[jira] [Updated] (MESOS-920) Set GLOG_drop_log_memory=false in environment prior to logging initialization.
[ https://issues.apache.org/jira/browse/MESOS-920?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Michael Park updated MESOS-920: --- Fix Version/s: 0.24.2 0.25.1 0.26.1 > Set GLOG_drop_log_memory=false in environment prior to logging initialization. > -- > > Key: MESOS-920 > URL: https://issues.apache.org/jira/browse/MESOS-920 > Project: Mesos > Issue Type: Improvement > Components: technical debt >Affects Versions: 0.15.0, 0.16.0 >Reporter: Benjamin Mahler >Assignee: Kapil Arya >Priority: Blocker > Labels: mesosphere > Fix For: 0.27.0, 0.26.1, 0.25.1, 0.24.2 > > > We've observed issues where the masters are slow to respond. Two perf traces > collected while the masters were slow to respond: > {noformat} > 25.84% [kernel][k] default_send_IPI_mask_sequence_phys > 20.44% [kernel][k] native_write_msr_safe > 4.54% [kernel][k] _raw_spin_lock > 2.95% libc-2.5.so [.] _int_malloc > 1.82% libc-2.5.so [.] malloc > 1.55% [kernel][k] apic_timer_interrupt > 1.36% libc-2.5.so [.] _int_free > {noformat} > {noformat} > 29.03% [kernel][k] default_send_IPI_mask_sequence_phys > 9.64% [kernel][k] _raw_spin_lock > 7.38% [kernel][k] native_write_msr_safe > 2.43% libc-2.5.so [.] _int_malloc > 2.05% libc-2.5.so [.] _int_free > 1.67% [kernel][k] apic_timer_interrupt > 1.58% libc-2.5.so [.] malloc > {noformat} > These have been found to be attributed to the posix_fadvise calls made by > glog. We can disable these via the environment: > {noformat} > GLOG_DEFINE_bool(drop_log_memory, true, "Drop in-memory buffers of log > contents. " > "Logs can grow very quickly and they are rarely read before > they " > "need to be evicted from memory. Instead, drop them from > memory " > "as soon as they are flushed to disk."); > {noformat} > {code} > if (FLAGS_drop_log_memory) { > if (file_length_ >= logging::kPageSize) { > // don't evict the most recent page > uint32 len = file_length_ & ~(logging::kPageSize - 1); > posix_fadvise(fileno(file_), 0, len, POSIX_FADV_DONTNEED); > } > } > {code} > We should set GLOG_drop_log_memory=false prior to making our call to > google::InitGoogleLogging, to avoid others running into this issue. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (MESOS-920) Set GLOG_drop_log_memory=false in environment prior to logging initialization.
[ https://issues.apache.org/jira/browse/MESOS-920?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Kapil Arya updated MESOS-920: - Fix Version/s: 0.27.0 > Set GLOG_drop_log_memory=false in environment prior to logging initialization. > -- > > Key: MESOS-920 > URL: https://issues.apache.org/jira/browse/MESOS-920 > Project: Mesos > Issue Type: Improvement > Components: technical debt >Affects Versions: 0.15.0, 0.16.0 >Reporter: Benjamin Mahler >Assignee: Kapil Arya >Priority: Blocker > Labels: mesosphere > Fix For: 0.27.0 > > > We've observed issues where the masters are slow to respond. Two perf traces > collected while the masters were slow to respond: > {noformat} > 25.84% [kernel][k] default_send_IPI_mask_sequence_phys > 20.44% [kernel][k] native_write_msr_safe > 4.54% [kernel][k] _raw_spin_lock > 2.95% libc-2.5.so [.] _int_malloc > 1.82% libc-2.5.so [.] malloc > 1.55% [kernel][k] apic_timer_interrupt > 1.36% libc-2.5.so [.] _int_free > {noformat} > {noformat} > 29.03% [kernel][k] default_send_IPI_mask_sequence_phys > 9.64% [kernel][k] _raw_spin_lock > 7.38% [kernel][k] native_write_msr_safe > 2.43% libc-2.5.so [.] _int_malloc > 2.05% libc-2.5.so [.] _int_free > 1.67% [kernel][k] apic_timer_interrupt > 1.58% libc-2.5.so [.] malloc > {noformat} > These have been found to be attributed to the posix_fadvise calls made by > glog. We can disable these via the environment: > {noformat} > GLOG_DEFINE_bool(drop_log_memory, true, "Drop in-memory buffers of log > contents. " > "Logs can grow very quickly and they are rarely read before > they " > "need to be evicted from memory. Instead, drop them from > memory " > "as soon as they are flushed to disk."); > {noformat} > {code} > if (FLAGS_drop_log_memory) { > if (file_length_ >= logging::kPageSize) { > // don't evict the most recent page > uint32 len = file_length_ & ~(logging::kPageSize - 1); > posix_fadvise(fileno(file_), 0, len, POSIX_FADV_DONTNEED); > } > } > {code} > We should set GLOG_drop_log_memory=false prior to making our call to > google::InitGoogleLogging, to avoid others running into this issue. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (MESOS-920) Set GLOG_drop_log_memory=false in environment prior to logging initialization.
[ https://issues.apache.org/jira/browse/MESOS-920?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Benjamin Mahler updated MESOS-920: -- Shepherd: Benjamin Mahler > Set GLOG_drop_log_memory=false in environment prior to logging initialization. > -- > > Key: MESOS-920 > URL: https://issues.apache.org/jira/browse/MESOS-920 > Project: Mesos > Issue Type: Improvement > Components: technical debt >Affects Versions: 0.15.0, 0.16.0 >Reporter: Benjamin Mahler >Assignee: Kapil Arya > > We've observed issues where the masters are slow to respond. Two perf traces > collected while the masters were slow to respond: > {noformat} > 25.84% [kernel][k] default_send_IPI_mask_sequence_phys > 20.44% [kernel][k] native_write_msr_safe > 4.54% [kernel][k] _raw_spin_lock > 2.95% libc-2.5.so [.] _int_malloc > 1.82% libc-2.5.so [.] malloc > 1.55% [kernel][k] apic_timer_interrupt > 1.36% libc-2.5.so [.] _int_free > {noformat} > {noformat} > 29.03% [kernel][k] default_send_IPI_mask_sequence_phys > 9.64% [kernel][k] _raw_spin_lock > 7.38% [kernel][k] native_write_msr_safe > 2.43% libc-2.5.so [.] _int_malloc > 2.05% libc-2.5.so [.] _int_free > 1.67% [kernel][k] apic_timer_interrupt > 1.58% libc-2.5.so [.] malloc > {noformat} > These have been found to be attributed to the posix_fadvise calls made by > glog. We can disable these via the environment: > {noformat} > GLOG_DEFINE_bool(drop_log_memory, true, "Drop in-memory buffers of log > contents. " > "Logs can grow very quickly and they are rarely read before > they " > "need to be evicted from memory. Instead, drop them from > memory " > "as soon as they are flushed to disk."); > {noformat} > {code} > if (FLAGS_drop_log_memory) { > if (file_length_ >= logging::kPageSize) { > // don't evict the most recent page > uint32 len = file_length_ & ~(logging::kPageSize - 1); > posix_fadvise(fileno(file_), 0, len, POSIX_FADV_DONTNEED); > } > } > {code} > We should set GLOG_drop_log_memory=false prior to making our call to > google::InitGoogleLogging, to avoid others running into this issue. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (MESOS-920) Set GLOG_drop_log_memory=false in environment prior to logging initialization.
[ https://issues.apache.org/jira/browse/MESOS-920?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Kapil Arya updated MESOS-920: - Target Version/s: 0.27.0 Priority: Blocker (was: Major) > Set GLOG_drop_log_memory=false in environment prior to logging initialization. > -- > > Key: MESOS-920 > URL: https://issues.apache.org/jira/browse/MESOS-920 > Project: Mesos > Issue Type: Improvement > Components: technical debt >Affects Versions: 0.15.0, 0.16.0 >Reporter: Benjamin Mahler >Assignee: Kapil Arya >Priority: Blocker > Labels: mesosphere > > We've observed issues where the masters are slow to respond. Two perf traces > collected while the masters were slow to respond: > {noformat} > 25.84% [kernel][k] default_send_IPI_mask_sequence_phys > 20.44% [kernel][k] native_write_msr_safe > 4.54% [kernel][k] _raw_spin_lock > 2.95% libc-2.5.so [.] _int_malloc > 1.82% libc-2.5.so [.] malloc > 1.55% [kernel][k] apic_timer_interrupt > 1.36% libc-2.5.so [.] _int_free > {noformat} > {noformat} > 29.03% [kernel][k] default_send_IPI_mask_sequence_phys > 9.64% [kernel][k] _raw_spin_lock > 7.38% [kernel][k] native_write_msr_safe > 2.43% libc-2.5.so [.] _int_malloc > 2.05% libc-2.5.so [.] _int_free > 1.67% [kernel][k] apic_timer_interrupt > 1.58% libc-2.5.so [.] malloc > {noformat} > These have been found to be attributed to the posix_fadvise calls made by > glog. We can disable these via the environment: > {noformat} > GLOG_DEFINE_bool(drop_log_memory, true, "Drop in-memory buffers of log > contents. " > "Logs can grow very quickly and they are rarely read before > they " > "need to be evicted from memory. Instead, drop them from > memory " > "as soon as they are flushed to disk."); > {noformat} > {code} > if (FLAGS_drop_log_memory) { > if (file_length_ >= logging::kPageSize) { > // don't evict the most recent page > uint32 len = file_length_ & ~(logging::kPageSize - 1); > posix_fadvise(fileno(file_), 0, len, POSIX_FADV_DONTNEED); > } > } > {code} > We should set GLOG_drop_log_memory=false prior to making our call to > google::InitGoogleLogging, to avoid others running into this issue. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (MESOS-920) Set GLOG_drop_log_memory=false in environment prior to logging initialization.
[ https://issues.apache.org/jira/browse/MESOS-920?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Benjamin Mahler updated MESOS-920: -- Description: We've observed issues where the masters are slow to respond. Two perf traces collected while the masters were slow to respond: {noformat} 25.84% [kernel][k] default_send_IPI_mask_sequence_phys 20.44% [kernel][k] native_write_msr_safe 4.54% [kernel][k] _raw_spin_lock 2.95% libc-2.5.so [.] _int_malloc 1.82% libc-2.5.so [.] malloc 1.55% [kernel][k] apic_timer_interrupt 1.36% libc-2.5.so [.] _int_free {noformat} {noformat} 29.03% [kernel][k] default_send_IPI_mask_sequence_phys 9.64% [kernel][k] _raw_spin_lock 7.38% [kernel][k] native_write_msr_safe 2.43% libc-2.5.so [.] _int_malloc 2.05% libc-2.5.so [.] _int_free 1.67% [kernel][k] apic_timer_interrupt 1.58% libc-2.5.so [.] malloc {noformat} These have been found to be attributed to the posix_fadvise calls made by glog. We can disable these via the environment: {noformat} GLOG_DEFINE_bool(drop_log_memory, true, "Drop in-memory buffers of log contents. " "Logs can grow very quickly and they are rarely read before they " "need to be evicted from memory. Instead, drop them from memory " "as soon as they are flushed to disk."); {noformat} {code} if (FLAGS_drop_log_memory) { if (file_length_ >= logging::kPageSize) { // don't evict the most recent page uint32 len = file_length_ & ~(logging::kPageSize - 1); posix_fadvise(fileno(file_), 0, len, POSIX_FADV_DONTNEED); } } {code} We should set GLOG_drop_log_memory=false prior to making our call to google::InitGoogleLogging, to avoid others running into this issue. was: We've observed performance scaling issues attributed to the posix_fadvise calls made by glog. This can currently only disabled via the environment: GLOG_DEFINE_bool(drop_log_memory, true, "Drop in-memory buffers of log contents. " "Logs can grow very quickly and they are rarely read before they " "need to be evicted from memory. Instead, drop them from memory " "as soon as they are flushed to disk."); if (FLAGS_drop_log_memory) { if (file_length_ >= logging::kPageSize) { // don't evict the most recent page uint32 len = file_length_ & ~(logging::kPageSize - 1); posix_fadvise(fileno(file_), 0, len, POSIX_FADV_DONTNEED); } } We should set GLOG_drop_log_memory=false prior to making our call to google::InitGoogleLogging. > Set GLOG_drop_log_memory=false in environment prior to logging initialization. > -- > > Key: MESOS-920 > URL: https://issues.apache.org/jira/browse/MESOS-920 > Project: Mesos > Issue Type: Improvement > Components: technical debt >Affects Versions: 0.15.0, 0.16.0 >Reporter: Benjamin Mahler > > We've observed issues where the masters are slow to respond. Two perf traces > collected while the masters were slow to respond: > {noformat} > 25.84% [kernel][k] default_send_IPI_mask_sequence_phys > 20.44% [kernel][k] native_write_msr_safe > 4.54% [kernel][k] _raw_spin_lock > 2.95% libc-2.5.so [.] _int_malloc > 1.82% libc-2.5.so [.] malloc > 1.55% [kernel][k] apic_timer_interrupt > 1.36% libc-2.5.so [.] _int_free > {noformat} > {noformat} > 29.03% [kernel][k] default_send_IPI_mask_sequence_phys > 9.64% [kernel][k] _raw_spin_lock > 7.38% [kernel][k] native_write_msr_safe > 2.43% libc-2.5.so [.] _int_malloc > 2.05% libc-2.5.so [.] _int_free > 1.67% [kernel][k] apic_timer_interrupt > 1.58% libc-2.5.so [.] malloc > {noformat} > These have been found to be attributed to the posix_fadvise calls made by > glog. We can disable these via the environment: > {noformat} > GLOG_DEFINE_bool(drop_log_memory, true, "Drop in-memory buffers of log > contents. " > "Logs can grow very quickly and they are rarely read before > they " > "need to be evicted from memory. Instead, drop them from > memory " > "as soon as they are flushed to disk."); > {noformat} > {code} > if (FLAGS_drop_log_memory) { > if (file_length_ >= logging::kPageSize) { > // don't evict the most recent page > uint32 len = file_length_ & ~(logging::kPageSize - 1); >
[jira] [Updated] (MESOS-920) Set GLOG_drop_log_memory=false in environment prior to logging initialization.
[ https://issues.apache.org/jira/browse/MESOS-920?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Benjamin Mahler updated MESOS-920: -- Component/s: technical debt Set GLOG_drop_log_memory=false in environment prior to logging initialization. -- Key: MESOS-920 URL: https://issues.apache.org/jira/browse/MESOS-920 Project: Mesos Issue Type: Improvement Components: technical debt Affects Versions: 0.16.0, 0.15.0 Reporter: Benjamin Mahler We've observed performance scaling issues attributed to the posix_fadvise calls made by glog. This can currently only disabled via the environment: GLOG_DEFINE_bool(drop_log_memory, true, Drop in-memory buffers of log contents. Logs can grow very quickly and they are rarely read before they need to be evicted from memory. Instead, drop them from memory as soon as they are flushed to disk.); if (FLAGS_drop_log_memory) { if (file_length_ = logging::kPageSize) { // don't evict the most recent page uint32 len = file_length_ ~(logging::kPageSize - 1); posix_fadvise(fileno(file_), 0, len, POSIX_FADV_DONTNEED); } } We should set GLOG_drop_log_memory=false prior to making our call to google::InitGoogleLogging. -- This message was sent by Atlassian JIRA (v6.3.4#6332)