#include <linux/version.h>
#include <linux/user_namespace.h>
-#ifdef HAVE_UIDGID_HEADER
-# include <linux/uidgid.h>
-#endif
+#include <linux/uidgid.h>
+
#include <uapi/linux/lustre/lustre_param.h>
#include <lprocfs_status.h>
#include <obd_support.h>
goto free_kobj;
llite_root = debugfs_create_dir("llite", debugfs_lustre_root);
- if (IS_ERR_OR_NULL(llite_root)) {
- rc = llite_root ? PTR_ERR(llite_root) : -ENOMEM;
- llite_root = NULL;
+ return 0;
+
free_kobj:
- kobject_put(llite_kobj);
- llite_kobj = NULL;
- }
+ kobject_put(llite_kobj);
+ llite_kobj = NULL;
return rc;
}
LDEBUGFS_SEQ_FOPS_RO(ll_site_stats);
-static int ll_max_readahead_mb_seq_show(struct seq_file *m, void *v)
+static ssize_t max_read_ahead_mb_show(struct kobject *kobj,
+ struct attribute *attr, char *buf)
{
- struct super_block *sb = m->private;
- struct ll_sb_info *sbi = ll_s2sbi(sb);
- long pages_number;
- int mult;
-
- spin_lock(&sbi->ll_lock);
- pages_number = sbi->ll_ra_info.ra_max_pages;
- spin_unlock(&sbi->ll_lock);
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
- mult = 1 << (20 - PAGE_SHIFT);
- return lprocfs_seq_read_frac_helper(m, pages_number, mult);
+ return scnprintf(buf, PAGE_SIZE, "%lu\n",
+ PAGES_TO_MiB(sbi->ll_ra_info.ra_max_pages));
}
-static ssize_t
-ll_max_readahead_mb_seq_write(struct file *file, const char __user *buffer,
- size_t count, loff_t *off)
+static ssize_t max_read_ahead_mb_store(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buffer, size_t count)
{
- struct seq_file *m = file->private_data;
- struct super_block *sb = m->private;
- struct ll_sb_info *sbi = ll_s2sbi(sb);
- __s64 pages_number;
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
+ u64 ra_max_mb, pages_number;
int rc;
- rc = lprocfs_str_with_units_to_s64(buffer, count, &pages_number, 'M');
+ rc = sysfs_memparse(buffer, count, &ra_max_mb, "MiB");
if (rc)
return rc;
- pages_number >>= PAGE_SHIFT;
-
- if (pages_number < 0 || pages_number > totalram_pages / 2) {
+ pages_number = round_up(ra_max_mb, 1024 * 1024) >> PAGE_SHIFT;
+ CDEBUG(D_INFO, "%s: set max_read_ahead_mb=%llu (%llu pages)\n",
+ sbi->ll_fsname, PAGES_TO_MiB(pages_number), pages_number);
+ if (pages_number > cfs_totalram_pages() / 2) {
/* 1/2 of RAM */
- CERROR("%s: can't set max_readahead_mb=%lu > %luMB\n",
- ll_get_fsname(sb, NULL, 0),
- (unsigned long)pages_number >> (20 - PAGE_SHIFT),
- totalram_pages >> (20 - PAGE_SHIFT + 1));
+ CERROR("%s: cannot set max_read_ahead_mb=%llu > totalram/2=%luMB\n",
+ sbi->ll_fsname, PAGES_TO_MiB(pages_number),
+ PAGES_TO_MiB(cfs_totalram_pages() / 2));
return -ERANGE;
}
return count;
}
+LUSTRE_RW_ATTR(max_read_ahead_mb);
-LDEBUGFS_SEQ_FOPS(ll_max_readahead_mb);
-
-static int ll_max_readahead_per_file_mb_seq_show(struct seq_file *m, void *v)
+static ssize_t max_read_ahead_per_file_mb_show(struct kobject *kobj,
+ struct attribute *attr,
+ char *buf)
{
- struct super_block *sb = m->private;
- struct ll_sb_info *sbi = ll_s2sbi(sb);
- long pages_number;
- int mult;
-
- spin_lock(&sbi->ll_lock);
- pages_number = sbi->ll_ra_info.ra_max_pages_per_file;
- spin_unlock(&sbi->ll_lock);
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
- mult = 1 << (20 - PAGE_SHIFT);
- return lprocfs_seq_read_frac_helper(m, pages_number, mult);
+ return scnprintf(buf, PAGE_SIZE, "%lu\n",
+ PAGES_TO_MiB(sbi->ll_ra_info.ra_max_pages_per_file));
}
-static ssize_t
-ll_max_readahead_per_file_mb_seq_write(struct file *file,
- const char __user *buffer,
- size_t count, loff_t *off)
+static ssize_t max_read_ahead_per_file_mb_store(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buffer,
+ size_t count)
{
- struct seq_file *m = file->private_data;
- struct super_block *sb = m->private;
- struct ll_sb_info *sbi = ll_s2sbi(sb);
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
+ u64 ra_max_file_mb, pages_number;
int rc;
- __s64 pages_number;
- rc = lprocfs_str_with_units_to_s64(buffer, count, &pages_number, 'M');
+ rc = sysfs_memparse(buffer, count, &ra_max_file_mb, "MiB");
if (rc)
return rc;
- pages_number >>= PAGE_SHIFT;
-
- if (pages_number < 0 || pages_number > sbi->ll_ra_info.ra_max_pages) {
- CERROR("%s: can't set max_readahead_per_file_mb=%lu > "
- "max_read_ahead_mb=%lu\n", ll_get_fsname(sb, NULL, 0),
- (unsigned long)pages_number >> (20 - PAGE_SHIFT),
- sbi->ll_ra_info.ra_max_pages >> (20 - PAGE_SHIFT));
+ pages_number = round_up(ra_max_file_mb, 1024 * 1024) >> PAGE_SHIFT;
+ if (pages_number > sbi->ll_ra_info.ra_max_pages) {
+ CERROR("%s: cannot set max_read_ahead_per_file_mb=%llu > max_read_ahead_mb=%lu\n",
+ sbi->ll_fsname, PAGES_TO_MiB(pages_number),
+ PAGES_TO_MiB(sbi->ll_ra_info.ra_max_pages));
return -ERANGE;
}
return count;
}
+LUSTRE_RW_ATTR(max_read_ahead_per_file_mb);
-LDEBUGFS_SEQ_FOPS(ll_max_readahead_per_file_mb);
-
-static int ll_max_read_ahead_whole_mb_seq_show(struct seq_file *m, void *v)
+static ssize_t max_read_ahead_whole_mb_show(struct kobject *kobj,
+ struct attribute *attr, char *buf)
{
- struct super_block *sb = m->private;
- struct ll_sb_info *sbi = ll_s2sbi(sb);
- long pages_number;
- int mult;
-
- spin_lock(&sbi->ll_lock);
- pages_number = sbi->ll_ra_info.ra_max_read_ahead_whole_pages;
- spin_unlock(&sbi->ll_lock);
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
- mult = 1 << (20 - PAGE_SHIFT);
- return lprocfs_seq_read_frac_helper(m, pages_number, mult);
+ return scnprintf(buf, PAGE_SIZE, "%lu\n",
+ PAGES_TO_MiB(sbi->ll_ra_info.ra_max_read_ahead_whole_pages));
}
-static ssize_t
-ll_max_read_ahead_whole_mb_seq_write(struct file *file,
- const char __user *buffer,
- size_t count, loff_t *off)
+static ssize_t max_read_ahead_whole_mb_store(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buffer, size_t count)
{
- struct seq_file *m = file->private_data;
- struct super_block *sb = m->private;
- struct ll_sb_info *sbi = ll_s2sbi(sb);
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
+ u64 ra_max_whole_mb, pages_number;
int rc;
- __s64 pages_number;
- rc = lprocfs_str_with_units_to_s64(buffer, count, &pages_number, 'M');
+ rc = sysfs_memparse(buffer, count, &ra_max_whole_mb, "MiB");
if (rc)
return rc;
- pages_number >>= PAGE_SHIFT;
-
+ pages_number = round_up(ra_max_whole_mb, 1024 * 1024) >> PAGE_SHIFT;
/* Cap this at the current max readahead window size, the readahead
- * algorithm does this anyway so it's pointless to set it larger. */
- if (pages_number < 0 ||
- pages_number > sbi->ll_ra_info.ra_max_pages_per_file) {
- int pages_shift = 20 - PAGE_SHIFT;
- CERROR("%s: can't set max_read_ahead_whole_mb=%lu > "
- "max_read_ahead_per_file_mb=%lu\n",
- ll_get_fsname(sb, NULL, 0),
- (unsigned long)pages_number >> pages_shift,
- sbi->ll_ra_info.ra_max_pages_per_file >> pages_shift);
+ * algorithm does this anyway so it's pointless to set it larger.
+ */
+ if (pages_number > sbi->ll_ra_info.ra_max_pages_per_file) {
+ CERROR("%s: cannot set max_read_ahead_whole_mb=%llu > max_read_ahead_per_file_mb=%lu\n",
+ sbi->ll_fsname, PAGES_TO_MiB(pages_number),
+ PAGES_TO_MiB(sbi->ll_ra_info.ra_max_pages_per_file));
+
return -ERANGE;
}
return count;
}
-
-LDEBUGFS_SEQ_FOPS(ll_max_read_ahead_whole_mb);
+LUSTRE_RW_ATTR(max_read_ahead_whole_mb);
static int ll_max_cached_mb_seq_show(struct seq_file *m, void *v)
{
struct super_block *sb = m->private;
struct ll_sb_info *sbi = ll_s2sbi(sb);
struct cl_client_cache *cache = sbi->ll_cache;
- int shift = 20 - PAGE_SHIFT;
long max_cached_mb;
long unused_mb;
- max_cached_mb = cache->ccc_lru_max >> shift;
- unused_mb = atomic_long_read(&cache->ccc_lru_left) >> shift;
+ mutex_lock(&cache->ccc_max_cache_mb_lock);
+ max_cached_mb = PAGES_TO_MiB(cache->ccc_lru_max);
+ unused_mb = PAGES_TO_MiB(atomic_long_read(&cache->ccc_lru_left));
+ mutex_unlock(&cache->ccc_max_cache_mb_lock);
seq_printf(m, "users: %d\n"
"max_cached_mb: %ld\n"
"used_mb: %ld\n"
long diff = 0;
long nrpages = 0;
__u16 refcheck;
- __s64 pages_number;
+ u64 pages_number;
int rc;
- char kernbuf[128];
+ char kernbuf[128], *ptr;
ENTRY;
if (count >= sizeof(kernbuf))
if (copy_from_user(kernbuf, buffer, count))
RETURN(-EFAULT);
- kernbuf[count] = 0;
+ kernbuf[count] = '\0';
- buffer += lprocfs_find_named_value(kernbuf, "max_cached_mb:", &count) -
- kernbuf;
- rc = lprocfs_str_with_units_to_s64(buffer, count, &pages_number, 'M');
+ ptr = lprocfs_find_named_value(kernbuf, "max_cached_mb:", &count);
+ rc = sysfs_memparse(ptr, count, &pages_number, "MiB");
if (rc)
RETURN(rc);
pages_number >>= PAGE_SHIFT;
- if (pages_number < 0 || pages_number > totalram_pages) {
+ if (pages_number < 0 || pages_number > cfs_totalram_pages()) {
CERROR("%s: can't set max cache more than %lu MB\n",
- ll_get_fsname(sb, NULL, 0),
- totalram_pages >> (20 - PAGE_SHIFT));
+ sbi->ll_fsname,
+ PAGES_TO_MiB(cfs_totalram_pages()));
RETURN(-ERANGE);
}
/* Allow enough cache so clients can make well-formed RPCs */
pages_number = max_t(long, pages_number, PTLRPC_MAX_BRW_PAGES);
- spin_lock(&sbi->ll_lock);
+ mutex_lock(&cache->ccc_max_cache_mb_lock);
diff = pages_number - cache->ccc_lru_max;
- spin_unlock(&sbi->ll_lock);
/* easy - add more LRU slots. */
if (diff >= 0) {
env = cl_env_get(&refcheck);
if (IS_ERR(env))
- RETURN(PTR_ERR(env));
+ GOTO(out_unlock, rc = PTR_ERR(env));
diff = -diff;
while (diff > 0) {
/* reduce LRU budget from free slots. */
do {
- long ov, nv;
+ long lru_left_old, lru_left_new, lru_left_ret;
- ov = atomic_long_read(&cache->ccc_lru_left);
- if (ov == 0)
+ lru_left_old = atomic_long_read(&cache->ccc_lru_left);
+ if (lru_left_old == 0)
break;
- nv = ov > diff ? ov - diff : 0;
- rc = atomic_long_cmpxchg(&cache->ccc_lru_left, ov, nv);
- if (likely(ov == rc)) {
- diff -= ov - nv;
- nrpages += ov - nv;
+ lru_left_new = lru_left_old > diff ?
+ lru_left_old - diff : 0;
+ lru_left_ret =
+ atomic_long_cmpxchg(&cache->ccc_lru_left,
+ lru_left_old,
+ lru_left_new);
+ if (likely(lru_left_old == lru_left_ret)) {
+ diff -= lru_left_old - lru_left_new;
+ nrpages += lru_left_old - lru_left_new;
break;
}
} while (1);
break;
}
+ /* Request extra free slots to avoid them all being used
+ * by other processes before this can continue shrinking.
+ */
+ tmp = diff + min_t(long, diff, MiB_TO_PAGES(1024));
/* difficult - have to ask OSCs to drop LRU slots. */
- tmp = diff << 1;
rc = obd_set_info_async(env, sbi->ll_dt_exp,
sizeof(KEY_CACHE_LRU_SHRINK),
KEY_CACHE_LRU_SHRINK,
out:
if (rc >= 0) {
- spin_lock(&sbi->ll_lock);
cache->ccc_lru_max = pages_number;
- spin_unlock(&sbi->ll_lock);
rc = count;
} else {
atomic_long_add(nrpages, &cache->ccc_lru_left);
}
+out_unlock:
+ mutex_unlock(&cache->ccc_max_cache_mb_lock);
return rc;
}
-
LDEBUGFS_SEQ_FOPS(ll_max_cached_mb);
static ssize_t checksums_show(struct kobject *kobj, struct attribute *attr,
}
LUSTRE_RW_ATTR(lazystatfs);
+static ssize_t statfs_max_age_show(struct kobject *kobj, struct attribute *attr,
+ char *buf)
+{
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
+
+ return snprintf(buf, PAGE_SIZE, "%u\n", sbi->ll_statfs_max_age);
+}
+
+static ssize_t statfs_max_age_store(struct kobject *kobj,
+ struct attribute *attr, const char *buffer,
+ size_t count)
+{
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
+ unsigned int val;
+ int rc;
+
+ rc = kstrtouint(buffer, 10, &val);
+ if (rc)
+ return rc;
+ if (val > OBD_STATFS_CACHE_MAX_AGE)
+ return -EINVAL;
+
+ sbi->ll_statfs_max_age = val;
+
+ return count;
+}
+LUSTRE_RW_ATTR(statfs_max_age);
+
static ssize_t max_easize_show(struct kobject *kobj,
struct attribute *attr,
char *buf)
if (rc)
return rc;
- return sprintf(buf, "%u\n", ealen);
+ /* Limit xattr size returned to userspace based on kernel maximum */
+ return snprintf(buf, PAGE_SIZE, "%u\n",
+ ealen > XATTR_SIZE_MAX ? XATTR_SIZE_MAX : ealen);
}
LUSTRE_RO_ATTR(max_easize);
if (rc)
return rc;
- return sprintf(buf, "%u\n", ealen);
+ /* Limit xattr size returned to userspace based on kernel maximum */
+ return snprintf(buf, PAGE_SIZE, "%u\n",
+ ealen > XATTR_SIZE_MAX ? XATTR_SIZE_MAX : ealen);
}
/**
while (flags != 0) {
if (ARRAY_SIZE(str) <= i) {
CERROR("%s: Revise array LL_SBI_FLAGS to match sbi "
- "flags please.\n", ll_get_fsname(sb, NULL, 0));
+ "flags please.\n", ll_s2sbi(sb)->ll_fsname);
return -EINVAL;
}
}
LUSTRE_RW_ATTR(tiny_write);
+static ssize_t max_read_ahead_async_active_show(struct kobject *kobj,
+ struct attribute *attr,
+ char *buf)
+{
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
+
+ return snprintf(buf, PAGE_SIZE, "%u\n",
+ sbi->ll_ra_info.ra_async_max_active);
+}
+
+static ssize_t max_read_ahead_async_active_store(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buffer,
+ size_t count)
+{
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
+ unsigned int val;
+ int rc;
+
+ rc = kstrtouint(buffer, 10, &val);
+ if (rc)
+ return rc;
+
+ /**
+ * It doesn't make any sense to make it exceed what
+ * workqueue could acutally support. This can easily
+ * over subscripe the cores but Lustre internally
+ * throttles to avoid those impacts.
+ */
+ if (val > WQ_UNBOUND_MAX_ACTIVE) {
+ CERROR("%s: cannot set max_read_ahead_async_active=%u larger than %u\n",
+ sbi->ll_fsname, val, WQ_UNBOUND_MAX_ACTIVE);
+ return -ERANGE;
+ }
+
+ spin_lock(&sbi->ll_lock);
+ sbi->ll_ra_info.ra_async_max_active = val;
+ spin_unlock(&sbi->ll_lock);
+
+ return count;
+}
+LUSTRE_RW_ATTR(max_read_ahead_async_active);
+
+static ssize_t read_ahead_async_file_threshold_mb_show(struct kobject *kobj,
+ struct attribute *attr,
+ char *buf)
+{
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
+
+ return snprintf(buf, PAGE_SIZE, "%lu\n",
+ PAGES_TO_MiB(sbi->ll_ra_info.ra_async_pages_per_file_threshold));
+}
+
+static ssize_t
+read_ahead_async_file_threshold_mb_store(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buffer, size_t count)
+{
+ unsigned long pages_number;
+ unsigned long max_ra_per_file;
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
+ int rc;
+
+ rc = kstrtoul(buffer, 10, &pages_number);
+ if (rc)
+ return rc;
+
+ pages_number = MiB_TO_PAGES(pages_number);
+ max_ra_per_file = sbi->ll_ra_info.ra_max_pages_per_file;
+ if (pages_number < 0 || pages_number > max_ra_per_file) {
+ CERROR("%s: can't set read_ahead_async_file_threshold_mb=%lu > "
+ "max_read_readahead_per_file_mb=%lu\n", sbi->ll_fsname,
+ PAGES_TO_MiB(pages_number),
+ PAGES_TO_MiB(max_ra_per_file));
+ return -ERANGE;
+ }
+ sbi->ll_ra_info.ra_async_pages_per_file_threshold = pages_number;
+
+ return count;
+}
+LUSTRE_RW_ATTR(read_ahead_async_file_threshold_mb);
+
static ssize_t fast_read_show(struct kobject *kobj,
struct attribute *attr,
char *buf)
}
LUSTRE_RW_ATTR(fast_read);
+static ssize_t file_heat_show(struct kobject *kobj,
+ struct attribute *attr,
+ char *buf)
+{
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
+
+ return snprintf(buf, PAGE_SIZE, "%u\n",
+ !!(sbi->ll_flags & LL_SBI_FILE_HEAT));
+}
+
+static ssize_t file_heat_store(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buffer,
+ size_t count)
+{
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
+ bool val;
+ int rc;
+
+ rc = kstrtobool(buffer, &val);
+ if (rc)
+ return rc;
+
+ spin_lock(&sbi->ll_lock);
+ if (val)
+ sbi->ll_flags |= LL_SBI_FILE_HEAT;
+ else
+ sbi->ll_flags &= ~LL_SBI_FILE_HEAT;
+ spin_unlock(&sbi->ll_lock);
+
+ return count;
+}
+LUSTRE_RW_ATTR(file_heat);
+
+static ssize_t heat_decay_percentage_show(struct kobject *kobj,
+ struct attribute *attr,
+ char *buf)
+{
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
+
+ return snprintf(buf, PAGE_SIZE, "%u\n",
+ (sbi->ll_heat_decay_weight * 100 + 128) / 256);
+}
+
+static ssize_t heat_decay_percentage_store(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buffer,
+ size_t count)
+{
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
+ unsigned long val;
+ int rc;
+
+ rc = kstrtoul(buffer, 10, &val);
+ if (rc)
+ return rc;
+
+ if (val < 0 || val > 100)
+ return -ERANGE;
+
+ sbi->ll_heat_decay_weight = (val * 256 + 50) / 100;
+
+ return count;
+}
+LUSTRE_RW_ATTR(heat_decay_percentage);
+
+static ssize_t heat_period_second_show(struct kobject *kobj,
+ struct attribute *attr,
+ char *buf)
+{
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
+
+ return snprintf(buf, PAGE_SIZE, "%u\n", sbi->ll_heat_period_second);
+}
+
+static ssize_t heat_period_second_store(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buffer,
+ size_t count)
+{
+ struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
+ ll_kset.kobj);
+ unsigned long val;
+ int rc;
+
+ rc = kstrtoul(buffer, 10, &val);
+ if (rc)
+ return rc;
+
+ if (val <= 0)
+ return -ERANGE;
+
+ sbi->ll_heat_period_second = val;
+
+ return count;
+}
+LUSTRE_RW_ATTR(heat_period_second);
+
static int ll_unstable_stats_seq_show(struct seq_file *m, void *v)
{
struct super_block *sb = m->private;
struct ll_sb_info *sbi = ll_s2sbi(sb);
struct root_squash_info *squash = &sbi->ll_squash;
- return lprocfs_wr_root_squash(buffer, count, squash,
- ll_get_fsname(sb, NULL, 0));
+ return lprocfs_wr_root_squash(buffer, count, squash, sbi->ll_fsname);
}
LDEBUGFS_SEQ_FOPS(ll_root_squash);
struct root_squash_info *squash = &sbi->ll_squash;
int len;
- down_read(&squash->rsi_sem);
+ spin_lock(&squash->rsi_lock);
if (!list_empty(&squash->rsi_nosquash_nids)) {
len = cfs_print_nidlist(m->buf + m->count, m->size - m->count,
&squash->rsi_nosquash_nids);
} else {
seq_puts(m, "NONE\n");
}
- up_read(&squash->rsi_sem);
+ spin_unlock(&squash->rsi_lock);
return 0;
}
struct root_squash_info *squash = &sbi->ll_squash;
int rc;
- rc = lprocfs_wr_nosquash_nids(buffer, count, squash,
- ll_get_fsname(sb, NULL, 0));
+ rc = lprocfs_wr_nosquash_nids(buffer, count, squash, sbi->ll_fsname);
if (rc < 0)
return rc;
LDEBUGFS_SEQ_FOPS(ll_nosquash_nids);
-struct lprocfs_vars lprocfs_llite_obd_vars[] = {
+static int ll_pcc_seq_show(struct seq_file *m, void *v)
+{
+ struct super_block *sb = m->private;
+ struct ll_sb_info *sbi = ll_s2sbi(sb);
+
+ return pcc_super_dump(&sbi->ll_pcc_super, m);
+}
+
+static ssize_t ll_pcc_seq_write(struct file *file, const char __user *buffer,
+ size_t count, loff_t *off)
+{
+ struct seq_file *m = file->private_data;
+ struct super_block *sb = m->private;
+ struct ll_sb_info *sbi = ll_s2sbi(sb);
+ int rc;
+ char *kernbuf;
+
+ if (count >= LPROCFS_WR_PCC_MAX_CMD)
+ return -EINVAL;
+
+ if (!(exp_connect_flags2(sbi->ll_md_exp) & OBD_CONNECT2_PCC))
+ return -EOPNOTSUPP;
+
+ OBD_ALLOC(kernbuf, count + 1);
+ if (kernbuf == NULL)
+ return -ENOMEM;
+
+ if (copy_from_user(kernbuf, buffer, count))
+ GOTO(out_free_kernbuff, rc = -EFAULT);
+
+ rc = pcc_cmd_handle(kernbuf, count, &sbi->ll_pcc_super);
+out_free_kernbuff:
+ OBD_FREE(kernbuf, count + 1);
+ return rc ? rc : count;
+}
+LDEBUGFS_SEQ_FOPS(ll_pcc);
+
+struct ldebugfs_vars lprocfs_llite_obd_vars[] = {
{ .name = "site",
.fops = &ll_site_stats_fops },
- { .name = "max_read_ahead_mb",
- .fops = &ll_max_readahead_mb_fops },
- { .name = "max_read_ahead_per_file_mb",
- .fops = &ll_max_readahead_per_file_mb_fops },
- { .name = "max_read_ahead_whole_mb",
- .fops = &ll_max_read_ahead_whole_mb_fops },
{ .name = "max_cached_mb",
.fops = &ll_max_cached_mb_fops },
{ .name = "statahead_stats",
.fops = &ll_root_squash_fops },
{ .name = "nosquash_nids",
.fops = &ll_nosquash_nids_fops },
+ { .name = "pcc",
+ .fops = &ll_pcc_fops, },
{ NULL }
};
&lustre_attr_uuid.attr,
&lustre_attr_checksums.attr,
&lustre_attr_checksum_pages.attr,
+ &lustre_attr_max_read_ahead_mb.attr,
+ &lustre_attr_max_read_ahead_per_file_mb.attr,
+ &lustre_attr_max_read_ahead_whole_mb.attr,
+ &lustre_attr_max_read_ahead_async_active.attr,
+ &lustre_attr_read_ahead_async_file_threshold_mb.attr,
&lustre_attr_stats_track_pid.attr,
&lustre_attr_stats_track_ppid.attr,
&lustre_attr_stats_track_gid.attr,
&lustre_attr_statahead_max.attr,
&lustre_attr_statahead_agl.attr,
&lustre_attr_lazystatfs.attr,
+ &lustre_attr_statfs_max_age.attr,
&lustre_attr_max_easize.attr,
&lustre_attr_default_easize.attr,
&lustre_attr_xattr_cache.attr,
&lustre_attr_fast_read.attr,
&lustre_attr_tiny_write.attr,
+ &lustre_attr_file_heat.attr,
+ &lustre_attr_heat_decay_percentage.attr,
+ &lustre_attr_heat_period_second.attr,
NULL,
};
};
static const struct llite_file_opcode {
- __u32 opcode;
- __u32 type;
- const char *opname;
+ __u32 opcode;
+ __u32 type;
+ const char *opname;
} llite_opcode_table[LPROC_LL_FILE_OPCODES] = {
- /* file operation */
- { LPROC_LL_DIRTY_HITS, LPROCFS_TYPE_REGS, "dirty_pages_hits" },
- { LPROC_LL_DIRTY_MISSES, LPROCFS_TYPE_REGS, "dirty_pages_misses" },
- { LPROC_LL_READ_BYTES, LPROCFS_CNTR_AVGMINMAX|LPROCFS_TYPE_BYTES,
- "read_bytes" },
- { LPROC_LL_WRITE_BYTES, LPROCFS_CNTR_AVGMINMAX|LPROCFS_TYPE_BYTES,
- "write_bytes" },
- { LPROC_LL_BRW_READ, LPROCFS_CNTR_AVGMINMAX|LPROCFS_TYPE_PAGES,
- "brw_read" },
- { LPROC_LL_BRW_WRITE, LPROCFS_CNTR_AVGMINMAX|LPROCFS_TYPE_PAGES,
- "brw_write" },
- { LPROC_LL_IOCTL, LPROCFS_TYPE_REGS, "ioctl" },
- { LPROC_LL_OPEN, LPROCFS_TYPE_REGS, "open" },
- { LPROC_LL_RELEASE, LPROCFS_TYPE_REGS, "close" },
- { LPROC_LL_MAP, LPROCFS_TYPE_REGS, "mmap" },
- { LPROC_LL_FAULT, LPROCFS_TYPE_REGS, "page_fault" },
- { LPROC_LL_MKWRITE, LPROCFS_TYPE_REGS, "page_mkwrite" },
- { LPROC_LL_LLSEEK, LPROCFS_TYPE_REGS, "seek" },
- { LPROC_LL_FSYNC, LPROCFS_TYPE_REGS, "fsync" },
- { LPROC_LL_READDIR, LPROCFS_TYPE_REGS, "readdir" },
- /* inode operation */
- { LPROC_LL_SETATTR, LPROCFS_TYPE_REGS, "setattr" },
- { LPROC_LL_TRUNC, LPROCFS_TYPE_REGS, "truncate" },
- { LPROC_LL_FLOCK, LPROCFS_TYPE_REGS, "flock" },
- { LPROC_LL_GETATTR, LPROCFS_TYPE_REGS, "getattr" },
- /* dir inode operation */
- { LPROC_LL_CREATE, LPROCFS_TYPE_REGS, "create" },
- { LPROC_LL_LINK, LPROCFS_TYPE_REGS, "link" },
- { LPROC_LL_UNLINK, LPROCFS_TYPE_REGS, "unlink" },
- { LPROC_LL_SYMLINK, LPROCFS_TYPE_REGS, "symlink" },
- { LPROC_LL_MKDIR, LPROCFS_TYPE_REGS, "mkdir" },
- { LPROC_LL_RMDIR, LPROCFS_TYPE_REGS, "rmdir" },
- { LPROC_LL_MKNOD, LPROCFS_TYPE_REGS, "mknod" },
- { LPROC_LL_RENAME, LPROCFS_TYPE_REGS, "rename" },
- /* special inode operation */
- { LPROC_LL_STAFS, LPROCFS_TYPE_REGS, "statfs" },
- { LPROC_LL_ALLOC_INODE, LPROCFS_TYPE_REGS, "alloc_inode" },
- { LPROC_LL_SETXATTR, LPROCFS_TYPE_REGS, "setxattr" },
- { LPROC_LL_GETXATTR, LPROCFS_TYPE_REGS, "getxattr" },
- { LPROC_LL_GETXATTR_HITS, LPROCFS_TYPE_REGS, "getxattr_hits" },
- { LPROC_LL_LISTXATTR, LPROCFS_TYPE_REGS, "listxattr" },
- { LPROC_LL_REMOVEXATTR, LPROCFS_TYPE_REGS, "removexattr" },
- { LPROC_LL_INODE_PERM, LPROCFS_TYPE_REGS, "inode_permission" },
+ /* file operation */
+ { LPROC_LL_READ_BYTES, LPROCFS_TYPE_BYTES_FULL, "read_bytes" },
+ { LPROC_LL_WRITE_BYTES, LPROCFS_TYPE_BYTES_FULL, "write_bytes" },
+ { LPROC_LL_READ, LPROCFS_TYPE_LATENCY, "read" },
+ { LPROC_LL_WRITE, LPROCFS_TYPE_LATENCY, "write" },
+ { LPROC_LL_IOCTL, LPROCFS_TYPE_REQS, "ioctl" },
+ { LPROC_LL_OPEN, LPROCFS_TYPE_LATENCY, "open" },
+ { LPROC_LL_RELEASE, LPROCFS_TYPE_LATENCY, "close" },
+ { LPROC_LL_MMAP, LPROCFS_TYPE_LATENCY, "mmap" },
+ { LPROC_LL_FAULT, LPROCFS_TYPE_LATENCY, "page_fault" },
+ { LPROC_LL_MKWRITE, LPROCFS_TYPE_LATENCY, "page_mkwrite" },
+ { LPROC_LL_LLSEEK, LPROCFS_TYPE_LATENCY, "seek" },
+ { LPROC_LL_FSYNC, LPROCFS_TYPE_LATENCY, "fsync" },
+ { LPROC_LL_READDIR, LPROCFS_TYPE_LATENCY, "readdir" },
+ /* inode operation */
+ { LPROC_LL_SETATTR, LPROCFS_TYPE_LATENCY, "setattr" },
+ { LPROC_LL_TRUNC, LPROCFS_TYPE_LATENCY, "truncate" },
+ { LPROC_LL_FLOCK, LPROCFS_TYPE_LATENCY, "flock" },
+ { LPROC_LL_GETATTR, LPROCFS_TYPE_LATENCY, "getattr" },
+ { LPROC_LL_FALLOCATE, LPROCFS_TYPE_LATENCY, "fallocate"},
+ /* dir inode operation */
+ { LPROC_LL_CREATE, LPROCFS_TYPE_LATENCY, "create" },
+ { LPROC_LL_LINK, LPROCFS_TYPE_LATENCY, "link" },
+ { LPROC_LL_UNLINK, LPROCFS_TYPE_LATENCY, "unlink" },
+ { LPROC_LL_SYMLINK, LPROCFS_TYPE_LATENCY, "symlink" },
+ { LPROC_LL_MKDIR, LPROCFS_TYPE_LATENCY, "mkdir" },
+ { LPROC_LL_RMDIR, LPROCFS_TYPE_LATENCY, "rmdir" },
+ { LPROC_LL_MKNOD, LPROCFS_TYPE_LATENCY, "mknod" },
+ { LPROC_LL_RENAME, LPROCFS_TYPE_LATENCY, "rename" },
+ /* special inode operation */
+ { LPROC_LL_STATFS, LPROCFS_TYPE_LATENCY, "statfs" },
+ { LPROC_LL_SETXATTR, LPROCFS_TYPE_LATENCY, "setxattr" },
+ { LPROC_LL_GETXATTR, LPROCFS_TYPE_LATENCY, "getxattr" },
+ { LPROC_LL_GETXATTR_HITS, LPROCFS_TYPE_REQS, "getxattr_hits" },
+ { LPROC_LL_LISTXATTR, LPROCFS_TYPE_LATENCY, "listxattr" },
+ { LPROC_LL_REMOVEXATTR, LPROCFS_TYPE_LATENCY, "removexattr" },
+ { LPROC_LL_INODE_PERM, LPROCFS_TYPE_LATENCY, "inode_permission" },
};
-void ll_stats_ops_tally(struct ll_sb_info *sbi, int op, int count)
+void ll_stats_ops_tally(struct ll_sb_info *sbi, int op, long count)
{
- if (!sbi->ll_stats)
- return;
- if (sbi->ll_stats_track_type == STATS_TRACK_ALL)
- lprocfs_counter_add(sbi->ll_stats, op, count);
- else if (sbi->ll_stats_track_type == STATS_TRACK_PID &&
- sbi->ll_stats_track_id == current->pid)
- lprocfs_counter_add(sbi->ll_stats, op, count);
- else if (sbi->ll_stats_track_type == STATS_TRACK_PPID &&
- sbi->ll_stats_track_id == current->parent->pid)
- lprocfs_counter_add(sbi->ll_stats, op, count);
+ if (!sbi->ll_stats)
+ return;
+
+ if (sbi->ll_stats_track_type == STATS_TRACK_ALL)
+ lprocfs_counter_add(sbi->ll_stats, op, count);
+ else if (sbi->ll_stats_track_type == STATS_TRACK_PID &&
+ sbi->ll_stats_track_id == current->pid)
+ lprocfs_counter_add(sbi->ll_stats, op, count);
+ else if (sbi->ll_stats_track_type == STATS_TRACK_PPID &&
+ sbi->ll_stats_track_id == current->parent->pid)
+ lprocfs_counter_add(sbi->ll_stats, op, count);
else if (sbi->ll_stats_track_type == STATS_TRACK_GID &&
sbi->ll_stats_track_id ==
from_kgid(&init_user_ns, current_gid()))
[RA_STAT_EOF] = "read-ahead to EOF",
[RA_STAT_MAX_IN_FLIGHT] = "hit max r-a issue",
[RA_STAT_WRONG_GRAB_PAGE] = "wrong page from grab_cache_page",
- [RA_STAT_FAILED_REACH_END] = "failed to reach end"
+ [RA_STAT_FAILED_REACH_END] = "failed to reach end",
+ [RA_STAT_ASYNC] = "async readahead",
+ [RA_STAT_FAILED_FAST_READ] = "failed to fast read",
};
int ll_debugfs_register_super(struct super_block *sb, const char *name)
{
struct lustre_sb_info *lsi = s2lsi(sb);
struct ll_sb_info *sbi = ll_s2sbi(sb);
- int err, id, rc;
+ int err, id;
ENTRY;
LASSERT(sbi);
if (IS_ERR_OR_NULL(llite_root))
goto out_ll_kset;
- sbi->ll_debugfs_entry = ldebugfs_register(name, llite_root,
- lprocfs_llite_obd_vars, sb);
- if (IS_ERR_OR_NULL(sbi->ll_debugfs_entry)) {
- err = sbi->ll_debugfs_entry ? PTR_ERR(sbi->ll_debugfs_entry) :
- -ENOMEM;
- sbi->ll_debugfs_entry = NULL;
- RETURN(err);
- }
+ sbi->ll_debugfs_entry = debugfs_create_dir(name, llite_root);
+ ldebugfs_add_vars(sbi->ll_debugfs_entry, lprocfs_llite_obd_vars, sb);
- rc = ldebugfs_seq_create(sbi->ll_debugfs_entry, "dump_page_cache",0444,
- &vvp_dump_pgcache_file_ops, sbi);
- if (rc)
- CWARN("Error adding the dump_page_cache file\n");
+ debugfs_create_file("dump_page_cache", 0444, sbi->ll_debugfs_entry, sbi,
+ &vvp_dump_pgcache_file_ops);
- rc = ldebugfs_seq_create(sbi->ll_debugfs_entry, "extents_stats", 0644,
- &ll_rw_extents_stats_fops, sbi);
- if (rc)
- CWARN("Error adding the extent_stats file\n");
+ debugfs_create_file("extents_stats", 0644, sbi->ll_debugfs_entry, sbi,
+ &ll_rw_extents_stats_fops);
- rc = ldebugfs_seq_create(sbi->ll_debugfs_entry,
- "extents_stats_per_process", 0644,
- &ll_rw_extents_stats_pp_fops, sbi);
- if (rc)
- CWARN("Error adding the extents_stats_per_process file\n");
+ debugfs_create_file("extents_stats_per_process", 0644,
+ sbi->ll_debugfs_entry, sbi,
+ &ll_rw_extents_stats_pp_fops);
- rc = ldebugfs_seq_create(sbi->ll_debugfs_entry, "offset_stats", 0644,
- &ll_rw_offset_stats_fops, sbi);
- if (rc)
- CWARN("Error adding the offset_stats file\n");
+ debugfs_create_file("offset_stats", 0644, sbi->ll_debugfs_entry, sbi,
+ &ll_rw_offset_stats_fops);
/* File operations stats */
sbi->ll_stats = lprocfs_alloc_stats(LPROC_LL_FILE_OPCODES,
/* do counter init */
for (id = 0; id < LPROC_LL_FILE_OPCODES; id++) {
u32 type = llite_opcode_table[id].type;
- void *ptr = NULL;
+ void *ptr = "unknown";
- if (type & LPROCFS_TYPE_REGS)
- ptr = "regs";
+ if (type & LPROCFS_TYPE_REQS)
+ ptr = "reqs";
else if (type & LPROCFS_TYPE_BYTES)
ptr = "bytes";
- else if (type & LPROCFS_TYPE_PAGES)
- ptr = "pages";
+ else if (type & LPROCFS_TYPE_USEC)
+ ptr = "usec";
lprocfs_counter_init(sbi->ll_stats,
- llite_opcode_table[id].opcode,
- (type & LPROCFS_CNTR_AVGMINMAX),
+ llite_opcode_table[id].opcode, type,
llite_opcode_table[id].opname, ptr);
}
- err = ldebugfs_register_stats(sbi->ll_debugfs_entry, "stats",
- sbi->ll_stats);
- if (err)
- GOTO(out_stats, err);
+ debugfs_create_file("stats", 0644, sbi->ll_debugfs_entry,
+ sbi->ll_stats, &ldebugfs_stats_seq_fops);
sbi->ll_ra_stats = lprocfs_alloc_stats(ARRAY_SIZE(ra_stat_string),
LPROCFS_STATS_FLAG_NONE);
lprocfs_counter_init(sbi->ll_ra_stats, id, 0,
ra_stat_string[id], "pages");
- err = ldebugfs_register_stats(sbi->ll_debugfs_entry, "read_ahead_stats",
- sbi->ll_ra_stats);
- if (err)
- GOTO(out_ra_stats, err);
+ debugfs_create_file("read_ahead_stats", 0644, sbi->ll_debugfs_entry,
+ sbi->ll_ra_stats, &ldebugfs_stats_seq_fops);
out_ll_kset:
/* Yes we also register sysfs mount kset here as well */
out_stats:
lprocfs_free_stats(&sbi->ll_stats);
out_debugfs:
- ldebugfs_remove(&sbi->ll_debugfs_entry);
+ debugfs_remove_recursive(sbi->ll_debugfs_entry);
RETURN(err);
}
struct lustre_sb_info *lsi = s2lsi(sb);
struct ll_sb_info *sbi = ll_s2sbi(sb);
- if (!IS_ERR_OR_NULL(sbi->ll_debugfs_entry))
- ldebugfs_remove(&sbi->ll_debugfs_entry);
+ debugfs_remove_recursive(sbi->ll_debugfs_entry);
if (sbi->ll_dt_obd)
sysfs_remove_link(&sbi->ll_kset.kobj,
write_tot += pp_info->pp_w_hist.oh_buckets[i];
}
- for(i = 0; i < LL_HIST_MAX; i++) {
- r = pp_info->pp_r_hist.oh_buckets[i];
- w = pp_info->pp_w_hist.oh_buckets[i];
- read_cum += r;
- write_cum += w;
- end = BIT(i + LL_HIST_START - units);
+ for(i = 0; i < LL_HIST_MAX; i++) {
+ r = pp_info->pp_r_hist.oh_buckets[i];
+ w = pp_info->pp_w_hist.oh_buckets[i];
+ read_cum += r;
+ write_cum += w;
+ end = 1 << (i + LL_HIST_START - units);
seq_printf(seq, "%4lu%c - %4lu%c%c: %14lu %4u %4u | "
"%14lu %4u %4u\n", start, *unitp, end, *unitp,
- (i == LL_HIST_MAX - 1) ? '+' : ' ',
- r, pct(r, read_tot), pct(read_cum, read_tot),
- w, pct(w, write_tot), pct(write_cum, write_tot));
- start = end;
- if (start == BIT(10)) {
- start = 1;
- units += 10;
- unitp++;
- }
- if (read_cum == read_tot && write_cum == write_tot)
- break;
- }
+ (i == LL_HIST_MAX - 1) ? '+' : ' ',
+ r, pct(r, read_tot), pct(read_cum, read_tot),
+ w, pct(w, write_tot), pct(write_cum, write_tot));
+ start = end;
+ if (start == (1 << 10)) {
+ start = 1;
+ units += 10;
+ unitp++;
+ }
+ if (read_cum == read_tot && write_cum == write_tot)
+ break;
+ }
}
static int ll_rw_extents_stats_pp_seq_show(struct seq_file *seq, void *v)
lprocfs_oh_clear(&io_extents->pp_extents[cur].pp_w_hist);
}
- for(i = 0; (count >= BIT(LL_HIST_START << i)) &&
- (i < (LL_HIST_MAX - 1)); i++);
- if (rw == 0) {
- io_extents->pp_extents[cur].pp_r_hist.oh_buckets[i]++;
- io_extents->pp_extents[LL_PROCESS_HIST_MAX].pp_r_hist.oh_buckets[i]++;
- } else {
- io_extents->pp_extents[cur].pp_w_hist.oh_buckets[i]++;
- io_extents->pp_extents[LL_PROCESS_HIST_MAX].pp_w_hist.oh_buckets[i]++;
- }
+ for (i = 0; (count >= 1 << (LL_HIST_START + i)) &&
+ (i < (LL_HIST_MAX - 1)); i++);
+ if (rw == 0) {
+ io_extents->pp_extents[cur].pp_r_hist.oh_buckets[i]++;
+ io_extents->pp_extents[LL_PROCESS_HIST_MAX].pp_r_hist.oh_buckets[i]++;
+ } else {
+ io_extents->pp_extents[cur].pp_w_hist.oh_buckets[i]++;
+ io_extents->pp_extents[LL_PROCESS_HIST_MAX].pp_w_hist.oh_buckets[i]++;
+ }
spin_unlock(&sbi->ll_pp_extent_lock);
spin_lock(&sbi->ll_process_lock);
for (i = 0; i < LL_OFFSET_HIST_MAX; i++) {
if (offset[i].rw_pid != 0)
seq_printf(seq,
- "%3c %10d %14llu %14llu %17lu %17lu %14llu\n",
+ "%3c %10d %14llu %14llu %17lu %17lu %14lld\n",
offset[i].rw_op == READ ? 'R' : 'W',
offset[i].rw_pid,
offset[i].rw_range_start,
for (i = 0; i < LL_PROCESS_HIST_MAX; i++) {
if (process[i].rw_pid != 0)
seq_printf(seq,
- "%3c %10d %14llu %14llu %17lu %17lu %14llu\n",
+ "%3c %10d %14llu %14llu %17lu %17lu %14lld\n",
process[i].rw_op == READ ? 'R' : 'W',
process[i].rw_pid,
process[i].rw_range_start,
git://git.whamcloud.com / fs / lustre-release.git / blobdiff