X-Git-Url: https://git.saurik.com/redis.git/blobdiff_plain/af4e866dbb1455a50d51b3d5f46832f1a36e2080..144a5e72f2adc9d151438569f680533e41778504:/src/vm.c?ds=inline

diff --git a/src/vm.c b/src/vm.c
index 1aaa57eb..ee831fb9 100644
--- a/src/vm.c
+++ b/src/vm.c
@@ -86,10 +86,9 @@ void vmInit(void) {
     } else {
         redisLog(REDIS_NOTICE,"Swap file allocated with success");
     }
-    server.vm_bitmap = zmalloc((server.vm_pages+7)/8);
+    server.vm_bitmap = zcalloc((server.vm_pages+7)/8);
     redisLog(REDIS_VERBOSE,"Allocated %lld bytes page table for %lld pages",
         (long long) (server.vm_pages+7)/8, server.vm_pages);
-    memset(server.vm_bitmap,0,(server.vm_pages+7)/8);
 
     /* Initialize threaded I/O (used by Virtual Memory) */
     server.io_newjobs = listCreate();
@@ -111,6 +110,11 @@ void vmInit(void) {
     /* LZF requires a lot of stack */
     pthread_attr_init(&server.io_threads_attr);
     pthread_attr_getstacksize(&server.io_threads_attr, &stacksize);
+
+    /* Solaris may report a stacksize of 0, let's set it to 1 otherwise
+     * multiplying it by 2 in the while loop later will not really help ;) */
+    if (!stacksize) stacksize = 1;
+
     while (stacksize < REDIS_THREAD_STACK_SIZE) stacksize *= 2;
     pthread_attr_setstacksize(&server.io_threads_attr, stacksize);
     /* Listen for events in the threaded I/O pipe */
@@ -396,15 +400,20 @@ double computeObjectSwappability(robj *o) {
         z = (o->type == REDIS_ZSET);
         d = z ? ((zset*)o->ptr)->dict : o->ptr;
 
-        asize = sizeof(dict)+(sizeof(struct dictEntry*)*dictSlots(d));
-        if (z) asize += sizeof(zset)-sizeof(dict);
-        if (dictSize(d)) {
-            de = dictGetRandomKey(d);
-            ele = dictGetEntryKey(de);
-            elesize = (ele->encoding == REDIS_ENCODING_RAW) ?
-                            (sizeof(*o)+sdslen(ele->ptr)) : sizeof(*o);
-            asize += (sizeof(struct dictEntry)+elesize)*dictSize(d);
-            if (z) asize += sizeof(zskiplistNode)*dictSize(d);
+        if (!z && o->encoding == REDIS_ENCODING_INTSET) {
+            intset *is = o->ptr;
+            asize = sizeof(*is)+is->encoding*is->length;
+        } else {
+            asize = sizeof(dict)+(sizeof(struct dictEntry*)*dictSlots(d));
+            if (z) asize += sizeof(zset)-sizeof(dict);
+            if (dictSize(d)) {
+                de = dictGetRandomKey(d);
+                ele = dictGetEntryKey(de);
+                elesize = (ele->encoding == REDIS_ENCODING_RAW) ?
+                                (sizeof(*o)+sdslen(ele->ptr)) : sizeof(*o);
+                asize += (sizeof(struct dictEntry)+elesize)*dictSize(d);
+                if (z) asize += sizeof(zskiplistNode)*dictSize(d);
+            }
         }
         break;
     case REDIS_HASH:
@@ -544,7 +553,15 @@ void freeIOJob(iojob *j) {
 
 /* Every time a thread finished a Job, it writes a byte into the write side
  * of an unix pipe in order to "awake" the main thread, and this function
- * is called. */
+ * is called.
+ *
+ * Note that this is called both by the event loop, when a I/O thread
+ * sends a byte in the notification pipe, and is also directly called from
+ * waitEmptyIOJobsQueue().
+ *
+ * In the latter case we don't want to swap more, so we use the
+ * "privdata" argument setting it to a not NULL value to signal this
+ * condition. */
 void vmThreadedIOCompletedJob(aeEventLoop *el, int fd, void *privdata,
             int mask)
 {
@@ -554,6 +571,8 @@ void vmThreadedIOCompletedJob(aeEventLoop *el, int fd, void *privdata,
     REDIS_NOTUSED(mask);
     REDIS_NOTUSED(privdata);
 
+    if (privdata != NULL) trytoswap = 0; /* check the comments above... */
+
     /* For every byte we read in the read side of the pipe, there is one
      * I/O job completed to process. */
     while((retval = read(fd,buf,1)) == 1) {
@@ -865,7 +884,8 @@ void waitEmptyIOJobsQueue(void) {
         io_processed_len = listLength(server.io_processed);
         unlockThreadedIO();
         if (io_processed_len) {
-            vmThreadedIOCompletedJob(NULL,server.io_ready_pipe_read,NULL,0);
+            vmThreadedIOCompletedJob(NULL,server.io_ready_pipe_read,
+                                                        (void*)0xdeadbeef,0);
             usleep(1000); /* 1 millisecond */
         } else {
             usleep(10000); /* 10 milliseconds */
@@ -1075,6 +1095,11 @@ int dontWaitForSwappedKey(redisClient *c, robj *key) {
     listIter li;
     struct dictEntry *de;
 
+    /* The key object might be destroyed when deleted from the c->io_keys
+     * list (and the "key" argument is physically the same object as the
+     * object inside the list), so we need to protect it. */
+    incrRefCount(key);
+
     /* Remove the key from the list of keys this client is waiting for. */
     listRewind(c->io_keys,&li);
     while ((ln = listNext(&li)) != NULL) {
@@ -1095,6 +1120,7 @@ int dontWaitForSwappedKey(redisClient *c, robj *key) {
     if (listLength(l) == 0)
         dictDelete(c->db->io_keys,key);
 
+    decrRefCount(key);
     return listLength(c->io_keys) == 0;
 }