Hi! > This is an experimantal patch aimed at the "unable to freeze processes under > load" problem. > > On my box the 2.6.16-rc1-mm4 kernel with this patch applied survives the > "dd if=/dev/hda of=/dev/null" test. > > Please have a look. It makes it better (well, I used my own, simpler variant, but that should not matter; patch is attached). I now can't reproduce hangs with simple stress testing, but running kernel make alongside that makes it hang sometimes. Example of non-frozen gcc: gcc D EEE06A70 0 1750 1749 1751 (NOTLB) df85df38 00000046 bf878130 eee06a70 00004111 eee06a70 eee06a70 003d0900 00000000 c0137cf5 df85c000 00000000 c058ada2 c012503e ef2c915c ef2c9030 c1c0b480 7c3b8500 003d0927 df85c000 00000a98 7c3b8500 003d0927 c0770800 Call Trace: [<c0137cf5>] attach_pid+0x25/0xb0 [<c058ada2>] _write_unlock_irq+0x12/0x30 [<c012503e>] copy_process+0xe5e/0x11b0 [<c0588f74>] wait_for_completion+0x94/0xd0 [<c0121690>] default_wake_function+0x0/0x10 [<c01254d9>] do_fork+0x149/0x210 [<c0101218>] sys_vfork+0x28/0x30 [<c0103231>] syscall_call+0x7/0xb ...maybe solving this would solve journalling problems, too? It is similar AFAICT. Pavel diff --git a/kernel/power/disk.c b/kernel/power/disk.c index e24446f..90d6c1a 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -87,7 +87,6 @@ static int prepare_processes(void) int error; pm_prepare_console(); - sys_sync(); disable_nonboot_cpus(); if (freeze_processes()) { diff --git a/kernel/power/process.c b/kernel/power/process.c index 02a1b3a..bd16e44 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -16,7 +16,7 @@ /* * Timeout for stopping processes */ -#define TIMEOUT (6 * HZ) +#define TIMEOUT (60 * HZ) static inline int freezeable(struct task_struct * p) @@ -54,32 +54,53 @@ void refrigerator(void) current->state = save; } +static void freeze_process(struct task_struct *p) +{ + unsigned long flags; + + freeze(p); + spin_lock_irqsave(&p->sighand->siglock, flags); + signal_wake_up(p, 0); + spin_unlock_irqrestore(&p->sighand->siglock, flags); +} + /* 0 = success, else # of processes that we failed to stop */ int freeze_processes(void) { - int todo; + int todo, user_frozen, nr_user; unsigned long start_time; struct task_struct *g, *p; unsigned long flags; printk( "Stopping tasks: " ); start_time = jiffies; + user_frozen = 0; do { - todo = 0; + nr_user = todo = 0; read_lock(&tasklist_lock); do_each_thread(g, p) { if (!freezeable(p)) continue; if (frozen(p)) continue; - - freeze(p); - spin_lock_irqsave(&p->sighand->siglock, flags); - signal_wake_up(p, 0); - spin_unlock_irqrestore(&p->sighand->siglock, flags); - todo++; + if (p->mm) { + /* The task is a user-space one. Freeze it */ + freeze_process(p); + todo++; + nr_user++; + } else { + /* Freeze only if the user space is frozen */ + if (user_frozen) + freeze_process(p); + todo++; + } } while_each_thread(g, p); read_unlock(&tasklist_lock); + if (!user_frozen && !nr_user) { + printk("sync"); + sys_sync(); + } + user_frozen = !nr_user; yield(); /* Yield is okay here */ if (todo && time_after(jiffies, start_time + TIMEOUT)) { printk( "\n" ); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 41f6636..c9c293f 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -80,7 +80,7 @@ static int save_highmem_zone(struct zone void *kaddr; unsigned long pfn = zone_pfn + zone->zone_start_pfn; - if (!(pfn%1000)) + if (!(pfn%10000)) printk("."); if (!pfn_valid(pfn)) continue; @@ -121,13 +121,14 @@ int save_highmem(void) struct zone *zone; int res = 0; - pr_debug("swsusp: Saving Highmem\n"); + pr_debug("swsusp: Saving Highmem"); for_each_zone (zone) { if (is_highmem(zone)) res = save_highmem_zone(zone); if (res) return res; } + printk("\n"); return 0; } -- Thanks, Sharp!