, sizeof(pmc));
SIZE_T virtualMemUsedByMe = pmc.PrivateUsage;
Total Physical Memory (RAM):
Same code as in "Total Virtual Memory" and then
DWORDLONG totalPhysMem = memInfo.ullTotalPhys;
Physical Memory currently used:
Same code as in "Total Virtual Memory" and then
DWORDLONG physMemUsed = memInfo.ullTotalPhys - memInfo.ullAvailPhys;
Physical Memory currently used by current process:
Same code as in "Virtual Memory currently used by current process" and then
SIZE_T physMemUsedByMe = pmc.WorkingSetSize;
CPU currently used:
#include "TCHAR.h"
#include "pdh.h"
static PDH_HQUERY cpuQuery;
static PDH_HCOUNTER cpuTotal;
void init(){
PdhOpenQuery(NULL, NULL, &cpuQuery);
// You can also use L"\\Processor(*)\\% Processor Time" and get individual CPU values with PdhGetFormattedCounterArray()
PdhAddEnglishCounter(cpuQuery, L"\\Processor(_Total)\\% Processor Time", NULL, &cpuTotal);
PdhCollectQueryData(cpuQuery);
}
double getCurrentValue(){
PDH_FMT_COUNTERVALUE counterVal;
PdhCollectQueryData(cpuQuery);
PdhGetFormattedCounterValue(cpuTotal, PDH_FMT_DOUBLE, NULL, &counterVal);
return counterVal.doubleValue;
}
CPU currently used by current process:
#include "windows.h"
static ULARGE_INTEGER lastCPU, lastSysCPU, lastUserCPU;
static int numProcessors;
static HANDLE self;
void init(){
SYSTEM_INFO sysInfo;
FILETIME ftime, fsys, fuser;
GetSystemInfo(&sysInfo);
numProcessors = sysInfo.dwNumberOfProcessors;
GetSystemTimeAsFileTime(&ftime);
memcpy(&lastCPU, &ftime, sizeof(FILETIME));
self = GetCurrentProcess();
GetProcessTimes(self, &ftime, &ftime, &fsys, &fuser);
memcpy(&lastSysCPU, &fsys, sizeof(FILETIME));
memcpy(&lastUserCPU, &fuser, sizeof(FILETIME));
}
double getCurrentValue(){
FILETIME ftime, fsys, fuser;
ULARGE_INTEGER now, sys, user;
double percent;
GetSystemTimeAsFileTime(&ftime);
memcpy(&now, &ftime, sizeof(FILETIME));
GetProcessTimes(self, &ftime, &ftime, &fsys, &fuser);
memcpy(&sys, &fsys, sizeof(FILETIME));
memcpy(&user, &fuser, sizeof(FILETIME));
percent = (sys.QuadPart - lastSysCPU.QuadPart) +
(user.QuadPart - lastUserCPU.QuadPart);
percent /= (now.QuadPart - lastCPU.QuadPart);
percent /= numProcessors;
lastCPU = now;
lastUserCPU = user;
lastSysCPU = sys;
return percent * 100;
}
Linux
On Linux the choice that seemed obvious at first was to use the POSIX APIs like getrusage()
etc. I spent some time trying to get this to work, but never got meaningful values. When I finally checked the kernel sources themselves, I found out that apparently these APIs are not yet completely implemented as of Linux kernel 2.6!?
In the end I got all values via a combination of reading the pseudo-filesystem /proc
and kernel calls.
Total Virtual Memory:
#include "sys/types.h"
#include "sys/sysinfo.h"
struct sysinfo memInfo;
sysinfo (&memInfo);
long long totalVirtualMem = memInfo.totalram;
//Add other values in next statement to avoid int overflow on right hand side...
totalVirtualMem += memInfo.totalswap;
totalVirtualMem *= memInfo.mem_unit;
Virtual Memory currently used:
Same code as in "Total Virtual Memory" and then
long long virtualMemUsed = memInfo.totalram - memInfo.freeram;
//Add other values in next statement to avoid int overflow on right hand side...
virtualMemUsed += memInfo.totalswap - memInfo.freeswap;
virtualMemUsed *= memInfo.mem_unit;
Virtual Memory currently used by current process:
#include "stdlib.h"
#include "stdio.h"
#include "string.h"
int parseLine(char* line){
// This assumes that a digit will be found and the line ends in " Kb".
int i = strlen(line);
const char* p = line;
while (*p <'0' || *p > '9') p++;
line[i-3] = '\0';
i = atoi(p);
return i;
}
int getValue(){ //Note: this value is in KB!
FILE* file = fopen("/proc/self/status", "r");
int result = -1;
char line[128];
while (fgets(line, 128, file) != NULL){
if (strncmp(line, "VmSize:", 7) == 0){
result = parseLine(line);
break;
}
}
fclose(file);
return result;
}
Total Physical Memory (RAM):
Same code as in "Total Virtual Memory" and then
long long totalPhysMem = memInfo.totalram;
//Multiply in next statement to avoid int overflow on right hand side...
totalPhysMem *= memInfo.mem_unit;
Physical Memory currently used:
Same code as in "Total Virtual Memory" and then
long long physMemUsed = memInfo.totalram - memInfo.freeram;
//Multiply in next statement to avoid int overflow on right hand side...
physMemUsed *= memInfo.mem_unit;
Physical Memory currently used by current process:
Change getValue() in "Virtual Memory currently used by current process" as follows:
int getValue(){ //Note: this value is in KB!
FILE* file = fopen("/proc/self/status", "r");
int result = -1;
char line[128];
while (fgets(line, 128, file) != NULL){
if (strncmp(line, "VmRSS:", 6) == 0){
result = parseLine(line);
break;
}
}
fclose(file);
return result;
}
CPU currently used:
#include "stdlib.h"
#include "stdio.h"
#include "string.h"
static unsigned long long lastTotalUser, lastTotalUserLow, lastTotalSys, lastTotalIdle;
void init(){
FILE* file = fopen("/proc/stat", "r");
fscanf(file, "cpu %llu %llu %llu %llu", &lastTotalUser, &lastTotalUserLow,
&lastTotalSys, &lastTotalIdle);
fclose(file);
}
double getCurrentValue(){
double percent;
FILE* file;
unsigned long long totalUser, totalUserLow, totalSys, totalIdle, total;
file = fopen("/proc/stat", "r");
fscanf(file, "cpu %llu %llu %llu %llu", &totalUser, &totalUserLow,
&totalSys, &totalIdle);
fclose(file);
if (totalUser < lastTotalUser || totalUserLow < lastTotalUserLow ||
totalSys < lastTotalSys || totalIdle < lastTotalIdle){
//Overflow detection. Just skip this value.
percent = -1.0;
}
else{
total = (totalUser - lastTotalUser) + (totalUserLow - lastTotalUserLow) +
(totalSys - lastTotalSys);
percent = total;
total += (totalIdle - lastTotalIdle);
percent /= total;
percent *= 100;
}
lastTotalUser = totalUser;
lastTotalUserLow = totalUserLow;
lastTotalSys = totalSys;
lastTotalIdle = totalIdle;
return percent;
}
CPU currently used by current process:
#include "stdlib.h"
#include "stdio.h"
#include "string.h"
#include "sys/times.h"
#include "sys/vtimes.h"
static clock_t lastCPU, lastSysCPU, lastUserCPU;
static int numProcessors;
void init(){
FILE* file;
struct tms timeSample;
char line[128];
lastCPU = times(&timeSample);
lastSysCPU = timeSample.tms_stime;
lastUserCPU = timeSample.tms_utime;
file = fopen("/proc/cpuinfo", "r");
numProcessors = 0;
while(fgets(line, 128, file) != NULL){
if (strncmp(line, "processor", 9) == 0) numProcessors++;
}
fclose(file);
}
double getCurrentValue(){
struct tms timeSample;
clock_t now;
double percent;
now = times(&timeSample);
if (now <= lastCPU || timeSample.tms_stime < lastSysCPU ||
timeSample.tms_utime < lastUserCPU){
//Overflow detection. Just skip this value.
percent = -1.0;
}
else{
percent = (timeSample.tms_stime - lastSysCPU) +
(timeSample.tms_utime - lastUserCPU);
percent /= (now - lastCPU);
percent /= numProcessors;
percent *= 100;
}
lastCPU = now;
lastSysCPU = timeSample.tms_stime;
lastUserCPU = timeSample.tms_utime;
return percent;
}
TODO: Other Platforms
I would assume, that some of the Linux code also works for the Unixes, except for the parts that read the /proc pseudo-filesystem. Perhaps on Unix these parts can be replaced by getrusage()
and similar functions?
This has been a long-standing complaint with Java, but it's largely meaningless, and usually based on looking at the wrong information. The usual phrasing is something like "Hello World on Java takes 10 megabytes! Why does it need that?" Well, here's a way to make Hello World on a 64-bit JVM claim to take over 4 gigabytes ... at least by one form of measurement.
java -Xms1024m -Xmx4096m com.example.Hello
Different Ways to Measure Memory
On Linux, the top command gives you several different numbers for memory. Here's what it says about the Hello World example:
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
2120 kgregory 20 0 4373m 15m 7152 S 0 0.2 0:00.10 java
- VIRT is the virtual memory space: the sum of everything in the virtual memory map (see below). It is largely meaningless, except when it isn't (see below).
- RES is the resident set size: the number of pages that are currently resident in RAM. In almost all cases, this is the only number that you should use when saying "too big." But it's still not a very good number, especially when talking about Java.
- SHR is the amount of resident memory that is shared with other processes. For a Java process, this is typically limited to shared libraries and memory-mapped JARfiles. In this example, I only had one Java process running, so I suspect that the 7k is a result of libraries used by the OS.
- SWAP isn't turned on by default, and isn't shown here. It indicates the amount of virtual memory that is currently resident on disk, whether or not it's actually in the swap space. The OS is very good about keeping active pages in RAM, and the only cures for swapping are (1) buy more memory, or (2) reduce the number of processes, so it's best to ignore this number.
The situation for Windows Task Manager is a bit more complicated. Under Windows XP, there are "Memory Usage" and "Virtual Memory Size" columns, but the official documentation is silent on what they mean. Windows Vista and Windows 7 add more columns, and they're actually documented. Of these, the "Working Set" measurement is the most useful; it roughly corresponds to the sum of RES and SHR on Linux.
Understanding the Virtual Memory Map
The virtual memory consumed by a process is the total of everything that's in the process memory map. This includes data (eg, the Java heap), but also all of the shared libraries and memory-mapped files used by the program. On Linux, you can use the pmap command to see all of the things mapped into the process space (from here on out I'm only going to refer to Linux, because it's what I use; I'm sure there are equivalent tools for Windows). Here's an excerpt from the memory map of the "Hello World" program; the entire memory map is over 100 lines long, and it's not unusual to have a thousand-line list.
0000000040000000 36K r-x-- /usr/local/java/jdk-1.6-x64/bin/java
0000000040108000 8K rwx-- /usr/local/java/jdk-1.6-x64/bin/java
0000000040eba000 676K rwx-- [ anon ]
00000006fae00000 21248K rwx-- [ anon ]
00000006fc2c0000 62720K rwx-- [ anon ]
0000000700000000 699072K rwx-- [ anon ]
000000072aab0000 2097152K rwx-- [ anon ]
00000007aaab0000 349504K rwx-- [ anon ]
00000007c0000000 1048576K rwx-- [ anon ]
...
00007fa1ed00d000 1652K r-xs- /usr/local/java/jdk-1.6-x64/jre/lib/rt.jar
...
00007fa1ed1d3000 1024K rwx-- [ anon ]
00007fa1ed2d3000 4K ----- [ anon ]
00007fa1ed2d4000 1024K rwx-- [ anon ]
00007fa1ed3d4000 4K ----- [ anon ]
...
00007fa1f20d3000 164K r-x-- /usr/local/java/jdk-1.6-x64/jre/lib/amd64/libjava.so
00007fa1f20fc000 1020K ----- /usr/local/java/jdk-1.6-x64/jre/lib/amd64/libjava.so
00007fa1f21fb000 28K rwx-- /usr/local/java/jdk-1.6-x64/jre/lib/amd64/libjava.so
...
00007fa1f34aa000 1576K r-x-- /lib/x86_64-linux-gnu/libc-2.13.so
00007fa1f3634000 2044K ----- /lib/x86_64-linux-gnu/libc-2.13.so
00007fa1f3833000 16K r-x-- /lib/x86_64-linux-gnu/libc-2.13.so
00007fa1f3837000 4K rwx-- /lib/x86_64-linux-gnu/libc-2.13.so
...
A quick explanation of the format: each row starts with the virtual memory address of the segment. This is followed by the segment size, permissions, and the source of the segment. This last item is either a file or "anon", which indicates a block of memory allocated via mmap.
Starting from the top, we have
- The JVM loader (ie, the program that gets run when you type
java
). This is very small; all it does is load in the shared libraries where the real JVM code is stored.
- A bunch of anon blocks holding the Java heap and internal data. This is a Sun JVM, so the heap is broken into multiple generations, each of which is its own memory block. Note that the JVM allocates virtual memory space based on the
-Xmx
value; this allows it to have a contiguous heap. The -Xms
value is used internally to say how much of the heap is "in use" when the program starts, and to trigger garbage collection as that limit is approached.
- A memory-mapped JARfile, in this case the file that holds the "JDK classes." When you memory-map a JAR, you can access the files within it very efficiently (versus reading it from the start each time). The Sun JVM will memory-map all JARs on the classpath; if your application code needs to access a JAR, you can also memory-map it.
- Per-thread data for two threads. The 1M block is the thread stack. I didn't have a good explanation for the 4k block, but @ericsoe identified it as a "guard block": it does not have read/write permissions, so will cause a segment fault if accessed, and the JVM catches that and translates it to a
StackOverFlowError
. For a real app, you will see dozens if not hundreds of these entries repeated through the memory map.
- One of the shared libraries that holds the actual JVM code. There are several of these.
- The shared library for the C standard library. This is just one of many things that the JVM loads that are not strictly part of Java.
The shared libraries are particularly interesting: each shared library has at least two segments: a read-only segment containing the library code, and a read-write segment that contains global per-process data for the library (I don't know what the segment with no permissions is; I've only seen it on x64 Linux). The read-only portion of the library can be shared between all processes that use the library; for example, libc
has 1.5M of virtual memory space that can be shared.
When is Virtual Memory Size Important?
The virtual memory map contains a lot of stuff. Some of it is read-only, some of it is shared, and some of it is allocated but never touched (eg, almost all of the 4Gb of heap in this example). But the operating system is smart enough to only load what it needs, so the virtual memory size is largely irrelevant.
Where virtual memory size is important is if you're running on a 32-bit operating system, where you can only allocate 2Gb (or, in some cases, 3Gb) of process address space. In that case you're dealing with a scarce resource, and might have to make tradeoffs, such as reducing your heap size in order to memory-map a large file or create lots of threads.
But, given that 64-bit machines are ubiquitous, I don't think it will be long before Virtual Memory Size is a completely irrelevant statistic.
When is Resident Set Size Important?
Resident Set size is that portion of the virtual memory space that is actually in RAM. If your RSS grows to be a significant portion of your total physical memory, it might be time to start worrying. If your RSS grows to take up all your physical memory, and your system starts swapping, it's well past time to start worrying.
But RSS is also misleading, especially on a lightly loaded machine. The operating system doesn't expend a lot of effort to reclaiming the pages used by a process. There's little benefit to be gained by doing so, and the potential for an expensive page fault if the process touches the page in the future. As a result, the RSS statistic may include lots of pages that aren't in active use.
Bottom Line
Unless you're swapping, don't get overly concerned about what the various memory statistics are telling you. With the caveat that an ever-growing RSS may indicate some sort of memory leak.
With a Java program, it's far more important to pay attention to what's happening in the heap. The total amount of space consumed is important, and there are some steps that you can take to reduce that. More important is the amount of time that you spend in garbage collection, and which parts of the heap are getting collected.
Accessing the disk (ie, a database) is expensive, and memory is cheap. If you can trade one for the other, do so.
Best Answer
Things that (may) increase virtual bytes without increasing private bytes I can think of right now:
Binaries are often shared (i.e. not private), but occupy significant address space. This can be even larger than the size of the binary
Using VirtualAlloc to reserve sequential address space without committing / accessing it. Custom Memory Managers might do that.
Using a memory mapped file (without completely accessing it)