diff --git a/src/allocator.cpp b/src/allocator.cpp
index 2893a56b7..06ec6cf84 100644
--- a/src/allocator.cpp
+++ b/src/allocator.cpp
@@ -142,3 +142,35 @@ uint64_t allocator::get_free_count()
 {
     return free;
 }
+
+void bitmap_set(void *bitmap, uint64_t start, uint64_t len, uint64_t bitmap_granularity)
+{
+    if (start == 0)
+    {
+        if (len == 32*bitmap_granularity)
+        {
+            *((uint32_t*)bitmap) = UINT32_MAX;
+            return;
+        }
+        else if (len == 64*bitmap_granularity)
+        {
+            *((uint64_t*)bitmap) = UINT64_MAX;
+            return;
+        }
+    }
+    unsigned bit_start = start / bitmap_granularity;
+    unsigned bit_end = ((start + len) + bitmap_granularity - 1) / bitmap_granularity;
+    while (bit_start < bit_end)
+    {
+        if (!(bit_start & 7) && bit_end >= bit_start+8)
+        {
+            ((uint8_t*)bitmap)[bit_start / 8] = UINT8_MAX;
+            bit_start += 8;
+        }
+        else
+        {
+            ((uint8_t*)bitmap)[bit_start / 8] |= 1 << (bit_start % 8);
+            bit_start++;
+        }
+    }
+}
diff --git a/src/allocator.h b/src/allocator.h
index 1bc5d4441..1a759297f 100644
--- a/src/allocator.h
+++ b/src/allocator.h
@@ -21,3 +21,5 @@ public:
     uint64_t find_free();
     uint64_t get_free_count();
 };
+
+void bitmap_set(void *bitmap, uint64_t start, uint64_t len, uint64_t bitmap_granularity);
diff --git a/src/blockstore_flush.cpp b/src/blockstore_flush.cpp
index b3920a7f8..ee573954d 100644
--- a/src/blockstore_flush.cpp
+++ b/src/blockstore_flush.cpp
@@ -432,14 +432,14 @@ resume_1:
             if (clean_init_bitmap)
             {
                 memset(new_clean_bitmap, 0, bs->clean_entry_bitmap_size);
-                bitmap_set(new_clean_bitmap, clean_bitmap_offset, clean_bitmap_len);
+                bitmap_set(new_clean_bitmap, clean_bitmap_offset, clean_bitmap_len, bs->bitmap_granularity);
             }
         }
         for (it = v.begin(); it != v.end(); it++)
         {
             if (new_clean_bitmap)
             {
-                bitmap_set(new_clean_bitmap, it->offset, it->len);
+                bitmap_set(new_clean_bitmap, it->offset, it->len, bs->bitmap_granularity);
             }
             await_sqe(4);
             data->iov = (struct iovec){ it->buf, (size_t)it->len };
@@ -885,35 +885,3 @@ bool journal_flusher_co::fsync_batch(bool fsync_meta, int wait_base)
     }
     return true;
 }
-
-void journal_flusher_co::bitmap_set(void *bitmap, uint64_t start, uint64_t len)
-{
-    if (start == 0)
-    {
-        if (len == 32*bs->bitmap_granularity)
-        {
-            *((uint32_t*)bitmap) = UINT32_MAX;
-            return;
-        }
-        else if (len == 64*bs->bitmap_granularity)
-        {
-            *((uint64_t*)bitmap) = UINT64_MAX;
-            return;
-        }
-    }
-    unsigned bit_start = start / bs->bitmap_granularity;
-    unsigned bit_end = ((start + len) + bs->bitmap_granularity - 1) / bs->bitmap_granularity;
-    while (bit_start < bit_end)
-    {
-        if (!(bit_start & 7) && bit_end >= bit_start+8)
-        {
-            ((uint8_t*)bitmap)[bit_start / 8] = UINT8_MAX;
-            bit_start += 8;
-        }
-        else
-        {
-            ((uint8_t*)bitmap)[bit_start / 8] |= 1 << (bit_start % 8);
-            bit_start++;
-        }
-    }
-}
diff --git a/src/blockstore_flush.h b/src/blockstore_flush.h
index 0bf4ebe05..cf8d2e1d0 100644
--- a/src/blockstore_flush.h
+++ b/src/blockstore_flush.h
@@ -69,7 +69,6 @@ class journal_flusher_co
     bool modify_meta_read(uint64_t meta_loc, flusher_meta_write_t &wr, int wait_base);
     void update_clean_db();
     bool fsync_batch(bool fsync_meta, int wait_base);
-    void bitmap_set(void *bitmap, uint64_t start, uint64_t len);
 public:
     journal_flusher_co();
     bool loop();
diff --git a/src/osd_primary.cpp b/src/osd_primary.cpp
index d62434ca7..1bcf60df9 100644
--- a/src/osd_primary.cpp
+++ b/src/osd_primary.cpp
@@ -115,7 +115,7 @@ void osd_t::continue_primary_read(osd_op_t *cur_op)
         if (pg.state == PG_ACTIVE || op_data->scheme == POOL_SCHEME_REPLICATED)
         {
             // Fast happy-path
-            cur_op->buf = alloc_read_buffer(op_data->stripes, op_data->pg_data_size, 0);
+            cur_op->buf = alloc_read_buffer(op_data->stripes, op_data->pg_data_size, 0, 0);
             submit_primary_subops(SUBMIT_READ, op_data->target_ver,
                 (op_data->scheme == POOL_SCHEME_REPLICATED ? pg.pg_size : op_data->pg_data_size), pg.cur_set.data(), cur_op);
             op_data->st = 1;
@@ -133,7 +133,7 @@ void osd_t::continue_primary_read(osd_op_t *cur_op)
             op_data->pg_size = pg.pg_size;
             op_data->scheme = pg.scheme;
             op_data->degraded = 1;
-            cur_op->buf = alloc_read_buffer(op_data->stripes, pg.pg_size, 0);
+            cur_op->buf = alloc_read_buffer(op_data->stripes, pg.pg_size, 0, 0);
             submit_primary_subops(SUBMIT_READ, op_data->target_ver, pg.pg_size, cur_set, cur_op);
             op_data->st = 1;
         }
@@ -152,11 +152,11 @@ resume_2:
         osd_rmw_stripe_t *stripes = op_data->stripes;
         if (op_data->scheme == POOL_SCHEME_XOR)
         {
-            reconstruct_stripes_xor(stripes, op_data->pg_size);
+            reconstruct_stripes_xor(stripes, op_data->pg_size, 0);
         }
         else if (op_data->scheme == POOL_SCHEME_JERASURE)
         {
-            reconstruct_stripes_jerasure(stripes, op_data->pg_size, op_data->pg_data_size);
+            reconstruct_stripes_jerasure(stripes, op_data->pg_size, op_data->pg_data_size, 0);
         }
         for (int role = 0; role < op_data->pg_size; role++)
         {
diff --git a/src/osd_primary_write.cpp b/src/osd_primary_write.cpp
index d40257cf5..e984b2191 100644
--- a/src/osd_primary_write.cpp
+++ b/src/osd_primary_write.cpp
@@ -77,7 +77,7 @@ resume_1:
     else
     {
         cur_op->rmw_buf = calc_rmw(cur_op->buf, op_data->stripes, op_data->prev_set,
-            pg.pg_size, op_data->pg_data_size, pg.pg_cursize, pg.cur_set.data(), bs_block_size);
+            pg.pg_size, op_data->pg_data_size, pg.pg_cursize, pg.cur_set.data(), bs_block_size, 0);
         if (!cur_op->rmw_buf)
         {
             // Refuse partial overwrite of an incomplete object
@@ -120,11 +120,11 @@ resume_3:
         // Recover missing stripes, calculate parity
         if (pg.scheme == POOL_SCHEME_XOR)
         {
-            calc_rmw_parity_xor(op_data->stripes, pg.pg_size, op_data->prev_set, pg.cur_set.data(), bs_block_size);
+            calc_rmw_parity_xor(op_data->stripes, pg.pg_size, op_data->prev_set, pg.cur_set.data(), bs_block_size, 0);
         }
         else if (pg.scheme == POOL_SCHEME_JERASURE)
         {
-            calc_rmw_parity_jerasure(op_data->stripes, pg.pg_size, op_data->pg_data_size, op_data->prev_set, pg.cur_set.data(), bs_block_size);
+            calc_rmw_parity_jerasure(op_data->stripes, pg.pg_size, op_data->pg_data_size, op_data->prev_set, pg.cur_set.data(), bs_block_size, 0);
         }
     }
     // Send writes
diff --git a/src/osd_rmw.cpp b/src/osd_rmw.cpp
index acde6abca..02ef23e48 100644
--- a/src/osd_rmw.cpp
+++ b/src/osd_rmw.cpp
@@ -7,6 +7,7 @@
 #include <jerasure/reed_sol.h>
 #include <jerasure.h>
 #include <map>
+#include "allocator.h"
 #include "xor.h"
 #include "osd_rmw.h"
 #include "malloc_or_die.h"
@@ -81,7 +82,7 @@ void split_stripes(uint64_t pg_minsize, uint32_t bs_block_size, uint32_t start,
     }
 }
 
-void reconstruct_stripes_xor(osd_rmw_stripe_t *stripes, int pg_size)
+void reconstruct_stripes_xor(osd_rmw_stripe_t *stripes, int pg_size, uint32_t bitmap_size)
 {
     for (int role = 0; role < pg_size; role++)
     {
@@ -106,6 +107,7 @@ void reconstruct_stripes_xor(osd_rmw_stripe_t *stripes, int pg_size)
                             stripes[other].read_buf + (stripes[role].read_start - stripes[other].read_start),
                             stripes[role].read_buf, stripes[role].read_end - stripes[role].read_start
                         );
+                        memxor(stripes[prev].bmp_buf, stripes[other].bmp_buf, stripes[role].bmp_buf, bitmap_size);
                         prev = -1;
                     }
                     else
@@ -116,6 +118,7 @@ void reconstruct_stripes_xor(osd_rmw_stripe_t *stripes, int pg_size)
                             stripes[other].read_buf + (stripes[role].read_start - stripes[other].read_start),
                             stripes[role].read_buf, stripes[role].read_end - stripes[role].read_start
                         );
+                        memxor(stripes[role].bmp_buf, stripes[other].bmp_buf, stripes[role].bmp_buf, bitmap_size);
                     }
                 }
             }
@@ -230,7 +233,7 @@ int* get_jerasure_decoding_matrix(osd_rmw_stripe_t *stripes, int pg_size, int pg
     return dec_it->second;
 }
 
-void reconstruct_stripes_jerasure(osd_rmw_stripe_t *stripes, int pg_size, int pg_minsize)
+void reconstruct_stripes_jerasure(osd_rmw_stripe_t *stripes, int pg_size, int pg_minsize, uint32_t bitmap_size)
 {
     int *dm_ids = get_jerasure_decoding_matrix(stripes, pg_size, pg_minsize);
     if (!dm_ids)
@@ -257,6 +260,18 @@ void reconstruct_stripes_jerasure(osd_rmw_stripe_t *stripes, int pg_size, int pg
                 pg_minsize, OSD_JERASURE_W, decoding_matrix+(role*pg_minsize), dm_ids, role,
                 data_ptrs, data_ptrs+pg_minsize, stripes[role].read_end - stripes[role].read_start
             );
+            for (int other = 0; other < pg_size; other++)
+            {
+                if (stripes[other].read_end != 0 && !stripes[other].missing)
+                {
+                    data_ptrs[other] = (char*)(stripes[other].bmp_buf);
+                }
+            }
+            data_ptrs[role] = (char*)stripes[role].bmp_buf;
+            jerasure_matrix_dotprod(
+                pg_minsize, OSD_JERASURE_W, decoding_matrix+(role*pg_minsize), dm_ids, role,
+                data_ptrs, data_ptrs+pg_minsize, bitmap_size
+            );
         }
     }
 }
@@ -294,7 +309,7 @@ int extend_missing_stripes(osd_rmw_stripe_t *stripes, osd_num_t *osd_set, int pg
     return 0;
 }
 
-void* alloc_read_buffer(osd_rmw_stripe_t *stripes, int read_pg_size, uint64_t add_size)
+void* alloc_read_buffer(osd_rmw_stripe_t *stripes, int read_pg_size, uint64_t add_size, uint32_t bitmap_size)
 {
     // Calculate buffer size
     uint64_t buf_size = add_size;
@@ -306,7 +321,7 @@ void* alloc_read_buffer(osd_rmw_stripe_t *stripes, int read_pg_size, uint64_t ad
         }
     }
     // Allocate buffer
-    void *buf = memalign_or_die(MEM_ALIGNMENT, buf_size);
+    void *buf = memalign_or_die(MEM_ALIGNMENT, buf_size + bitmap_size*read_pg_size);
     uint64_t buf_pos = add_size;
     for (int role = 0; role < read_pg_size; role++)
     {
@@ -316,11 +331,21 @@ void* alloc_read_buffer(osd_rmw_stripe_t *stripes, int read_pg_size, uint64_t ad
             buf_pos += stripes[role].read_end - stripes[role].read_start;
         }
     }
+    // Bitmaps are allocated in the end so data buffers remain aligned
+    if (bitmap_size > 0)
+    {
+        for (int role = 0; role < read_pg_size; role++)
+        {
+            stripes[role].bmp_buf = buf + buf_pos;
+            buf_pos += bitmap_size;
+        }
+    }
     return buf;
 }
 
 void* calc_rmw(void *request_buf, osd_rmw_stripe_t *stripes, uint64_t *read_osd_set,
-    uint64_t pg_size, uint64_t pg_minsize, uint64_t pg_cursize, uint64_t *write_osd_set, uint64_t chunk_size)
+    uint64_t pg_size, uint64_t pg_minsize, uint64_t pg_cursize, uint64_t *write_osd_set,
+    uint64_t chunk_size, uint32_t bitmap_size)
 {
     // Generic parity modification (read-modify-write) algorithm
     // Read -> Reconstruct missing chunks -> Calc parity chunks -> Write
@@ -420,7 +445,7 @@ void* calc_rmw(void *request_buf, osd_rmw_stripe_t *stripes, uint64_t *read_osd_
         }
     }
     // Allocate read buffers
-    void *rmw_buf = alloc_read_buffer(stripes, pg_size, (write_parity ? pg_size-pg_minsize : 0) * (end - start));
+    void *rmw_buf = alloc_read_buffer(stripes, pg_size, (write_parity ? pg_size-pg_minsize : 0) * (end - start), bitmap_size);
     // Position write buffers
     uint64_t buf_pos = 0, in_pos = 0;
     for (int role = 0; role < pg_size; role++)
@@ -521,11 +546,12 @@ static void xor_multiple_buffers(buf_len_t *xor1, int n1, buf_len_t *xor2, int n
 }
 
 static void calc_rmw_parity_copy_mod(osd_rmw_stripe_t *stripes, int pg_size, int pg_minsize,
-    uint64_t *read_osd_set, uint64_t *write_osd_set, uint32_t chunk_size, uint32_t &start, uint32_t &end)
+    uint64_t *read_osd_set, uint64_t *write_osd_set, uint32_t chunk_size, uint32_t bitmap_granularity,
+    uint32_t &start, uint32_t &end)
 {
     if (write_osd_set[pg_minsize] != 0 || write_osd_set != read_osd_set)
     {
-        // Required for the next two if()s
+        // start & end are required for calc_rmw_parity
         for (int role = 0; role < pg_minsize; role++)
         {
             if (stripes[role].req_end != 0)
@@ -543,6 +569,20 @@ static void calc_rmw_parity_copy_mod(osd_rmw_stripe_t *stripes, int pg_size, int
             }
         }
     }
+    // Set bitmap bits accordingly
+    if (bitmap_granularity > 0)
+    {
+        for (int role = 0; role < pg_minsize; role++)
+        {
+            if (stripes[role].req_end != 0)
+            {
+                bitmap_set(
+                    stripes[role].bmp_buf, stripes[role].req_start,
+                    stripes[role].req_end-stripes[role].req_start, bitmap_granularity
+                );
+            }
+        }
+    }
     if (write_osd_set != read_osd_set)
     {
         for (int role = 0; role < pg_minsize; role++)
@@ -603,12 +643,14 @@ static void calc_rmw_parity_copy_parity(osd_rmw_stripe_t *stripes, int pg_size,
 #endif
 }
 
-void calc_rmw_parity_xor(osd_rmw_stripe_t *stripes, int pg_size, uint64_t *read_osd_set, uint64_t *write_osd_set, uint32_t chunk_size)
+void calc_rmw_parity_xor(osd_rmw_stripe_t *stripes, int pg_size, uint64_t *read_osd_set, uint64_t *write_osd_set,
+    uint32_t chunk_size, uint32_t bitmap_size)
 {
+    uint32_t bitmap_granularity = bitmap_size > 0 ? chunk_size / bitmap_size / 8 : 0;
     int pg_minsize = pg_size-1;
-    reconstruct_stripes_xor(stripes, pg_size);
+    reconstruct_stripes_xor(stripes, pg_size, bitmap_size);
     uint32_t start = 0, end = 0;
-    calc_rmw_parity_copy_mod(stripes, pg_size, pg_minsize, read_osd_set, write_osd_set, chunk_size, start, end);
+    calc_rmw_parity_copy_mod(stripes, pg_size, pg_minsize, read_osd_set, write_osd_set, chunk_size, bitmap_granularity, start, end);
     if (write_osd_set[pg_minsize] != 0 && end != 0)
     {
         // Calculate new parity (XOR k+1)
@@ -626,9 +668,11 @@ void calc_rmw_parity_xor(osd_rmw_stripe_t *stripes, int pg_size, uint64_t *read_
                 if (prev == -1)
                 {
                     xor1[n1++] = { .buf = stripes[parity].write_buf, .len = end-start };
+                    memxor(stripes[parity].bmp_buf, stripes[other].bmp_buf, stripes[parity].bmp_buf, bitmap_size);
                 }
                 else
                 {
+                    memxor(stripes[prev].bmp_buf, stripes[other].bmp_buf, stripes[parity].bmp_buf, bitmap_size);
                     get_old_new_buffers(stripes[prev], start, end, xor1, n1);
                     prev = -1;
                 }
@@ -641,12 +685,13 @@ void calc_rmw_parity_xor(osd_rmw_stripe_t *stripes, int pg_size, uint64_t *read_
 }
 
 void calc_rmw_parity_jerasure(osd_rmw_stripe_t *stripes, int pg_size, int pg_minsize,
-    uint64_t *read_osd_set, uint64_t *write_osd_set, uint32_t chunk_size)
+    uint64_t *read_osd_set, uint64_t *write_osd_set, uint32_t chunk_size, uint32_t bitmap_size)
 {
+    uint32_t bitmap_granularity = bitmap_size > 0 ? chunk_size / bitmap_size / 8 : 0;
     reed_sol_matrix_t *matrix = get_jerasure_matrix(pg_size, pg_minsize);
-    reconstruct_stripes_jerasure(stripes, pg_size, pg_minsize);
+    reconstruct_stripes_jerasure(stripes, pg_size, pg_minsize, bitmap_size);
     uint32_t start = 0, end = 0;
-    calc_rmw_parity_copy_mod(stripes, pg_size, pg_minsize, read_osd_set, write_osd_set, chunk_size, start, end);
+    calc_rmw_parity_copy_mod(stripes, pg_size, pg_minsize, read_osd_set, write_osd_set, chunk_size, bitmap_granularity, start, end);
     if (end != 0)
     {
         int i;
@@ -701,6 +746,14 @@ void calc_rmw_parity_jerasure(osd_rmw_stripe_t *stripes, int pg_size, int pg_min
                 );
                 pos = next_end;
             }
+            for (int i = 0; i < pg_size; i++)
+            {
+                data_ptrs[i] = stripes[i].bmp_buf;
+            }
+            jerasure_matrix_encode(
+                pg_minsize, pg_size-pg_minsize, OSD_JERASURE_W, matrix->data,
+                (char**)data_ptrs, (char**)data_ptrs+pg_minsize, bitmap_size
+            );
         }
     }
     calc_rmw_parity_copy_parity(stripes, pg_size, pg_minsize, read_osd_set, write_osd_set, chunk_size, start, end);
diff --git a/src/osd_rmw.h b/src/osd_rmw.h
index 5f0e30ef7..931c5cb19 100644
--- a/src/osd_rmw.h
+++ b/src/osd_rmw.h
@@ -20,6 +20,7 @@ struct buf_len_t
 struct osd_rmw_stripe_t
 {
     void *read_buf, *write_buf;
+    void *bmp_buf;
     uint32_t req_start, req_end;
     uint32_t read_start, read_end;
     uint32_t write_start, write_end;
@@ -30,20 +31,22 @@ struct osd_rmw_stripe_t
 
 void split_stripes(uint64_t pg_minsize, uint32_t bs_block_size, uint32_t start, uint32_t len, osd_rmw_stripe_t *stripes);
 
-void reconstruct_stripes_xor(osd_rmw_stripe_t *stripes, int pg_size);
+void reconstruct_stripes_xor(osd_rmw_stripe_t *stripes, int pg_size, uint32_t bitmap_size);
 
 int extend_missing_stripes(osd_rmw_stripe_t *stripes, osd_num_t *osd_set, int pg_minsize, int pg_size);
 
-void* alloc_read_buffer(osd_rmw_stripe_t *stripes, int read_pg_size, uint64_t add_size);
+void* alloc_read_buffer(osd_rmw_stripe_t *stripes, int read_pg_size, uint64_t add_size, uint32_t bitmap_size);
 
 void* calc_rmw(void *request_buf, osd_rmw_stripe_t *stripes, uint64_t *read_osd_set,
-    uint64_t pg_size, uint64_t pg_minsize, uint64_t pg_cursize, uint64_t *write_osd_set, uint64_t chunk_size);
+    uint64_t pg_size, uint64_t pg_minsize, uint64_t pg_cursize, uint64_t *write_osd_set,
+    uint64_t chunk_size, uint32_t bitmap_size);
 
-void calc_rmw_parity_xor(osd_rmw_stripe_t *stripes, int pg_size, uint64_t *read_osd_set, uint64_t *write_osd_set, uint32_t chunk_size);
+void calc_rmw_parity_xor(osd_rmw_stripe_t *stripes, int pg_size, uint64_t *read_osd_set, uint64_t *write_osd_set,
+    uint32_t chunk_size, uint32_t bitmap_size);
 
 void use_jerasure(int pg_size, int pg_minsize, bool use);
 
-void reconstruct_stripes_jerasure(osd_rmw_stripe_t *stripes, int pg_size, int pg_minsize);
+void reconstruct_stripes_jerasure(osd_rmw_stripe_t *stripes, int pg_size, int pg_minsize, uint32_t bitmap_size);
 
 void calc_rmw_parity_jerasure(osd_rmw_stripe_t *stripes, int pg_size, int pg_minsize,
-    uint64_t *read_osd_set, uint64_t *write_osd_set, uint32_t chunk_size);
+    uint64_t *read_osd_set, uint64_t *write_osd_set, uint32_t chunk_size, uint32_t bitmap_size);
diff --git a/src/osd_rmw_test.cpp b/src/osd_rmw_test.cpp
index 79e840422..64b278c71 100644
--- a/src/osd_rmw_test.cpp
+++ b/src/osd_rmw_test.cpp
@@ -126,12 +126,13 @@ void test1()
 
 void test4()
 {
+    const uint32_t bmp = 4;
     osd_num_t osd_set[3] = { 1, 0, 3 };
     osd_rmw_stripe_t stripes[3] = { 0 };
     // Test 4.1
     split_stripes(2, 128*1024, 128*1024-4096, 8192, stripes);
     void* write_buf = malloc(8192);
-    void* rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 2, osd_set, 128*1024);
+    void* rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 2, osd_set, 128*1024, bmp);
     assert(stripes[0].read_start == 0 && stripes[0].read_end == 128*1024);
     assert(stripes[1].read_start == 4096 && stripes[1].read_end == 128*1024);
     assert(stripes[2].read_start == 4096 && stripes[2].read_end == 128*1024);
@@ -149,7 +150,13 @@ void test4()
     set_pattern(stripes[0].read_buf, 128*1024, PATTERN1); // old data
     set_pattern(stripes[1].read_buf, 128*1024-4096, UINT64_MAX); // didn't read it, it's missing
     set_pattern(stripes[2].read_buf, 128*1024-4096, 0); // old parity = 0
-    calc_rmw_parity_xor(stripes, 3, osd_set, osd_set, 128*1024);
+    memset(stripes[0].bmp_buf, 0, bmp);
+    memset(stripes[1].bmp_buf, 0, bmp);
+    memset(stripes[2].bmp_buf, 0, bmp);
+    calc_rmw_parity_xor(stripes, 3, osd_set, osd_set, 128*1024, bmp);
+    assert(*(uint32_t*)stripes[0].bmp_buf == 0x80000000);
+    assert(*(uint32_t*)stripes[1].bmp_buf == 0x00000001);
+    assert(*(uint32_t*)stripes[2].bmp_buf == 0x80000001); // XOR
     check_pattern(stripes[2].write_buf, 4096, PATTERN0^PATTERN1); // new parity
     check_pattern(stripes[2].write_buf+4096, 128*1024-4096*2, 0); // new parity
     check_pattern(stripes[2].write_buf+128*1024-4096, 4096, PATTERN0^PATTERN1); // new parity
@@ -181,7 +188,7 @@ void test5()
     assert(stripes[2].req_end == 0);
     // Test 5.2
     void *write_buf = malloc(64*1024*3);
-    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 2, osd_set, 128*1024);
+    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 2, osd_set, 128*1024, 0);
     assert(stripes[0].read_start == 64*1024 && stripes[0].read_end == 128*1024);
     assert(stripes[1].read_start == 64*1024 && stripes[1].read_end == 128*1024);
     assert(stripes[2].read_start == 64*1024 && stripes[2].read_end == 128*1024);
@@ -218,7 +225,7 @@ void test6()
     // Test 6.1
     split_stripes(2, 128*1024, 0, 64*1024*3, stripes);
     void *write_buf = malloc(64*1024*3);
-    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 3, osd_set, 128*1024);
+    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 3, osd_set, 128*1024, 0);
     assert(stripes[0].read_end == 0);
     assert(stripes[1].read_start == 64*1024 && stripes[1].read_end == 128*1024);
     assert(stripes[2].read_end == 0);
@@ -261,7 +268,7 @@ void test7()
     // Test 7.1
     split_stripes(2, 128*1024, 128*1024-4096, 8192, stripes);
     void *write_buf = malloc(8192);
-    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 2, write_osd_set, 128*1024);
+    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 2, write_osd_set, 128*1024, 0);
     assert(stripes[0].read_start == 0 && stripes[0].read_end == 128*1024);
     assert(stripes[1].read_start == 0 && stripes[1].read_end == 128*1024);
     assert(stripes[2].read_start == 0 && stripes[2].read_end == 128*1024);
@@ -279,7 +286,7 @@ void test7()
     set_pattern(stripes[0].read_buf, 128*1024, PATTERN1); // old data
     set_pattern(stripes[1].read_buf, 128*1024, UINT64_MAX); // didn't read it, it's missing
     set_pattern(stripes[2].read_buf, 128*1024, 0); // old parity = 0
-    calc_rmw_parity_xor(stripes, 3, osd_set, write_osd_set, 128*1024);
+    calc_rmw_parity_xor(stripes, 3, osd_set, write_osd_set, 128*1024, 0);
     assert(stripes[0].write_start == 128*1024-4096 && stripes[0].write_end == 128*1024);
     assert(stripes[1].write_start == 0 && stripes[1].write_end == 128*1024);
     assert(stripes[2].write_start == 0 && stripes[2].write_end == 128*1024);
@@ -314,7 +321,7 @@ void test8()
     // Test 8.1
     split_stripes(2, 128*1024, 0, 128*1024+4096, stripes);
     void *write_buf = malloc(128*1024+4096);
-    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 2, write_osd_set, 128*1024);
+    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 2, write_osd_set, 128*1024, 0);
     assert(stripes[0].read_start == 0 && stripes[0].read_end == 0);
     assert(stripes[1].read_start == 4096 && stripes[1].read_end == 128*1024);
     assert(stripes[2].read_start == 0 && stripes[2].read_end == 0);
@@ -330,7 +337,7 @@ void test8()
     // Test 8.2
     set_pattern(write_buf, 128*1024+4096, PATTERN0);
     set_pattern(stripes[1].read_buf, 128*1024-4096, PATTERN1);
-    calc_rmw_parity_xor(stripes, 3, osd_set, write_osd_set, 128*1024);
+    calc_rmw_parity_xor(stripes, 3, osd_set, write_osd_set, 128*1024, 0);
     assert(stripes[0].write_start == 0 && stripes[0].write_end == 128*1024); // recheck again
     assert(stripes[1].write_start == 0 && stripes[1].write_end == 4096);     // recheck again
     assert(stripes[2].write_start == 0 && stripes[2].write_end == 128*1024); // recheck again
@@ -373,7 +380,7 @@ void test9()
     assert(stripes[2].req_start == 0 && stripes[2].req_end == 0);
     // Test 9.1
     void *write_buf = NULL;
-    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 3, write_osd_set, 128*1024);
+    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 3, write_osd_set, 128*1024, 0);
     assert(stripes[0].read_start == 0 && stripes[0].read_end == 128*1024);
     assert(stripes[1].read_start == 0 && stripes[1].read_end == 128*1024);
     assert(stripes[2].read_start == 0 && stripes[2].read_end == 128*1024);
@@ -389,7 +396,7 @@ void test9()
     // Test 9.2
     set_pattern(stripes[1].read_buf, 128*1024, 0);
     set_pattern(stripes[2].read_buf, 128*1024, PATTERN1);
-    calc_rmw_parity_xor(stripes, 3, osd_set, write_osd_set, 128*1024);
+    calc_rmw_parity_xor(stripes, 3, osd_set, write_osd_set, 128*1024, 0);
     assert(stripes[0].write_start == 0 && stripes[0].write_end == 128*1024);
     assert(stripes[1].write_start == 0 && stripes[1].write_end == 0);
     assert(stripes[2].write_start == 0 && stripes[2].write_end == 0);
@@ -428,7 +435,7 @@ void test10()
     assert(stripes[2].req_start == 0 && stripes[2].req_end == 0);
     // Test 10.1
     void *write_buf = malloc(256*1024);
-    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 3, write_osd_set, 128*1024);
+    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 3, write_osd_set, 128*1024, 0);
     assert(rmw_buf);
     assert(stripes[0].read_start == 0 && stripes[0].read_end == 0);
     assert(stripes[1].read_start == 0 && stripes[1].read_end == 0);
@@ -445,7 +452,7 @@ void test10()
     // Test 10.2
     set_pattern(stripes[0].write_buf, 128*1024, PATTERN1);
     set_pattern(stripes[1].write_buf, 128*1024, PATTERN2);
-    calc_rmw_parity_xor(stripes, 3, osd_set, write_osd_set, 128*1024);
+    calc_rmw_parity_xor(stripes, 3, osd_set, write_osd_set, 128*1024, 0);
     assert(stripes[0].write_start == 0 && stripes[0].write_end == 128*1024);
     assert(stripes[1].write_start == 0 && stripes[1].write_end == 128*1024);
     assert(stripes[2].write_start == 0 && stripes[2].write_end == 128*1024);
@@ -484,7 +491,7 @@ void test11()
     assert(stripes[2].req_start == 0 && stripes[2].req_end == 0);
     // Test 11.1
     void *write_buf = malloc(256*1024);
-    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 3, write_osd_set, 128*1024);
+    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 3, write_osd_set, 128*1024, 0);
     assert(rmw_buf);
     assert(stripes[0].read_start == 0 && stripes[0].read_end == 128*1024);
     assert(stripes[1].read_start == 0 && stripes[1].read_end == 0);
@@ -501,7 +508,7 @@ void test11()
     // Test 11.2
     set_pattern(stripes[0].read_buf, 128*1024, PATTERN1);
     set_pattern(stripes[1].write_buf, 128*1024, PATTERN2);
-    calc_rmw_parity_xor(stripes, 3, osd_set, write_osd_set, 128*1024);
+    calc_rmw_parity_xor(stripes, 3, osd_set, write_osd_set, 128*1024, 0);
     assert(stripes[0].write_start == 0 && stripes[0].write_end == 0);
     assert(stripes[1].write_start == 0 && stripes[1].write_end == 128*1024);
     assert(stripes[2].write_start == 0 && stripes[2].write_end == 128*1024);
@@ -539,7 +546,7 @@ void test12()
     assert(stripes[1].req_start == 0 && stripes[1].req_end == 0);
     assert(stripes[2].req_start == 0 && stripes[2].req_end == 0);
     // Test 12.1
-    void *rmw_buf = calc_rmw(NULL, stripes, osd_set, 3, 2, 3, write_osd_set, 128*1024);
+    void *rmw_buf = calc_rmw(NULL, stripes, osd_set, 3, 2, 3, write_osd_set, 128*1024, 0);
     assert(rmw_buf);
     assert(stripes[0].read_start == 0 && stripes[0].read_end == 128*1024);
     assert(stripes[1].read_start == 0 && stripes[1].read_end == 128*1024);
@@ -556,7 +563,7 @@ void test12()
     // Test 12.2
     set_pattern(stripes[0].read_buf, 128*1024, PATTERN1);
     set_pattern(stripes[1].read_buf, 128*1024, PATTERN2);
-    calc_rmw_parity_xor(stripes, 3, osd_set, write_osd_set, 128*1024);
+    calc_rmw_parity_xor(stripes, 3, osd_set, write_osd_set, 128*1024, 0);
     assert(stripes[0].write_start == 0 && stripes[0].write_end == 0);
     assert(stripes[1].write_start == 0 && stripes[1].write_end == 0);
     assert(stripes[2].write_start == 0 && stripes[2].write_end == 128*1024);
@@ -596,7 +603,7 @@ void test13()
     assert(stripes[2].req_start == 0 && stripes[2].req_end == 0);
     assert(stripes[3].req_start == 0 && stripes[3].req_end == 0);
     // Test 13.1
-    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 4, 2, 4, write_osd_set, 128*1024);
+    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 4, 2, 4, write_osd_set, 128*1024, 0);
     assert(rmw_buf);
     assert(stripes[0].read_start == 0 && stripes[0].read_end == 128*1024-4096);
     assert(stripes[1].read_start == 4096 && stripes[1].read_end == 128*1024);
@@ -618,7 +625,7 @@ void test13()
     set_pattern(write_buf, 8192, PATTERN3);
     set_pattern(stripes[0].read_buf, 128*1024-4096, PATTERN1);
     set_pattern(stripes[1].read_buf, 128*1024-4096, PATTERN2);
-    calc_rmw_parity_jerasure(stripes, 4, 2, osd_set, write_osd_set, 128*1024);
+    calc_rmw_parity_jerasure(stripes, 4, 2, osd_set, write_osd_set, 128*1024, 0);
     assert(stripes[0].write_start == 128*1024-4096 && stripes[0].write_end == 128*1024);
     assert(stripes[1].write_start == 0 && stripes[1].write_end == 4096);
     assert(stripes[2].write_start == 0 && stripes[2].write_end == 128*1024);
@@ -645,7 +652,7 @@ void test13()
     assert(stripes[1].read_start == 0 && stripes[1].read_end == 128*1024);
     assert(stripes[2].read_start == 0 && stripes[2].read_end == 128*1024);
     assert(stripes[3].read_start == 0 && stripes[3].read_end == 128*1024);
-    void *read_buf = alloc_read_buffer(stripes, 4, 0);
+    void *read_buf = alloc_read_buffer(stripes, 4, 0, 0);
     assert(read_buf);
     assert(stripes[0].read_buf == read_buf);
     assert(stripes[1].read_buf == read_buf+128*1024);
@@ -653,7 +660,7 @@ void test13()
     assert(stripes[3].read_buf == read_buf+3*128*1024);
     memcpy(read_buf+2*128*1024, rmw_buf, 128*1024);
     memcpy(read_buf+3*128*1024, rmw_buf+128*1024, 128*1024);
-    reconstruct_stripes_jerasure(stripes, 4, 2);
+    reconstruct_stripes_jerasure(stripes, 4, 2, 0);
     check_pattern(stripes[0].read_buf, 128*1024-4096, PATTERN1);
     check_pattern(stripes[0].read_buf+128*1024-4096, 4096, PATTERN3);
     check_pattern(stripes[1].read_buf, 4096, PATTERN3);
@@ -676,7 +683,7 @@ void test13()
     assert(stripes[1].read_start == 0 && stripes[1].read_end == 0);
     assert(stripes[2].read_start == 0 && stripes[2].read_end == 128*1024);
     assert(stripes[3].read_start == 0 && stripes[3].read_end == 128*1024);
-    read_buf = alloc_read_buffer(stripes, 4, 0);
+    read_buf = alloc_read_buffer(stripes, 4, 0, 0);
     assert(read_buf);
     assert(stripes[0].read_buf == read_buf);
     assert(stripes[1].read_buf == NULL);
@@ -684,7 +691,7 @@ void test13()
     assert(stripes[3].read_buf == read_buf+2*128*1024);
     memcpy(read_buf+128*1024, rmw_buf, 128*1024);
     memcpy(read_buf+2*128*1024, rmw_buf+128*1024, 128*1024);
-    reconstruct_stripes_jerasure(stripes, 4, 2);
+    reconstruct_stripes_jerasure(stripes, 4, 2, 0);
     check_pattern(stripes[0].read_buf, 128*1024-4096, PATTERN1);
     check_pattern(stripes[0].read_buf+128*1024-4096, 4096, PATTERN3);
     free(read_buf);
@@ -711,6 +718,7 @@ void test13()
 
 void test14()
 {
+    const int bmp = 4;
     use_jerasure(3, 2, true);
     osd_num_t osd_set[3] = { 1, 2, 0 };
     osd_num_t write_osd_set[3] = { 1, 2, 3 };
@@ -722,7 +730,7 @@ void test14()
     assert(stripes[1].req_start == 0 && stripes[1].req_end == 4096);
     assert(stripes[2].req_start == 0 && stripes[2].req_end == 0);
     // Test 13.1
-    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 3, write_osd_set, 128*1024);
+    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 3, 2, 3, write_osd_set, 128*1024, bmp);
     assert(rmw_buf);
     assert(stripes[0].read_start == 0 && stripes[0].read_end == 128*1024-4096);
     assert(stripes[1].read_start == 4096 && stripes[1].read_end == 128*1024);
@@ -740,7 +748,13 @@ void test14()
     set_pattern(write_buf, 8192, PATTERN3);
     set_pattern(stripes[0].read_buf, 128*1024-4096, PATTERN1);
     set_pattern(stripes[1].read_buf, 128*1024-4096, PATTERN2);
-    calc_rmw_parity_jerasure(stripes, 3, 2, osd_set, write_osd_set, 128*1024);
+    memset(stripes[0].bmp_buf, 0, bmp);
+    memset(stripes[1].bmp_buf, 0, bmp);
+    memset(stripes[2].bmp_buf, 0, bmp);
+    calc_rmw_parity_jerasure(stripes, 3, 2, osd_set, write_osd_set, 128*1024, bmp);
+    assert(*(uint32_t*)stripes[0].bmp_buf == 0x80000000);
+    assert(*(uint32_t*)stripes[1].bmp_buf == 0x00000001);
+    assert(*(uint32_t*)stripes[2].bmp_buf == 0x80000001); // jerasure 2+1 is still just XOR
     assert(stripes[0].write_start == 128*1024-4096 && stripes[0].write_end == 128*1024);
     assert(stripes[1].write_start == 0 && stripes[1].write_end == 4096);
     assert(stripes[2].write_start == 0 && stripes[2].write_end == 128*1024);
@@ -763,7 +777,7 @@ void test14()
     assert(stripes[0].read_start == 0 && stripes[0].read_end == 128*1024);
     assert(stripes[1].read_start == 0 && stripes[1].read_end == 128*1024);
     assert(stripes[2].read_start == 0 && stripes[2].read_end == 128*1024);
-    void *read_buf = alloc_read_buffer(stripes, 3, 0);
+    void *read_buf = alloc_read_buffer(stripes, 3, 0, bmp);
     assert(read_buf);
     assert(stripes[0].read_buf == read_buf);
     assert(stripes[1].read_buf == read_buf+128*1024);
@@ -771,7 +785,7 @@ void test14()
     set_pattern(stripes[1].read_buf, 4096, PATTERN3);
     set_pattern(stripes[1].read_buf+4096, 128*1024-4096, PATTERN2);
     memcpy(stripes[2].read_buf, rmw_buf, 128*1024);
-    reconstruct_stripes_jerasure(stripes, 3, 2);
+    reconstruct_stripes_jerasure(stripes, 3, 2, bmp);
     check_pattern(stripes[0].read_buf, 128*1024-4096, PATTERN1);
     check_pattern(stripes[0].read_buf+128*1024-4096, 4096, PATTERN3);
     free(read_buf);