feat(script): Add dry-run functionality (#1)

README.md

@@ -6,7 +6,7 @@ Arch Linux pacman hook for automatic ZFS snapshots
 
 Get started like so:
 
-1. Install dependency `zfs-auto-snapshot`
+1. Install dependency `jq`
 1. Clone repo into arbitrary path `<repo>`
 1. Make `pacman-zfs-snapshot.sh` executable
     ```
@@ -14,20 +14,27 @@ Get started like so:
     ```
 1. Symlink to files, for example
     ```
-    ln -s <repo>/pacman-zfs-snapshot.sh /usr/local/bin/pacman-zfs-snapshot
+    sudo ln -s <repo>/pacman-zfs-snapshot.sh /usr/local/bin/pacman-zfs-snapshot
-    ln -s <repo>/pacman-zfs-snapshot.hook /usr/share/libalpm/hooks/pacman-zfs-snapshot.hook
+    sudo ln -s <repo>/pacman-zfs-snapshot-install.hook /usr/share/libalpm/hooks/pacman-zfs-snapshot-install.hook
-    ln -s <repo>/pacman-zfs-snapshot.conf /etc/pacman-zfs-snapshot.conf
+    sudo ln -s <repo>/pacman-zfs-snapshot-remove.hook /usr/share/libalpm/hooks/pacman-zfs-snapshot-remove.hook
+    sudo ln -s <repo>/pacman-zfs-snapshot-upgrade.hook /usr/share/libalpm/hooks/pacman-zfs-snapshot-upgrade.hook
+    sudo ln -s <repo>/pacman-zfs-snapshot.conf /etc/pacman-zfs-snapshot.conf
     ```
     Note that while you may choose arbitrary locations for symlinks the `pacman-zfs-snapshot.hook` file references `/usr/local/bin/pacman-zfs-snapshot`. Change that accordingly if you need to.
-1. Adjust `pacman-zfs-snapshot.conf` to your liking
+1. For datasets you want auto-snapshotted add property `space.quico:auto-snapshot=true`
+    ```
+    zfs set space.quico:auto-snapshot=true zpool/root/archlinux
+    ```
+    With any other property and any other value datasets will not be auto-snapshotted.
+1. Adjust `pacman-zfs-snapshot.conf` to your liking. You may want to set `do_dry_run='true'` for a start and just reinstall a benign package to get a feel for what this hook would do.
 
 # What's it do?
 
 In `pacman` on every `PreTransaction`, meaning right before any actual operation on a package begins, we trigger a ZFS snapshot. By default we identify the active system dataset by doing `findmnt / --noheadings --output source`. If exactly one source returns that is the exact name of a ZFS dataset in an imported zpool we create a snapshot on it. If no source returns we silently exit. If more than one source returns we raise an error and halt the `pacman` transaction.
 
-We retain two different snapshot chains, one for `pacman` transactions that only affect what we are calling _trivial_ packages and a separate chain for _important_ packages. By default only the exact regular expression package name match `^linux$` is considered important. Whenever an important package is affected by a transaction a snapshot goes into the corresponding chain. In all other cases - when an important package is not affected - snapshots go into the trivial chain
+We retain two different snapshot chains, one for `pacman` transactions that only affect what we are calling _trivial_ packages and a separate chain for _important_ packages. By default only the exact regular expression package name match `^linux$` is considered important. Whenever an important package is affected by a transaction a snapshot goes into the corresponding chain. In all other cases - when an important package is not affected - snapshots go into the trivial chain.
 
-We use `zfs-auto-snapshot` both for snapshot creation and for destroying old snapshots. The _trivial_ snapshot chain by default keeps 15 snapshots, the _important_ chain keeps 5. The thought process here is that you will likely not futz around with a kernel every day whereas you may very well install arbitrary packages multiple times a day. Snapshots should keep you safe for a couple of days hence the defaults of 5 and 15 snapshots, respectively.
+The _trivial_ snapshot chain by default keeps 15 snapshots, the _important_ chain keeps 5. The thought process here is that you will likely not futz around with a kernel every day whereas you may very well install arbitrary packages multiple times a day. Snapshots should keep you safe for a couple of days hence the defaults of 5 and 15 snapshots, respectively.
 
 You may optionally include more ZFS datasets in this snapshot mechanism. Have a look at `pacman-zfs-snapshot.conf`, its comments should be clear enough to get you going.
 
@@ -50,7 +57,7 @@ Commit _types_ besides `fix` and `feat` are:
 
 The following _scopes_ are known for this project. A Conventional Commits commit message may optionally use one of the following scopes or none:
 
-- `auto`: Change how `zfs-auto-snapshot` is run
 - `conf`: How we deal with script config
 - `script`: Any other script work that doesn't specifically fall into the above scopes
+- `hook`: Configuring the hook(s)
 - `meta`: Affects the project's repo layout, readme content, file names etc.

pacman-zfs-snapshot-install.hook

@@ -1,14 +1,12 @@
 [Trigger]
 Operation = Install
-Operation = Upgrade
-Operation = Remove
 Type = Package
 Target = *
 
 [Action]
 Description = Create ZFS snapshot on active system dataset
 When = PreTransaction
-Exec = /bin/sh -c 'while read -r f; do echo "$f"; done | /usr/local/bin/pacman-zfs-snapshot'
+Exec = /bin/sh -c 'while read -r f; do echo "$f"; done | /usr/local/bin/pacman-zfs-snapshot install'
-Depends = zfs-auto-snapshot
+Depends = jq
 AbortOnFail
 NeedsTargets

pacman-zfs-snapshot-remove.hook

@@ -0,0 +1,12 @@
+[Trigger]
+Operation = Remove
+Type = Package
+Target = *
+
+[Action]
+Description = Create ZFS snapshot on active system dataset
+When = PreTransaction
+Exec = /bin/sh -c 'while read -r f; do echo "$f"; done | /usr/local/bin/pacman-zfs-snapshot remove'
+Depends = jq
+AbortOnFail
+NeedsTargets

pacman-zfs-snapshot-upgrade.hook

@@ -0,0 +1,12 @@
+[Trigger]
+Operation = Upgrade
+Type = Package
+Target = *
+
+[Action]
+Description = Create ZFS snapshot on active system dataset
+When = PreTransaction
+Exec = /bin/sh -c 'while read -r f; do echo "$f"; done | /usr/local/bin/pacman-zfs-snapshot upgrade'
+Depends = jq
+AbortOnFail
+NeedsTargets

pacman-zfs-snapshot.conf

@@ -1,12 +1,35 @@
+do_dry_run='true'
+
 # Pipe-separated list of kernel names. Will be matched against regular
 # expression ^this_var_here$. Snapshots taken before a pacman transaction on
 # an important package have a separate retention from snapshots for trivial
 # packages. Lends itself to keeping kernel updates separate from everything
 # else.
 important_names='tmux'
+# zfs pkgs, systemd?
 
 snaps_trivial_keep='15'
 snaps_important_keep='5'
 
 snaps_trivial_suffix='trv'
 snaps_important_suffix='imp'
+
+pkgs_list_max_length='24'
+
+# Hook will by default snapshot all datasets that have the property
+# 'space.quico:auto-snapshot=true' set, even the ones that are not currently
+# mounted and may belong to unrelated operating systems. Set
+# snap_only_local_datasets='true' to limit snapshots to only those datasets
+# that have aforementioned property and at the same time are currently
+# mounted in your running OS. Currently mounted is defined as:
+# findmnt --json --list --output 'fstype,source,target' | \
+# jq --raw-output '.[][] | select(.fstype=="zfs") | .source'
+snap_only_local_datasets='true'
+
+snap_field_separator='_'
+snap_name_prefix='pac'
+snap_date_format='+F-%H%M'
+
+snap_op_installation_suffix='inst'
+snap_op_remove_suffix='rmvl'
+snap_op_upgrade_suffix='upgr'

pacman-zfs-snapshot.sh

@@ -5,6 +5,9 @@ while read pkg; do
     pkgs+=("${pkg}")
 done
 
+declare operation
+operation="${1}"
+
 declare conf_file
 conf_file='/etc/pacman-zfs-snapshot.conf'
 
@@ -13,11 +16,46 @@ if [[ -r "${conf_file}" ]]; then
     source "${conf_file}"
 fi
 
+if [[ ! "${do_dry_run}" ]]; then do_dry_run='true'; fi
 if [[ ! "${important_names}" ]]; then important_names='linux'; fi
-if [[ ! "${snaps_trivial_keep}" ]]; then snaps_trivial_keep='5'; fi
+if [[ ! "${snaps_trivial_keep}" ]]; then snaps_trivial_keep='15'; fi
 if [[ ! "${snaps_important_keep}" ]]; then snaps_important_keep='5'; fi
 if [[ ! "${snaps_trivial_suffix}" ]]; then snaps_trivial_suffix='trv'; fi
 if [[ ! "${snaps_important_suffix}" ]]; then snaps_important_suffix='imp'; fi
+if [[ ! "${pkgs_list_max_length}" ]]; then pkgs_list_max_length='24'; fi
+if [[ ! "${snap_only_local_datasets}" ]]; then snap_only_local_datasets='true'; fi
+if [[ ! "${snap_field_separator}" ]]; then snap_field_separator='_'; fi
+if [[ ! "${snap_name_prefix}" ]]; then snap_name_prefix='pac'; fi
+if [[ ! "${snap_date_format}" ]]; then snap_date_format='+F-%H%M'; fi
+if [[ ! "${snap_op_installation_suffix}" ]]; then snap_op_installation_suffix='inst'; fi
+if [[ ! "${snap_op_remove_suffix}" ]]; then snap_op_remove_suffix='rmvl'; fi
+if [[ ! "${snap_op_upgrade_suffix}" ]]; then snap_op_upgrade_suffix='upgr'; fi
+
+function pprint () {
+    local style msg exit_code
+    style="${1:?}"
+    msg="${2:?}"
+    exit_code="${3}"
+
+    local color_reset color_lyellow
+    color_reset='\e[0m'
+    color_lyellow='\e[93m'
+    color_red='\e[31m'
+
+    case "${style}" in
+        warn)
+            printf -- "${color_lyellow}"'[WARN]'"${color_reset}"' %s\n' "${msg}"
+            ;;
+        err)
+            printf -- "${color_red}"'[ERR]'"${color_reset}"' %s\n' "${msg}"
+            ;;
+        info)
+            printf -- '[INFO] %s\n' "${msg}"
+            ;;
+    esac
+
+    [[ "${exit_code}" ]] && exit "${exit_code}"
+}
 
 function split_pkgs_by_importance () {
     local pkgs_in_transaction
@@ -26,22 +64,214 @@ function split_pkgs_by_importance () {
         if grep -Piq -- '^'"${important_names}"'$' <<<"${pkg}"; then
             important_pkgs_in_transaction+=("${pkg}")
         else
-            unimportant_pkgs_in_transaction+=("${pkg}")
+            trivial_pkgs_in_transaction+=("${pkg}")
         fi
     done
 }
 
+function set_severity () {
+    if [[ "${#important_pkgs_in_transaction[@]}" -ge '1' ]]; then
+        severity="${snaps_important_suffix}"
+    else
+        severity="${snaps_trivial_suffix}"
+    fi
+}
+
+function get_globally_snappable_datasets () {
+    local datasets_list
+    # For all datasets show their 'space.quico:auto-snapshot' property; only
+    # print dataset name in column 1 and property value in column 2. In awk
+    # limit this list to datasets where tab-delimited column 2 has exact
+    # string '^true$' then further limit output by eliminating snapshots
+    # from list, i.e. dataset names that contain an '@' character.
+    datasets_list="$(zfs get -H -o 'name,value' 'space.quico:auto-snapshot' | \
+                     awk -F'\t' '{if($2 ~ /^true$/ && $1 !~ /@/) print $1}')"
+    while IFS= read -r dataset; do
+        globally_snappable_datasets+=("${dataset}")
+    done <<<"${datasets_list}"
+}
+
+function get_local_snappable_datasets () {
+    local datasets_list
+    datasets_list="$(findmnt --json --list --output 'fstype,source,target' | \
+                     jq --raw-output '.[][] | select(.fstype=="zfs") | .source')"
+    while IFS= read -r dataset; do
+        local_snappable_datasets+=("${dataset}")
+    done <<<"${datasets_list}"
+}
+
+function trim_globally_snappable_datasets () {
+    for global_dataset in "${globally_snappable_datasets[@]}"; do
+        for local_dataset in "${local_snappable_datasets[@]}"; do
+            if grep -Piq -- '^'"${local_dataset}"'$' <<<"${global_dataset}"; then
+                snappable_datasets+=("${global_dataset}")
+            fi
+        done
+    done
+}
+
+function write_pkg_list_oneline () {
+    local unabridged_pkg_list_oneline
+    if [[ "${severity}" == 'imp' ]]; then
+        for pkg in "${important_pkgs_in_transaction[@]}"; do
+            if [[ "${unabridged_pkg_list_oneline}" ]]; then
+                unabridged_pkg_list_oneline="${unabridged_pkg_list_oneline}"','"${pkg}"
+            else
+                unabridged_pkg_list_oneline="${pkg}"
+            fi
+        done
+    fi
+    if [[ "${#trivial_pkgs_in_transaction[@]}" -ge '1' ]]; then
+        for pkg in "${trivial_pkgs_in_transaction[@]}"; do
+            if [[ "${unabridged_pkg_list_oneline}" ]]; then
+                unabridged_pkg_list_oneline="${unabridged_pkg_list_oneline}"','"${pkg}"
+            else
+                unabridged_pkg_list_oneline="${pkg}"
+            fi
+        done
+    fi
+}
+
+function find_max_dataset_name_length () {
+    local longest_op_suffix op_suffix_string
+    longest_op_suffix='0'
+    for op_suffix in "${snap_op_installation_suffix}" "${snap_op_remove_suffix}" "${snap_op_upgrade_suffix}"; do
+        if [[ "${#op_suffix}" -gt "${longest_op_suffix}" ]]; then
+            longest_op_suffix="${#op_suffix}"
+        fi
+    done
+    op_suffix_string="$(head -c "${longest_op_suffix}" '/dev/zero' | tr '\0' '_')"
+
+    local longest_sev_suffix sev_suffix_string
+    longest_sev_suffix='0'
+    for sev_suffix in "${snaps_trivial_suffix}" "${snaps_important_suffix}"; do
+        if [[ "${#sev_suffix}" -gt "${longest_sev_suffix}" ]]; then
+            longest_sev_suffix="${#sev_suffix}"
+        fi
+    done
+    sev_suffix_string="$(head -c "${longest_sev_suffix}" '/dev/zero' | tr '\0' '_')"
+
+    local max_dataset_name_length dataset_name_no_pkgs
+    max_dataset_name_length='0'
+    for dataset in "${snappable_datasets[@]}"; do
+        dataset_name_no_pkgs="${dataset}"'@'"${snap_name_prefix}${snap_field_separator}${date_string}${snap_field_separator}"'op:'"${op_suffix_string}${snap_field_separator}"'sev:'"${sev_suffix_string}${snap_field_separator}"'pkgs:'
+        if [[ "${#dataset_name_no_pkgs}" -gt "${max_dataset_name_length}" ]]; then
+            max_dataset_name_length="${#dataset_name_no_pkgs}"
+        fi
+    done
+
+    if [[ "${max_dataset_name_length}" -gt "${max_zfs_snapshot_name_length}" ]]; then
+        pprint 'warn' 'Snapshot name would exceed ZFS '"${max_zfs_snapshot_name_length}"' chars limit. Skipping snapshots ...' '0'
+    fi
+}
+
+function trim_pkg_list_oneline () {
+    local available_pkg_list_length
+    available_pkg_list_length="$((${max_zfs_snapshot_name_length} - ${max_dataset_name_length}))"
+    if [[ "${available_pkg_list_length}" -lt "{pkgs_list_max_length}" ]]; then
+        # If we have fewer characters available than the user wants limit
+        # package list length
+        pkgs_list_max_length="${available_pkg_list_length}"
+    fi
+
+    local shorter_pkg_list
+    shorter_pkg_list="${pkg_list_oneline}"
+    while [[ "${#shorter_pkg_list}" -gt "${pkgs_list_max_length}" ]]; do
+        shorter_pkg_list="${shorter_pkg_list%,*}"
+        if ! grep -Piq ',' <<<"${shorter_pkg_list}"; then
+            # Only one package remains in package list, no need to continue
+            break
+        fi
+    done
+    if [[ "${#shorter_pkg_list}" -gt "${pkgs_list_max_length}" ]]; do
+        # If this is still too long we empty the package list
+        shorter_pkg_list=''
+    done
+    trimmed_pkg_list_oneline="${shorter_pkg_list}"
+}
+
+function do_snaps () {
+    local snap_name
+    for snappable_dataset in "${snappable_datasets[@]}"; do
+        snap_name="${snappable_dataset}"'@'"${snap_name_prefix}${snap_field_separator}${date_string}${snap_field_separator}"'op:'"${operation}${snap_field_separator}"'sev:'"${severity}${snap_field_separator}"'pkgs:'"${trimmed_pkg_list_oneline}"
+        if [[ "${do_dry_run}" == 'true' ]]; then
+            pprint 'info' 'Dry-run, pretending to run zfs snapshot '"${snap_name}"
+        else
+            zfs snapshot "${snap_name}" && {
+                successfully_snapped_datasets+=("${snappable_dataset}")
+                pprint 'info' 'Snapshot done: '"${snap_name}"
+            } || {
+                pprint 'warn' 'Snapshot failed: '"${snap_name}"
+            }
+        fi
+    done
+}
+
+function get_snaps_in_cur_sev () {
+    local dataset_to_query
+    dataset_to_query="${1:?}"
+    snap_list="$(zfs list -H -o 'name' -t snapshot "${dataset_to_query}")"
+    snaps_done_by_us="$(grep -Pi -- '@'"${snap_name_prefix}${snap_field_separator}" <<<"${snap_list}")"
+    snaps_in_cur_sev="$(grep -Pi -- "${snap_field_separator}"'sev:'"${severity}${snap_field_separator}" <<<"${snaps_done_by_us}")"
+    printf -- '%s' "${snaps_in_cur_sev}"
+}
+
+function do_retention () {
+    local snap_list snaps_done_by_us snaps_in_cur_sev snaps_limit oldest_snap
+    if [[ "${do_dry_run}" == 'true' ]]; then
+        pprint 'info' 'Dry-run, skipping potential zfs destroy operations ...'
+    else
+        for successfully_snapped_dataset in "${successfully_snapped_datasets[@]}"; do        
+            snaps_in_cur_sev="$(get_snaps_in_cur_sev "${successfully_snapped_dataset}")"
+            if [[ "${severity}" == "${snaps_important_suffix}" ]]; then
+                snaps_limit="${snaps_important_keep}"
+            else
+                snaps_limit="${snaps_trivial_keep}"
+            fi
+            while [[ "$(get_snaps_in_cur_sev "${successfully_snapped_dataset}" | wc -l)" -gt "${snaps_limit}" ]]; do
+                oldest_snap="$(get_snaps_in_cur_sev "${successfully_snapped_dataset}" | head -n1)"
+                zfs destroy "${oldest_snap}"
+            done
+        done
+    fi
+}
+
 function main () {
     local pkgs_in_transaction
     pkgs_in_transaction=("${@}")
 
-    declare -a important_pkgs_in_transaction unimportant_pkgs_in_transaction
+    local -a important_pkgs_in_transaction trivial_pkgs_in_transaction
     split_pkgs_by_importance "${pkgs_in_transaction[@]}"
 
-    
+    local severity
-    #for pkg in "${!important_pkgs_in_transaction[@]}"; do
+    set_severity
-    #    printf -- 'Array item '"'"'%s'"'"' equals '"'"'%s'"'"'\n' "${pkg}" "${important_pkgs_in_transaction[${pkg}]}"
+
-    #done
+    local -a globally_snappable_datasets
+    get_globally_snappable_datasets
+
+    local -a snappable_datasets
+    if [[ "${snap_only_local_datasets}" == 'true' ]]; then
+        local local_snappable_datasets
+        get_local_snappable_datasets
+        trim_globally_snappable_datasets
+    else
+        snappable_datasets=("${globally_snappable_datasets}")
+    fi
+
+    local pkg_list_oneline
+    write_pkg_list_oneline
+
+    local date_string max_zfs_snapshot_name_length max_dataset_name_length
+    date_string="$(date +"${snap_date_format}")"
+    max_zfs_snapshot_name_length='255'
+    find_max_dataset_name_length
+
+    local trimmed_pkg_list_oneline
+    trim_pkg_list_oneline
+
+    local -a successfully_snapped_datasets
+    do_snaps
+    do_retention
 }
 
 main "${pkgs[@]}"