store-copy: 'populate-store' can optionally deduplicate files.

Until now deduplication was performed as an additional pass after
copying files, which involve re-traversing all the files that had just
been copied.

* guix/store/deduplication.scm (copy-file/deduplicate): New procedure.
* tests/store-deduplication.scm ("copy-file/deduplicate"): New test.
* guix/build/store-copy.scm (populate-store): Add #:deduplicate?
parameter and honor it.
* tests/gexp.scm ("gexp->derivation, store copy"): Pass #:deduplicate? #f
to 'populate-store'.
* gnu/build/image.scm (initialize-root-partition): Pass #:deduplicate?
to 'populate-store'.  Pass #:deduplicate? #f to 'register-closure'.
* gnu/build/vm.scm (root-partition-initializer): Likewise.
* gnu/build/install.scm (populate-single-profile-directory): Pass
 #:deduplicate? #f to 'populate-store'.
* gnu/build/linux-initrd.scm (build-initrd): Likewise.
* guix/scripts/pack.scm (self-contained-tarball)[import-module?]: New
procedure.
[build]: Pass it as an argument to 'source-module-closure'.
* guix/scripts/pack.scm (squashfs-image)[build]: Wrap in
'with-extensions'.
* gnu/system/linux-initrd.scm (expression->initrd)[import-module?]: New
procedure.
[builder]: Pass it to 'source-module-closure'.
* gnu/system/install.scm (cow-store-service-type)[import-module?]: New
procedure.  Pass it to 'source-module-closure'.

3 files changed, 159 insertions, 128 deletions

diff --git a/guix/build/store-copy.scm b/guix/build/store-copy.scm
index 95dcb8e114..7f0672cd9d 100644
--- a/guix/build/store-copy.scm
+++ b/guix/build/store-copy.scm
@@ -20,6 +20,7 @@
   #:use-module ((guix build utils) #:hide (copy-recursively))
   #:use-module (guix sets)
   #:use-module (guix progress)
+  #:autoload   (guix store deduplication) (copy-file/deduplicate)
   #:use-module (srfi srfi-1)
   #:use-module (srfi srfi-9)
   #:use-module (srfi srfi-26)
@@ -242,10 +243,13 @@ permissions.  Write verbose output to the LOG port."
                         lstat)))
 
 (define* (populate-store reference-graphs target
-                         #:key (log-port (current-error-port)))
+                         #:key
+                         (deduplicate? #t)
+                         (log-port (current-error-port)))
   "Populate the store under directory TARGET with the items specified in
 REFERENCE-GRAPHS, a list of reference-graph files.  Items copied to TARGET
-maintain timestamps and permissions."
+maintain timestamps and permissions.  When DEDUPLICATE? is true, deduplicate
+regular files as they are copied to TARGET."
   (define store
     (string-append target (%store-directory)))
 
@@ -273,6 +277,11 @@ maintain timestamps and permissions."
                                       (string-append target thing)
                                       #:keep-mtime? #t
                                       #:keep-permissions? #t
+                                      #:copy-file
+                                      (if deduplicate?
+                                          (cut copy-file/deduplicate <> <>
+                                               #:store store)
+                                          copy-file)
                                       #:log (%make-void-port "w"))
                     (report))
                   things)))))
diff --git a/guix/scripts/pack.scm b/guix/scripts/pack.scm
index 1612ec8f04..440c4b0903 100644
--- a/guix/scripts/pack.scm
+++ b/guix/scripts/pack.scm
@@ -203,12 +203,19 @@ added to the pack."
                      #+(file-append glibc-utf8-locales "/lib/locale"))
              (setlocale LC_ALL "en_US.utf8"))))
 
+  (define (import-module? module)
+    ;; Since we don't use deduplication support in 'populate-store', don't
+    ;; import (guix store deduplication) and its dependencies, which includes
+    ;; Guile-Gcrypt.  That way we can run tests with '--bootstrap'.
+    (and (not-config? module)
+         (not (equal? '(guix store deduplication) module))))
+
   (define build
     (with-imported-modules (source-module-closure
                             `((guix build utils)
                               (guix build union)
                               (gnu build install))
-                            #:select? not-config?)
+                            #:select? import-module?)
       #~(begin
           (use-modules (guix build utils)
                        ((guix build union) #:select (relative-file-name))
@@ -382,138 +389,139 @@ added to the pack."
         `(("/bin" -> "bin") ,@symlinks)))
 
   (define build
-    (with-imported-modules (source-module-closure
-                            '((guix build utils)
-                              (guix build store-copy)
-                              (guix build union)
-                              (gnu build install))
-                            #:select? not-config?)
-      #~(begin
-          (use-modules (guix build utils)
-                       (guix build store-copy)
-                       ((guix build union) #:select (relative-file-name))
-                       (gnu build install)
-                       (srfi srfi-1)
-                       (srfi srfi-26)
-                       (ice-9 match))
+    (with-extensions (list guile-gcrypt)
+      (with-imported-modules (source-module-closure
+                              '((guix build utils)
+                                (guix build store-copy)
+                                (guix build union)
+                                (gnu build install))
+                              #:select? not-config?)
+        #~(begin
+            (use-modules (guix build utils)
+                         (guix build store-copy)
+                         ((guix build union) #:select (relative-file-name))
+                         (gnu build install)
+                         (srfi srfi-1)
+                         (srfi srfi-26)
+                         (ice-9 match))
 
-          (define database #+database)
-          (define entry-point #$entry-point)
+            (define database #+database)
+            (define entry-point #$entry-point)
 
-          (define (mksquashfs args)
-            (apply invoke "mksquashfs"
-                   `(,@args
+            (define (mksquashfs args)
+              (apply invoke "mksquashfs"
+                     `(,@args
 
-                     ;; Do not create a "recovery file" when appending to the
-                     ;; file system since it's useless in this case.
-                     "-no-recovery"
+                       ;; Do not create a "recovery file" when appending to the
+                       ;; file system since it's useless in this case.
+                       "-no-recovery"
 
-                     ;; Do not attempt to store extended attributes.
-                     ;; See <https://bugs.gnu.org/40043>.
-                     "-no-xattrs"
+                       ;; Do not attempt to store extended attributes.
+                       ;; See <https://bugs.gnu.org/40043>.
+                       "-no-xattrs"
 
-                     ;; Set file times and the file system creation time to
-                     ;; one second after the Epoch.
-                     "-all-time" "1" "-mkfs-time" "1"
+                       ;; Set file times and the file system creation time to
+                       ;; one second after the Epoch.
+                       "-all-time" "1" "-mkfs-time" "1"
 
-                     ;; Reset all UIDs and GIDs.
-                     "-force-uid" "0" "-force-gid" "0")))
+                       ;; Reset all UIDs and GIDs.
+                       "-force-uid" "0" "-force-gid" "0")))
 
-          (setenv "PATH" #+(file-append archiver "/bin"))
+            (setenv "PATH" #+(file-append archiver "/bin"))
 
-          ;; We need an empty file in order to have a valid file argument when
-          ;; we reparent the root file system.  Read on for why that's
-          ;; necessary.
-          (with-output-to-file ".empty" (lambda () (display "")))
-
-          ;; Create the squashfs image in several steps.
-          ;; Add all store items.  Unfortunately mksquashfs throws away all
-          ;; ancestor directories and only keeps the basename.  We fix this
-          ;; in the following invocations of mksquashfs.
-          (mksquashfs `(,@(map store-info-item
-                               (call-with-input-file "profile"
-                                 read-reference-graph))
-                        #$environment
-                        ,#$output
-
-                        ;; Do not perform duplicate checking because we
-                        ;; don't have any dupes.
-                        "-no-duplicates"
-                        "-comp"
-                        ,#+(compressor-name compressor)))
-
-          ;; Here we reparent the store items.  For each sub-directory of
-          ;; the store prefix we need one invocation of "mksquashfs".
-          (for-each (lambda (dir)
-                      (mksquashfs `(".empty"
-                                    ,#$output
-                                    "-root-becomes" ,dir)))
-                    (reverse (string-tokenize (%store-directory)
-                                              (char-set-complement (char-set #\/)))))
-
-          ;; Add symlinks and mount points.
-          (mksquashfs
-           `(".empty"
-             ,#$output
-             ;; Create SYMLINKS via pseudo file definitions.
-             ,@(append-map
-                (match-lambda
-                  ((source '-> target)
-                   ;; Create relative symlinks to work around a bug in
-                   ;; Singularity 2.x:
-                   ;;   https://bugs.gnu.org/34913
-                   ;;   https://github.com/sylabs/singularity/issues/1487
-                   (let ((target (string-append #$profile "/" target)))
-                     (list "-p"
-                           (string-join
-                            ;; name s mode uid gid symlink
-                            (list source
-                                  "s" "777" "0" "0"
-                                  (relative-file-name (dirname source)
-                                                      target)))))))
-                '#$symlinks*)
-
-             "-p" "/.singularity.d d 555 0 0"
-
-             ;; Create the environment file.
-             "-p" "/.singularity.d/env d 555 0 0"
-             "-p" ,(string-append
-                    "/.singularity.d/env/90-environment.sh s 777 0 0 "
-                    (relative-file-name "/.singularity.d/env"
-                                        #$environment))
-
-             ;; Create /.singularity.d/actions, and optionally the 'run'
-             ;; script, used by 'singularity run'.
-             "-p" "/.singularity.d/actions d 555 0 0"
-
-             ,@(if entry-point
-                   `(;; This one if for Singularity 2.x.
-                     "-p"
-                     ,(string-append
-                       "/.singularity.d/actions/run s 777 0 0 "
-                       (relative-file-name "/.singularity.d/actions"
-                                           (string-append #$profile "/"
-                                                          entry-point)))
-
-                     ;; This one is for Singularity 3.x.
-                     "-p"
-                     ,(string-append
-                       "/.singularity.d/runscript s 777 0 0 "
-                       (relative-file-name "/.singularity.d"
-                                           (string-append #$profile "/"
-                                                          entry-point))))
-                   '())
-
-             ;; Create empty mount points.
-             "-p" "/proc d 555 0 0"
-             "-p" "/sys d 555 0 0"
-             "-p" "/dev d 555 0 0"
-             "-p" "/home d 555 0 0"))
-
-          (when database
-            ;; Initialize /var/guix.
-            (install-database-and-gc-roots "var-etc" database #$profile)
-            (mksquashfs `("var-etc" ,#$output))))))
+            ;; We need an empty file in order to have a valid file argument when
+            ;; we reparent the root file system.  Read on for why that's
+            ;; necessary.
+            (with-output-to-file ".empty" (lambda () (display "")))
+
+            ;; Create the squashfs image in several steps.
+            ;; Add all store items.  Unfortunately mksquashfs throws away all
+            ;; ancestor directories and only keeps the basename.  We fix this
+            ;; in the following invocations of mksquashfs.
+            (mksquashfs `(,@(map store-info-item
+                                 (call-with-input-file "profile"
+                                   read-reference-graph))
+                          #$environment
+                          ,#$output
+
+                          ;; Do not perform duplicate checking because we
+                          ;; don't have any dupes.
+                          "-no-duplicates"
+                          "-comp"
+                          ,#+(compressor-name compressor)))
+
+            ;; Here we reparent the store items.  For each sub-directory of
+            ;; the store prefix we need one invocation of "mksquashfs".
+            (for-each (lambda (dir)
+                        (mksquashfs `(".empty"
+                                      ,#$output
+                                      "-root-becomes" ,dir)))
+                      (reverse (string-tokenize (%store-directory)
+                                                (char-set-complement (char-set #\/)))))
+
+            ;; Add symlinks and mount points.
+            (mksquashfs
+             `(".empty"
+               ,#$output
+               ;; Create SYMLINKS via pseudo file definitions.
+               ,@(append-map
+                  (match-lambda
+                    ((source '-> target)
+                     ;; Create relative symlinks to work around a bug in
+                     ;; Singularity 2.x:
+                     ;;   https://bugs.gnu.org/34913
+                     ;;   https://github.com/sylabs/singularity/issues/1487
+                     (let ((target (string-append #$profile "/" target)))
+                       (list "-p"
+                             (string-join
+                              ;; name s mode uid gid symlink
+                              (list source
+                                    "s" "777" "0" "0"
+                                    (relative-file-name (dirname source)
+                                                        target)))))))
+                  '#$symlinks*)
+
+               "-p" "/.singularity.d d 555 0 0"
+
+               ;; Create the environment file.
+               "-p" "/.singularity.d/env d 555 0 0"
+               "-p" ,(string-append
+                      "/.singularity.d/env/90-environment.sh s 777 0 0 "
+                      (relative-file-name "/.singularity.d/env"
+                                          #$environment))
+
+               ;; Create /.singularity.d/actions, and optionally the 'run'
+               ;; script, used by 'singularity run'.
+               "-p" "/.singularity.d/actions d 555 0 0"
+
+               ,@(if entry-point
+                     `( ;; This one if for Singularity 2.x.
+                       "-p"
+                       ,(string-append
+                         "/.singularity.d/actions/run s 777 0 0 "
+                         (relative-file-name "/.singularity.d/actions"
+                                             (string-append #$profile "/"
+                                                            entry-point)))
+
+                       ;; This one is for Singularity 3.x.
+                       "-p"
+                       ,(string-append
+                         "/.singularity.d/runscript s 777 0 0 "
+                         (relative-file-name "/.singularity.d"
+                                             (string-append #$profile "/"
+                                                            entry-point))))
+                     '())
+
+               ;; Create empty mount points.
+               "-p" "/proc d 555 0 0"
+               "-p" "/sys d 555 0 0"
+               "-p" "/dev d 555 0 0"
+               "-p" "/home d 555 0 0"))
+
+            (when database
+              ;; Initialize /var/guix.
+              (install-database-and-gc-roots "var-etc" database #$profile)
+              (mksquashfs `("var-etc" ,#$output)))))))
 
   (gexp->derivation (string-append name
                                    (compressor-extension compressor)
diff --git a/guix/store/deduplication.scm b/guix/store/deduplication.scm
index b4d37d4525..8564f12107 100644
--- a/guix/store/deduplication.scm
+++ b/guix/store/deduplication.scm
@@ -34,7 +34,8 @@
   #:use-module (guix serialization)
   #:export (nar-sha256
             deduplicate
-            dump-file/deduplicate))
+            dump-file/deduplicate
+            copy-file/deduplicate))
 
 ;; XXX: This port is used as a workaround on Guile <= 2.2.4 where
 ;; 'port-position' throws to 'out-of-range' when the offset is great than or
@@ -256,3 +257,16 @@ down the road."
           (get-hash)))))
 
   (deduplicate file hash #:store store))
+
+(define* (copy-file/deduplicate source target
+                                #:key (store (%store-directory)))
+  "Like 'copy-file', but additionally deduplicate TARGET in STORE."
+  (call-with-input-file source
+    (lambda (input)
+      (let ((stat (stat input)))
+        (dump-file/deduplicate target input (stat:size stat)
+                               (if (zero? (logand (stat:mode stat)
+                                                  #o100))
+                                   'regular
+                                   'executable)
+                               #:store store)))))