Query syntax:

  • Use tag1 tag2 to match all tags.
  • tag1 or tag2 will match any tag.
  • Negate a tag with -tag1.
  • Group sub-queries with (tag1 or tag2).
  • Quote strings to include special characters.
  • Restrict search to a specific realm with realm:wiki.

Showing objects tagged with 'performance'

Results (1 - 100 of 103)

1 2
  • #1247 enhancement: bootstrap hickups when network is down (new)
  • #1664 enhancement: [w/ PATCH] Disabling loading of images durings Tor (for performance) ... (closed: wontfix)
  • #1749 project: Split relay and link crypto across multiple CPU cores (assigned)
  • #1854 task: Investigate raising the minimum bandwidth for getting the Fast flag (closed: wontfix)
  • #1991 enhancement: Recognize poor guard performance and switch? (closed: wontfix)
  • #2149 enhancement: new 'extra dormant' mode for people who never use their tor (closed: implemented)
  • #2178 defect: We launch dummy descriptor fetches more often than needed (new)
  • #2179 enhancement: Stream fairness: Stop packaging inbufs onto circuits greedily (new)
  • #2394 enhancement: Visualize self-reported vs. measured bandwidth of relays (closed: wontfix)
  • #2395 enhancement: Break Wed and Wee weights into two classes each (assigned)
  • #2536 enhancement: Disable outgoing token bucket and reduce token bucket refill interval (closed: wontfix)
  • #2878 enhancement: Don't bootstrap from an old consensus if we're about to replace it (needs_information)
  • #3044 task: At what bandwidth threshold is being a dir mirror unwise? (closed: wontfix)
  • #3711 task: Application support for optimistic data: Torsocks (needs_revision)
  • #3847 enhancement: Provide ability to round robin outgoing exit connections on multiple ... (new)
  • #4248 task: Hack up stunnel to test a transport that uses a vanilla SSL handshake (closed: wontfix)
  • #4482 task: Research: what's the relationship between capacity, bytes used, and ... (closed: wontfix)
  • #4486 task: Research: should N23 actually help in practice? (closed: invalid)
  • #4487 task: Research: Does N23 help especially much in cases where the first hop ... (closed: wontfix)
  • #4506 task: Simulate the N23 design to see how it performs for typical and for ... (closed: wontfix)
  • #4585 defect: Is round-robining between each TLS conn the optimal scheduling approach? (closed: wontfix)
  • #4682 project: Deal with 'double door' effects because our read and write rate ... (assigned)
  • #4708 enhancement: Implement bwauth cap for latency (new)
  • #4709 enhancement: Implement bwauth cap for TCP socket exhaustion (new)
  • #4712 task: Review and update any existing patches for proposal 182 ("credit buckets") (new)
  • #4730 defect: Bwauth: Use only "slow" measurements for positive feedback (closed: wontfix)
  • #5190 task: Collect Rob's patch for throttling flows at guards (closed: fixed)
  • #5271 enhancement: add log messages when a hidden service consistently doesn't have any ... (new)
  • #5398 task: Compare variance between simulation runs (Shadow and Experimentor) (closed: wontfix)
  • #5464 enhancement: Decentralized measurement for network load balancing (assigned)
  • #5707 enhancement: Use end to end stream timing data to further prune circuits (assigned)
  • #5915 enhancement: Write patch to make socks handshakes succeed instantly (new)
  • #7134 project: Add statistics on time spent on crypto operations (needs_information)
  • #7346 project: Add stream-level pushback into n23 design (new)
  • #7357 enhancement: Collect more statistics to better understand simulations (new)
  • #7358 task: Decide on list of stats to collect (new)
  • #7360 task: Document process of collection and extraction, formatting, etc. (new)
  • #7382 enhancement: Design/implement technique for measuring/collecting inter-relay ... (new)
  • #7572 defect: Make relay crypto run on multiple CPU cores (assigned)
  • #7707 defect: Impose a minimum write size for TLS writes (needs_information)
  • #8190 enhancement: Relays should publish number of refill intervals where the token ... (new)
  • #8453 enhancement: Alter flag-weight balancing equations (new)
  • #8897 enhancement: Faster curve25519 implementation for ntor (needs_revision)
  • #9324 enhancement: Recommend node type based on internet speed (closed: wontfix)
  • #9662 defect: Make ntor handshake faster (assigned)
  • #9664 enhancement: Precompute ephemeral keypairs for ntor (needs_revision)
  • #9685 enhancement: Improve Tor2web mode performance by having Tor2web client to be the ... (reopened)
  • #12169 enhancement: Improve speed by fixing tor_memeq performance, bottleneck(s) (closed: invalid)
  • #12541 enhancement: Integrate KIST socket/circuit scheduling (closed: implemented)
  • #13194 enhancement: Track time between ESTABLISH_RENDEZVOUS and RENDEZVOUS1 cell (new)
  • #13449 defect: bwauth takes a long time to scan the network (closed: wontfix)
  • #13450 defect: BwAuth is leaving ~10% of relays unmeasured (closed: worksforme)
  • #13737 enhancement: Move circuit building crypto to worker (assigned)
  • #13738 enhancement: Make worker handle introduction point crypto (new)
  • #13739 defect: Optimize the functions called in circuit_launch_by_extend_info() (new)
  • #13792 enhancement: HS statistics for private tor network to gather info on services, ... (new)
  • #14056 defect: IPredator complains that we call time() too much when running over 500Mbps (new)
  • #15017 enhancement: Experiment: does BIO_f_buffer help performance with read/write syscalls? (new)
  • #15463 defect: Tor deals poorly with a very large number of incoming connection requests. (new)
  • #15918 enhancement: Investigate using the EVP interface for non-oneshot hash calls. (new)
  • #16646 defect: Cannibalized intro point circuits are now 4 hops, instead of 3 (HS-side) (new)
  • #16682 enhancement: Deploy TCP Fast Open at exits (and maybe inter-node?) (new)
  • #16785 enhancement: Only build/use ed25519-donna. (new)
  • #18284 enhancement: Add RSOSIntroductionPoints feature (new)
  • #18859 defect: A new SOCKS connection should use a pre-built circuit for its first stream (closed: fixed)
  • #19980 enhancement: Use OpenSSL 1.1.0 X5519 in Tor when available (if it's good) (new)
  • #20615 defect: Your Guard is failing an extremely large amounts of circuits. (closed: not a bug)
  • #21253 task: Add link handshakes to benchmark program (needs_revision)
  • #21339 defect: Prefer Chacha on servers that lack AES hardware support? (new)
  • #21394 defect: connection timeouts are affecting Tor Browser usability (merge_ready)
  • #21421 enhancement: Maybe check for GUARD_WAIT circuit readiness whenever a guard fails (new)
  • #22589 defect: Tor circuit is too slow! (new)
  • #22663 defect: Tor keeps using a very slow guard (new)
  • #22798 defect: Windows relay is several times slower than Linux relay (merge_ready)
  • #22848 defect: Increase default Tor buffer sizes on Windows (new)
  • #23595 enhancement: Support KIST on other platforms. (new)
  • #24014 enhancement: Make exits check DNS periodically, and disable exit traffic if it fails (new)
  • #24022 defect: Make clients avoid retrying slow exits when they time out (closed: wontfix)
  • #24045 defect: Measure and map overloaded or over-weighted relays (reopened)
  • #24712 defect: Client builds and timeouts tons of circs to connect to HS (new)
  • #24767 enhancement: All relays are constantly connecting to down relays and failing over ... (closed: fixed)
  • #24857 defect: Tor uses 100% CPU when accessing the cache directory on Windows (needs_revision)
  • #24973 defect: Tor should be more gentle when launching dozens of circuits at once (needs_information)
  • #25007 enhancement: See if we can allocate less for HMAC in Tor relays (new)
  • #25008 defect: Call protocol_list_supports_protocol less often to save time and allocation (closed: implemented)
  • #25148 defect: Make geoip_client_cache_total_allocation() use ... (closed: fixed)
  • #25149 enhancement: Hook rephist subsystem into the OOM handler (new)
  • #25150 enhancement: Avoid malloc/free on each server-side ntor handshake (closed: fixed)
  • #25152 defect: Try to call less circuitmux_find_map_entry() (needs_information)
  • #25192 defect: change of bandwidth accounting intveral from 4 to 24 hours results in ... (closed: invalid)
  • #25372 defect: relay: Allocation for compression goes very high (new)
  • #25461 defect: main event-loop spins consuming 100% of a CPU core running ... (assigned)
  • #26121 defect: BUILDTIMEOUT_SET totals are still off (closed: fixed)
  • #26262 enhancement: Create unittests for circuit timeout tracking (new)
  • #26900 enhancement: Reduce background compression thread priority (new)
  • #26930 defect: Potential thundering herd HS upload once a day with hsv3 (closed: not a bug)
  • #28481 defect: Tor's startup time is getting slower on Android (new)
  • #28837 enhancement: Use openssl's SHA3 implementations when they are faster. (needs_review)
  • #28838 defect: Make curve25519_basepoint_spot_check() faster (needs_review)
  • #28839 defect: Speed up parsing RSA onion keys from microdescriptors (needs_review)
1 2