Branch HEAD

b=13805
i=ericm
i=bobijam

add support for several checksum algorithms. Currently, CRC32 and
Adler-32 are supported. The checksum type can be changed on the fly
through /proc/fs/lustre/osc/*/checksum_type.

diff --git a/lustre/ChangeLog b/lustre/ChangeLog
index d6921a5..27cfdd9 100644 (file)
--- a/lustre/ChangeLog
+++ b/lustre/ChangeLog
@@ -22,10 +22,10 @@ Frequency  : occasional
 Bugzilla   : 13537
 Description: Correctly check stale fid, not start epoch if ost not support SOM
 Details    : open with flag O_CREATE need set old fid in op_fid3 because op_fid2
 Bugzilla   : 13537
 Description: Correctly check stale fid, not start epoch if ost not support SOM
 Details    : open with flag O_CREATE need set old fid in op_fid3 because op_fid2

-             overwrited with new generated fid, but mds can anwer with one of these
-             two fids and both is not stale. setattr incorectly start epoch and
-             assume will be called done_writeting, but without SOM done_writing
-             never called.
+            overwrited with new generated fid, but mds can anwer with one of these
+            two fids and both is not stale. setattr incorectly start epoch and
+            assume will be called done_writeting, but without SOM done_writing
+            never called.

 
 Severity   : major
 Frequency  : rare, depends on device drivers and load
 
 Severity   : major
 Frequency  : rare, depends on device drivers and load


@@ -41,9 +41,9 @@ Severity   : normal
 Frequency  : occasional
 Bugzilla   : 13730
 Description: Do not fail import if osc_interpret_create gets -EAGAIN
 Frequency  : occasional
 Bugzilla   : 13730
 Description: Do not fail import if osc_interpret_create gets -EAGAIN

-Details    : If osc_interpret_create got -EAGAIN it immediately exits and 
-            wakeup oscc_waitq.  After wakeup oscc_wait_for_objects call 
-            oscc_has_objects and see OSC has no objests and call 
+Details    : If osc_interpret_create got -EAGAIN it immediately exits and
+            wakeup oscc_waitq.  After wakeup oscc_wait_for_objects call
+            oscc_has_objects and see OSC has no objests and call

             oscc_internal_create to resend create request.
 
 Severity   : enhancement
             oscc_internal_create to resend create request.
 
 Severity   : enhancement


@@ -84,7 +84,7 @@ Details    : Don't allow skipping OSTs if index has been specified, make locking
 Severity   : normal
 Bugzilla   : 12228
 Description: LBUG in ptlrpc_check_set() bad phase ebc0de00
 Severity   : normal
 Bugzilla   : 12228
 Description: LBUG in ptlrpc_check_set() bad phase ebc0de00

-Details    : access to bitfield in structure is always rounded to long 
+Details    : access to bitfield in structure is always rounded to long

             and this produce problem with not atomic change any bit.
 
 Severity   : normal
             and this produce problem with not atomic change any bit.
 
 Severity   : normal


@@ -100,7 +100,7 @@ Description: If llog cancel was not send before clean_exports phase, this can
             produce deadlock in llog code.
 Details    : If llog thread has last reference to obd and call class_import_put
             this produce deadlock because llog_cleanup_commit_master wait when
             produce deadlock in llog code.
 Details    : If llog thread has last reference to obd and call class_import_put
             this produce deadlock because llog_cleanup_commit_master wait when

-            last llog_commit_thread exited, but this never success because was 
+            last llog_commit_thread exited, but this never success because was

             called from llog_commit_thread.
 
 Severity   : normal
             called from llog_commit_thread.
 
 Severity   : normal


@@ -160,7 +160,7 @@ Frequency  : rare, at shutdown
 Description: access already free / zero obd_namespace.
 Details    : if client_disconnect_export was called without force flag set,
             and exist connect request in flight, this can produce access to
 Description: access already free / zero obd_namespace.
 Details    : if client_disconnect_export was called without force flag set,
             and exist connect request in flight, this can produce access to

-            NULL pointer (or already free pointer) when connect_interpret 
+            NULL pointer (or already free pointer) when connect_interpret

             store ocd flags in obd_namespace.
 
 Severity   : minor
             store ocd flags in obd_namespace.
 
 Severity   : minor


@@ -178,7 +178,7 @@ Details    : Make lustre randomly failed allocating memory for testing purpose.
 Severity   : enhancement
 Bugzilla   : 12702
 Description: lost problems with lov objid file
 Severity   : enhancement
 Bugzilla   : 12702
 Description: lost problems with lov objid file

-Details    : Fixes some scability and access to not inited memory problems 
+Details    : Fixes some scability and access to not inited memory problems

             in work with lov objdid file.
 
 Severity   : major
             in work with lov objdid file.
 
 Severity   : major


@@ -220,18 +220,18 @@ Description: Update to RHEL4 latest kernel.
 Severity   : enhancement
 Bugzilla   : 13690
 Description: Build SLES10 patchless client fails
 Severity   : enhancement
 Bugzilla   : 13690
 Description: Build SLES10 patchless client fails

-Details    : The configure was broken by run ./configure with 
+Details    : The configure was broken by run ./configure with

             --with-linux-obj=.... argument for patchless client. When the
             configure use --with-linux-obj, the LINUXINCLUDE= -Iinclude
             --with-linux-obj=.... argument for patchless client. When the
             configure use --with-linux-obj, the LINUXINCLUDE= -Iinclude

-            can't search header adequately. Use absolute path such as 
-            -I($LINUX)/include instead. 
+            can't search header adequately. Use absolute path such as
+            -I($LINUX)/include instead.

 
 Severity   : normal
 Bugzilla   : 13888
 Description: interrupt oig_wait produce painc on resend.
 Details    : brw_redo_request can be used for resend requests from ptlrpcd and
             private set, and this produce situation when rq_ptlrpcd_data not
 
 Severity   : normal
 Bugzilla   : 13888
 Description: interrupt oig_wait produce painc on resend.
 Details    : brw_redo_request can be used for resend requests from ptlrpcd and
             private set, and this produce situation when rq_ptlrpcd_data not

-            copyed to new allocated request and triggered LBUG on assert 
+            copyed to new allocated request and triggered LBUG on assert

             req->rq_ptlrpcd_data != NULL. But this member used only for wakeup
             ptlrpcd set if request is changed and can be safety changed to use
             rq_set directly.
             req->rq_ptlrpcd_data != NULL. But this member used only for wakeup
             ptlrpcd set if request is changed and can be safety changed to use
             rq_set directly.


@@ -256,10 +256,10 @@ Details    : This causes SLES 10 clients to behave as patchless clients
 Severity   : enhancement
 Bugzilla   : 2262
 Description: self-adjustable client's lru lists
 Severity   : enhancement
 Bugzilla   : 2262
 Description: self-adjustable client's lru lists

-Details    : use adaptive algorithm for managing client cached locks lru 
+Details    : use adaptive algorithm for managing client cached locks lru

             lists according to current server load, other client's work
             lists according to current server load, other client's work

-            pattern, memory activities, etc. Both, server and client 
-            side namespaces provide number of proc tunables for controlling 
+            pattern, memory activities, etc. Both, server and client
+            side namespaces provide number of proc tunables for controlling

             things
 
 Severity   : enhancement
             things
 
 Severity   : enhancement


@@ -381,7 +381,7 @@ Details    : set obd_health_check_timeout as 1.5x of obd_timeout
 Severity   : normal
 Bugzilla   : 12192
 Description: llapi_file_create() does not allow some changes
 Severity   : normal
 Bugzilla   : 12192
 Description: llapi_file_create() does not allow some changes

-Details    : add llapi_file_open() that allows specifying the mode and 
+Details    : add llapi_file_open() that allows specifying the mode and

             open flags, and also returns an open file handle.
 
 Severity   : normal
             open flags, and also returns an open file handle.
 
 Severity   : normal


@@ -392,9 +392,9 @@ Details    : Remove mnt_lustre_list in vfs_intent-2.6-rhel4.patch.
 Severity   : normal
 Bugzilla   : 10657
 Description: Add journal checksum support.(Kernel part)
 Severity   : normal
 Bugzilla   : 10657
 Description: Add journal checksum support.(Kernel part)

-Details    : The journal checksum feature adds two new flags i.e 
-            JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT and 
-            JBD2_FEATURE_COMPAT_CHECKSUM. JBD2_FEATURE_CHECKSUM flag 
+Details    : The journal checksum feature adds two new flags i.e
+            JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT and
+            JBD2_FEATURE_COMPAT_CHECKSUM. JBD2_FEATURE_CHECKSUM flag

             indicates that the commit block contains the checksum for
             the blocks described by the descriptor blocks. Now commit
             record can be sent to disk without waiting for descriptor
             indicates that the commit block contains the checksum for
             the blocks described by the descriptor blocks. Now commit
             record can be sent to disk without waiting for descriptor


@@ -414,7 +414,7 @@ Details    : execute lfs setstripe on client
 Severity   : major
 Bugzilla   : 12223
 Description: mds_obd_create error creating tmp object
 Severity   : major
 Bugzilla   : 12223
 Description: mds_obd_create error creating tmp object

-Details    : When the user sets quota on root, llog will be affected and can't 
+Details    : When the user sets quota on root, llog will be affected and can't

             create files and write files.
 
 Severity   : normal
             create files and write files.
 
 Severity   : normal


@@ -422,7 +422,7 @@ Frequency  : Always on ia64 patchless client, and possibly others.
 Bugzilla   : 12826
 Description: Add EXPORT_SYMBOL check for node_to_cpumask symbol.
 Details    : This allows the patchless client to be loaded on architectures
 Bugzilla   : 12826
 Description: Add EXPORT_SYMBOL check for node_to_cpumask symbol.
 Details    : This allows the patchless client to be loaded on architectures

-            without this export. 
+            without this export.

 
 Severity   : normal
 Bugzilla   : 13039
 
 Severity   : normal
 Bugzilla   : 13039


@@ -500,7 +500,7 @@ Details    : When generating the bio request for lustre file writes the
 
 Severity   : normal
 Bugzilla   : 11230
 
 Severity   : normal
 Bugzilla   : 11230

-Description: Tune the kernel for good SCSI performance. 
+Description: Tune the kernel for good SCSI performance.

 Details    : Set the value of /sys/block/{dev}/queue/max_sectors_kb
             to the value of /sys/block/{dev}/queue/max_hw_sectors_kb
             in mount_lustre.
 Details    : Set the value of /sys/block/{dev}/queue/max_sectors_kb
             to the value of /sys/block/{dev}/queue/max_hw_sectors_kb
             in mount_lustre.


@@ -542,8 +542,8 @@ Frequency  : only on ppc
 Bugzilla   : 12234
 Description: /proc/fs/lustre/devices broken on ppc
 Details    : The patch as applied to 1.6.2 doesn't look correct for all arches.
 Bugzilla   : 12234
 Description: /proc/fs/lustre/devices broken on ppc
 Details    : The patch as applied to 1.6.2 doesn't look correct for all arches.

-            We should make sure the type of 'index' is loff_t and then cast 
-            explicitly as needed below.  Do not assign an explicitly cast 
+            We should make sure the type of 'index' is loff_t and then cast
+            explicitly as needed below.  Do not assign an explicitly cast

             loff_t to an int.
 
 Severity   : normal
             loff_t to an int.
 
 Severity   : normal


@@ -562,14 +562,14 @@ Severity   : normal
 Bugzilla   : 13304
 Frequency  : Always, for kernels after 2.6.16
 Description: Fix warning idr_remove called for id=.. which is not allocated.
 Bugzilla   : 13304
 Frequency  : Always, for kernels after 2.6.16
 Description: Fix warning idr_remove called for id=.. which is not allocated.

-Details    : Last kernels save old s_dev before kill super and not allow 
+Details    : Last kernels save old s_dev before kill super and not allow

             to restore from callback - restore it before call kill_anon_super.
 
 Severity   : minor
 Bugzilla   : 12948
 Description: buffer overruns could theoretically occur
 Details    : llapi_semantic_traverse() modifies the "path" argument by
             to restore from callback - restore it before call kill_anon_super.
 
 Severity   : minor
 Bugzilla   : 12948
 Description: buffer overruns could theoretically occur
 Details    : llapi_semantic_traverse() modifies the "path" argument by

-            appending values to the end of the origin string, and a 
+            appending values to the end of the origin string, and a

             overrun may occur. Adding buffer overrun check in liblustreapi.
 
 Severity   : normal
             overrun may occur. Adding buffer overrun check in liblustreapi.
 
 Severity   : normal


@@ -602,12 +602,12 @@ Severity   : critical
 Bugzilla   : 13751
 Description: Kernel patches update for RHEL5 2.6.18-8.1.14.el5.
 Details    : Modify target file & which_patch.
 Bugzilla   : 13751
 Description: Kernel patches update for RHEL5 2.6.18-8.1.14.el5.
 Details    : Modify target file & which_patch.

-            A flaw was found in the IA32 system call emulation provided 
-            on AMD64 and Intel 64 platforms. An improperly validated 64-bit 
-            value could be stored in the %RAX register, which could trigger an 
-            out-of-bounds system call table access. An untrusted local user 
-            could exploit this flaw to run code in the kernel 
-            (ie a root privilege escalation). (CVE-2007-4573). 
+            A flaw was found in the IA32 system call emulation provided
+            on AMD64 and Intel 64 platforms. An improperly validated 64-bit
+            value could be stored in the %RAX register, which could trigger an
+            out-of-bounds system call table access. An untrusted local user
+            could exploit this flaw to run code in the kernel
+            (ie a root privilege escalation). (CVE-2007-4573).

 
 Severity   : major
 Bugzilla   : 13093
 
 Severity   : major
 Bugzilla   : 13093


@@ -621,7 +621,7 @@ Bugzilla   : 13454
 Description: Add jbd statistics patch for RHEL5 and 2.6.18-vanilla
 
 Severity   : minor
 Description: Add jbd statistics patch for RHEL5 and 2.6.18-vanilla
 
 Severity   : minor

-Bugzilla   : 13732 
+Bugzilla   : 13732

 Description: change order of libsysio includes
 Details    : '#include sysio.h' should always come before '#include xtio.h'
 
 Description: change order of libsysio includes
 Details    : '#include sysio.h' should always come before '#include xtio.h'
 


@@ -759,13 +759,13 @@ Severity   : enhancement
 Bugzilla   : 14729
 Description: SNMP support enhancement
 Details    : Adding total number of sampled request for an MDS node in snmp
 Bugzilla   : 14729
 Description: SNMP support enhancement
 Details    : Adding total number of sampled request for an MDS node in snmp

-             support.
+            support.

 
 Severity   : enhancement
 Bugzilla   : 14748
 Description: Optimize ldlm waiting list processing for PR extent locks
 Details    : When processing waiting list for read extent lock and meeting read
 
 Severity   : enhancement
 Bugzilla   : 14748
 Description: Optimize ldlm waiting list processing for PR extent locks
 Details    : When processing waiting list for read extent lock and meeting read

-             lock that is same or wider to it that is not contended, skip
+            lock that is same or wider to it that is not contended, skip

             processing rest of the list and immediatelly return current
             status of conflictness, since we are guaranteed there are no
             conflicting locks in the rest of the list.
             processing rest of the list and immediatelly return current
             status of conflictness, since we are guaranteed there are no
             conflicting locks in the rest of the list.


@@ -777,19 +777,26 @@ Details    : When the failover node is the primary node, it is possible
             to have two identical connections in imp_conn_list. We must
             compare not conn's pointers but NIDs, otherwise we can defeat
             connection throttling.
             to have two identical connections in imp_conn_list. We must
             compare not conn's pointers but NIDs, otherwise we can defeat
             connection throttling.

-            
+

 Severity   : normal
 Bugzilla   : 13821
 Description: port llog fixes from b1_6 into HEAD
 Details    : Port llog reference couting and some llog cleanups from b1_6
 Severity   : normal
 Bugzilla   : 13821
 Description: port llog fixes from b1_6 into HEAD
 Details    : Port llog reference couting and some llog cleanups from b1_6

-             (bug 10800) into HEAD, for protect from panic and access to already
+            (bug 10800) into HEAD, for protect from panic and access to already

             free llog structures.
 
 Severity   : normal
 Bugzilla   : 14483
             free llog structures.
 
 Severity   : normal
 Bugzilla   : 14483

-Description: Detect stride IO mode in read-ahead 
+Description: Detect stride IO mode in read-ahead

 Details    : When a client does stride read, read-ahead should detect that and
 Details    : When a client does stride read, read-ahead should detect that and

-            read-ahead pages according to the detected stride pattern. 
+            read-ahead pages according to the detected stride pattern.
+
+Severity   : normal
+Bugzilla   : 13805
+Description: data checksumming impacts single node performance
+Details    : add support for several checksum algorithm. Currently, only CRC32
+            and Adler-32 are supported. The checksum type can be changed on
+            the fly via /proc/fs/lustre/osc/*/checksum_type.

 
 --------------------------------------------------------------------------------
 
 
 --------------------------------------------------------------------------------
 

diff --git a/lustre/include/linux/obd_support.h b/lustre/include/linux/obd_support.h
index d6f57c3..362cbcb 100644 (file)
--- a/lustre/include/linux/obd_support.h
+++ b/lustre/include/linux/obd_support.h
@@ -37,6 +37,7 @@
 #endif
 #include <libcfs/kp30.h>
 #include <linux/lustre_compat25.h>
 #endif
 #include <libcfs/kp30.h>
 #include <linux/lustre_compat25.h>

+#include <lustre/lustre_idl.h>

 
 /* Prefer the kernel's version, if it exports it, because it might be
  * optimized for this CPU. */
 
 /* Prefer the kernel's version, if it exports it, because it might be
  * optimized for this CPU. */


@@ -87,6 +88,69 @@ static inline __u32 zlib_adler32(__u32 adler, unsigned char const *p,
 # endif
 #endif /* __KERNEL__ */
 
 # endif
 #endif /* __KERNEL__ */
 

+static inline __u32 init_checksum(cksum_type_t cksum_type)
+{
+        switch(cksum_type) {
+        case OBD_CKSUM_CRC32:
+                return ~0U;
+#ifdef HAVE_ADLER
+        case OBD_CKSUM_ADLER:
+                return 1U;
+#endif
+        default:
+                CERROR("Unknown checksum type (%x)!!!\n", cksum_type);
+                LBUG();
+        }
+        return 0;
+}
+
+static inline __u32 compute_checksum(__u32 cksum, unsigned char const *p,
+                                     size_t len, cksum_type_t cksum_type)
+{
+        switch(cksum_type) {
+        case OBD_CKSUM_CRC32:
+                return crc32_le(cksum, p, len);
+#ifdef HAVE_ADLER
+        case OBD_CKSUM_ADLER:
+                return zlib_adler32(cksum, p, len);
+#endif
+        default:
+                CERROR("Unknown checksum type (%x)!!!\n", cksum_type);
+                LBUG();
+        }
+        return 0;
+}
+
+static inline obd_flag cksum_type_pack(cksum_type_t cksum_type)
+{
+        switch(cksum_type) {
+        case OBD_CKSUM_CRC32:
+                return OBD_FL_CKSUM_CRC32;
+#ifdef HAVE_ADLER
+        case OBD_CKSUM_ADLER:
+                return OBD_FL_CKSUM_ADLER;
+#endif
+        default:
+                CWARN("unknown cksum type %x\n", cksum_type);
+        }
+        return OBD_FL_CKSUM_CRC32;
+}
+
+static inline cksum_type_t cksum_type_unpack(obd_flag o_flags)
+{
+        o_flags &= OBD_FL_CKSUM_ALL;
+        if ((o_flags - 1) & o_flags)
+                CWARN("several checksum types are set: %x\n", o_flags);
+        if (o_flags & OBD_FL_CKSUM_ADLER)
+#ifdef HAVE_ADLER
+                return OBD_CKSUM_ADLER;
+#else
+                CWARN("checksum type is set to adler32, but adler32 is not "
+                      "supported (%x)\n", o_flags);
+#endif
+        return OBD_CKSUM_CRC32;
+}
+

 #ifdef __KERNEL__
 # include <linux/types.h>
 # include <linux/blkdev.h>
 #ifdef __KERNEL__
 # include <linux/types.h>
 # include <linux/blkdev.h>

diff --git a/lustre/include/lustre/lustre_idl.h b/lustre/include/lustre/lustre_idl.h
index 2a8786f..d79772c 100644 (file)
--- a/lustre/include/lustre/lustre_idl.h
+++ b/lustre/include/lustre/lustre_idl.h
@@ -578,7 +578,7 @@ extern void lustre_swab_ptlrpc_body(struct ptlrpc_body *pb);
                                 OBD_CONNECT_TRUNCLOCK | OBD_CONNECT_INDEX | \
                                 OBD_CONNECT_BRW_SIZE | OBD_CONNECT_QUOTA64 | \
                                 OBD_CONNECT_OSS_CAPA | OBD_CONNECT_CANCELSET | \
                                 OBD_CONNECT_TRUNCLOCK | OBD_CONNECT_INDEX | \
                                 OBD_CONNECT_BRW_SIZE | OBD_CONNECT_QUOTA64 | \
                                 OBD_CONNECT_OSS_CAPA | OBD_CONNECT_CANCELSET | \

-                                OBD_CONNECT_FID | \
+                                OBD_CONNECT_FID | OBD_CONNECT_CKSUM | \

                                 LRU_RESIZE_CONNECT_FLAG)
 #define ECHO_CONNECT_SUPPORTED (0)
 #define MGS_CONNECT_SUPPORTED  (OBD_CONNECT_VERSION | OBD_CONNECT_FID)
                                 LRU_RESIZE_CONNECT_FLAG)
 #define ECHO_CONNECT_SUPPORTED (0)
 #define MGS_CONNECT_SUPPORTED  (OBD_CONNECT_VERSION | OBD_CONNECT_FID)


@@ -607,14 +607,25 @@ struct obd_connect_data {
         __u32 ocd_nllg;          /* non-local-lustre-group */
         __u64 ocd_transno;       /* first transno from client to be replayed */
         __u32 ocd_group;         /* MDS group on OST */
         __u32 ocd_nllg;          /* non-local-lustre-group */
         __u64 ocd_transno;       /* first transno from client to be replayed */
         __u32 ocd_group;         /* MDS group on OST */

-        __u32 padding1;          /* also fix lustre_swab_connect */
+        __u32 ocd_cksum_types;   /* supported checksum algorithms */
+        __u64 padding1;          /* also fix lustre_swab_connect */

         __u64 padding2;          /* also fix lustre_swab_connect */
         __u64 padding2;          /* also fix lustre_swab_connect */

-        __u64 padding3;          /* also fix lustre_swab_connect */

 };
 
 extern void lustre_swab_connect(struct obd_connect_data *ocd);
 
 /*
 };
 
 extern void lustre_swab_connect(struct obd_connect_data *ocd);
 
 /*

+ * Supported checksum algorithms. Up to 32 checksum types are supported.
+ * (32-bit mask stored in obd_connect_data::ocd_cksum_types)
+ * Please update DECLARE_CKSUM_NAME/OBD_CKSUM_ALL in obd.h when adding a new
+ * algorithm and also the OBD_FL_CKSUM* flags.
+ */
+typedef enum {
+        OBD_CKSUM_CRC32 = 0x00000001,
+        OBD_CKSUM_ADLER = 0x00000002,
+} cksum_type_t;
+
+/*

  *   OST requests: OBDO & OBD request records
  */
 
  *   OST requests: OBDO & OBD request records
  */
 


@@ -674,6 +685,13 @@ typedef uint32_t        obd_count;
 #define OBD_FL_TRUNCLOCK     (0x00000800)
 
 /*
 #define OBD_FL_TRUNCLOCK     (0x00000800)
 
 /*

+ * Checksum types
+ */
+#define OBD_FL_CKSUM_CRC32    (0x00001000)
+#define OBD_FL_CKSUM_ADLER    (0x00002000)
+#define OBD_FL_CKSUM_ALL      (OBD_FL_CKSUM_CRC32 | OBD_FL_CKSUM_ADLER)
+
+/*

  * This should not be smaller than sizeof(struct lustre_handle) + sizeof(struct
  * llog_cookie) + sizeof(struct ll_fid). Nevertheless struct ll_fid is not
  * longer stored in o_inline, we keep this just for case.
  * This should not be smaller than sizeof(struct lustre_handle) + sizeof(struct
  * llog_cookie) + sizeof(struct ll_fid). Nevertheless struct ll_fid is not
  * longer stored in o_inline, we keep this just for case.

diff --git a/lustre/include/obd.h b/lustre/include/obd.h
index c9041ee..ce00d17 100644 (file)
--- a/lustre/include/obd.h
+++ b/lustre/include/obd.h
@@ -453,9 +453,13 @@ struct client_obd {
         atomic_t                 cl_mgc_refcount;
         struct obd_export       *cl_mgc_mgsexp;
 
         atomic_t                 cl_mgc_refcount;
         struct obd_export       *cl_mgc_mgsexp;
 

-        /* Flags section */
-        unsigned long            cl_checksum:1; /* debug checksums */
-
+        /* checksumming for data sent over the network */
+        unsigned int             cl_checksum:1; /* 0 = disabled, 1 = enabled */
+        /* supported checksum types that are worked out at connect time */
+        __u32                    cl_supp_cksum_types;
+        /* checksum algorithm to be used */
+        cksum_type_t             cl_cksum_type;
+ 

         /* also protected by the poorly named _loi_list_lock lock above */
         struct osc_async_rc      cl_ar;
 
         /* also protected by the poorly named _loi_list_lock lock above */
         struct osc_async_rc      cl_ar;
 


@@ -1438,4 +1442,24 @@ static inline struct lustre_capa *oinfo_capa(struct obd_info *oinfo)
         return oinfo->oi_capa;
 }
 
         return oinfo->oi_capa;
 }
 

+/*
+ * Checksums
+ */
+
+#ifdef HAVE_ADLER
+/* Default preferred checksum algorithm to use (if supported by the server) */
+#define OSC_DEFAULT_CKSUM OBD_CKSUM_ADLER
+/* Adler-32 is supported */
+#define CHECKSUM_ADLER OBD_CKSUM_ADLER
+#else
+#define OSC_DEFAULT_CKSUM OBD_CKSUM_CRC32
+#define CHECKSUM_ADLER 0
+#endif
+
+#define OBD_CKSUM_ALL (OBD_CKSUM_CRC32 | CHECKSUM_ADLER)
+
+/* Checksum algorithm names. Must be defined in the same order as the
+ * OBD_CKSUM_* flags. */
+#define DECLARE_CKSUM_NAME char *cksum_name[] = {"crc32", "adler"}
+

 #endif /* __OBD_H */
 #endif /* __OBD_H */

diff --git a/lustre/include/obd_support.h b/lustre/include/obd_support.h
index ce093b8..5d7a407 100644 (file)
--- a/lustre/include/obd_support.h
+++ b/lustre/include/obd_support.h
@@ -215,6 +215,8 @@ int __obd_fail_check_set(__u32 id, __u32 value, int set);
 #define OBD_FAIL_OSC_CHECKSUM_RECEIVE    0x408
 #define OBD_FAIL_OSC_CHECKSUM_SEND       0x409
 #define OBD_FAIL_OSC_BRW_PREP_REQ2       0x40a
 #define OBD_FAIL_OSC_CHECKSUM_RECEIVE    0x408
 #define OBD_FAIL_OSC_CHECKSUM_SEND       0x409
 #define OBD_FAIL_OSC_BRW_PREP_REQ2       0x40a

+#define OBD_FAIL_OSC_CONNECT_CKSUM       0x40b
+#define OBD_FAIL_OSC_CKSUM_ADLER_ONLY    0x40c

 
 #define OBD_FAIL_PTLRPC                  0x500
 #define OBD_FAIL_PTLRPC_ACK              0x501
 
 #define OBD_FAIL_PTLRPC                  0x500
 #define OBD_FAIL_PTLRPC_ACK              0x501

diff --git a/lustre/ldlm/ldlm_lib.c b/lustre/ldlm/ldlm_lib.c
index a5ce738..3b2ab47 100644 (file)
--- a/lustre/ldlm/ldlm_lib.c
+++ b/lustre/ldlm/ldlm_lib.c
@@ -276,7 +276,14 @@ int client_obd_setup(struct obd_device *obddev, struct lustre_cfg *lcfg)
         cfs_waitq_init(&cli->cl_destroy_waitq);
         atomic_set(&cli->cl_destroy_in_flight, 0);
 #ifdef ENABLE_CHECKSUM
         cfs_waitq_init(&cli->cl_destroy_waitq);
         atomic_set(&cli->cl_destroy_in_flight, 0);
 #ifdef ENABLE_CHECKSUM

+        /* Turn on checksumming by default. */

         cli->cl_checksum = 1;
         cli->cl_checksum = 1;

+        /*
+         * The supported checksum types will be worked out at connect time
+         * Set cl_chksum* to CRC32 for now to avoid returning screwed info
+         * through procfs.
+         */
+        cli->cl_cksum_type = cli->cl_supp_cksum_types = OBD_CKSUM_CRC32;

 #endif
         atomic_set(&cli->cl_resends, OSC_DEFAULT_RESENDS);
 
 #endif
         atomic_set(&cli->cl_resends, OSC_DEFAULT_RESENDS);
 

diff --git a/lustre/liblustre/Makefile.am b/lustre/liblustre/Makefile.am
index de73497..32cf927 100644 (file)
--- a/lustre/liblustre/Makefile.am
+++ b/lustre/liblustre/Makefile.am
@@ -65,7 +65,7 @@ liblustre_a_SOURCES = llite_lib.c llite_fid.c super.c namei.c rw.c file.c dir.c
                     llite_lib.h
 
 liblustre.a : $(LUSTRE_LIBS) $(LND_LIBS) $(LNET_LIBS) $(SYSIO_LIBS) $(QUOTA_LIBS)
                     llite_lib.h
 
 liblustre.a : $(LUSTRE_LIBS) $(LND_LIBS) $(LNET_LIBS) $(SYSIO_LIBS) $(QUOTA_LIBS)

-       sh $(srcdir)/genlib.sh "$(SYSIO)" "$(LIBS)" "$(LND_LIBS)" "$(PTHREAD_LIBS)" "$(QUOTA_LIBS)" "$(CAP_LIBS)"
+       sh $(srcdir)/genlib.sh "$(SYSIO)" "$(LIBS)" "$(LND_LIBS)" "$(PTHREAD_LIBS)" "$(QUOTA_LIBS)" "$(CAP_LIBS)" "$(ZLIB)"

 
 EXTRA_DIST = genlib.sh
 
 
 EXTRA_DIST = genlib.sh
 

diff --git a/lustre/liblustre/genlib.sh b/lustre/liblustre/genlib.sh
index 2fc5bb5..dbe849f 100755 (executable)
--- a/lustre/liblustre/genlib.sh
+++ b/lustre/liblustre/genlib.sh
@@ -24,6 +24,7 @@ LND_LIBS=$3
 PTHREAD_LIBS=$4
 QUOTA_LIBS=$5
 CAP_LIBS=$6
 PTHREAD_LIBS=$4
 QUOTA_LIBS=$5
 CAP_LIBS=$6

+ZLIB=$7

 
 if [ ! -f $SYSIO/lib/libsysio.a ]; then
   echo "ERROR: $SYSIO/lib/libsysio.a dosen't exist"
 
 if [ ! -f $SYSIO/lib/libsysio.a ]; then
   echo "ERROR: $SYSIO/lib/libsysio.a dosen't exist"

diff --git a/lustre/llite/llite_lib.c b/lustre/llite/llite_lib.c
index fc4ed66..86ab3b7 100644 (file)
--- a/lustre/llite/llite_lib.c
+++ b/lustre/llite/llite_lib.c
@@ -368,6 +368,20 @@ static int client_common_fill_super(struct super_block *sb, char *md, char *dt)
         if (sbi->ll_flags & LL_SBI_OSS_CAPA)
                 data->ocd_connect_flags |= OBD_CONNECT_OSS_CAPA;
 
         if (sbi->ll_flags & LL_SBI_OSS_CAPA)
                 data->ocd_connect_flags |= OBD_CONNECT_OSS_CAPA;
 

+        if (!OBD_FAIL_CHECK(OBD_FAIL_OSC_CONNECT_CKSUM)) {
+                /* OBD_CONNECT_CKSUM should always be set, even if checksums are
+                 * disabled by default, because it can still be enabled on the
+                 * fly via /proc. As a consequence, we still need to come to an
+                 * agreement on the supported algorithms at connect time */
+                data->ocd_connect_flags |= OBD_CONNECT_CKSUM;
+
+                if (OBD_FAIL_CHECK(OBD_FAIL_OSC_CKSUM_ADLER_ONLY))
+                        data->ocd_cksum_types = OBD_CKSUM_ADLER;
+                else
+                        /* send the list of supported checksum types */
+                        data->ocd_cksum_types = OBD_CKSUM_ALL;
+        }
+

 #ifdef HAVE_LRU_RESIZE_SUPPORT
         data->ocd_connect_flags |= OBD_CONNECT_LRU_RESIZE;
 #endif
 #ifdef HAVE_LRU_RESIZE_SUPPORT
         data->ocd_connect_flags |= OBD_CONNECT_LRU_RESIZE;
 #endif

diff --git a/lustre/obdfilter/filter.c b/lustre/obdfilter/filter.c
index 275d523..efc01d2 100644 (file)
--- a/lustre/obdfilter/filter.c
+++ b/lustre/obdfilter/filter.c
@@ -2458,6 +2458,30 @@ static int filter_connect_internal(struct obd_export *exp,
                 LASSERT(data->ocd_brw_size);
         }
 
                 LASSERT(data->ocd_brw_size);
         }
 

+        if (data->ocd_connect_flags & OBD_CONNECT_CKSUM) {
+                __u32 cksum_types = data->ocd_cksum_types;
+
+                /* The client set in ocd_cksum_types the checksum types it
+                 * supports. We have to mask off the algorithms that we don't
+                 * support */
+                if (cksum_types & OBD_CKSUM_ALL)
+                        data->ocd_cksum_types &= OBD_CKSUM_ALL;
+                else
+                        data->ocd_cksum_types = OBD_CKSUM_CRC32;
+
+                CDEBUG(D_RPCTRACE, "%s: cli %s supports cksum type %x, return "
+                                   "%x\n", exp->exp_obd->obd_name,
+                                   obd_export_nid2str(exp), cksum_types,
+                                   data->ocd_cksum_types);
+        } else {
+                /* This client does not support OBD_CONNECT_CKSUM
+                 * fall back to CRC32 */
+                CDEBUG(D_RPCTRACE, "%s: cli %s does not support "
+                                   "OBD_CONNECT_CKSUM, CRC32 will be used\n",
+                                   exp->exp_obd->obd_name,
+                                   obd_export_nid2str(exp));
+        }
+

         /* FIXME: Do the same with the MDS UUID and fsd_peeruuid.
          * FIXME: We don't strictly need the COMPAT flag for that,
          * FIXME: as fsd_peeruuid[0] will tell us if that is set.
         /* FIXME: Do the same with the MDS UUID and fsd_peeruuid.
          * FIXME: We don't strictly need the COMPAT flag for that,
          * FIXME: as fsd_peeruuid[0] will tell us if that is set.

diff --git a/lustre/osc/lproc_osc.c b/lustre/osc/lproc_osc.c
index 7980fd2..ba665a8 100644 (file)
--- a/lustre/osc/lproc_osc.c
+++ b/lustre/osc/lproc_osc.c
@@ -301,6 +301,62 @@ static int osc_wr_checksum(struct file *file, const char *buffer,
         return count;
 }
 
         return count;
 }
 

+static int osc_rd_checksum_type(char *page, char **start, off_t off, int count,
+                                int *eof, void *data)
+{
+        struct obd_device *obd = data;
+        int i, len =0;
+        DECLARE_CKSUM_NAME;
+
+        if (obd == NULL)
+                return 0;
+
+        for (i = 0; i < ARRAY_SIZE(cksum_name) && len < count; i++) {
+                if (((1 << i) & obd->u.cli.cl_supp_cksum_types) == 0)
+                        continue;
+                if (obd->u.cli.cl_cksum_type == (1 << i))
+                        len += snprintf(page + len, count - len, "[%s] ",
+                                        cksum_name[i]);
+                else
+                        len += snprintf(page + len, count - len, "%s ",
+                                        cksum_name[i]);
+        }
+        if (len < count)
+                len += sprintf(page + len, "\n");
+        return len;
+}
+
+static int osc_wd_checksum_type(struct file *file, const char *buffer,
+                                unsigned long count, void *data)
+{
+        struct obd_device *obd = data;
+        int i;
+        DECLARE_CKSUM_NAME;
+        char kernbuf[10];
+
+        if (obd == NULL)
+                return 0;
+
+        if (count > sizeof(kernbuf) - 1)
+                return -EINVAL;
+        if (copy_from_user(kernbuf, buffer, count))
+                return -EFAULT;
+        if (count > 0 && kernbuf[count - 1] == '\n')
+                kernbuf[count - 1] = '\0';
+        else
+                kernbuf[count] = '\0';
+
+        for (i = 0; i < ARRAY_SIZE(cksum_name); i++) {
+                if (((1 << i) & obd->u.cli.cl_supp_cksum_types) == 0)
+                        continue;
+                if (!strcmp(kernbuf, cksum_name[i])) {
+                       obd->u.cli.cl_cksum_type = 1 << i;
+                       return count;
+                }
+        }
+        return -EINVAL;
+}
+

 static int osc_rd_resend_count(char *page, char **start, off_t off, int count,
                                int *eof, void *data)
 {
 static int osc_rd_resend_count(char *page, char **start, off_t off, int count,
                                int *eof, void *data)
 {


@@ -353,6 +409,7 @@ static struct lprocfs_vars lprocfs_osc_obd_vars[] = {
         { "prealloc_next_id", osc_rd_prealloc_next_id, 0, 0 },
         { "prealloc_last_id", osc_rd_prealloc_last_id, 0, 0 },
         { "checksums",       osc_rd_checksum, osc_wr_checksum, 0 },
         { "prealloc_next_id", osc_rd_prealloc_next_id, 0, 0 },
         { "prealloc_last_id", osc_rd_prealloc_last_id, 0, 0 },
         { "checksums",       osc_rd_checksum, osc_wr_checksum, 0 },

+        { "checksum_type",   osc_rd_checksum_type, osc_wd_checksum_type, 0 },

         { "resend_count",    osc_rd_resend_count, osc_wr_resend_count, 0},
         { 0 }
 };
         { "resend_count",    osc_rd_resend_count, osc_wr_resend_count, 0},
         { 0 }
 };

diff --git a/lustre/osc/osc_request.c b/lustre/osc/osc_request.c
index 06ec3dd..cda2381 100644 (file)
--- a/lustre/osc/osc_request.c
+++ b/lustre/osc/osc_request.c
@@ -974,12 +974,14 @@ static inline int can_merge_pages(struct brw_page *p1, struct brw_page *p2)
 }
 
 static obd_count osc_checksum_bulk(int nob, obd_count pg_count,
 }
 
 static obd_count osc_checksum_bulk(int nob, obd_count pg_count,

-                                   struct brw_page **pga, int opc)
+                                   struct brw_page **pga, int opc,
+                                   cksum_type_t cksum_type)

 {
 {

-        __u32 cksum = ~0;
+        __u32 cksum;

         int i = 0;
 
         LASSERT (pg_count > 0);
         int i = 0;
 
         LASSERT (pg_count > 0);

+        cksum = init_checksum(cksum_type);

         while (nob > 0 && pg_count > 0) {
                 unsigned char *ptr = cfs_kmap(pga[i]->pg);
                 int off = pga[i]->off & ~CFS_PAGE_MASK;
         while (nob > 0 && pg_count > 0) {
                 unsigned char *ptr = cfs_kmap(pga[i]->pg);
                 int off = pga[i]->off & ~CFS_PAGE_MASK;


@@ -990,7 +992,7 @@ static obd_count osc_checksum_bulk(int nob, obd_count pg_count,
                 if (i == 0 && opc == OST_READ &&
                     OBD_FAIL_CHECK(OBD_FAIL_OSC_CHECKSUM_RECEIVE))
                         memcpy(ptr + off, "bad1", min(4, nob));
                 if (i == 0 && opc == OST_READ &&
                     OBD_FAIL_CHECK(OBD_FAIL_OSC_CHECKSUM_RECEIVE))
                         memcpy(ptr + off, "bad1", min(4, nob));

-                cksum = crc32_le(cksum, ptr + off, count);
+                cksum = compute_checksum(cksum, ptr + off, count, cksum_type);

                 cfs_kunmap(pga[i]->pg);
                 LL_CDEBUG_PAGE(D_PAGE, pga[i]->pg, "off %d checksum %x\n",
                                off, cksum);
                 cfs_kunmap(pga[i]->pg);
                 LL_CDEBUG_PAGE(D_PAGE, pga[i]->pg, "off %d checksum %x\n",
                                off, cksum);


@@ -1126,14 +1128,23 @@ static int osc_brw_prep_request(int cmd, struct client_obd *cli,struct obdo *oa,
         if (opc == OST_WRITE) {
                 if (unlikely(cli->cl_checksum) &&
                     req->rq_flvr.sf_bulk_hash == BULK_HASH_ALG_NULL) {
         if (opc == OST_WRITE) {
                 if (unlikely(cli->cl_checksum) &&
                     req->rq_flvr.sf_bulk_hash == BULK_HASH_ALG_NULL) {

-                        body->oa.o_valid |= OBD_MD_FLCKSUM;
+                        /* store cl_cksum_type in a local variable since
+                         * it can be changed via lprocfs */
+                        cksum_type_t cksum_type = cli->cl_cksum_type;
+
+                        if ((body->oa.o_valid & OBD_MD_FLFLAGS) == 0)
+                                oa->o_flags = body->oa.o_flags = 0;
+                        body->oa.o_flags |= cksum_type_pack(cksum_type);
+                        body->oa.o_valid |= OBD_MD_FLCKSUM | OBD_MD_FLFLAGS;

                         body->oa.o_cksum = osc_checksum_bulk(requested_nob,
                                                              page_count, pga,
                         body->oa.o_cksum = osc_checksum_bulk(requested_nob,
                                                              page_count, pga,

-                                                             OST_WRITE);
+                                                             OST_WRITE,
+                                                             cksum_type);

                         CDEBUG(D_PAGE, "checksum at write origin: %x\n",
                                body->oa.o_cksum);
                         /* save this in 'oa', too, for later checking */
                         CDEBUG(D_PAGE, "checksum at write origin: %x\n",
                                body->oa.o_cksum);
                         /* save this in 'oa', too, for later checking */

-                        oa->o_valid |= OBD_MD_FLCKSUM;
+                        oa->o_valid |= OBD_MD_FLCKSUM | OBD_MD_FLFLAGS;
+                        oa->o_flags |= cksum_type_pack(cksum_type);

                 } else {
                         /* clear out the checksum flag, in case this is a
                          * resend but cl_checksum is no longer set. b=11238 */
                 } else {
                         /* clear out the checksum flag, in case this is a
                          * resend but cl_checksum is no longer set. b=11238 */


@@ -1145,8 +1156,12 @@ static int osc_brw_prep_request(int cmd, struct client_obd *cli,struct obdo *oa,
                                      sizeof(__u32) * niocount);
         } else {
                 if (unlikely(cli->cl_checksum) &&
                                      sizeof(__u32) * niocount);
         } else {
                 if (unlikely(cli->cl_checksum) &&

-                    req->rq_flvr.sf_bulk_hash == BULK_HASH_ALG_NULL)
-                        body->oa.o_valid |= OBD_MD_FLCKSUM;
+                    req->rq_flvr.sf_bulk_hash == BULK_HASH_ALG_NULL) {
+                        if ((body->oa.o_valid & OBD_MD_FLFLAGS) == 0)
+                                body->oa.o_flags = 0;
+                        body->oa.o_flags |= cksum_type_pack(cli->cl_cksum_type);
+                        body->oa.o_valid |= OBD_MD_FLCKSUM | OBD_MD_FLFLAGS;
+                }

                 req_capsule_set_size(pill, &RMF_NIOBUF_REMOTE, RCL_SERVER, 0);
                 /* 1 RC for the whole I/O */
         }
                 req_capsule_set_size(pill, &RMF_NIOBUF_REMOTE, RCL_SERVER, 0);
                 /* 1 RC for the whole I/O */
         }


@@ -1172,21 +1187,31 @@ static int osc_brw_prep_request(int cmd, struct client_obd *cli,struct obdo *oa,
 }
 
 static int check_write_checksum(struct obdo *oa, const lnet_process_id_t *peer,
 }
 
 static int check_write_checksum(struct obdo *oa, const lnet_process_id_t *peer,

-                                __u32 client_cksum, __u32 server_cksum,
-                                int nob, obd_count page_count,
-                                struct brw_page **pga)
+                                __u32 client_cksum, __u32 server_cksum, int nob,
+                                obd_count page_count, struct brw_page **pga,
+                                cksum_type_t client_cksum_type)

 {
         __u32 new_cksum;
         char *msg;
 {
         __u32 new_cksum;
         char *msg;

+        cksum_type_t cksum_type;

 
         if (server_cksum == client_cksum) {
                 CDEBUG(D_PAGE, "checksum %x confirmed\n", client_cksum);
                 return 0;
         }
 
 
         if (server_cksum == client_cksum) {
                 CDEBUG(D_PAGE, "checksum %x confirmed\n", client_cksum);
                 return 0;
         }
 

-        new_cksum = osc_checksum_bulk(nob, page_count, pga, OST_WRITE);
+        if (oa->o_valid & OBD_MD_FLFLAGS)
+                cksum_type = cksum_type_unpack(oa->o_flags);
+        else
+                cksum_type = OBD_CKSUM_CRC32;
+
+        new_cksum = osc_checksum_bulk(nob, page_count, pga, OST_WRITE,
+                                      cksum_type);

 
 

-        if (new_cksum == server_cksum)
+        if (cksum_type != client_cksum_type)
+                msg = "the server did not use the checksum type specified in "
+                      "the original request - likely a protocol problem";
+        else if (new_cksum == server_cksum)

                 msg = "changed on the client after we checksummed it - "
                       "likely false positive due to mmap IO (bug 11742)";
         else if (new_cksum == client_cksum)
                 msg = "changed on the client after we checksummed it - "
                       "likely false positive due to mmap IO (bug 11742)";
         else if (new_cksum == client_cksum)


@@ -1206,8 +1231,9 @@ static int check_write_checksum(struct obdo *oa, const lnet_process_id_t *peer,
                            oa->o_valid & OBD_MD_FLGROUP ? oa->o_gr : (__u64)0,
                            pga[0]->off,
                            pga[page_count-1]->off + pga[page_count-1]->count - 1);
                            oa->o_valid & OBD_MD_FLGROUP ? oa->o_gr : (__u64)0,
                            pga[0]->off,
                            pga[page_count-1]->off + pga[page_count-1]->count - 1);

-        CERROR("original client csum %x, server csum %x, client csum now %x\n",
-               client_cksum, server_cksum, new_cksum);
+        CERROR("original client csum %x (type %x), server csum %x (type %x), "
+               "client csum now %x\n", client_cksum, client_cksum_type,
+               server_cksum, cksum_type, new_cksum);

         return 1;        
 }
 
         return 1;        
 }
 


@@ -1243,7 +1269,7 @@ static int osc_brw_fini_request(struct ptlrpc_request *req, int rc)
         if (rc < 0)
                 RETURN(rc);
 
         if (rc < 0)
                 RETURN(rc);
 

-        if (unlikely(aa->aa_oa->o_valid & OBD_MD_FLCKSUM))
+        if (aa->aa_oa->o_valid & OBD_MD_FLCKSUM)

                 client_cksum = aa->aa_oa->o_cksum; /* save for later */
 
         osc_update_grant(cli, body);
                 client_cksum = aa->aa_oa->o_cksum; /* save for later */
 
         osc_update_grant(cli, body);


@@ -1255,13 +1281,11 @@ static int osc_brw_fini_request(struct ptlrpc_request *req, int rc)
                 }
                 LASSERT(req->rq_bulk->bd_nob == aa->aa_requested_nob);
 
                 }
                 LASSERT(req->rq_bulk->bd_nob == aa->aa_requested_nob);
 

-                if (unlikely((aa->aa_oa->o_valid & OBD_MD_FLCKSUM) &&
-                             client_cksum &&
-                             check_write_checksum(&body->oa, peer, client_cksum,
-                                                  body->oa.o_cksum,
-                                                  aa->aa_requested_nob,
-                                                  aa->aa_page_count,
-                                                  aa->aa_ppga)))
+                if ((aa->aa_oa->o_valid & OBD_MD_FLCKSUM) && client_cksum &&
+                    check_write_checksum(&body->oa, peer, client_cksum,
+                                         body->oa.o_cksum, aa->aa_requested_nob,
+                                         aa->aa_page_count, aa->aa_ppga,
+                                         cksum_type_unpack(aa->aa_oa->o_flags)))

                         RETURN(-EAGAIN);
 
                 if (sptlrpc_cli_unwrap_bulk_write(req, req->rq_bulk))
                         RETURN(-EAGAIN);
 
                 if (sptlrpc_cli_unwrap_bulk_write(req, req->rq_bulk))


@@ -1292,14 +1316,20 @@ static int osc_brw_fini_request(struct ptlrpc_request *req, int rc)
                                          aa->aa_ppga))
                 GOTO(out, rc = -EAGAIN);
 
                                          aa->aa_ppga))
                 GOTO(out, rc = -EAGAIN);
 

-        if (unlikely(body->oa.o_valid & OBD_MD_FLCKSUM)) {
+        if (body->oa.o_valid & OBD_MD_FLCKSUM) {

                 static int cksum_counter;
                 __u32      server_cksum = body->oa.o_cksum;
                 char      *via;
                 char      *router;
                 static int cksum_counter;
                 __u32      server_cksum = body->oa.o_cksum;
                 char      *via;
                 char      *router;

+                cksum_type_t cksum_type;

 
 

+                if (body->oa.o_valid & OBD_MD_FLFLAGS)
+                        cksum_type = cksum_type_unpack(body->oa.o_flags);
+                else
+                        cksum_type = OBD_CKSUM_CRC32;

                 client_cksum = osc_checksum_bulk(rc, aa->aa_page_count,
                 client_cksum = osc_checksum_bulk(rc, aa->aa_page_count,

-                                                 aa->aa_ppga, OST_READ);
+                                                 aa->aa_ppga, OST_READ,
+                                                 cksum_type);

 
                 if (peer->nid == req->rq_bulk->bd_sender) {
                         via = router = "";
 
                 if (peer->nid == req->rq_bulk->bd_sender) {
                         via = router = "";


@@ -1332,8 +1362,8 @@ static int osc_brw_fini_request(struct ptlrpc_request *req, int rc)
                                            aa->aa_ppga[aa->aa_page_count-1]->off +
                                            aa->aa_ppga[aa->aa_page_count-1]->count -
                                                                         1);
                                            aa->aa_ppga[aa->aa_page_count-1]->off +
                                            aa->aa_ppga[aa->aa_page_count-1]->count -
                                                                         1);

-                        CERROR("client %x, server %x\n",
-                               client_cksum, server_cksum);
+                        CERROR("client %x, server %x, cksum_type %x\n",
+                               client_cksum, server_cksum, cksum_type);

                         cksum_counter = 0;
                         aa->aa_oa->o_cksum = client_cksum;
                         rc = -EAGAIN;
                         cksum_counter = 0;
                         aa->aa_oa->o_cksum = client_cksum;
                         rc = -EAGAIN;


@@ -1421,7 +1451,7 @@ int osc_brw_redo_request(struct ptlrpc_request *request,
                 CERROR("too many resend retries, returning error\n");
                 RETURN(-EIO);
         }
                 CERROR("too many resend retries, returning error\n");
                 RETURN(-EIO);
         }

-        
+

         DEBUG_REQ(D_ERROR, request, "redo for recoverable error");
 /*
         body = lustre_msg_buf(request->rq_reqmsg, REQ_REC_OFF, sizeof(*body));
         DEBUG_REQ(D_ERROR, request, "redo for recoverable error");
 /*
         body = lustre_msg_buf(request->rq_reqmsg, REQ_REC_OFF, sizeof(*body));


@@ -1439,7 +1469,7 @@ int osc_brw_redo_request(struct ptlrpc_request *request,
                 RETURN(rc);
 
         client_obd_list_lock(&aa->aa_cli->cl_loi_list_lock);
                 RETURN(rc);
 
         client_obd_list_lock(&aa->aa_cli->cl_loi_list_lock);

-   
+

         list_for_each_entry(oap, &aa->aa_oaps, oap_rpc_item) {
                 if (oap->oap_request != NULL) {
                         LASSERTF(request == oap->oap_request,
         list_for_each_entry(oap, &aa->aa_oaps, oap_rpc_item) {
                 if (oap->oap_request != NULL) {
                         LASSERTF(request == oap->oap_request,


@@ -1447,7 +1477,7 @@ int osc_brw_redo_request(struct ptlrpc_request *request,
                                  request, oap->oap_request);
                         if (oap->oap_interrupted) {
                                 client_obd_list_unlock(&aa->aa_cli->cl_loi_list_lock);
                                  request, oap->oap_request);
                         if (oap->oap_interrupted) {
                                 client_obd_list_unlock(&aa->aa_cli->cl_loi_list_lock);

-                                ptlrpc_req_finished(new_req);                        
+                                ptlrpc_req_finished(new_req);

                                 RETURN(-EINTR);
                         }
                 }
                                 RETURN(-EINTR);
                         }
                 }

diff --git a/lustre/ost/ost_handler.c b/lustre/ost/ost_handler.c
index a442e09..e6a139c 100644 (file)
--- a/lustre/ost/ost_handler.c
+++ b/lustre/ost/ost_handler.c
@@ -470,11 +470,13 @@ static int get_per_page_niobufs(struct obd_ioobj *ioo, int nioo,
         return npages;
 }
 
         return npages;
 }
 

-static __u32 ost_checksum_bulk(struct ptlrpc_bulk_desc *desc, int opc)
+static __u32 ost_checksum_bulk(struct ptlrpc_bulk_desc *desc, int opc,
+                               cksum_type_t cksum_type)

 {
 {

-        __u32 cksum = ~0;
+        __u32 cksum;

         int i;
 
         int i;
 

+        cksum = init_checksum(cksum_type);

         for (i = 0; i < desc->bd_iov_count; i++) {
                 struct page *page = desc->bd_iov[i].kiov_page;
                 int off = desc->bd_iov[i].kiov_offset & ~CFS_PAGE_MASK;
         for (i = 0; i < desc->bd_iov_count; i++) {
                 struct page *page = desc->bd_iov[i].kiov_page;
                 int off = desc->bd_iov[i].kiov_offset & ~CFS_PAGE_MASK;


@@ -486,7 +488,7 @@ static __u32 ost_checksum_bulk(struct ptlrpc_bulk_desc *desc, int opc)
                 if (i == 0 && opc == OST_WRITE &&
                     OBD_FAIL_CHECK(OBD_FAIL_OST_CHECKSUM_RECEIVE))
                         memcpy(ptr, "bad3", min(4, len));
                 if (i == 0 && opc == OST_WRITE &&
                     OBD_FAIL_CHECK(OBD_FAIL_OST_CHECKSUM_RECEIVE))
                         memcpy(ptr, "bad3", min(4, len));

-                cksum = crc32_le(cksum, ptr, len);
+                cksum = compute_checksum(cksum, ptr, len, cksum_type);

                 /* corrupt the data after we compute the checksum, to
                  * simulate an OST->client data error */
                 if (i == 0 && opc == OST_READ &&
                 /* corrupt the data after we compute the checksum, to
                  * simulate an OST->client data error */
                 if (i == 0 && opc == OST_READ &&


@@ -810,9 +812,14 @@ static int ost_brw_read(struct ptlrpc_request *req, struct obd_trans_info *oti)
                 }
         }
 
                 }
         }
 

-        if (unlikely(body->oa.o_valid & OBD_MD_FLCKSUM)) {
-                body->oa.o_cksum = ost_checksum_bulk(desc, OST_READ);
-                body->oa.o_valid = OBD_MD_FLCKSUM;
+        if (body->oa.o_valid & OBD_MD_FLCKSUM) {
+                cksum_type_t cksum_type = OBD_CKSUM_CRC32;
+
+                if (body->oa.o_valid & OBD_MD_FLFLAGS)
+                        cksum_type = cksum_type_unpack(body->oa.o_flags);
+                body->oa.o_flags = cksum_type_pack(cksum_type);
+                body->oa.o_valid = OBD_MD_FLCKSUM | OBD_MD_FLFLAGS;
+                body->oa.o_cksum = ost_checksum_bulk(desc, OST_READ, cksum_type);

                 CDEBUG(D_PAGE,"checksum at read origin: %x\n",body->oa.o_cksum);
         } else {
                 body->oa.o_valid = 0;
                 CDEBUG(D_PAGE,"checksum at read origin: %x\n",body->oa.o_cksum);
         } else {
                 body->oa.o_valid = 0;


@@ -931,7 +938,8 @@ static int ost_brw_write(struct ptlrpc_request *req, struct obd_trans_info *oti)
         int size[3] = { sizeof(struct ptlrpc_body), sizeof(*body) };
         int objcount, niocount, npages;
         int rc, swab, i, j;
         int size[3] = { sizeof(struct ptlrpc_body), sizeof(*body) };
         int objcount, niocount, npages;
         int rc, swab, i, j;

-        obd_count                client_cksum, server_cksum = 0;
+        obd_count                client_cksum = 0, server_cksum = 0;
+        cksum_type_t             cksum_type = OBD_CKSUM_CRC32;

         int                      no_reply = 0; 
         ENTRY;
 
         int                      no_reply = 0; 
         ENTRY;
 


@@ -1060,7 +1068,11 @@ static int ost_brw_write(struct ptlrpc_request *req, struct obd_trans_info *oti)
         ost_prolong_locks(exp, ioo, pp_rnb, LCK_PW);
 
         /* obd_preprw clobbers oa->valid, so save what we need */
         ost_prolong_locks(exp, ioo, pp_rnb, LCK_PW);
 
         /* obd_preprw clobbers oa->valid, so save what we need */

-        client_cksum = body->oa.o_valid & OBD_MD_FLCKSUM ? body->oa.o_cksum : 0;
+        if (body->oa.o_valid & OBD_MD_FLCKSUM) {
+                client_cksum = body->oa.o_cksum;
+                if (body->oa.o_valid & OBD_MD_FLFLAGS)
+                        cksum_type = cksum_type_unpack(body->oa.o_flags);
+        }

         
         /* Because we already sync grant info with client when reconnect,
          * grant info will be cleared for resent req, then fed_grant and 
         
         /* Because we already sync grant info with client when reconnect,
          * grant info will be cleared for resent req, then fed_grant and 


@@ -1124,8 +1136,10 @@ static int ost_brw_write(struct ptlrpc_request *req, struct obd_trans_info *oti)
 
         if (unlikely(client_cksum != 0 && rc == 0)) {
                 static int cksum_counter;
 
         if (unlikely(client_cksum != 0 && rc == 0)) {
                 static int cksum_counter;

-                server_cksum = ost_checksum_bulk(desc, OST_WRITE);
-                repbody->oa.o_valid |= OBD_MD_FLCKSUM;
+                repbody->oa.o_valid |= OBD_MD_FLCKSUM | OBD_MD_FLFLAGS;
+                repbody->oa.o_flags &= ~OBD_FL_CKSUM_ALL;
+                repbody->oa.o_flags |= cksum_type_pack(cksum_type);
+                server_cksum = ost_checksum_bulk(desc, OST_WRITE, cksum_type);

                 repbody->oa.o_cksum = server_cksum;
                 cksum_counter++;
                 if (unlikely(client_cksum != server_cksum)) {
                 repbody->oa.o_cksum = server_cksum;
                 cksum_counter++;
                 if (unlikely(client_cksum != server_cksum)) {


@@ -1144,7 +1158,7 @@ static int ost_brw_write(struct ptlrpc_request *req, struct obd_trans_info *oti)
                            objcount, ioo, npages, local_nb, oti, rc);
 
         if (unlikely(client_cksum != server_cksum && rc == 0)) {
                            objcount, ioo, npages, local_nb, oti, rc);
 
         if (unlikely(client_cksum != server_cksum && rc == 0)) {

-                int   new_cksum = ost_checksum_bulk(desc, OST_WRITE);
+                int  new_cksum = ost_checksum_bulk(desc, OST_WRITE, cksum_type);

                 char *msg;
                 char *via;
                 char *router;
                 char *msg;
                 char *via;
                 char *router;

diff --git a/lustre/ptlrpc/import.c b/lustre/ptlrpc/import.c
index 26695b4..c570f12 100644 (file)
--- a/lustre/ptlrpc/import.c
+++ b/lustre/ptlrpc/import.c
@@ -792,6 +792,38 @@ finish:
                                       newer : older, LUSTRE_VERSION_STRING);
                 }
 
                                       newer : older, LUSTRE_VERSION_STRING);
                 }
 

+                if (ocd->ocd_connect_flags & OBD_CONNECT_CKSUM) {
+                        /* We sent to the server ocd_cksum_types with bits set
+                         * for algorithms we understand. The server masked off
+                         * the checksum types it doesn't support */
+                        if ((ocd->ocd_cksum_types & OBD_CKSUM_ALL) == 0) {
+                                LCONSOLE_WARN("The negotiation of the checksum "
+                                              "alogrithm to use with server %s "
+                                              "failed (%x/%x), disabling "
+                                              "checksums\n",
+                                              obd2cli_tgt(imp->imp_obd),
+                                              ocd->ocd_cksum_types,
+                                              OBD_CKSUM_ALL);
+                                cli->cl_checksum = 0;
+                                cli->cl_supp_cksum_types = OBD_CKSUM_CRC32;
+                                cli->cl_cksum_type = OBD_CKSUM_CRC32;
+                        } else {
+                                cli->cl_supp_cksum_types = ocd->ocd_cksum_types;
+
+                                if (ocd->ocd_cksum_types & OSC_DEFAULT_CKSUM)
+                                        cli->cl_cksum_type = OSC_DEFAULT_CKSUM;
+                                else if (ocd->ocd_cksum_types & OBD_CKSUM_ADLER)
+                                        cli->cl_cksum_type = OBD_CKSUM_ADLER;
+                                else
+                                        cli->cl_cksum_type = OBD_CKSUM_CRC32;
+                        }
+                } else {
+                        /* The server does not support OBD_CONNECT_CKSUM.
+                         * Enforce CRC32 for backward compatibility*/
+                        cli->cl_supp_cksum_types = OBD_CKSUM_CRC32;
+                        cli->cl_cksum_type = OBD_CKSUM_CRC32;
+                }
+

                 if (ocd->ocd_connect_flags & OBD_CONNECT_BRW_SIZE) {
                         cli->cl_max_pages_per_rpc = 
                                 ocd->ocd_brw_size >> CFS_PAGE_SHIFT;
                 if (ocd->ocd_connect_flags & OBD_CONNECT_BRW_SIZE) {
                         cli->cl_max_pages_per_rpc = 
                                 ocd->ocd_brw_size >> CFS_PAGE_SHIFT;

diff --git a/lustre/ptlrpc/pack_generic.c b/lustre/ptlrpc/pack_generic.c
index da2f5e0..d222812 100644 (file)
--- a/lustre/ptlrpc/pack_generic.c
+++ b/lustre/ptlrpc/pack_generic.c
@@ -1721,9 +1721,9 @@ void lustre_swab_connect(struct obd_connect_data *ocd)
         __swab32s(&ocd->ocd_nllg);
         __swab64s(&ocd->ocd_transno);
         __swab32s(&ocd->ocd_group);
         __swab32s(&ocd->ocd_nllg);
         __swab64s(&ocd->ocd_transno);
         __swab32s(&ocd->ocd_group);

+        __swab32s(&ocd->ocd_cksum_types);

         CLASSERT(offsetof(typeof(*ocd), padding1) != 0);
         CLASSERT(offsetof(typeof(*ocd), padding2) != 0);
         CLASSERT(offsetof(typeof(*ocd), padding1) != 0);
         CLASSERT(offsetof(typeof(*ocd), padding2) != 0);

-        CLASSERT(offsetof(typeof(*ocd), padding3) != 0);

 }
 
 void lustre_swab_obdo (struct obdo  *o)
 }
 
 void lustre_swab_obdo (struct obdo  *o)

diff --git a/lustre/ptlrpc/wiretest.c b/lustre/ptlrpc/wiretest.c
index 6fe15c5..090fa86 100644 (file)
--- a/lustre/ptlrpc/wiretest.c
+++ b/lustre/ptlrpc/wiretest.c
@@ -437,18 +437,18 @@ void lustre_assert_wire_constants(void)
                  (long long)(int)offsetof(struct obd_connect_data, ocd_group));
         LASSERTF((int)sizeof(((struct obd_connect_data *)0)->ocd_group) == 4, " found %lld\n",
                  (long long)(int)sizeof(((struct obd_connect_data *)0)->ocd_group));
                  (long long)(int)offsetof(struct obd_connect_data, ocd_group));
         LASSERTF((int)sizeof(((struct obd_connect_data *)0)->ocd_group) == 4, " found %lld\n",
                  (long long)(int)sizeof(((struct obd_connect_data *)0)->ocd_group));

-        LASSERTF((int)offsetof(struct obd_connect_data, padding1) == 52, " found %lld\n",
+        LASSERTF((int)offsetof(struct obd_connect_data, ocd_cksum_types) == 52, " found %lld\n",
+                 (long long)(int)offsetof(struct obd_connect_data, ocd_cksum_types));
+        LASSERTF((int)sizeof(((struct obd_connect_data *)0)->ocd_cksum_types) == 4, " found %lld\n",
+                 (long long)(int)sizeof(((struct obd_connect_data *)0)->ocd_cksum_types));
+        LASSERTF((int)offsetof(struct obd_connect_data, padding1) == 56, " found %lld\n",

                  (long long)(int)offsetof(struct obd_connect_data, padding1));
                  (long long)(int)offsetof(struct obd_connect_data, padding1));

-        LASSERTF((int)sizeof(((struct obd_connect_data *)0)->padding1) == 4, " found %lld\n",
+        LASSERTF((int)sizeof(((struct obd_connect_data *)0)->padding1) == 8, " found %lld\n",

                  (long long)(int)sizeof(((struct obd_connect_data *)0)->padding1));
                  (long long)(int)sizeof(((struct obd_connect_data *)0)->padding1));

-        LASSERTF((int)offsetof(struct obd_connect_data, padding2) == 56, " found %lld\n",
+        LASSERTF((int)offsetof(struct obd_connect_data, padding2) == 64, " found %lld\n",

                  (long long)(int)offsetof(struct obd_connect_data, padding2));
         LASSERTF((int)sizeof(((struct obd_connect_data *)0)->padding2) == 8, " found %lld\n",
                  (long long)(int)sizeof(((struct obd_connect_data *)0)->padding2));
                  (long long)(int)offsetof(struct obd_connect_data, padding2));
         LASSERTF((int)sizeof(((struct obd_connect_data *)0)->padding2) == 8, " found %lld\n",
                  (long long)(int)sizeof(((struct obd_connect_data *)0)->padding2));

-        LASSERTF((int)offsetof(struct obd_connect_data, padding3) == 64, " found %lld\n",
-                 (long long)(int)offsetof(struct obd_connect_data, padding3));
-        LASSERTF((int)sizeof(((struct obd_connect_data *)0)->padding3) == 8, " found %lld\n",
-                 (long long)(int)sizeof(((struct obd_connect_data *)0)->padding3));

         CLASSERT(OBD_CONNECT_RDONLY == 0x00000001ULL);
         CLASSERT(OBD_CONNECT_INDEX == 0x00000002ULL);
         CLASSERT(OBD_CONNECT_GRANT == 0x00000008ULL);
         CLASSERT(OBD_CONNECT_RDONLY == 0x00000001ULL);
         CLASSERT(OBD_CONNECT_INDEX == 0x00000002ULL);
         CLASSERT(OBD_CONNECT_GRANT == 0x00000008ULL);


@@ -618,6 +618,11 @@ void lustre_assert_wire_constants(void)
         CLASSERT(OBD_FL_DEBUG_CHECK == (0x00000040));
         CLASSERT(OBD_FL_NO_USRQUOTA == (0x00000100));
         CLASSERT(OBD_FL_NO_GRPQUOTA == (0x00000200));
         CLASSERT(OBD_FL_DEBUG_CHECK == (0x00000040));
         CLASSERT(OBD_FL_NO_USRQUOTA == (0x00000100));
         CLASSERT(OBD_FL_NO_GRPQUOTA == (0x00000200));

+        CLASSERT(OBD_FL_TRUNCLOCK == (0x00000800));
+        CLASSERT(OBD_FL_CKSUM_CRC32 == (0x00001000));
+        CLASSERT(OBD_FL_CKSUM_ADLER == (0x00002000));
+        CLASSERT(OBD_CKSUM_CRC32 == (0x00000001));
+        CLASSERT(OBD_CKSUM_ADLER == (0x00000002));

 
         /* Checks for struct lov_mds_md_v1 */
         LASSERTF((int)sizeof(struct lov_mds_md_v1) == 32, " found %lld\n",
 
         /* Checks for struct lov_mds_md_v1 */
         LASSERTF((int)sizeof(struct lov_mds_md_v1) == 32, " found %lld\n",

diff --git a/lustre/tests/sanity.sh b/lustre/tests/sanity.sh
index 84294d0..f74f9e5 100644 (file)
--- a/lustre/tests/sanity.sh
+++ b/lustre/tests/sanity.sh
@@ -3270,10 +3270,22 @@ set_checksums()
        for f in $LPROC/osc/*/checksums; do
                echo $1 >> $f
        done
        for f in $LPROC/osc/*/checksums; do
                echo $1 >> $f
        done

-

        return 0
 }
 
        return 0
 }
 

+export ORIG_CSUM_TYPE=""
+CKSUM_TYPES=${CKSUM_TYPES:-"crc32 adler"}
+set_checksum_type()
+{
+       [ "$ORIG_CSUM_TYPE" ] || \
+               ORIG_CSUM_TYPE=`sed 's/.*\[\(.*\)\].*/\1/g' \
+                               $LPROC/osc/*osc-[^mM]*/checksum_type | head -n1`
+       for f in $LPROC/osc/*osc-*/checksum_type; do
+               echo $1 > $f
+       done
+       log "set checksum type to $1"
+       return 0
+}

 F77_TMP=$TMP/f77-temp
 F77SZ=8
 setup_f77() {
 F77_TMP=$TMP/f77-temp
 F77SZ=8
 setup_f77() {


@@ -3303,13 +3315,17 @@ run_test 77b "checksum error on client write ===================="
 
 test_77c() { # bug 10889
        [ ! -f $DIR/f77b ] && skip "requires 77b - skipping" && return  
 
 test_77c() { # bug 10889
        [ ! -f $DIR/f77b ] && skip "requires 77b - skipping" && return  

-       cancel_lru_locks osc
-       #define OBD_FAIL_OSC_CHECKSUM_RECEIVE    0x408
-       sysctl -w lustre.fail_loc=0x80000408

        set_checksums 1
        set_checksums 1

-       cmp $F77_TMP $DIR/f77b || error "file compare failed"
-       sysctl -w lustre.fail_loc=0
+       for algo in $CKSUM_TYPES; do
+               cancel_lru_locks osc
+               set_checksum_type $algo
+               #define OBD_FAIL_OSC_CHECKSUM_RECEIVE    0x408
+               sysctl -w lustre.fail_loc=0x80000408
+               cmp $F77_TMP $DIR/f77b || error "file compare failed"
+               sysctl -w lustre.fail_loc=0
+       done

        set_checksums 0
        set_checksums 0

+       set_checksum_type $ORIG_CSUM_TYPE

 }
 run_test 77c "checksum error on client read ==================="
 
 }
 run_test 77c "checksum error on client read ==================="
 


@@ -3338,12 +3354,17 @@ test_77e() { # bug 10889
 run_test 77e "checksum error on OST direct read ================"
 
 test_77f() { # bug 10889
 run_test 77e "checksum error on OST direct read ================"
 
 test_77f() { # bug 10889

-       #define OBD_FAIL_OSC_CHECKSUM_SEND       0x409
-       sysctl -w lustre.fail_loc=0x409

        set_checksums 1
        set_checksums 1

-       directio write $DIR/f77 0 $F77SZ $((1024 * 1024)) && \
-               error "direct write succeeded"
-       sysctl -w lustre.fail_loc=0
+       for algo in $CKSUM_TYPES; do
+               cancel_lru_locks osc
+               set_checksum_type $algo
+               #define OBD_FAIL_OSC_CHECKSUM_SEND       0x409
+               sysctl -w lustre.fail_loc=0x409
+               directio write $DIR/f77 0 $F77SZ $((1024 * 1024)) && \
+                       error "direct write succeeded"
+               sysctl -w lustre.fail_loc=0
+       done
+       set_checksum_type $ORIG_CSUM_TYPE

        set_checksums 0
 }
 run_test 77f "repeat checksum error on write (expect error) ===="
        set_checksums 0
 }
 run_test 77f "repeat checksum error on write (expect error) ===="


@@ -3376,6 +3397,32 @@ test_77h() { # bug 10889
 }
 run_test 77h "checksum error on OST read ======================="
 
 }
 run_test 77h "checksum error on OST read ======================="
 

+test_77i() { # bug 13805
+       #define OBD_FAIL_OSC_CONNECT_CKSUM       0x40b
+       sysctl -w lustre.fail_loc=0x40b
+       remount_client $MOUNT
+       sysctl -w lustre.fail_loc=0
+       for f in $LPROC/osc/*osc-[^mM]*/checksum_type; do
+               algo=`sed 's/.*\[\(.*\)\].*/\1/g' $f`
+               [ "$algo" = "crc32" ] || error "algo set to $algo instead of crc32"
+       done
+       remount_client $MOUNT
+}
+run_test 77i "client not supporting OSD_CONNECT_CKSUM =========="
+
+test_77j() { # bug 13805
+       #define OBD_FAIL_OSC_CKSUM_ADLER_ONLY    0x40c
+       sysctl -w lustre.fail_loc=0x40c
+       remount_client $MOUNT
+       sysctl -w lustre.fail_loc=0
+       for f in $LPROC/osc/*osc-[^mM]*/checksum_type; do
+               algo=`sed 's/.*\[\(.*\)\].*/\1/g' $f`
+               [ "$algo" = "adler" ] || error "algo set to $algo instead of adler"
+       done
+       remount_client $MOUNT
+}
+run_test 77j "client only supporting ADLER32 ===================="
+

 [ "$ORIG_CSUM" ] && set_checksums $ORIG_CSUM || true
 rm -f $F77_TMP
 unset F77_TMP
 [ "$ORIG_CSUM" ] && set_checksums $ORIG_CSUM || true
 rm -f $F77_TMP
 unset F77_TMP

diff --git a/lustre/tests/test-framework.sh b/lustre/tests/test-framework.sh
index d059bcb..e6bb07a 100644 (file)
--- a/lustre/tests/test-framework.sh
+++ b/lustre/tests/test-framework.sh
@@ -955,6 +955,12 @@ switch_identity() {
     fi
 }
 
     fi
 }
 

+remount_client()
+{
+       zconf_umount `hostname` $1 || error "umount failed"
+       zconf_mount `hostname` $1 || error "mount failed"
+}
+

 setupall() {
     load_modules
     init_gss
 setupall() {
     load_modules
     init_gss

diff --git a/lustre/utils/wirecheck.c b/lustre/utils/wirecheck.c
index c7ceb3f..b65f4ab 100644 (file)
--- a/lustre/utils/wirecheck.c
+++ b/lustre/utils/wirecheck.c
@@ -174,9 +174,9 @@ static void check_obd_connect_data(void)
         CHECK_MEMBER(obd_connect_data, ocd_nllg);
         CHECK_MEMBER(obd_connect_data, ocd_transno);
         CHECK_MEMBER(obd_connect_data, ocd_group);
         CHECK_MEMBER(obd_connect_data, ocd_nllg);
         CHECK_MEMBER(obd_connect_data, ocd_transno);
         CHECK_MEMBER(obd_connect_data, ocd_group);

+        CHECK_MEMBER(obd_connect_data, ocd_cksum_types);

         CHECK_MEMBER(obd_connect_data, padding1);
         CHECK_MEMBER(obd_connect_data, padding2);
         CHECK_MEMBER(obd_connect_data, padding1);
         CHECK_MEMBER(obd_connect_data, padding2);

-        CHECK_MEMBER(obd_connect_data, padding3);

 
         CHECK_CDEFINE(OBD_CONNECT_RDONLY);
         CHECK_CDEFINE(OBD_CONNECT_INDEX);
 
         CHECK_CDEFINE(OBD_CONNECT_RDONLY);
         CHECK_CDEFINE(OBD_CONNECT_INDEX);


@@ -283,6 +283,11 @@ check_obdo(void)
         CHECK_CDEFINE(OBD_FL_DEBUG_CHECK);
         CHECK_CDEFINE(OBD_FL_NO_USRQUOTA);
         CHECK_CDEFINE(OBD_FL_NO_GRPQUOTA);
         CHECK_CDEFINE(OBD_FL_DEBUG_CHECK);
         CHECK_CDEFINE(OBD_FL_NO_USRQUOTA);
         CHECK_CDEFINE(OBD_FL_NO_GRPQUOTA);

+        CHECK_CDEFINE(OBD_FL_TRUNCLOCK);
+        CHECK_CDEFINE(OBD_FL_CKSUM_CRC32);
+        CHECK_CDEFINE(OBD_FL_CKSUM_ADLER);
+        CHECK_CDEFINE(OBD_CKSUM_CRC32);
+        CHECK_CDEFINE(OBD_CKSUM_ADLER);

 }
 
 static void
 }
 
 static void

diff --git a/lustre/utils/wiretest.c b/lustre/utils/wiretest.c
index e963f86..e067dab 100644 (file)
--- a/lustre/utils/wiretest.c
+++ b/lustre/utils/wiretest.c
@@ -455,18 +455,18 @@ void lustre_assert_wire_constants(void)
                  (long long)(int)offsetof(struct obd_connect_data, ocd_group));
         LASSERTF((int)sizeof(((struct obd_connect_data *)0)->ocd_group) == 4, " found %lld\n",
                  (long long)(int)sizeof(((struct obd_connect_data *)0)->ocd_group));
                  (long long)(int)offsetof(struct obd_connect_data, ocd_group));
         LASSERTF((int)sizeof(((struct obd_connect_data *)0)->ocd_group) == 4, " found %lld\n",
                  (long long)(int)sizeof(((struct obd_connect_data *)0)->ocd_group));

-        LASSERTF((int)offsetof(struct obd_connect_data, padding1) == 52, " found %lld\n",
+        LASSERTF((int)offsetof(struct obd_connect_data, ocd_cksum_types) == 52, " found %lld\n",
+                 (long long)(int)offsetof(struct obd_connect_data, ocd_cksum_types));
+        LASSERTF((int)sizeof(((struct obd_connect_data *)0)->ocd_cksum_types) == 4, " found %lld\n",
+                 (long long)(int)sizeof(((struct obd_connect_data *)0)->ocd_cksum_types));
+        LASSERTF((int)offsetof(struct obd_connect_data, padding1) == 56, " found %lld\n",

                  (long long)(int)offsetof(struct obd_connect_data, padding1));
                  (long long)(int)offsetof(struct obd_connect_data, padding1));

-        LASSERTF((int)sizeof(((struct obd_connect_data *)0)->padding1) == 4, " found %lld\n",
+        LASSERTF((int)sizeof(((struct obd_connect_data *)0)->padding1) == 8, " found %lld\n",

                  (long long)(int)sizeof(((struct obd_connect_data *)0)->padding1));
                  (long long)(int)sizeof(((struct obd_connect_data *)0)->padding1));

-        LASSERTF((int)offsetof(struct obd_connect_data, padding2) == 56, " found %lld\n",
+        LASSERTF((int)offsetof(struct obd_connect_data, padding2) == 64, " found %lld\n",

                  (long long)(int)offsetof(struct obd_connect_data, padding2));
         LASSERTF((int)sizeof(((struct obd_connect_data *)0)->padding2) == 8, " found %lld\n",
                  (long long)(int)sizeof(((struct obd_connect_data *)0)->padding2));
                  (long long)(int)offsetof(struct obd_connect_data, padding2));
         LASSERTF((int)sizeof(((struct obd_connect_data *)0)->padding2) == 8, " found %lld\n",
                  (long long)(int)sizeof(((struct obd_connect_data *)0)->padding2));

-        LASSERTF((int)offsetof(struct obd_connect_data, padding3) == 64, " found %lld\n",
-                 (long long)(int)offsetof(struct obd_connect_data, padding3));
-        LASSERTF((int)sizeof(((struct obd_connect_data *)0)->padding3) == 8, " found %lld\n",
-                 (long long)(int)sizeof(((struct obd_connect_data *)0)->padding3));

         CLASSERT(OBD_CONNECT_RDONLY == 0x00000001ULL);
         CLASSERT(OBD_CONNECT_INDEX == 0x00000002ULL);
         CLASSERT(OBD_CONNECT_GRANT == 0x00000008ULL);
         CLASSERT(OBD_CONNECT_RDONLY == 0x00000001ULL);
         CLASSERT(OBD_CONNECT_INDEX == 0x00000002ULL);
         CLASSERT(OBD_CONNECT_GRANT == 0x00000008ULL);


@@ -636,7 +636,12 @@ void lustre_assert_wire_constants(void)
         CLASSERT(OBD_FL_DEBUG_CHECK == (0x00000040));
         CLASSERT(OBD_FL_NO_USRQUOTA == (0x00000100));
         CLASSERT(OBD_FL_NO_GRPQUOTA == (0x00000200));
         CLASSERT(OBD_FL_DEBUG_CHECK == (0x00000040));
         CLASSERT(OBD_FL_NO_USRQUOTA == (0x00000100));
         CLASSERT(OBD_FL_NO_GRPQUOTA == (0x00000200));

-
+        CLASSERT(OBD_FL_TRUNCLOCK == (0x00000800));
+        CLASSERT(OBD_FL_CKSUM_CRC32 == (0x00001000));
+        CLASSERT(OBD_FL_CKSUM_ADLER == (0x00002000));
+        CLASSERT(OBD_CKSUM_CRC32 == (0x00000001));
+        CLASSERT(OBD_CKSUM_ADLER == (0x00000002));
+ 

         /* Checks for struct lov_mds_md_v1 */
         LASSERTF((int)sizeof(struct lov_mds_md_v1) == 32, " found %lld\n",
                  (long long)(int)sizeof(struct lov_mds_md_v1));
         /* Checks for struct lov_mds_md_v1 */
         LASSERTF((int)sizeof(struct lov_mds_md_v1) == 32, " found %lld\n",
                  (long long)(int)sizeof(struct lov_mds_md_v1));