YaacovHazan ea930a352c Report child copy-on-write info continuously
Add INFO field, rdb_active_cow_size, to report COW of a live fork child while
it's active.
- once in 1024 keys check the time, and if there's more than one second since
  the last report send a report to the parent via the pipe.
- refactor the child_info_data struct, it's an implementation detail that
  shouldn't be in the server struct, and not used to communicate data between
  caller and callee
- remove the magic value from that struct (not sure what it was good for), and
  instead add handling of short reads.
- add another value to the structure, cow_type, to indicate if the report is
  for the new rdb_active_cow_size field, or it's the last report of a
  successful operation
- add new Module API to report the active COW
- add more asserts variants to test.tcl
2021-01-07 16:14:29 +02:00

275 lines
9.4 KiB
Tcl

set server_path [tmpdir "server.rdb-encoding-test"]
# Copy RDB with different encodings in server path
exec cp tests/assets/encodings.rdb $server_path
start_server [list overrides [list "dir" $server_path "dbfilename" "encodings.rdb"]] {
test "RDB encoding loading test" {
r select 0
csvdump r
} {"0","compressible","string","aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
"0","hash","hash","a","1","aa","10","aaa","100","b","2","bb","20","bbb","200","c","3","cc","30","ccc","300","ddd","400","eee","5000000000",
"0","hash_zipped","hash","a","1","b","2","c","3",
"0","list","list","1","2","3","a","b","c","100000","6000000000","1","2","3","a","b","c","100000","6000000000","1","2","3","a","b","c","100000","6000000000",
"0","list_zipped","list","1","2","3","a","b","c","100000","6000000000",
"0","number","string","10"
"0","set","set","1","100000","2","3","6000000000","a","b","c",
"0","set_zipped_1","set","1","2","3","4",
"0","set_zipped_2","set","100000","200000","300000","400000",
"0","set_zipped_3","set","1000000000","2000000000","3000000000","4000000000","5000000000","6000000000",
"0","string","string","Hello World"
"0","zset","zset","a","1","b","2","c","3","aa","10","bb","20","cc","30","aaa","100","bbb","200","ccc","300","aaaa","1000","cccc","123456789","bbbb","5000000000",
"0","zset_zipped","zset","a","1","b","2","c","3",
}
}
set server_path [tmpdir "server.rdb-startup-test"]
start_server [list overrides [list "dir" $server_path] keep_persistence true] {
test {Server started empty with non-existing RDB file} {
r debug digest
} {0000000000000000000000000000000000000000}
# Save an RDB file, needed for the next test.
r save
}
start_server [list overrides [list "dir" $server_path] keep_persistence true] {
test {Server started empty with empty RDB file} {
r debug digest
} {0000000000000000000000000000000000000000}
}
start_server [list overrides [list "dir" $server_path] keep_persistence true] {
test {Test RDB stream encoding} {
for {set j 0} {$j < 1000} {incr j} {
if {rand() < 0.9} {
r xadd stream * foo $j
} else {
r xadd stream * bar $j
}
}
r xgroup create stream mygroup 0
set records [r xreadgroup GROUP mygroup Alice COUNT 2 STREAMS stream >]
r xack stream mygroup [lindex [lindex [lindex [lindex $records 0] 1] 0] 0]
set digest [r debug digest]
r config set sanitize-dump-payload no
r debug reload
set newdigest [r debug digest]
assert {$digest eq $newdigest}
}
test {Test RDB stream encoding - sanitize dump} {
r config set sanitize-dump-payload yes
r debug reload
set newdigest [r debug digest]
assert {$digest eq $newdigest}
}
# delete the stream, maybe valgrind will find something
r del stream
}
# Helper function to start a server and kill it, just to check the error
# logged.
set defaults {}
proc start_server_and_kill_it {overrides code} {
upvar defaults defaults srv srv server_path server_path
set config [concat $defaults $overrides]
set srv [start_server [list overrides $config keep_persistence true]]
uplevel 1 $code
kill_server $srv
}
# Make the RDB file unreadable
file attributes [file join $server_path dump.rdb] -permissions 0222
# Detect root account (it is able to read the file even with 002 perm)
set isroot 0
catch {
open [file join $server_path dump.rdb]
set isroot 1
}
# Now make sure the server aborted with an error
if {!$isroot} {
start_server_and_kill_it [list "dir" $server_path] {
test {Server should not start if RDB file can't be open} {
wait_for_condition 50 100 {
[string match {*Fatal error loading*} \
[exec tail -1 < [dict get $srv stdout]]]
} else {
fail "Server started even if RDB was unreadable!"
}
}
}
}
# Fix permissions of the RDB file.
file attributes [file join $server_path dump.rdb] -permissions 0666
# Corrupt its CRC64 checksum.
set filesize [file size [file join $server_path dump.rdb]]
set fd [open [file join $server_path dump.rdb] r+]
fconfigure $fd -translation binary
seek $fd -8 end
puts -nonewline $fd "foobar00"; # Corrupt the checksum
close $fd
# Now make sure the server aborted with an error
start_server_and_kill_it [list "dir" $server_path] {
test {Server should not start if RDB is corrupted} {
wait_for_condition 50 100 {
[string match {*CRC error*} \
[exec tail -10 < [dict get $srv stdout]]]
} else {
fail "Server started even if RDB was corrupted!"
}
}
}
start_server {} {
test {Test FLUSHALL aborts bgsave} {
# 1000 keys with 1ms sleep per key shuld take 1 second
r config set rdb-key-save-delay 1000
r debug populate 1000
r bgsave
assert_equal [s rdb_bgsave_in_progress] 1
r flushall
# wait half a second max
wait_for_condition 5 100 {
[s rdb_bgsave_in_progress] == 0
} else {
fail "bgsave not aborted"
}
# veirfy that bgsave failed, by checking that the change counter is still high
assert_lessthan 999 [s rdb_changes_since_last_save]
# make sure the server is still writable
r set x xx
}
test {bgsave resets the change counter} {
r config set rdb-key-save-delay 0
r bgsave
wait_for_condition 50 100 {
[s rdb_bgsave_in_progress] == 0
} else {
fail "bgsave not done"
}
assert_equal [s rdb_changes_since_last_save] 0
}
}
test {client freed during loading} {
start_server [list overrides [list key-load-delay 10 rdbcompression no]] {
# create a big rdb that will take long to load. it is important
# for keys to be big since the server processes events only once in 2mb.
# 100mb of rdb, 100k keys will load in more than 1 second
r debug populate 100000 key 1000
restart_server 0 false false
# make sure it's still loading
assert_equal [s loading] 1
# connect and disconnect 10 clients
set clients {}
for {set j 0} {$j < 10} {incr j} {
lappend clients [redis_deferring_client]
}
foreach rd $clients {
$rd debug log bla
}
foreach rd $clients {
$rd read
}
foreach rd $clients {
$rd close
}
# make sure the server freed the clients
wait_for_condition 100 100 {
[s connected_clients] < 3
} else {
fail "clients didn't disconnect"
}
# make sure it's still loading
assert_equal [s loading] 1
# no need to keep waiting for loading to complete
exec kill [srv 0 pid]
}
}
start_server {overrides {save ""}} {
test {Test child sending COW info} {
# make sure that rdb_last_cow_size and current_cow_size are zero (the test using new server),
# so that the comparisons during the test will be valid
assert {[s current_cow_size] == 0}
assert {[s rdb_last_cow_size] == 0}
# using a 200us delay, the bgsave is empirically taking about 10 seconds.
# we need it to take more than some 5 seconds, since redis only report COW once a second.
r config set rdb-key-save-delay 200
# populate the db with 10k keys of 4k each
set rd [redis_deferring_client 0]
set size 4096
set cmd_count 10000
for {set k 0} {$k < $cmd_count} {incr k} {
$rd set key$k [string repeat A $size]
}
for {set k 0} {$k < $cmd_count} {incr k} {
catch { $rd read }
}
$rd close
# start background rdb save
r bgsave
# on each iteration, we will write some key to the server to trigger copy-on-write, and
# wait to see that it reflected in INFO.
set iteration 1
while 1 {
# take a sample before writing new data to the server
set cow_size [s current_cow_size]
if {$::verbose} {
puts "COW info before copy-on-write: $cow_size"
}
# trigger copy-on-write
r setrange key$iteration 0 [string repeat B $size]
# wait to see that current_cow_size value updated (as long as the child is in progress)
wait_for_condition 80 100 {
[s rdb_bgsave_in_progress] == 0 ||
[s current_cow_size] >= $cow_size + $size
} else {
if {$::verbose} {
puts "COW info on fail: [s current_cow_size]"
}
fail "COW info didn't report"
}
# for no accurate, stop after 2 iterations
if {!$::accurate && $iteration == 2} {
break
}
# stop iterating if the bgsave completed
if { [s rdb_bgsave_in_progress] == 0 } {
break
}
incr iteration 1
}
# make sure we saw report of current_cow_size
assert_morethan_equal $iteration 2
# if bgsave completed, check that rdb_last_cow_size value is at least as last rdb_active_cow_size.
if { [s rdb_bgsave_in_progress] == 0 } {
assert_morethan_equal [s rdb_last_cow_size] $cow_size
}
}
}