From 9cedc786ba132935748bdca8bc33b56c366b531e Mon Sep 17 00:00:00 2001 From: Robert Yang Date: Thu, 3 Apr 2014 17:32:16 +0800 Subject: useradd_base.bbclass: avoid the traffic crowding Currently, it would sleep 1 second when fail to add the user, this maybe not enough when we use the sstate cache, as my test shows below, nearly all the useradd actions are doing in the same minute when mirror from ssate cache, and it would fail when the load is high, I got these time by adding strace before the useradd for debugging: 2014-03-31 14:48:22.978079781 +0800 /tmp/log/pulseaudio.4.c 2014-03-31 14:48:22.028079813 +0800 /tmp/log/pulseaudio.1.c 2014-03-31 14:48:21.949079816 +0800 /tmp/log/pulseaudio.3.c 2014-03-31 14:48:20.903079852 +0800 /tmp/log/pulseaudio.2.c 2014-03-31 14:48:20.006079883 +0800 /tmp/log/nfs-utils.9.c 2014-03-31 14:48:18.876079923 +0800 /tmp/log/xuser-account.9.c 2014-03-31 14:48:18.824079924 +0800 /tmp/log/pulseaudio.0.c 2014-03-31 14:48:17.826079959 +0800 /tmp/log/xuser-account.8.c 2014-03-31 14:48:17.766079961 +0800 /tmp/log/nfs-utils.8.c 2014-03-31 14:48:16.794079995 +0800 /tmp/log/xuser-account.7.c 2014-03-31 14:48:16.735079997 +0800 /tmp/log/nfs-utils.7.c 2014-03-31 14:48:14.719080066 +0800 /tmp/log/xuser-account.5.c 2014-03-31 14:48:14.677080068 +0800 /tmp/log/nfs-utils.5.c 2014-03-31 14:48:12.621080139 +0800 /tmp/log/nfs-utils.3.c 2014-03-31 14:48:11.589080175 +0800 /tmp/log/nfs-utils.2.c 2014-03-31 14:48:10.242080221 +0800 /tmp/log/builder.0.c 2014-03-31 14:48:09.523080246 +0800 /tmp/log/nfs-utils.0.c 2014-03-31 14:48:09.488080248 +0800 /tmp/log/openssh.0.c 2014-03-31 14:48:09.485080248 +0800 /tmp/log/rpcbind.1.c 2014-03-31 14:48:07.590080313 +0800 /tmp/log/rpcbind.0.c 2014-03-31 14:28:15.437121590 +0800 /tmp/log/avahi.0.c 2014-03-31 14:18:19.067142238 +0800 /tmp/log/dbus.0.c The nfs-utils and xuser-account are failed to add the user. The useradd command needs two locks, passwd.lock and group.lock, it may get one, but can't get another one if we look into these .c files, sleep 1 second is not enough, it needs more seconds, the reason is that, if succeed, it doesn't have any side effects, if failed, we need wait for more seconds rather than make it more crowding. I've tried to use "sleep 5", but it didn't make much better since they would sleep and wake up nearly at the same time, I also tried to use "sleep ", that didn't make much better ,either. I think that a better ways is sleep more and more seconds (up to 10 seconds) when failed, this can't fix the problem that they may do the actions at the same time, but the logic is: if it is not crowding, sleep less time should be OK, otherwise sleep more and more time. Here is the testing result which seems much better: 2014-04-03 14:09:56.605185284 +0800 dbus.0.c 2014-04-03 14:09:39.899185862 +0800 rpcbind.5.c 2014-04-03 14:09:38.400185914 +0800 distcc.4.c 2014-04-03 14:09:35.206186025 +0800 pulseaudio.1.c 2014-04-03 14:09:33.979186067 +0800 rpcbind.4.c 2014-04-03 14:09:33.364186089 +0800 pulseaudio.0.c 2014-04-03 14:09:33.360186089 +0800 distcc.3.c 2014-04-03 14:09:30.996186171 +0800 avahi-ui.0.c 2014-04-03 14:09:30.298186195 +0800 distcc.2.c 2014-04-03 14:09:29.905186208 +0800 rpcbind.3.c 2014-04-03 14:09:29.410186226 +0800 avahi-ui.2.c 2014-04-03 14:09:28.239186266 +0800 distcc.1.c 2014-04-03 14:09:27.298186299 +0800 xuser-account.0.c 2014-04-03 14:09:27.032186308 +0800 distcc.0.c 2014-04-03 14:09:26.836186315 +0800 rpcbind.2.c 2014-04-03 14:09:25.846186349 +0800 nfs-utils.1.c 2014-04-03 14:09:25.752186352 +0800 avahi-ui.1.c 2014-04-03 14:09:24.779186386 +0800 builder.0.c 2014-04-03 14:09:24.746186387 +0800 rpcbind.1.c 2014-04-03 14:09:23.916186416 +0800 openssh.1.c 2014-04-03 14:09:23.848186418 +0800 nfs-utils.0.c 2014-04-03 14:09:23.594186427 +0800 rpcbind.0.c 2014-04-03 14:09:22.609186461 +0800 ppp-dialin.0.c 2014-04-03 14:09:21.817186488 +0800 openssh.0.c [YOCTO #6085] Signed-off-by: Robert Yang --- meta/classes/useradd_base.bbclass | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'meta/classes/useradd_base.bbclass') diff --git a/meta/classes/useradd_base.bbclass b/meta/classes/useradd_base.bbclass index 7aafe29a4a..c47b1eb810 100644 --- a/meta/classes/useradd_base.bbclass +++ b/meta/classes/useradd_base.bbclass @@ -24,7 +24,6 @@ perform_groupadd () { group_exists="`grep "^$groupname:" $rootdir/etc/group || true`" if test "x$group_exists" = "x"; then bbwarn "groupadd command did not succeed. Retrying..." - sleep 1 else break fi @@ -32,6 +31,7 @@ perform_groupadd () { if test $count = $retries; then bbfatal "Tried running groupadd command $retries times without scucess, giving up" fi + sleep $count done else bbwarn "group $groupname already exists, not re-creating it" @@ -52,7 +52,6 @@ perform_useradd () { user_exists="`grep "^$username:" $rootdir/etc/passwd || true`" if test "x$user_exists" = "x"; then bbwarn "useradd command did not succeed. Retrying..." - sleep 1 else break fi @@ -60,6 +59,7 @@ perform_useradd () { if test $count = $retries; then bbfatal "Tried running useradd command $retries times without scucess, giving up" fi + sleep $count done else bbwarn "user $username already exists, not re-creating it" @@ -90,7 +90,6 @@ perform_groupmems () { mem_exists="`grep "^$groupname:[^:]*:[^:]*:\([^,]*,\)*$username\(,[^,]*\)*" $rootdir/etc/group || true`" if test "x$mem_exists" = "x"; then bbwarn "groupmems command did not succeed. Retrying..." - sleep 1 else break fi @@ -102,6 +101,7 @@ perform_groupmems () { fi bbfatal "Tried running groupmems command $retries times without scucess, giving up" fi + sleep $count done else bbwarn "group $groupname already contains $username, not re-adding it" @@ -126,7 +126,6 @@ perform_groupdel () { group_exists="`grep "^$groupname:" $rootdir/etc/group || true`" if test "x$group_exists" != "x"; then bbwarn "groupdel command did not succeed. Retrying..." - sleep 1 else break fi @@ -134,6 +133,7 @@ perform_groupdel () { if test $count = $retries; then bbfatal "Tried running groupdel command $retries times without scucess, giving up" fi + sleep $count done else bbwarn "group $groupname doesn't exist, not removing it" @@ -154,7 +154,6 @@ perform_userdel () { user_exists="`grep "^$username:" $rootdir/etc/passwd || true`" if test "x$user_exists" != "x"; then bbwarn "userdel command did not succeed. Retrying..." - sleep 1 else break fi @@ -162,6 +161,7 @@ perform_userdel () { if test $count = $retries; then bbfatal "Tried running userdel command $retries times without scucess, giving up" fi + sleep $count done else bbwarn "user $username doesn't exist, not removing it" @@ -184,7 +184,6 @@ perform_groupmod () { eval $PSEUDO groupmod $opts if test $? != 0; then bbwarn "groupmod command did not succeed. Retrying..." - sleep 1 else break fi @@ -192,6 +191,7 @@ perform_groupmod () { if test $count = $retries; then bbfatal "Tried running groupmod command $retries times without scucess, giving up" fi + sleep $count done else bbwarn "group $groupname doesn't exist, unable to modify it" @@ -214,7 +214,6 @@ perform_usermod () { eval $PSEUDO usermod $opts if test $? != 0; then bbwarn "usermod command did not succeed. Retrying..." - sleep 1 else break fi @@ -222,6 +221,7 @@ perform_usermod () { if test $count = $retries; then bbfatal "Tried running usermod command $retries times without scucess, giving up" fi + sleep $count done else bbwarn "user $username doesn't exist, unable to modify it" -- cgit 1.2.3-korg