Don't dump pages which only contain zero bytes

Signed-off-by: Volker Simonis <[email protected]>
checkpoint-restore · Jan 15, 2024 · 9bdc424 · 9bdc424
1 parent cda1c5c
commit 9bdc424
Show file tree

Hide file tree

Showing 7 changed files with 146 additions and 4 deletions.
diff --git a/criu/config.c b/criu/config.c
@@ -650,6 +650,7 @@ int parse_options(int argc, char **argv, bool *usage_error, bool *has_exec_cmd,
 		{ "ms", no_argument, 0, 1054 },
 		BOOL_OPT("track-mem", &opts.track_mem),
 		BOOL_OPT("auto-dedup", &opts.auto_dedup),
+		BOOL_OPT("zero-pages", &opts.zero_pages),
 		{ "libdir", required_argument, 0, 'L' },
 		{ "cpu-cap", optional_argument, 0, 1057 },
 		BOOL_OPT("force-irmap", &opts.force_irmap),

diff --git a/criu/crtools.c b/criu/crtools.c
@@ -541,6 +541,12 @@ int main(int argc, char *argv[], char *envp[])
 	       "                        pages images of previous dump\n"
 	       "                        when used on restore, as soon as page is restored, it\n"
 	       "                        will be punched from the image\n"
+	       "  --zero-pages          don't dump pages containing only zero bytes. This is a\n"
+	       "                        potentially expensive operation because it checks for\n"
+	       "                        every single process page if it contains only zeros but\n"
+               "                        it can significantly decrease the image size if many\n"
+               "                        such pages exist. It effectively replaces such pages\n"
+	       "                        which the kernel's zero-page on restore.\n"
 	       "  --pre-dump-mode       splice - parasite based pre-dumping (default)\n"
 	       "                        read   - process_vm_readv syscall based pre-dumping\n"
 	       "\n"

diff --git a/criu/include/cr_options.h b/criu/include/cr_options.h
@@ -157,6 +157,7 @@ struct cr_options {
 	int track_mem;
 	char *img_parent;
 	int auto_dedup;
+	int zero_pages;
 	unsigned int cpu_cap;
 	int force_irmap;
 	char **exec_cmd;

diff --git a/criu/mem.c b/criu/mem.c
@@ -3,8 +3,10 @@
 #include <sys/mman.h>
 #include <errno.h>
 #include <fcntl.h>
+#include <string.h>
 #include <sys/syscall.h>
 #include <sys/prctl.h>
+#include <sys/uio.h>
 
 #include "types.h"
 #include "cr_options.h"
@@ -31,6 +33,7 @@
 #include "prctl.h"
 #include "compel/infect-util.h"
 #include "pidfd-store.h"
+#include "xmalloc.h"
 
 #include "protobuf.h"
 #include "images/pagemap.pb-c.h"
@@ -172,17 +175,58 @@ static int generate_iovs(struct pstree_item *item, struct vma_area *vma, struct
 	unsigned long pages[3] = {};
 	int ret = 0;
 
+	static char *ZERO_PAGE = NULL;
+	static char *REMOTE_PAGE = NULL;
+	int zero = 0;
+	struct iovec  local[2];
+	struct iovec  remote[1];
+	int nread = 0;
+	if (opts.zero_pages && ZERO_PAGE == NULL) {
+		ZERO_PAGE = xmalloc(PAGE_SIZE);
+		REMOTE_PAGE = xmalloc(PAGE_SIZE);
+		if (ZERO_PAGE == NULL || REMOTE_PAGE == NULL) {
+			pr_warn("Can't allocate memory - disabling --zero-pages");
+			opts.zero_pages = 0;
+		} else	{
+			memzero(ZERO_PAGE, PAGE_SIZE);
+			local[0].iov_base = REMOTE_PAGE;
+			local[0].iov_len = PAGE_SIZE;
+			remote[0].iov_base = (void *) 0x0;
+			remote[0].iov_len = PAGE_SIZE;
+		}
+	}
+
 	nr_to_scan = (vma_area_len(vma) - *off) / PAGE_SIZE;
 
 	for (pfn = 0; pfn < nr_to_scan; pfn++) {
 		unsigned long vaddr;
 		unsigned int ppb_flags = 0;
 		int st;
 
-		if (!should_dump_page(vma->e, at[pfn]))
-			continue;
-
 		vaddr = vma->e->start + *off + pfn * PAGE_SIZE;
+		/*
+		 * If should_dump_page() returns true, it means the page is in the dumpees resident memory
+		 * (i.e. bit 63 of the page frame number 'at[pfn]' is set) but it is not the zero-page.
+		 */
+		if (should_dump_page(vma->e, at[pfn])) {
+			if (opts.zero_pages) {
+				remote[0].iov_base = (void*)vaddr;
+				nread = process_vm_readv(item->pid->real, local, 1, remote, 1, 0);
+				if (nread == PAGE_SIZE) {
+					zero = memcmp(ZERO_PAGE, REMOTE_PAGE, PAGE_SIZE);
+					/*
+					 * If the page contains just zeros we can treat it like the zero page and skip it.
+					 * At restore it will be replaced by a reference to the zero page and COWed if accessed.
+					 */
+					if (zero == 0) {
+						pr_info("Zero page detected at virtual addr = %p\n", (void*)vaddr);
+						continue;
+					}
+				}
+			}
+		} else {
+			continue;
+		}
 
 		if (vma_entry_can_be_lazy(vma->e) && !is_stack(item, vaddr))
 			ppb_flags |= PPB_LAZY;

diff --git a/test/javaTests/pom.xml b/test/javaTests/pom.xml
@@ -18,6 +18,7 @@
 					<!-- Suite testng xml file to consider for test execution -->
 					<suiteXmlFiles>
 						<suiteXmlFile>test.xml</suiteXmlFile>
+						<suiteXmlFile>test-zero.xml</suiteXmlFile>
 					</suiteXmlFiles>
 				</configuration>
 			</plugin>

diff --git a/test/javaTests/src/org/criu/java/tests/CheckpointRestore.java b/test/javaTests/src/org/criu/java/tests/CheckpointRestore.java
@@ -112,7 +112,7 @@ public void runtest(String testName, String checkpointOpt, String restoreOpt) th
 		String pid;
 		int exitCode;
 
-		System.out.println("======= Testing " + testName + " ========");
+		System.out.println("======= Testing " + testName + " " + checkpointOpt + " ========");
 
 		testSetup(testName);
 

diff --git a/test/javaTests/test-zero.xml b/test/javaTests/test-zero.xml
@@ -0,0 +1,89 @@
+<?xml version = "1.0" encoding = "UTF-8"?>
+<!DOCTYPE suite SYSTEM "http://testng.org/testng-1.0.dtd" >
+
+<suite name = "Suite2">
+	<parameter name="checkpointOpt" value="--zero-pages"/>
+	<parameter name="restoreOpt" value=""/>
+
+	<test name = "test1-FileRead">
+		<parameter name="testname" value="FileRead"/>
+		<classes>
+			<class name = "org.criu.java.tests.CheckpointRestore"/>
+		</classes>
+	</test>
+
+	<test name = "test2-ReadWrite">
+		<parameter name="testname" value="ReadWrite"/>
+		<classes>
+			<class name = "org.criu.java.tests.CheckpointRestore"/>
+		</classes>
+	</test>
+
+	<test name = "test3-MemoryMappings">
+		<parameter name="testname" value="MemoryMappings"/>
+		<classes>
+			<class name = "org.criu.java.tests.CheckpointRestore"/>
+		</classes>
+	</test>
+
+	<test name = "test4-MultipleFileRead">
+		<parameter name="testname" value="MultipleFileRead"/>
+		<classes>
+			<class name = "org.criu.java.tests.CheckpointRestore"/>
+		</classes>
+	</test>
+
+	<test name = "test5-MultipleFileWrite">
+		<parameter name="testname" value="MultipleFileWrite"/>
+		<classes>
+			<class name = "org.criu.java.tests.CheckpointRestore"/>
+		</classes>
+	</test>
+
+	<test name = "test6-Sockets">
+		<parameter name="testname" value="Sockets"/>
+		<parameter name="checkpointOpt" value="--tcp-established --zero-pages"/>
+		<parameter name="restoreOpt" value="--tcp-established"/>
+		<classes>
+			<class name = "org.criu.java.tests.CheckpointRestore"/>
+		</classes>
+	</test>
+
+	<test name = "test7-SocketsListen">
+		<parameter name="testname" value="SocketsListen"/>
+		<parameter name="checkpointOpt" value="--tcp-established --zero-pages"/>
+		<parameter name="restoreOpt" value="--tcp-established"/>
+		<classes>
+			<class name = "org.criu.java.tests.CheckpointRestore"/>
+		</classes>
+	</test>
+
+	<test name = "test8-SocketsConnect">
+		<parameter name="testname" value="SocketsConnect"/>
+		<parameter name="checkpointOpt" value="--tcp-established --zero-pages"/>
+		<parameter name="restoreOpt" value="--tcp-established"/>
+		<classes>
+			<class name = "org.criu.java.tests.CheckpointRestore"/>
+		</classes>
+	</test>
+
+	<test name = "test9-SocketsMultiple">
+		<parameter name="testname" value="SocketsMultiple"/>
+		<parameter name="checkpointOpt" value="--tcp-established --zero-pages"/>
+		<parameter name="restoreOpt" value="--tcp-established"/>
+		<classes>
+			<class name = "org.criu.java.tests.CheckpointRestore"/>
+		</classes>
+	</test>
+
+	<test name = "test10-SocketsData">
+		<parameter name="testname" value="SocketsData"/>
+		<parameter name="checkpointOpt" value="--tcp-established --zero-pages"/>
+		<parameter name="restoreOpt" value="--tcp-established"/>
+		<classes>
+			<class name = "org.criu.java.tests.CheckpointRestore"/>
+		</classes>
+
+	</test>
+
+</suite>